mirror of
https://github.com/Tencent/BrowserSkill.git
synced 2026-09-10 13:01:23 +08:00
Compare commits
5
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Ljy-0827
|
27b5d988be | ||
|
Ljy-0827
|
28892ea01a | ||
|
Ljy-0827
|
a6d4c14968 | ||
|
Ljy-0827
|
d1c1778054 | ||
|
Ljy-0827
|
d75495878a |
@@ -37,35 +37,6 @@ jobs:
|
||||
- name: Run Rust tests
|
||||
run: cargo test --workspace --locked
|
||||
|
||||
windows-daemon:
|
||||
name: Windows daemon, installer and cancellation regression tests
|
||||
runs-on: windows-latest
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v6
|
||||
|
||||
- uses: dtolnay/rust-toolchain@stable
|
||||
|
||||
- name: Run Windows named-pipe tests
|
||||
run: cargo test -p bsk --lib --locked daemon::ipc::windows::tests
|
||||
|
||||
- name: Run Windows process liveness tests
|
||||
run: cargo test -p bsk --lib --locked daemon::lockfile::tests
|
||||
|
||||
- name: Run Windows update tests
|
||||
run: cargo test -p bsk --lib --locked cli::update::tests
|
||||
|
||||
- name: Run Windows update and cancellation process tests
|
||||
run: cargo test -p bsk --test windows_update --test windows_parent_cancel --locked
|
||||
|
||||
- name: Run installer tests (Windows PowerShell 5.1)
|
||||
shell: powershell
|
||||
run: ./scripts/install-windows.test.ps1
|
||||
|
||||
- name: Run installer tests (PowerShell 7)
|
||||
shell: pwsh
|
||||
run: ./scripts/install-windows.test.ps1
|
||||
|
||||
frontend:
|
||||
name: Frontend lint, typecheck, tests, build
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
-116
@@ -1,116 +0,0 @@
|
||||
# Changelog
|
||||
|
||||
All notable changes to BrowserSkill will be documented in this file.
|
||||
The format is based on [Keep a Changelog](https://keepachangelog.com/).
|
||||
|
||||
Starting from 0.2.0, CLI / Extension / DSH Plugin share the same version number.
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
### Added
|
||||
|
||||
- [Scroll-to element primitive](docs/scroll-to.md) across CLI, Extension and DSH Plugin,
|
||||
with ancestor-clipped visible bounds, iframe support and cooperative cancellation
|
||||
|
||||
## [0.2.1] - 2026-09-09
|
||||
|
||||
### Changed
|
||||
- DSH Plugin: clarified installation, configuration, profile restart, and upgrade instructions
|
||||
|
||||
### Fixed
|
||||
- CLI: reliable Windows self-updates, including executable replacement and daemon restart
|
||||
- CLI: Windows named-pipe connection continuity and stale daemon process detection
|
||||
- Windows installer: PowerShell 5.1 compatibility, path quoting, and staged executable replacement
|
||||
- CLI / DSH Plugin: cancellation propagation and upload/download cleanup when the parent process exits
|
||||
- Extension: tab ownership and session cleanup when agent tabs fail to open or borrowed tabs are returned or closed
|
||||
- Extension: navigation recovery when other extensions restrict Chrome DevTools Protocol access
|
||||
- Extension: background input filling, automatic append behavior, and verification of field values before reporting success
|
||||
- Extension: match observed form state to the correct element after page changes
|
||||
- Extension: UUID generation fallback for recording and overlays on insecure origins
|
||||
- Browser locale matching for regional language variants
|
||||
- DSH Plugin: observation state synchronization, thumbnail capture lifecycle, and stale preview cleanup
|
||||
- DSH Plugin: removed the obsolete client runtime host dependency
|
||||
|
||||
## [0.2.0] - 2026-09-02
|
||||
|
||||
### Added
|
||||
- File transfer: upload and download support across CLI, Extension, and DSH Plugin
|
||||
- File transfer: drag-and-drop upload (`drop-to-upload`)
|
||||
- VOM semantic graph, name enrichment, and hover perception modules
|
||||
- VOM hover probing (opt-in via `observe` parameter)
|
||||
- DSH Plugin: browser tool parity with CLI commands
|
||||
- Edge Add-ons automated publishing in CI
|
||||
- Protocol upgrade reminder when CLI / Extension protocol versions differ
|
||||
- Browser evaluation harness (`evals/browser/`)
|
||||
- Unified release script (`scripts/release.mjs`)
|
||||
|
||||
### Changed
|
||||
- **Version scheme**: all three components now share the same semver
|
||||
- VOM rendering algorithm optimizations
|
||||
- Leaner SKILL.md agent instructions
|
||||
- DSH Plugin: simplified browser commands
|
||||
- Borrow confirmation UX — proactive focus and longer timeout
|
||||
- PiP window now has a close button
|
||||
|
||||
### Fixed
|
||||
- Screenshot media type detection (was hard-coded to `image/png`)
|
||||
- DSH Plugin session lifecycle stability
|
||||
- DSH Plugin Cordis package ID mismatch
|
||||
- Observation thumbnail media type sniffing
|
||||
- Upload/download race conditions and layout bypass issues
|
||||
- VOM repeated name and safety policy issues
|
||||
|
||||
---
|
||||
|
||||
*Previous releases used independent version numbers per component.*
|
||||
|
||||
## CLI 0.1.11 / Extension 0.1.7 / DSH Plugin 0.1.2 — 2026-08-26 ~ 2026-08-29
|
||||
|
||||
### Added
|
||||
- DSH Plugin sidebar integration, session lifecycle, and archive cleanup
|
||||
- Recorder iframe and OOPIF support
|
||||
|
||||
### Changed
|
||||
- VOM functional refactor
|
||||
|
||||
### Fixed
|
||||
- Recorder safety policy and bug fixes
|
||||
|
||||
## CLI 0.1.10 / Extension 0.1.6 — 2026-08-08
|
||||
|
||||
### Added
|
||||
- VOM observation recording and settled-state detection
|
||||
- Record overlay timer
|
||||
|
||||
### Fixed
|
||||
- Browser keepalive disconnect handling
|
||||
|
||||
## CLI 0.1.9 / Extension 0.1.5 — 2026-07-29
|
||||
|
||||
### Added
|
||||
- CLI auto-update mechanism
|
||||
- Trace v3 protocol and recorder
|
||||
|
||||
### Fixed
|
||||
- MV3 keepalive disconnect
|
||||
|
||||
## CLI 0.1.8 / Extension 0.1.4 — 2026-07-22
|
||||
|
||||
### Added
|
||||
- More browser interaction actions
|
||||
|
||||
### Fixed
|
||||
- Windows named-pipe hash-only path issue
|
||||
|
||||
## CLI 0.1.7 / Extension 0.1.3 — 2026-07-07
|
||||
|
||||
Initial public release pair.
|
||||
|
||||
## CLI 0.1.6 — 2026-06-30
|
||||
|
||||
### Fixed
|
||||
- Minor CLI fixes
|
||||
|
||||
## CLI 0.1.5 / Extension 0.1.2 — 2026-06-22
|
||||
|
||||
First tagged releases.
|
||||
Generated
+2
-2
@@ -134,7 +134,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "bsk"
|
||||
version = "0.2.1"
|
||||
version = "0.1.11"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"base64",
|
||||
@@ -169,7 +169,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "bsk-protocol"
|
||||
version = "0.2.1"
|
||||
version = "0.1.11"
|
||||
dependencies = [
|
||||
"schemars",
|
||||
"semver",
|
||||
|
||||
+2
-2
@@ -7,7 +7,7 @@ members = [
|
||||
default-members = ["crates/bsk-cli"]
|
||||
|
||||
[workspace.package]
|
||||
version = "0.2.1"
|
||||
version = "0.1.11"
|
||||
edition = "2024"
|
||||
rust-version = "1.85"
|
||||
license = "MIT"
|
||||
@@ -43,7 +43,7 @@ rand = "0.8"
|
||||
uuid = { version = "1", features = ["v4", "serde"] }
|
||||
|
||||
# Workspace crates (version required for `cargo publish` of dependents)
|
||||
bsk-protocol = { version = "0.2.1", path = "crates/bsk-protocol" }
|
||||
bsk-protocol = { version = "0.1.9", path = "crates/bsk-protocol" }
|
||||
|
||||
[profile.release]
|
||||
strip = "symbols"
|
||||
|
||||
@@ -147,26 +147,20 @@ Start a new Agent session and write a prompt that needs the browser, for example
|
||||
Using [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) (`dsh`)?
|
||||
BrowserSkill ships a first-class dsh plugin on npm as
|
||||
[`@wxg-prc-cpg/browser-skill-dsh-plugin`](https://www.npmjs.com/package/@wxg-prc-cpg/browser-skill-dsh-plugin).
|
||||
It gives the agent native `browser_*` tools and a live view of its browser sessions
|
||||
in the Web UI. The plugin runs `bsk` on the agent's behalf.
|
||||
It injects native `browser_*` tools (no shelling out to `bsk`) and a live Web UI
|
||||
overlay of each Agent Window.
|
||||
|
||||
Install the `bsk` CLI and connect the browser extension first. Then add the plugin
|
||||
to a dsh profile and start it (replace `web` with your profile name):
|
||||
Add it to a dsh profile, then start that profile:
|
||||
|
||||
```sh
|
||||
dsh plugin --profile web add @wxg-prc-cpg/browser-skill-dsh-plugin
|
||||
dsh --profile web
|
||||
```
|
||||
|
||||
The plugin includes the `browser-skill` skill, so `bsk install-skill` is not needed
|
||||
for dsh. Installed plugins do not update automatically. To upgrade this plugin:
|
||||
|
||||
```sh
|
||||
dsh plugin --profile web update @wxg-prc-cpg/browser-skill-dsh-plugin --latest
|
||||
```
|
||||
|
||||
Restart the profile after upgrading. See the
|
||||
[plugin README](packages/dsh-plugin-browserskill/README.md) for usage and configuration.
|
||||
The plugin carries its own copy of the skill, so `bsk install-skill` is not needed
|
||||
for dsh — but the `bsk` CLI and the browser extension are still prerequisites. See
|
||||
the [plugin README](packages/dsh-plugin-browserskill/README.md) for the tool list,
|
||||
configuration, and the observation overlay.
|
||||
|
||||
## How It Works
|
||||
|
||||
@@ -207,9 +201,6 @@ through the [plugin](#deepseek-harness-plugin): the agent calls injected
|
||||
|
||||
## For Developers
|
||||
|
||||
The [scroll-to primitive reference](docs/scroll-to.md) covers its CLI, protocol
|
||||
and plugin entry points, visible bounds and interruption behavior.
|
||||
|
||||
The repository is a Cargo + pnpm workspace:
|
||||
|
||||
- `crates/bsk-cli` — `bsk` CLI and local daemon
|
||||
|
||||
+3
-11
@@ -125,22 +125,16 @@ bsk install-skill
|
||||
|
||||
## DeepSeek Harness 插件
|
||||
|
||||
在用 [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness)（`dsh`）？BrowserSkill 提供了官方 dsh 插件，已发布到 npm：[`@wxg-prc-cpg/browser-skill-dsh-plugin`](https://www.npmjs.com/package/@wxg-prc-cpg/browser-skill-dsh-plugin)。它为 Agent 提供原生 `browser_*` 工具，由插件代为调用 `bsk`，并在 Web UI 中实时展示浏览器会话。
|
||||
在用 [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness)（`dsh`）？BrowserSkill 提供了官方 dsh 插件，已发布到 npm：[`@wxg-prc-cpg/browser-skill-dsh-plugin`](https://www.npmjs.com/package/@wxg-prc-cpg/browser-skill-dsh-plugin)。它会注入原生 `browser_*` 工具（无需再通过 Shell 调用 `bsk`），并在 Web UI 中实时观察每个 Agent Window。
|
||||
|
||||
先安装 `bsk` CLI 并连接浏览器扩展，再将插件装进 dsh profile 并启动（将 `web` 替换为你的 profile 名称）：
|
||||
把它装进某个 dsh profile，然后启动该 profile：
|
||||
|
||||
```sh
|
||||
dsh plugin --profile web add @wxg-prc-cpg/browser-skill-dsh-plugin
|
||||
dsh --profile web
|
||||
```
|
||||
|
||||
插件自带 `browser-skill` skill，所以在 dsh 下无需执行 `bsk install-skill`。已安装的插件不会自动更新；升级此插件请运行：
|
||||
|
||||
```sh
|
||||
dsh plugin --profile web update @wxg-prc-cpg/browser-skill-dsh-plugin --latest
|
||||
```
|
||||
|
||||
升级后重启该 profile。用法与配置见[插件 README](packages/dsh-plugin-browserskill/README.md)。
|
||||
插件自带 skill，所以在 dsh 下无需执行 `bsk install-skill`；但 `bsk` CLI 和浏览器扩展仍是前置条件。工具清单、配置项与观察浮层见[插件 README](packages/dsh-plugin-browserskill/README.md)。
|
||||
|
||||
## 工作原理
|
||||
|
||||
@@ -177,8 +171,6 @@ Agent 不直接与浏览器通信。它通过 `bsk` CLI 下发浏览器任务；
|
||||
|
||||
## 面向开发者
|
||||
|
||||
[scroll-to 原语说明](docs/scroll-to.md)介绍 CLI、协议和插件入口，以及可见区域、错误和中断语义。
|
||||
|
||||
本仓库是 Cargo + pnpm workspace：
|
||||
|
||||
- `crates/bsk-cli` — `bsk` CLI 与本地 daemon
|
||||
|
||||
@@ -1,81 +0,0 @@
|
||||
<!doctype html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<title>BrowserSkill file-transfer fixture</title>
|
||||
<style>
|
||||
body { font: 16px system-ui; max-width: 760px; margin: 48px auto; }
|
||||
.actions { display: flex; gap: 12px; align-items: center; margin: 24px 0; }
|
||||
button, a { padding: 10px 16px; border: 1px solid #777; border-radius: 8px; }
|
||||
a[aria-disabled="true"] { opacity: .45; pointer-events: none; }
|
||||
#drop { padding: 36px; border: 3px dashed #777; border-radius: 12px; text-align: center; }
|
||||
#drop.dragging { border-color: #2563eb; background: #eff6ff; }
|
||||
img { display: block; max-width: 480px; max-height: 360px; margin-top: 20px; }
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
<h1>Upload then download the same image</h1>
|
||||
<p id="status">No image selected</p>
|
||||
<div class="actions">
|
||||
<button id="upload" type="button">Upload through file input</button>
|
||||
<input id="file" type="file" accept="image/png" hidden />
|
||||
<a id="download" aria-disabled="true">Download uploaded image</a>
|
||||
</div>
|
||||
<div id="drop" role="button" tabindex="0">Drop an image here</div>
|
||||
<img id="preview" alt="Uploaded image preview" hidden />
|
||||
<script>
|
||||
const input = document.querySelector('#file');
|
||||
const upload = document.querySelector('#upload');
|
||||
const drop = document.querySelector('#drop');
|
||||
const download = document.querySelector('#download');
|
||||
const preview = document.querySelector('#preview');
|
||||
const status = document.querySelector('#status');
|
||||
let objectUrl;
|
||||
|
||||
window.__bskTransferFixture = { events: [], result: null };
|
||||
|
||||
function accept(file, mechanism) {
|
||||
if (!file) return;
|
||||
if (objectUrl) URL.revokeObjectURL(objectUrl);
|
||||
objectUrl = URL.createObjectURL(file);
|
||||
preview.src = objectUrl;
|
||||
preview.hidden = false;
|
||||
download.href = objectUrl;
|
||||
download.download = file.name;
|
||||
download.removeAttribute('aria-disabled');
|
||||
status.textContent = `Ready via ${mechanism}: ${file.name} (${file.size} bytes)`;
|
||||
window.__bskTransferFixture.result = {
|
||||
mechanism,
|
||||
name: file.name,
|
||||
size: file.size,
|
||||
type: file.type,
|
||||
hasPathProperty: 'path' in file,
|
||||
};
|
||||
}
|
||||
|
||||
upload.addEventListener('click', () => input.click());
|
||||
input.addEventListener('change', () => accept(input.files[0], 'input'));
|
||||
|
||||
for (const type of ['dragenter', 'dragover']) {
|
||||
drop.addEventListener(type, event => {
|
||||
const types = [...event.dataTransfer.types];
|
||||
window.__bskTransferFixture.events.push({ type, types });
|
||||
if (!types.includes('Files')) return;
|
||||
event.preventDefault();
|
||||
drop.classList.add('dragging');
|
||||
});
|
||||
}
|
||||
drop.addEventListener('dragleave', () => drop.classList.remove('dragging'));
|
||||
drop.addEventListener('drop', event => {
|
||||
window.__bskTransferFixture.events.push({
|
||||
type: 'drop',
|
||||
types: [...event.dataTransfer.types],
|
||||
fileCount: event.dataTransfer.files.length,
|
||||
});
|
||||
event.preventDefault();
|
||||
drop.classList.remove('dragging');
|
||||
accept(event.dataTransfer.files[0], 'drop');
|
||||
});
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@browser-skill/extension",
|
||||
"version": "0.2.1",
|
||||
"version": "0.1.7",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"scripts": {
|
||||
|
||||
@@ -29,24 +29,6 @@ function fakeApi() {
|
||||
}
|
||||
|
||||
describe("ChromiumCdp", () => {
|
||||
it("changes attachment identity only across real debugger attachments", async () => {
|
||||
const { api, onEvent, onDetach } = fakeApi();
|
||||
const cdp = new ChromiumCdp(api);
|
||||
expect(cdp.getAttachmentId(4)).toBeUndefined();
|
||||
await cdp.ensureAttached(4);
|
||||
const first = cdp.getAttachmentId(4);
|
||||
expect(first).toBeTruthy();
|
||||
await cdp.ensureAttached(4);
|
||||
onEvent.fire({ tabId: 4 }, "Target.attachedToTarget", { sessionId: "child" });
|
||||
expect(cdp.getAttachmentId(4)).toBe(first);
|
||||
onDetach.fire({ tabId: 4 }, "target_closed");
|
||||
expect(cdp.getAttachmentId(4)).toBeUndefined();
|
||||
await cdp.ensureAttached(4);
|
||||
expect(cdp.getAttachmentId(4)).not.toBe(first);
|
||||
await cdp.detach(4);
|
||||
expect(cdp.getAttachmentId(4)).toBeUndefined();
|
||||
});
|
||||
|
||||
it("discovers multiple iframe targets and recursively routes nested OOPIF commands", async () => {
|
||||
const { api, onEvent } = fakeApi();
|
||||
(api.sendCommand as ReturnType<typeof vi.fn>).mockImplementation(
|
||||
@@ -272,69 +254,6 @@ describe("ChromiumCdp", () => {
|
||||
expect(cdp.isAttached(7)).toBe(false);
|
||||
});
|
||||
|
||||
it.each([
|
||||
false,
|
||||
true,
|
||||
])("waits for detach before reconnecting a returned tab (detach rejects: %s)", async (rejectDetach) => {
|
||||
const { api } = fakeApi();
|
||||
const attached = new Set<number>();
|
||||
let finishDetach!: () => void;
|
||||
vi.mocked(api.attach).mockImplementation(async ({ tabId }) => {
|
||||
if (attached.has(tabId!)) throw new Error("Another debugger is already attached");
|
||||
attached.add(tabId!);
|
||||
});
|
||||
vi.mocked(api.detach).mockImplementation(async ({ tabId }) => {
|
||||
attached.delete(tabId!);
|
||||
});
|
||||
vi.mocked(api.detach).mockImplementationOnce(
|
||||
({ tabId }) =>
|
||||
new Promise<void>((resolve, reject) => {
|
||||
finishDetach = () => {
|
||||
attached.delete(tabId!);
|
||||
if (rejectDetach) reject(new Error("tab already detached"));
|
||||
else resolve();
|
||||
};
|
||||
}),
|
||||
);
|
||||
const cdp = new ChromiumCdp(api);
|
||||
cdp.trackSessionTab("aa11", 7);
|
||||
await cdp.ensureAttached(7);
|
||||
const returning = cdp.releaseSessionTab("aa11", 7);
|
||||
await vi.waitFor(() => expect(api.detach).toHaveBeenCalledOnce());
|
||||
let duplicateDetachFinished = false;
|
||||
const duplicateDetach = cdp.detach(7).then(() => {
|
||||
duplicateDetachFinished = true;
|
||||
});
|
||||
|
||||
cdp.trackSessionTab("bb22", 7);
|
||||
// Register rejection handlers immediately; the pre-fix driver rejects
|
||||
// both commands while the browser still has the previous attachment.
|
||||
const pending = Promise.allSettled([
|
||||
cdp.send(7, "Runtime.evaluate", { expression: "document.title" }),
|
||||
cdp.send(7, "DOM.getDocument"),
|
||||
]);
|
||||
await cdp.send(8, "DOM.getDocument");
|
||||
const finishedEarly = duplicateDetachFinished;
|
||||
finishDetach();
|
||||
await Promise.all([returning, duplicateDetach]);
|
||||
|
||||
expect(await pending).toEqual([
|
||||
{ status: "fulfilled", value: { ok: true } },
|
||||
{ status: "fulfilled", value: { ok: true } },
|
||||
]);
|
||||
expect(finishedEarly).toBe(false);
|
||||
expect(vi.mocked(api.attach).mock.calls.filter(([target]) => target.tabId === 7)).toHaveLength(
|
||||
2,
|
||||
);
|
||||
expect(cdp.isAttached(7)).toBe(true);
|
||||
expect(cdp.isAttached(8)).toBe(true);
|
||||
await cdp.detachSession("bb22");
|
||||
expect(api.detach).toHaveBeenCalledTimes(2);
|
||||
expect(cdp.isAttached(7)).toBe(false);
|
||||
expect(attached.has(7)).toBe(false);
|
||||
expect(cdp.isAttached(8)).toBe(true);
|
||||
});
|
||||
|
||||
it("detachAll() iterates every cached tab", async () => {
|
||||
const { api } = fakeApi();
|
||||
const cdp = new ChromiumCdp(api);
|
||||
@@ -732,155 +651,6 @@ describe("ChromiumCdp", () => {
|
||||
expect(cdp.networkEntriesSince(33, 0, 50, 1000).entries[0].url).toBeUndefined();
|
||||
});
|
||||
|
||||
it("releases only the returning session's claim on a tab", async () => {
|
||||
const { api } = fakeApi();
|
||||
const cdp = new ChromiumCdp(api);
|
||||
await cdp.ensureAttached(1);
|
||||
await cdp.ensureAttached(2);
|
||||
cdp.trackSessionTab("aa11", 1);
|
||||
cdp.trackSessionTab("bb22", 1);
|
||||
cdp.trackSessionTab("aa11", 2);
|
||||
|
||||
await cdp.releaseSessionTab("unknown", 1);
|
||||
await cdp.releaseSessionTab("aa11", 1);
|
||||
expect(api.detach).not.toHaveBeenCalled();
|
||||
|
||||
await cdp.releaseSessionTab("bb22", 1);
|
||||
await cdp.releaseSessionTab("bb22", 1);
|
||||
expect(api.detach).toHaveBeenCalledExactlyOnceWith({ tabId: 1 });
|
||||
expect(cdp.isAttached(2)).toBe(true);
|
||||
|
||||
await cdp.detachSession("aa11");
|
||||
expect(api.detach).toHaveBeenCalledTimes(2);
|
||||
expect(api.detach).toHaveBeenLastCalledWith({ tabId: 2 });
|
||||
});
|
||||
|
||||
it.each([
|
||||
false,
|
||||
true,
|
||||
])("releases a tab with an attachment in flight (new owner: %s)", async (newOwner) => {
|
||||
const { api } = fakeApi();
|
||||
let finishAttach!: () => void;
|
||||
vi.mocked(api.attach).mockImplementationOnce(
|
||||
() =>
|
||||
new Promise<void>((resolve) => {
|
||||
finishAttach = resolve;
|
||||
}),
|
||||
);
|
||||
const cdp = new ChromiumCdp(api);
|
||||
cdp.trackSessionTab("aa11", 1);
|
||||
const attaching = cdp.ensureAttached(1);
|
||||
const releasing = cdp.releaseSessionTab("aa11", 1);
|
||||
if (newOwner) cdp.trackSessionTab("bb22", 1);
|
||||
finishAttach();
|
||||
await Promise.all([attaching, releasing]);
|
||||
|
||||
expect(cdp.isAttached(1)).toBe(newOwner);
|
||||
expect(api.detach).toHaveBeenCalledTimes(newOwner ? 0 : 1);
|
||||
});
|
||||
|
||||
it("stops accepting dialogs on a returned tab even when another session keeps CDP attached", async () => {
|
||||
const { api, onEvent } = fakeApi();
|
||||
let controlled = true;
|
||||
const cdp = new ChromiumCdp(api, { shouldAutoAcceptDialog: () => controlled });
|
||||
cdp.trackSessionTab("aa11", 1);
|
||||
cdp.trackSessionTab("bb22", 1);
|
||||
await cdp.ensureAttached(1);
|
||||
onEvent.fire({ tabId: 1 }, "Page.javascriptDialogOpening", {
|
||||
type: "confirm",
|
||||
message: "before return",
|
||||
});
|
||||
await vi.waitFor(() => expect(cdp.dialogsSince(1, 0)).toHaveLength(1));
|
||||
vi.mocked(api.sendCommand).mockClear();
|
||||
|
||||
controlled = false;
|
||||
await cdp.releaseSessionTab("aa11", 1);
|
||||
expect(cdp.isAttached(1)).toBe(true);
|
||||
onEvent.fire({ tabId: 1 }, "Page.javascriptDialogOpening", {
|
||||
type: "confirm",
|
||||
message: "after return",
|
||||
});
|
||||
await Promise.resolve();
|
||||
expect(api.sendCommand).not.toHaveBeenCalled();
|
||||
expect(cdp.dialogsSince(1, 0)).toHaveLength(1);
|
||||
|
||||
controlled = true;
|
||||
onEvent.fire({ tabId: 1 }, "Page.javascriptDialogOpening", {
|
||||
type: "alert",
|
||||
message: "borrowed again",
|
||||
});
|
||||
await vi.waitFor(() => expect(cdp.dialogsSince(1, 0)).toHaveLength(2));
|
||||
expect(api.sendCommand).toHaveBeenCalledExactlyOnceWith(
|
||||
{ tabId: 1 },
|
||||
"Page.handleJavaScriptDialog",
|
||||
{ accept: true },
|
||||
);
|
||||
});
|
||||
|
||||
it("ignores dialog events after detach, including a pending eligibility check", async () => {
|
||||
const { api, onEvent } = fakeApi();
|
||||
let resolveEligibility!: (value: boolean) => void;
|
||||
const shouldAutoAcceptDialog = vi.fn(
|
||||
() =>
|
||||
new Promise<boolean>((resolve) => {
|
||||
resolveEligibility = resolve;
|
||||
}),
|
||||
);
|
||||
const cdp = new ChromiumCdp(api, { shouldAutoAcceptDialog });
|
||||
await cdp.ensureAttached(1);
|
||||
onEvent.fire({ tabId: 1 }, "Page.javascriptDialogOpening", { type: "alert" });
|
||||
await cdp.detach(1);
|
||||
resolveEligibility(true);
|
||||
await Promise.resolve();
|
||||
onEvent.fire({ tabId: 1 }, "Page.javascriptDialogOpening", { type: "alert" });
|
||||
|
||||
expect(shouldAutoAcceptDialog).toHaveBeenCalledOnce();
|
||||
expect(api.sendCommand).not.toHaveBeenCalledWith(
|
||||
expect.anything(),
|
||||
"Page.handleJavaScriptDialog",
|
||||
expect.anything(),
|
||||
);
|
||||
expect(cdp.dialogsSince(1, 0)).toEqual([]);
|
||||
});
|
||||
|
||||
it("does not accept dialogs when the tab's current scope cannot be determined", async () => {
|
||||
const { api, onEvent } = fakeApi();
|
||||
const shouldAutoAcceptDialog = vi.fn(async () => {
|
||||
throw new Error("tab is gone");
|
||||
});
|
||||
const cdp = new ChromiumCdp(api, { shouldAutoAcceptDialog });
|
||||
await cdp.ensureAttached(1);
|
||||
vi.mocked(api.sendCommand).mockClear();
|
||||
|
||||
onEvent.fire({ tabId: 1 }, "Page.javascriptDialogOpening", { type: "confirm" });
|
||||
await Promise.resolve();
|
||||
|
||||
expect(shouldAutoAcceptDialog).toHaveBeenCalledWith(1);
|
||||
expect(api.sendCommand).not.toHaveBeenCalled();
|
||||
expect(cdp.dialogsSince(1, 0)).toEqual([]);
|
||||
});
|
||||
|
||||
it("does not restore dialog state when an acceptance completes after detach", async () => {
|
||||
const { api, onEvent } = fakeApi();
|
||||
const cdp = new ChromiumCdp(api);
|
||||
await cdp.ensureAttached(1);
|
||||
let finishAccept!: () => void;
|
||||
vi.mocked(api.sendCommand).mockImplementationOnce(
|
||||
() =>
|
||||
new Promise<void>((resolve) => {
|
||||
finishAccept = resolve;
|
||||
}),
|
||||
);
|
||||
|
||||
onEvent.fire({ tabId: 1 }, "Page.javascriptDialogOpening", { type: "alert" });
|
||||
await cdp.detach(1);
|
||||
finishAccept();
|
||||
await Promise.resolve();
|
||||
|
||||
expect(cdp.dialogsSince(1, 0)).toEqual([]);
|
||||
expect(cdp.dialogCursor(1)).toBe(0);
|
||||
});
|
||||
|
||||
it("detachSession only detaches tabs no other session owns", async () => {
|
||||
const { api } = fakeApi();
|
||||
const cdp = new ChromiumCdp(api);
|
||||
|
||||
@@ -164,9 +164,7 @@ async function settleBeforeDeadline(promises: Promise<void>[], deadline: number)
|
||||
export class ChromiumCdp {
|
||||
private readonly api: CdpDebuggerApi;
|
||||
private readonly attachedTabs = new Set<number>();
|
||||
private readonly attachmentIds = new Map<number, string>();
|
||||
private readonly attachInFlight = new Map<number, Promise<void>>();
|
||||
private readonly detachInFlight = new Map<number, Promise<void>>();
|
||||
private readonly tabOwners = new Map<number, Set<string>>();
|
||||
private readonly dialogBuffers = new Map<number, JavaScriptDialogInfo[]>();
|
||||
private readonly dialogSequences = new Map<number, number>();
|
||||
@@ -184,13 +182,7 @@ export class ChromiumCdp {
|
||||
private networkSubscription: { dispose(): void } | null = null;
|
||||
private frameTargetSubscription: { dispose(): void } | null = null;
|
||||
|
||||
constructor(
|
||||
api: CdpDebuggerApi = chromeDebuggerApi,
|
||||
private readonly options: {
|
||||
/** CDP observation alone does not authorize dismissing user dialogs. */
|
||||
shouldAutoAcceptDialog?: (tabId: number) => boolean | Promise<boolean>;
|
||||
} = {},
|
||||
) {
|
||||
constructor(api: CdpDebuggerApi = chromeDebuggerApi) {
|
||||
this.api = api;
|
||||
this.bindAutoDetach();
|
||||
this.bindDialogHandler();
|
||||
@@ -199,17 +191,8 @@ export class ChromiumCdp {
|
||||
this.bindFrameTargetHandler();
|
||||
}
|
||||
|
||||
/** Identity of this actual debugger attachment, independent of frame topology. */
|
||||
getAttachmentId(tabId: number): string | undefined {
|
||||
return this.attachmentIds.get(tabId);
|
||||
}
|
||||
|
||||
/** Attach to `tabId` if we haven't already in this driver. */
|
||||
async ensureAttached(tabId: number): Promise<void> {
|
||||
// Returning a tab clears the cache before Chrome finishes detaching.
|
||||
// New observers must wait before opening the next connection to that tab.
|
||||
const detaching = this.detachInFlight.get(tabId);
|
||||
if (detaching) await detaching;
|
||||
if (this.attachedTabs.has(tabId)) return;
|
||||
const existing = this.attachInFlight.get(tabId);
|
||||
if (existing) {
|
||||
@@ -223,7 +206,6 @@ export class ChromiumCdp {
|
||||
await this.enableConsoleDomains(tabId);
|
||||
await this.enableNetworkDomainBestEffort(tabId);
|
||||
this.attachedTabs.add(tabId);
|
||||
this.attachmentIds.set(tabId, crypto.randomUUID());
|
||||
await this.enableFrameDiscovery({ tabId }).catch((err) => {
|
||||
console.debug("[bsk cdp] frame discovery unavailable", { tabId, err });
|
||||
});
|
||||
@@ -443,32 +425,20 @@ export class ChromiumCdp {
|
||||
|
||||
/** Detach if attached; never throws. */
|
||||
async detach(tabId: number): Promise<void> {
|
||||
const existing = this.detachInFlight.get(tabId);
|
||||
if (existing) {
|
||||
await existing;
|
||||
return;
|
||||
}
|
||||
this.attachInFlight.delete(tabId);
|
||||
if (!this.attachedTabs.has(tabId)) return;
|
||||
this.attachedTabs.delete(tabId);
|
||||
this.attachmentIds.delete(tabId);
|
||||
this.clearDialogState(tabId);
|
||||
this.clearConsoleState(tabId);
|
||||
this.clearNetworkState(tabId);
|
||||
this.clearFrameState(tabId);
|
||||
const detach = (async () => {
|
||||
try {
|
||||
await this.api.detach({ tabId });
|
||||
} catch (err) {
|
||||
// Tab may already be gone — Chrome auto-detaches on close. Log
|
||||
// at debug so production builds aren't noisy.
|
||||
console.debug("[bsk cdp] detach failed (likely tab already closed)", err);
|
||||
}
|
||||
})().finally(() => {
|
||||
this.detachInFlight.delete(tabId);
|
||||
});
|
||||
this.detachInFlight.set(tabId, detach);
|
||||
await detach;
|
||||
try {
|
||||
await this.api.detach({ tabId });
|
||||
} catch (err) {
|
||||
// Tab may already be gone — Chrome auto-detaches on close. Log
|
||||
// at debug so production builds aren't noisy.
|
||||
console.debug("[bsk cdp] detach failed (likely tab already closed)", err);
|
||||
}
|
||||
}
|
||||
|
||||
/** True iff `ensureAttached(tabId)` has succeeded since the last detach. */
|
||||
@@ -483,17 +453,6 @@ export class ChromiumCdp {
|
||||
this.tabOwners.set(tabId, owners);
|
||||
}
|
||||
|
||||
/** Release one session's claim, preserving attachments still used by another. */
|
||||
async releaseSessionTab(sessionId: string, tabId: number): Promise<void> {
|
||||
const owners = this.tabOwners.get(tabId);
|
||||
if (!owners?.delete(sessionId) || owners.size > 0) return;
|
||||
this.tabOwners.delete(tabId);
|
||||
// An observation may still be attaching when the tab is returned. Wait
|
||||
// for it so detach cannot miss the attachment or remove a new owner's claim.
|
||||
await this.attachInFlight.get(tabId)?.catch(() => {});
|
||||
if (!this.tabOwners.has(tabId)) await this.detach(tabId);
|
||||
}
|
||||
|
||||
/** Subscribe to all CDP events. Returned disposable removes the listener. */
|
||||
onEvent(handler: (source: CdpDebuggee, method: string, params: unknown) => void): {
|
||||
dispose(): void;
|
||||
@@ -510,7 +469,6 @@ export class ChromiumCdp {
|
||||
this.attachInFlight.clear();
|
||||
this.tabOwners.clear();
|
||||
this.attachedTabs.clear();
|
||||
this.attachmentIds.clear();
|
||||
this.dialogBuffers.clear();
|
||||
this.dialogSequences.clear();
|
||||
this.consoleBuffers.clear();
|
||||
@@ -681,23 +639,13 @@ export class ChromiumCdp {
|
||||
}
|
||||
|
||||
private async onJavaScriptDialogOpening(tabId: number, params: unknown): Promise<void> {
|
||||
if (!this.attachedTabs.has(tabId) && !this.attachInFlight.has(tabId)) return;
|
||||
const parsed = parseDialogOpeningParams(params);
|
||||
try {
|
||||
if (
|
||||
this.options.shouldAutoAcceptDialog &&
|
||||
!(await this.options.shouldAutoAcceptDialog(tabId))
|
||||
) {
|
||||
return;
|
||||
}
|
||||
// The tab may have been returned while its current scope was checked.
|
||||
if (!this.attachedTabs.has(tabId) && !this.attachInFlight.has(tabId)) return;
|
||||
const handleParams: { accept: boolean; promptText?: string } = { accept: true };
|
||||
if (parsed.type === "prompt") {
|
||||
handleParams.promptText = parsed.defaultPrompt ?? "";
|
||||
}
|
||||
await this.api.sendCommand({ tabId }, "Page.handleJavaScriptDialog", handleParams);
|
||||
if (!this.attachedTabs.has(tabId) && !this.attachInFlight.has(tabId)) return;
|
||||
const sequence = (this.dialogSequences.get(tabId) ?? 0) + 1;
|
||||
this.dialogSequences.set(tabId, sequence);
|
||||
this.appendDialog(tabId, {
|
||||
@@ -857,7 +805,6 @@ export class ChromiumCdp {
|
||||
const listener = (source: chrome.debugger.Debuggee, _reason: string) => {
|
||||
if (typeof source.tabId === "number") {
|
||||
this.attachedTabs.delete(source.tabId);
|
||||
this.attachmentIds.delete(source.tabId);
|
||||
this.attachInFlight.delete(source.tabId);
|
||||
this.tabOwners.delete(source.tabId);
|
||||
this.clearDialogState(source.tabId);
|
||||
@@ -888,9 +835,15 @@ export class ChromiumCdp {
|
||||
|
||||
/** Detach tabs only when no other live session has claimed them. */
|
||||
async detachSession(sessionId: string): Promise<void> {
|
||||
await Promise.all(
|
||||
Array.from(this.tabOwners.keys(), (tabId) => this.releaseSessionTab(sessionId, tabId)),
|
||||
);
|
||||
const tabsToDetach: number[] = [];
|
||||
for (const [tabId, owners] of this.tabOwners) {
|
||||
owners.delete(sessionId);
|
||||
if (owners.size === 0) {
|
||||
this.tabOwners.delete(tabId);
|
||||
tabsToDetach.push(tabId);
|
||||
}
|
||||
}
|
||||
await Promise.all(tabsToDetach.map((tabId) => this.detach(tabId)));
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -45,32 +45,10 @@ function portHarness() {
|
||||
|
||||
describe("RecordFrameAgent", () => {
|
||||
afterEach(() => {
|
||||
vi.unstubAllGlobals();
|
||||
document.documentElement.removeAttribute(RECORD_DOCUMENT_ATTRIBUTE);
|
||||
document.body.replaceChildren();
|
||||
});
|
||||
|
||||
it("starts when crypto.randomUUID is unavailable", async () => {
|
||||
const harness = portHarness();
|
||||
const getRandomValues = vi.fn((bytes: Uint8Array) => {
|
||||
bytes.fill(0x11);
|
||||
return bytes;
|
||||
});
|
||||
vi.stubGlobal("crypto", { getRandomValues });
|
||||
vi.stubGlobal("chrome", {
|
||||
runtime: {
|
||||
connect: vi.fn(() => harness.port),
|
||||
sendMessage: vi.fn(),
|
||||
},
|
||||
});
|
||||
const agent = new RecordFrameAgent();
|
||||
|
||||
await expect(
|
||||
agent.start({ type: RECORD_FRAME_START, requestId: "rec-http", startedAtMs: 10 }),
|
||||
).resolves.toEqual({ ok: true });
|
||||
expect(getRandomValues).toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("keeps a failed stop retryable and flushes the final dirty fill", async () => {
|
||||
const harness = portHarness();
|
||||
const sendMessage = vi
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
import { createRandomUuid } from "@/lib/random-uuid";
|
||||
import {
|
||||
isAcceptedRecordStepAck,
|
||||
RECORD_STEP,
|
||||
@@ -19,7 +18,7 @@ export class RecordStepDelivery {
|
||||
constructor(
|
||||
requestId: string,
|
||||
send: SendRecordStepMessage = (message) => chrome.runtime.sendMessage(message),
|
||||
producerId: string = createRandomUuid(),
|
||||
producerId: string = crypto.randomUUID(),
|
||||
) {
|
||||
this.#requestId = requestId;
|
||||
this.#producerId = producerId;
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
import { createRandomUuid } from "@/lib/random-uuid";
|
||||
import {
|
||||
markRecordingDocument,
|
||||
type RecordingDocumentMarker,
|
||||
@@ -68,7 +67,7 @@ export class RecordFrameAgent {
|
||||
async #start(
|
||||
message: RecordFrameStartMessage,
|
||||
): Promise<{ ok: true } | { ok: false; error: string }> {
|
||||
const producerId = createRandomUuid();
|
||||
const producerId = crypto.randomUUID();
|
||||
const root = await waitForDocumentElement();
|
||||
if (this.#disposed) return { ok: false, error: "recording document is disposed" };
|
||||
const marker = markRecordingDocument(producerId, root);
|
||||
|
||||
@@ -25,7 +25,7 @@ import { recordFrameCoordinator } from "@/lib/recording/frame-coordinator";
|
||||
import { attachSessionsLiveFlag } from "@/lib/sessions-live-flag";
|
||||
import { createDisconnectCleanup } from "@/session-manager/disconnect-cleanup";
|
||||
import { attachSessionEventHandler } from "@/session-manager/event-handler";
|
||||
import { isAgentControlledTab, SessionManager } from "@/session-manager/manager";
|
||||
import { SessionManager } from "@/session-manager/manager";
|
||||
import {
|
||||
attachBorrowNotificationButtonHandler,
|
||||
attachBorrowNotificationClickHandler,
|
||||
@@ -41,8 +41,6 @@ import {
|
||||
attachRecordStepListener,
|
||||
type RecordRuntimeDeps,
|
||||
} from "@/tools/record";
|
||||
import { chromeTabsApi } from "@/tools/shared";
|
||||
import { chromeTabMutationApi } from "@/tools/tabs";
|
||||
import { detectBrowserMeta } from "@/transport/handshake";
|
||||
import type { Transport } from "@/transport/transport";
|
||||
import { WSTransport } from "@/transport/ws-transport";
|
||||
@@ -51,12 +49,7 @@ export default defineBackground(() => {
|
||||
const controller = new ConnectionController();
|
||||
const transport = new WSTransport({ url: __BSK_DAEMON_WS_URL__ });
|
||||
const sessions = new SessionManager();
|
||||
const cdp = new ChromiumCdp(undefined, {
|
||||
shouldAutoAcceptDialog: async (tabId) => {
|
||||
const tab = await chrome.tabs.get(tabId);
|
||||
return sessions.findByWindowId(tab.windowId) !== null;
|
||||
},
|
||||
});
|
||||
const cdp = new ChromiumCdp();
|
||||
const sessionsLive = attachSessionsLiveFlag({ manager: sessions });
|
||||
let overlayGeneration = 0;
|
||||
const controlModes = new Map<string, OverlayMode>();
|
||||
@@ -87,24 +80,6 @@ export default defineBackground(() => {
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Authoritative overlay state for a specific tab. Agent Window tabs are
|
||||
* free by default; only tabs explicitly claimed through session startup,
|
||||
* `tab_create`, or `tab_borrow` receive the control overlay.
|
||||
*/
|
||||
function overlayStateForTab(tabId?: number, windowId?: number): OverlayAgentStateMessage {
|
||||
if (typeof tabId === "number" && typeof windowId === "number") {
|
||||
const ctx = sessions.findByWindowId(windowId);
|
||||
if (ctx && isAgentControlledTab(ctx, tabId)) return overlayStateForWindow(windowId);
|
||||
}
|
||||
return {
|
||||
type: OVERLAY_AGENT_STATE,
|
||||
sessionId: null,
|
||||
mode: "hidden",
|
||||
generation: overlayGeneration,
|
||||
};
|
||||
}
|
||||
|
||||
async function pushOverlayStateToTab(
|
||||
tabId: number,
|
||||
state: OverlayAgentStateMessage,
|
||||
@@ -116,18 +91,13 @@ export default defineBackground(() => {
|
||||
}
|
||||
}
|
||||
|
||||
async function pushOverlayStateForTab(tabId: number, windowId?: number): Promise<void> {
|
||||
const state = overlayStateForTab(tabId, windowId);
|
||||
await pushOverlayStateToTab(tabId, state);
|
||||
}
|
||||
|
||||
async function pushOverlayStateForWindow(windowId: number): Promise<void> {
|
||||
const state = overlayStateForWindow(windowId);
|
||||
const tabs = await chrome.tabs.query({ windowId });
|
||||
await Promise.all(
|
||||
tabs.map((tab) => {
|
||||
if (typeof tab.id !== "number") return Promise.resolve();
|
||||
return pushOverlayStateForTab(tab.id, windowId);
|
||||
}),
|
||||
tabs.map((tab) =>
|
||||
typeof tab.id === "number" ? pushOverlayStateToTab(tab.id, state) : Promise.resolve(),
|
||||
),
|
||||
);
|
||||
}
|
||||
|
||||
@@ -166,30 +136,13 @@ export default defineBackground(() => {
|
||||
if (typeof tab.windowId !== "number") return;
|
||||
pushOverlayStateForAgentWindow(tab.windowId);
|
||||
});
|
||||
// Newly observed tabs are free unless the agent's own creation path has
|
||||
// already claimed their concrete id. This listener only renders that
|
||||
// state; it never infers or mutates ownership from event ordering.
|
||||
chrome.tabs.onCreated.addListener((tab) => {
|
||||
if (typeof tab.windowId !== "number" || typeof tab.id !== "number") return;
|
||||
if (!sessions.findByWindowId(tab.windowId)) return;
|
||||
void pushOverlayStateForTab(tab.id, tab.windowId);
|
||||
});
|
||||
chrome.tabs.onRemoved.addListener((tabId, removeInfo) => {
|
||||
sessions.forgetClosedTab(tabId, { isWindowClosing: removeInfo.isWindowClosing });
|
||||
});
|
||||
// Re-sync the storage.session flag on SW startup so a previous SW's
|
||||
// stale `true` does not keep waking us on every page load until the
|
||||
// first mutation (review M4/M5 round 3 m-R3-1).
|
||||
void sessionsLive.refresh();
|
||||
const cleanupAfterDisconnect = createDisconnectCleanup({
|
||||
manager: sessions,
|
||||
// Same contract as the dispatcher's `tool.session_stop`: without these
|
||||
// deps the agent-tab cleanup and the window-release path are dead code.
|
||||
sessionStopDeps: {
|
||||
cdp,
|
||||
tabManagement: { tabs: chromeTabMutationApi },
|
||||
tabsQuery: chromeTabsApi,
|
||||
},
|
||||
sessionStopDeps: { cdp },
|
||||
onSessionsChanged: () => {
|
||||
void sessionsLive.syncFromManager();
|
||||
},
|
||||
@@ -223,9 +176,6 @@ export default defineBackground(() => {
|
||||
recording: recordDeps,
|
||||
onSessionsChanged: onOverlaySessionStateChanged,
|
||||
onBrowserControlResumed,
|
||||
onAgentTabClaimed: (tabId, windowId) => {
|
||||
void pushOverlayStateForTab(tabId, windowId);
|
||||
},
|
||||
approveBorrow: (ctx) =>
|
||||
requestBorrowConfirmation(ctx.tabId, {
|
||||
...(ctx.signal !== undefined ? { signal: ctx.signal } : {}),
|
||||
@@ -359,11 +309,7 @@ export default defineBackground(() => {
|
||||
}
|
||||
|
||||
if (msg.kind === OVERLAY_MSG_READY) {
|
||||
// Resolve from explicit tab ownership before sending so free tabs never
|
||||
// flash the control mask.
|
||||
if (typeof sender.tab?.id === "number") {
|
||||
void pushOverlayStateForTab(sender.tab.id, sender.tab.windowId);
|
||||
}
|
||||
sendResponse(overlayStateForWindow(sender.tab?.windowId));
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
@@ -122,8 +122,8 @@ describe("App", () => {
|
||||
|
||||
expect(screen.queryByText(/^扩展 v/)).toBeNull();
|
||||
expect(screen.queryByText(/^daemon v/)).toBeNull();
|
||||
expect(screen.getByTitle("扩展版本").textContent).toBe(`Ext ${EXTENSION_VERSION}`);
|
||||
expect(screen.getByTitle("bsk 版本").textContent).toBe(`CLI ${mockDaemonVersion}`);
|
||||
expect(screen.getByTitle("扩展版本").textContent).toBe(EXTENSION_VERSION);
|
||||
expect(screen.getByTitle("bsk 版本").textContent).toBe(mockDaemonVersion);
|
||||
expect(screen.getByText("03c3e47f")).toBeTruthy();
|
||||
|
||||
const copyButton = screen.getByRole("button", { name: "复制实例 ID" });
|
||||
|
||||
@@ -267,9 +267,9 @@ export function App() {
|
||||
data-slot="popup-meta"
|
||||
>
|
||||
<div className="flex shrink-0 items-center gap-1">
|
||||
<span title={t("popup.daemonVersionHint")}>CLI {daemonVersion}</span>
|
||||
<span title={t("popup.extensionVersionHint")}>{extensionVersion}</span>
|
||||
<span aria-hidden>/</span>
|
||||
<span title={t("popup.extensionVersionHint")}>Ext {extensionVersion}</span>
|
||||
<span title={t("popup.daemonVersionHint")}>{daemonVersion}</span>
|
||||
</div>
|
||||
<div className="flex min-w-0 items-center justify-end gap-1">
|
||||
<span className="shrink-0">{t("popup.instanceTitle")}</span>
|
||||
|
||||
@@ -2,7 +2,7 @@ import { describe, expect, it, vi } from "vitest";
|
||||
import {
|
||||
CAPTURE_SUPPRESS,
|
||||
type CaptureSuppressMessage,
|
||||
withExtensionOverlayHidden,
|
||||
withOverlaysHiddenForCapture,
|
||||
} from "../capture-suppress-bridge";
|
||||
|
||||
function recordingSendToTab(events: string[]) {
|
||||
@@ -12,12 +12,12 @@ function recordingSendToTab(events: string[]) {
|
||||
});
|
||||
}
|
||||
|
||||
describe("withExtensionOverlayHidden", () => {
|
||||
describe("withOverlaysHiddenForCapture", () => {
|
||||
it("sends begin → fn → end and returns fn's result", async () => {
|
||||
const events: string[] = [];
|
||||
const sendToTab = recordingSendToTab(events);
|
||||
|
||||
const result = await withExtensionOverlayHidden(
|
||||
const result = await withOverlaysHiddenForCapture(
|
||||
7,
|
||||
async () => {
|
||||
events.push("capture");
|
||||
@@ -37,7 +37,7 @@ describe("withExtensionOverlayHidden", () => {
|
||||
const sendToTab = recordingSendToTab(events);
|
||||
|
||||
await expect(
|
||||
withExtensionOverlayHidden(
|
||||
withOverlaysHiddenForCapture(
|
||||
7,
|
||||
async () => {
|
||||
events.push("capture");
|
||||
@@ -55,7 +55,7 @@ describe("withExtensionOverlayHidden", () => {
|
||||
});
|
||||
const fn = vi.fn(async () => "shot");
|
||||
|
||||
const result = await withExtensionOverlayHidden(7, fn, sendToTab);
|
||||
const result = await withOverlaysHiddenForCapture(7, fn, sendToTab);
|
||||
|
||||
expect(result).toBe("shot");
|
||||
expect(fn).toHaveBeenCalledTimes(1);
|
||||
@@ -69,7 +69,7 @@ describe("withExtensionOverlayHidden", () => {
|
||||
return { type: CAPTURE_SUPPRESS, ok: true };
|
||||
});
|
||||
|
||||
const result = await withExtensionOverlayHidden(7, async () => "shot", sendToTab);
|
||||
const result = await withOverlaysHiddenForCapture(7, async () => "shot", sendToTab);
|
||||
|
||||
expect(result).toBe("shot");
|
||||
expect(sendToTab).toHaveBeenCalledTimes(2);
|
||||
|
||||
@@ -1,30 +0,0 @@
|
||||
import { afterEach, describe, expect, it, vi } from "vitest";
|
||||
import { createRandomUuid } from "../random-uuid";
|
||||
|
||||
describe("createRandomUuid", () => {
|
||||
afterEach(() => {
|
||||
vi.unstubAllGlobals();
|
||||
});
|
||||
|
||||
it("uses crypto.randomUUID when it is available", () => {
|
||||
const randomUUID = vi.fn(() => "00000000-0000-4000-8000-000000000000");
|
||||
vi.stubGlobal("crypto", { randomUUID, getRandomValues: vi.fn() });
|
||||
|
||||
expect(createRandomUuid()).toBe("00000000-0000-4000-8000-000000000000");
|
||||
expect(randomUUID).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it("falls back to getRandomValues and sets UUID v4 bits", () => {
|
||||
const bytes = new Uint8Array(16).fill(0xff);
|
||||
const getRandomValues = vi.fn((target: Uint8Array) => {
|
||||
target.set(bytes);
|
||||
return target;
|
||||
});
|
||||
vi.stubGlobal("crypto", { getRandomValues });
|
||||
|
||||
const uuid = createRandomUuid();
|
||||
|
||||
expect(uuid).toBe("ffffffff-ffff-4fff-bfff-ffffffffffff");
|
||||
expect(getRandomValues).toHaveBeenCalledOnce();
|
||||
});
|
||||
});
|
||||
@@ -1,9 +1,9 @@
|
||||
/**
|
||||
* Wire protocol and background-side helper for temporarily excluding the
|
||||
* extension's in-page overlay. Screenshots use it to avoid captured chrome;
|
||||
* coordinate-driven native input uses it so Chrome hit-tests the page.
|
||||
* Wire protocol and background-side helper for hiding the extension's
|
||||
* in-page overlay while a screenshot is captured, so captured frames only
|
||||
* contain the page itself.
|
||||
*
|
||||
* The background wraps each bounded operation in `withExtensionOverlayHidden`,
|
||||
* The background wraps every capture in `withOverlaysHiddenForCapture`,
|
||||
* which sends `begin` (the content script hides the overlay host and only
|
||||
* acks once the compositor has produced an overlay-free frame) and always
|
||||
* follows up with `end`, even when the capture throws. Tabs without the
|
||||
@@ -46,7 +46,7 @@ const defaultSendToTab: CaptureSuppressSendToTab = (tabId, message) =>
|
||||
* (or any other `begin` failure) simply skips suppression — there is no
|
||||
* overlay to hide in that tab.
|
||||
*/
|
||||
export async function withExtensionOverlayHidden<T>(
|
||||
export async function withOverlaysHiddenForCapture<T>(
|
||||
tabId: number,
|
||||
fn: () => Promise<T>,
|
||||
sendToTab: CaptureSuppressSendToTab = defaultSendToTab,
|
||||
|
||||
@@ -3,10 +3,8 @@
|
||||
* between the content-script control overlay and the background SW.
|
||||
*
|
||||
* Content script → background:
|
||||
* - `{ kind: "overlay.ready" }` → background decides the per-tab state first
|
||||
* (see overlayStateForTab) and pushes the authoritative overlay state for
|
||||
* that tab. It also proactively pushes on tab create and control-mode
|
||||
* change, so a tab usually receives state before it ever sends ready.
|
||||
* - `{ kind: "overlay.ready" }` → background replies with the authoritative
|
||||
* overlay state for the sender's window.
|
||||
* - `{ kind: "overlay.interrupt", sessionId }` → background asks the
|
||||
* daemon (via a `session.user_interrupt` WS event) to cancel
|
||||
* every inflight + queued tool call for that session with
|
||||
|
||||
@@ -1,26 +0,0 @@
|
||||
/**
|
||||
* Generate a UUID v4 in browser contexts where randomUUID() is unavailable.
|
||||
*
|
||||
* Crypto.randomUUID() is restricted to secure contexts, while
|
||||
* crypto.getRandomValues() is available to content scripts on ordinary HTTP
|
||||
* origins. BrowserSkill records many intranet pages served over HTTP, so the
|
||||
* fallback is required for recording to work on those pages.
|
||||
*/
|
||||
export function createRandomUuid(): string {
|
||||
const cryptoApi = globalThis.crypto;
|
||||
if (typeof cryptoApi.randomUUID === "function") return cryptoApi.randomUUID();
|
||||
|
||||
const bytes = new Uint8Array(16);
|
||||
cryptoApi.getRandomValues(bytes);
|
||||
bytes[6] = (bytes[6]! & 0x0f) | 0x40;
|
||||
bytes[8] = (bytes[8]! & 0x3f) | 0x80;
|
||||
|
||||
const hex = Array.from(bytes, (byte) => byte.toString(16).padStart(2, "0")).join("");
|
||||
return [
|
||||
hex.slice(0, 8),
|
||||
hex.slice(8, 12),
|
||||
hex.slice(12, 16),
|
||||
hex.slice(16, 20),
|
||||
hex.slice(20),
|
||||
].join("-");
|
||||
}
|
||||
@@ -1,4 +1,3 @@
|
||||
import { createRandomUuid } from "../random-uuid";
|
||||
import {
|
||||
isRecordFrameQueryMessage,
|
||||
RECORD_FRAME_PORT,
|
||||
@@ -189,7 +188,7 @@ export class RecordFrameCoordinator {
|
||||
const recording = this.#recordings.get(requestId);
|
||||
if (!recording) return true;
|
||||
recording.finishing = true;
|
||||
const commandId = createRandomUuid();
|
||||
const commandId = crypto.randomUUID();
|
||||
const results = await Promise.all(
|
||||
[...recording.agents.values()].map((agent) => this.#stopAgent(agent, requestId, commandId)),
|
||||
);
|
||||
|
||||
@@ -9,7 +9,7 @@ describe("disconnect session cleanup", () => {
|
||||
const manager = new SessionManager({
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => nextWindowId++),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
remove,
|
||||
},
|
||||
});
|
||||
@@ -41,7 +41,7 @@ describe("disconnect session cleanup", () => {
|
||||
const manager = new SessionManager({
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 100),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
remove: vi.fn(() => removeGate),
|
||||
},
|
||||
});
|
||||
|
||||
@@ -39,7 +39,7 @@ describe("attachSessionEventHandler", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 4242),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
await manager.start("aa11");
|
||||
@@ -73,7 +73,7 @@ describe("attachSessionEventHandler", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 4242),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const ctx = await manager.start("aa11");
|
||||
@@ -87,7 +87,6 @@ describe("attachSessionEventHandler", () => {
|
||||
windowEvents: events.api,
|
||||
});
|
||||
|
||||
manager.forgetClosedTab(7, { isWindowClosing: true });
|
||||
events.emit(4242);
|
||||
for (let i = 0; i < 4; i += 1) await Promise.resolve();
|
||||
|
||||
@@ -114,7 +113,7 @@ describe("attachSessionEventHandler", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 1),
|
||||
remove: vi.fn(),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const transport = fakeTransport();
|
||||
@@ -130,7 +129,7 @@ describe("attachSessionEventHandler", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 1),
|
||||
remove: vi.fn(),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const transport = fakeTransport();
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { describe, expect, it, vi } from "vitest";
|
||||
import type { AgentWindowApi, AgentWindowCreateOptions } from "../agent-window";
|
||||
import { isAgentControlledTab, SessionManager } from "../manager";
|
||||
import { SessionManager } from "../manager";
|
||||
|
||||
function fakeAgentWindow(): AgentWindowApi & {
|
||||
createMock: ReturnType<typeof vi.fn>;
|
||||
@@ -13,7 +13,7 @@ function fakeAgentWindow(): AgentWindowApi & {
|
||||
return id;
|
||||
});
|
||||
const removeMock = vi.fn(async (_id: number) => {});
|
||||
const ensureActiveTabMock = vi.fn(async (_windowId: number, _url: string) => 0);
|
||||
const ensureActiveTabMock = vi.fn(async (_windowId: number, _url: string) => {});
|
||||
return {
|
||||
create: createMock,
|
||||
remove: removeMock,
|
||||
@@ -151,76 +151,6 @@ describe("SessionManager", () => {
|
||||
expect(sm.list()).toEqual([]);
|
||||
});
|
||||
|
||||
describe("explicit tab claims", () => {
|
||||
it("claims the exact home tab returned by AgentWindowApi", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow() });
|
||||
const ctx = await sm.start("aa11");
|
||||
expect(ctx.agentCreatedTabs).toEqual(new Set([0]));
|
||||
expect(isAgentControlledTab(ctx, 0)).toBe(true);
|
||||
});
|
||||
|
||||
it("keeps every other tab free without classification state", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow() });
|
||||
const ctx = await sm.start("aa11");
|
||||
expect(isAgentControlledTab(ctx, 99)).toBe(false);
|
||||
expect(ctx).not.toHaveProperty("userTabs");
|
||||
expect(ctx).not.toHaveProperty("pendingAgentTabCount");
|
||||
});
|
||||
|
||||
it("treats a committed borrow as an explicit claim", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow() });
|
||||
const ctx = await sm.start("aa11");
|
||||
const reservation = sm.tryReserveBorrow(42, ctx.sessionId);
|
||||
if ("borrowedBy" in reservation) throw new Error("unexpected borrow conflict");
|
||||
reservation.commit({ tabId: 42, originalWindowId: 7, originalIndex: 3 });
|
||||
expect(isAgentControlledTab(ctx, 42)).toBe(true);
|
||||
});
|
||||
|
||||
it("forgets an agent-created tab after Chrome removes it", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow() });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.agentCreatedTabs.add(42);
|
||||
sm.forgetClosedTab(42);
|
||||
expect(ctx.agentCreatedTabs.has(42)).toBe(false);
|
||||
expect(isAgentControlledTab(ctx, 0)).toBe(true);
|
||||
});
|
||||
|
||||
it("forgets closed borrows idempotently without affecting other tabs or sessions", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow() });
|
||||
const a = await sm.start("aa11");
|
||||
const b = await sm.start("bb22");
|
||||
a.borrowedTabs.set(42, { tabId: 42, originalWindowId: 7, originalIndex: 0 });
|
||||
a.borrowedTabs.set(43, { tabId: 43, originalWindowId: 7, originalIndex: 1 });
|
||||
b.borrowedTabs.set(44, { tabId: 44, originalWindowId: 8, originalIndex: 0 });
|
||||
|
||||
sm.forgetClosedTab(42);
|
||||
sm.forgetClosedTab(42);
|
||||
sm.forgetClosedTab(999);
|
||||
|
||||
expect(isAgentControlledTab(a, 42)).toBe(false);
|
||||
expect(sm.findBorrowingSession(42, null)).toBeNull();
|
||||
expect([...a.borrowedTabs.keys()]).toEqual([43]);
|
||||
expect([...b.borrowedTabs.keys()]).toEqual([44]);
|
||||
expect(sm.list()).toHaveLength(2);
|
||||
});
|
||||
|
||||
it("prevents an in-flight borrow from reclaiming a closed tab", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow() });
|
||||
const ctx = await sm.start("aa11");
|
||||
const reservation = sm.tryReserveBorrow(42, ctx.sessionId);
|
||||
if ("borrowedBy" in reservation) throw new Error("unexpected borrow conflict");
|
||||
|
||||
sm.forgetClosedTab(42);
|
||||
|
||||
expect(() =>
|
||||
reservation.commit({ tabId: 42, originalWindowId: 7, originalIndex: 0 }),
|
||||
).toThrow(/reservation disappeared/);
|
||||
reservation.release();
|
||||
expect(sm.findBorrowingSession(42, null)).toBeNull();
|
||||
expect(ctx.borrowedTabs.has(42)).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("findBorrowingSession", () => {
|
||||
it("returns null when no session has borrowed the tab", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow() });
|
||||
|
||||
@@ -13,6 +13,8 @@ describe("RefStore", () => {
|
||||
backendNodeId: 42,
|
||||
tabId: 7,
|
||||
generation: 0,
|
||||
kind: "dom",
|
||||
capabilities: ["interact", "screenshot"],
|
||||
});
|
||||
expect(s.size()).toBe(1);
|
||||
expect(s.isEmpty()).toBe(false);
|
||||
@@ -48,4 +50,31 @@ describe("RefStore", () => {
|
||||
cdpSessionId: "child-session",
|
||||
});
|
||||
});
|
||||
|
||||
it("preserves explicit capabilities for visual surface refs", () => {
|
||||
const s = new RefStore();
|
||||
s.set("e1", 42, {
|
||||
tabId: 7,
|
||||
kind: "surface",
|
||||
capabilities: ["screenshot"],
|
||||
});
|
||||
|
||||
expect(s.resolveEntry("e1")).toMatchObject({
|
||||
kind: "surface",
|
||||
capabilities: ["screenshot"],
|
||||
});
|
||||
});
|
||||
|
||||
it("never grants ordinary interaction to a surface through defaults or caller input", () => {
|
||||
const s = new RefStore();
|
||||
s.set("e1", 42, { tabId: 7, kind: "surface" });
|
||||
s.set("e2", 43, {
|
||||
tabId: 7,
|
||||
kind: "surface",
|
||||
capabilities: ["interact", "screenshot"],
|
||||
});
|
||||
|
||||
expect(s.resolveEntry("e1")?.capabilities).toEqual(["screenshot"]);
|
||||
expect(s.resolveEntry("e2")?.capabilities).toEqual(["screenshot"]);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -14,11 +14,8 @@ export interface AgentWindowApi {
|
||||
* Guarantee the Agent Window has an active, CDP-navigable tab.
|
||||
* `chrome://` pages (including the New Tab page) reject `Page.navigate`,
|
||||
* so sessions bootstrap with `about:blank` instead.
|
||||
*
|
||||
* Resolves with the id of the activated (or newly created) tab, so callers
|
||||
* can track the session's home tab without re-querying Chrome.
|
||||
*/
|
||||
ensureActiveTab(windowId: number, url: string): Promise<number>;
|
||||
ensureActiveTab(windowId: number, url: string): Promise<void>;
|
||||
}
|
||||
|
||||
/** Creation hints for a new Agent Window. */
|
||||
@@ -52,19 +49,15 @@ export const chromeAgentWindowApi: AgentWindowApi = {
|
||||
// cancellation success while the Agent Window remains open.
|
||||
await chrome.windows.remove(windowId);
|
||||
},
|
||||
async ensureActiveTab(windowId: number, url: string): Promise<number> {
|
||||
async ensureActiveTab(windowId: number, url: string): Promise<void> {
|
||||
const tabs = await chrome.tabs.query({ windowId });
|
||||
const first = tabs.find((t) => typeof t.id === "number");
|
||||
if (first?.id !== undefined) {
|
||||
if (first?.id) {
|
||||
if (!first.active) {
|
||||
await chrome.tabs.update(first.id, { active: true });
|
||||
}
|
||||
return first.id;
|
||||
return;
|
||||
}
|
||||
const created = await chrome.tabs.create({ windowId, url, active: true });
|
||||
if (typeof created?.id !== "number") {
|
||||
throw new Error("[bh] chrome.tabs.create returned no tab id");
|
||||
}
|
||||
return created.id;
|
||||
await chrome.tabs.create({ windowId, url, active: true });
|
||||
},
|
||||
};
|
||||
|
||||
@@ -6,20 +6,9 @@ export interface SessionContext {
|
||||
agentWindowId: number;
|
||||
refStore: RefStore;
|
||||
borrowedTabs: Map<number, BorrowedTab>;
|
||||
/**
|
||||
* Tabs explicitly claimed by the agent because it created them. This
|
||||
* includes the Agent Window's home tab and tabs created by `tool.tab_create`.
|
||||
* Tabs opened through Chrome UI never enter this set.
|
||||
*/
|
||||
agentCreatedTabs: Set<number>;
|
||||
createdAtMs: number;
|
||||
}
|
||||
|
||||
/** Whether this session has explicitly claimed control of `tabId`. */
|
||||
export function isAgentControlledTab(ctx: SessionContext, tabId: number): boolean {
|
||||
return ctx.agentCreatedTabs.has(tabId) || ctx.borrowedTabs.has(tabId);
|
||||
}
|
||||
|
||||
export interface BorrowedTab {
|
||||
tabId: number;
|
||||
originalWindowId: number;
|
||||
@@ -117,19 +106,6 @@ export class SessionManager {
|
||||
return Array.from(this.sessions.values());
|
||||
}
|
||||
|
||||
/**
|
||||
* Forget a tab Chrome has removed, including any uncommitted borrow.
|
||||
* Whole-window closures keep committed borrows until the window-removed
|
||||
* handler reports which user tabs could not be returned.
|
||||
*/
|
||||
forgetClosedTab(tabId: number, { isWindowClosing = false } = {}): void {
|
||||
this.borrowReservations.delete(tabId);
|
||||
for (const ctx of this.sessions.values()) {
|
||||
ctx.agentCreatedTabs.delete(tabId);
|
||||
if (!isWindowClosing) ctx.borrowedTabs.delete(tabId);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Look up whether `tabId` is currently borrowed by some *other*
|
||||
* session than the one calling. Used by M8 `tab_borrow` to refuse
|
||||
@@ -203,7 +179,7 @@ export class SessionManager {
|
||||
const { signal: _signal, ...createOptions } = opts;
|
||||
windowId = await this.agentWindow.create(AGENT_WINDOW_HOME, createOptions);
|
||||
throwIfSessionStartAborted(opts.signal);
|
||||
const homeTabId = await this.agentWindow.ensureActiveTab(windowId, AGENT_WINDOW_HOME);
|
||||
await this.agentWindow.ensureActiveTab(windowId, AGENT_WINDOW_HOME);
|
||||
throwIfSessionStartAborted(opts.signal);
|
||||
|
||||
const ctx: SessionContext = {
|
||||
@@ -211,10 +187,6 @@ export class SessionManager {
|
||||
agentWindowId: windowId,
|
||||
refStore: new RefStore(),
|
||||
borrowedTabs: new Map(),
|
||||
// The home tab is the session's first explicit claim. Every other
|
||||
// tab remains free until `tab_create` or `tab_borrow` identifies it
|
||||
// by its concrete Chrome tab id.
|
||||
agentCreatedTabs: new Set([homeTabId]),
|
||||
createdAtMs: this.now(),
|
||||
};
|
||||
this.sessions.set(sessionId, ctx);
|
||||
|
||||
@@ -1,37 +1,55 @@
|
||||
import type { VisualCandidate } from "@/tools/vom/visual-discovery";
|
||||
import type { Rect } from "@browser-skill/vom";
|
||||
|
||||
/** Session-local refs describe the latest observation. Reusing eN does not identify
|
||||
* which observation a caller read; generation is internal bookkeeping only. */
|
||||
/**
|
||||
* Per-session map from `@e<N>` snapshot refs to a CDP node address.
|
||||
*
|
||||
* Each fresh `tool.snapshot` resets the store: M6 will call
|
||||
* `replace(...)` with the new ref → node address pairs. A node address
|
||||
* includes the owning flat CDP session/frame when the element lives in
|
||||
* an OOPIF; tools resolve live geometry from that identity at call time.
|
||||
*
|
||||
* Refs are session-scoped (§7): looking up a ref in the wrong session
|
||||
* returns `null`, never silently leaks. Storing values in different
|
||||
* sessions is fine; they live in independent `RefStore` instances
|
||||
* inside the `SessionContext`.
|
||||
*/
|
||||
export type BackendNodeId = number;
|
||||
export type RefCapability = "interact" | "screenshot";
|
||||
export type RefTargetKind = "dom" | "surface";
|
||||
|
||||
export interface DomRefEntry {
|
||||
readonly kind: "dom";
|
||||
export interface RefEntry {
|
||||
backendNodeId: BackendNodeId;
|
||||
tabId: number | null;
|
||||
frameId?: string;
|
||||
cdpSessionId?: string;
|
||||
visibleRect?: Rect;
|
||||
kind: RefTargetKind;
|
||||
capabilities: RefCapability[];
|
||||
generation: number;
|
||||
}
|
||||
|
||||
export interface VisualRefInput {
|
||||
readonly kind: "visual-region";
|
||||
readonly candidate: VisualCandidate;
|
||||
}
|
||||
|
||||
export type RefEntry = DomRefEntry | (VisualRefInput & { readonly generation: number });
|
||||
|
||||
export type RefInput =
|
||||
| VisualRefInput
|
||||
| BackendNodeId
|
||||
| {
|
||||
backendNodeId: BackendNodeId;
|
||||
tabId: number;
|
||||
frameId?: string;
|
||||
cdpSessionId?: string;
|
||||
visibleRect?: Rect;
|
||||
kind?: RefTargetKind;
|
||||
capabilities?: RefCapability[];
|
||||
};
|
||||
|
||||
function capabilitiesFor(
|
||||
kind: RefTargetKind,
|
||||
capabilities: RefCapability[] | undefined,
|
||||
): RefCapability[] {
|
||||
if (kind === "surface") return ["screenshot"];
|
||||
return capabilities ?? ["interact", "screenshot"];
|
||||
}
|
||||
|
||||
export class RefStore {
|
||||
private map = new Map<string, RefEntry>();
|
||||
private readonly map = new Map<string, RefEntry>();
|
||||
private generation = 0;
|
||||
|
||||
size(): number {
|
||||
@@ -44,7 +62,7 @@ export class RefStore {
|
||||
|
||||
resolve(ref: string, opts: { tabId?: number } = {}): BackendNodeId | null {
|
||||
const entry = this.map.get(normaliseRef(ref));
|
||||
if (!entry || entry.kind !== "dom") return null;
|
||||
if (!entry) return null;
|
||||
if (opts.tabId !== undefined && entry.tabId !== opts.tabId) return null;
|
||||
return entry.backendNodeId;
|
||||
}
|
||||
@@ -58,11 +76,9 @@ export class RefStore {
|
||||
* Used after every fresh `tool.snapshot`.
|
||||
*/
|
||||
replace(entries: Iterable<readonly [string, RefInput]>): void {
|
||||
const generation = this.generation + 1;
|
||||
const next = new Map<string, RefEntry>();
|
||||
for (const [ref, input] of entries) next.set(normaliseRef(ref), this.entry(input, generation));
|
||||
this.map = next;
|
||||
this.generation = generation;
|
||||
this.map.clear();
|
||||
this.generation += 1;
|
||||
for (const [ref, input] of entries) this.map.set(normaliseRef(ref), this.entry(input));
|
||||
}
|
||||
|
||||
set(
|
||||
@@ -72,14 +88,20 @@ export class RefStore {
|
||||
tabId?: number;
|
||||
frameId?: string;
|
||||
cdpSessionId?: string;
|
||||
visibleRect?: Rect;
|
||||
kind?: RefTargetKind;
|
||||
capabilities?: RefCapability[];
|
||||
} = {},
|
||||
): void {
|
||||
const kind = opts.kind ?? "dom";
|
||||
this.map.set(normaliseRef(ref), {
|
||||
kind: "dom",
|
||||
backendNodeId: id,
|
||||
tabId: opts.tabId ?? null,
|
||||
...(opts.frameId ? { frameId: opts.frameId } : {}),
|
||||
...(opts.cdpSessionId ? { cdpSessionId: opts.cdpSessionId } : {}),
|
||||
...(opts.visibleRect ? { visibleRect: opts.visibleRect } : {}),
|
||||
kind,
|
||||
capabilities: capabilitiesFor(kind, opts.capabilities),
|
||||
generation: this.generation,
|
||||
});
|
||||
}
|
||||
@@ -92,37 +114,26 @@ export class RefStore {
|
||||
return this.map.entries();
|
||||
}
|
||||
|
||||
private entry(input: RefInput, generation: number): RefEntry {
|
||||
if (typeof input !== "number" && "kind" in input) {
|
||||
const { document } = input.candidate;
|
||||
if (
|
||||
!document?.attachmentId ||
|
||||
!document.frameId ||
|
||||
!Number.isSafeInteger(document.target?.tabId) ||
|
||||
!Number.isSafeInteger(document.documentElementBackendNodeId) ||
|
||||
document.documentElementBackendNodeId <= 0 ||
|
||||
!Number.isSafeInteger(input.candidate.backendNodeId) ||
|
||||
input.candidate.backendNodeId <= 0
|
||||
)
|
||||
throw new TypeError("visual ref requires a verified DOM identity and anchor");
|
||||
// Preserve the read-only evidence and shared clipping chain; do not clone ancestors per ref.
|
||||
return { kind: "visual-region", candidate: input.candidate, generation };
|
||||
}
|
||||
private entry(input: RefInput): RefEntry {
|
||||
if (typeof input === "number") {
|
||||
return {
|
||||
kind: "dom",
|
||||
backendNodeId: input,
|
||||
tabId: null,
|
||||
generation,
|
||||
kind: "dom",
|
||||
capabilities: ["interact", "screenshot"],
|
||||
generation: this.generation,
|
||||
};
|
||||
}
|
||||
const kind = input.kind ?? "dom";
|
||||
return {
|
||||
kind: "dom",
|
||||
backendNodeId: input.backendNodeId,
|
||||
tabId: input.tabId,
|
||||
...(input.frameId ? { frameId: input.frameId } : {}),
|
||||
...(input.cdpSessionId ? { cdpSessionId: input.cdpSessionId } : {}),
|
||||
generation,
|
||||
...(input.visibleRect ? { visibleRect: input.visibleRect } : {}),
|
||||
kind,
|
||||
capabilities: capabilitiesFor(kind, input.capabilities),
|
||||
generation: this.generation,
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,7 +13,7 @@ function fakeAgentWindow(ids: number[]) {
|
||||
return id;
|
||||
}),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
@@ -49,54 +49,13 @@ describe("ToolDispatcher", () => {
|
||||
vi.unstubAllGlobals();
|
||||
});
|
||||
|
||||
it.each([
|
||||
"tool.snapshot",
|
||||
"tool.evaluate",
|
||||
"tool.get_html",
|
||||
"tool.console",
|
||||
])("annotates Chrome extension-access failures from %s", async (method) => {
|
||||
const tab = { id: 7, windowId: 4242, active: true, url: "https://example.test" };
|
||||
vi.stubGlobal("chrome", {
|
||||
tabs: {
|
||||
get: vi.fn(async () => tab),
|
||||
query: vi.fn(async () => [tab]),
|
||||
},
|
||||
});
|
||||
const { transport, sent, deliver } = fakeTransport();
|
||||
const sessions = new SessionManager({
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 4242),
|
||||
remove: vi.fn(),
|
||||
ensureActiveTab: vi.fn(),
|
||||
},
|
||||
});
|
||||
await sessions.start("test");
|
||||
const error = new Error("Cannot access a chrome-extension:// URL of different extension");
|
||||
const cdp = {
|
||||
send: vi.fn().mockRejectedValue(error),
|
||||
ensureConsoleCapture: vi.fn().mockRejectedValue(error),
|
||||
consoleEntriesSince: vi.fn(),
|
||||
} as unknown as TestDispatcherCdp;
|
||||
const dispatcher = new ToolDispatcher({ transport, sessions, cdp });
|
||||
dispatcher.start();
|
||||
deliver(makeRequest(method, { session_id: "test", expression: "document.title" }));
|
||||
await vi.waitFor(() => expect(sent).toHaveLength(1));
|
||||
expect(sent[0]).toMatchObject({
|
||||
error: {
|
||||
code: "cdp_failed",
|
||||
data: { reason: "cdp_extension_access_denied" },
|
||||
},
|
||||
});
|
||||
dispatcher.stop();
|
||||
});
|
||||
|
||||
it("uses the configured recording runtime for start and stop", async () => {
|
||||
const { transport, sent, deliver } = fakeTransport();
|
||||
const sessions = new SessionManager({
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 4242),
|
||||
remove: vi.fn(),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
await sessions.start("aa11");
|
||||
@@ -158,7 +117,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 4242),
|
||||
remove: vi.fn(),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const dispatcher = new ToolDispatcher({ transport, sessions });
|
||||
@@ -181,7 +140,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create,
|
||||
remove: vi.fn(),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const dispatcher = new ToolDispatcher({ transport, sessions });
|
||||
@@ -199,7 +158,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 4242),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
await sessions.start("aa11");
|
||||
@@ -213,47 +172,6 @@ describe("ToolDispatcher", () => {
|
||||
expect(sent[0]).toEqual({ id: "r-1", result: {} });
|
||||
});
|
||||
|
||||
it("wires the production tab APIs into tool.session_stop so a surviving user tab releases the window", async () => {
|
||||
// Regression guard for the deps that session_stop reads directly: when
|
||||
// `tabManagement.tabs` / `tabsQuery` are not injected by the dispatcher,
|
||||
// the agent-tab cleanup and the release decision silently no-op and the
|
||||
// Agent Window is closed even though a user tab is still open (issue #57).
|
||||
const removeTab = vi.fn(async () => {});
|
||||
const closeWindow = vi.fn(async () => {});
|
||||
// After cleanup the window still holds one tab (id 99) that is neither
|
||||
// the home tab nor an agent-created tab — i.e. a genuine user tab.
|
||||
vi.stubGlobal("chrome", {
|
||||
tabs: {
|
||||
remove: removeTab,
|
||||
query: vi.fn(async () => [{ id: 99, windowId: 4242, active: true }]),
|
||||
},
|
||||
});
|
||||
const { transport, sent, deliver } = fakeTransport();
|
||||
const sessions = new SessionManager({
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 4242),
|
||||
remove: closeWindow,
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
},
|
||||
});
|
||||
await sessions.start("aa11");
|
||||
// Register the exact tab id returned by the agent's creation path.
|
||||
sessions.get("aa11")?.agentCreatedTabs.add(7);
|
||||
|
||||
const dispatcher = new ToolDispatcher({ transport, sessions });
|
||||
dispatcher.start();
|
||||
|
||||
deliver(makeRequest("tool.session_stop", { session_id: "aa11" }));
|
||||
await flushMicrotasks();
|
||||
|
||||
// The agent tab is closed through the real chrome.tabs surface...
|
||||
expect(removeTab).toHaveBeenCalledWith(7);
|
||||
// ...and the window is released rather than closed, so the user's tab survives.
|
||||
expect(closeWindow).not.toHaveBeenCalled();
|
||||
expect(sessions.has("aa11")).toBe(false);
|
||||
expect(sent[0]).toEqual({ id: "r-1", result: { window_released: true } });
|
||||
});
|
||||
|
||||
it("routes tool.console through the CDP console buffer", async () => {
|
||||
vi.stubGlobal("chrome", {
|
||||
tabs: {
|
||||
@@ -265,7 +183,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 4242),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
await sessions.start("aa11");
|
||||
@@ -328,7 +246,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 4242),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const ctx = await sessions.start("aa11");
|
||||
@@ -421,7 +339,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 4242),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
await sessions.start("aa11");
|
||||
@@ -457,7 +375,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 4242),
|
||||
remove,
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
await sessions.start("aa11");
|
||||
@@ -505,7 +423,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 1),
|
||||
remove: vi.fn(),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const dispatcher = new ToolDispatcher({ transport, sessions });
|
||||
@@ -525,7 +443,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 1),
|
||||
remove: vi.fn(),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const dispatcher = new ToolDispatcher({ transport, sessions });
|
||||
@@ -549,7 +467,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 1),
|
||||
remove: vi.fn(),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const dispatcher = new ToolDispatcher({ transport, sessions });
|
||||
@@ -566,7 +484,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 1),
|
||||
remove: vi.fn(),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const dispatcher = new ToolDispatcher({ transport, sessions });
|
||||
@@ -583,7 +501,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 1),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const onSessionsChanged = vi.fn();
|
||||
@@ -599,106 +517,17 @@ describe("ToolDispatcher", () => {
|
||||
expect(onSessionsChanged).toHaveBeenCalledTimes(2);
|
||||
});
|
||||
|
||||
it.each([
|
||||
"focus",
|
||||
"blur",
|
||||
"scroll_to",
|
||||
] as const)("routes %s with hover cleanup and cooperative cancellation", async (action) => {
|
||||
const tab = { id: 7, windowId: 4242, active: true };
|
||||
vi.stubGlobal("chrome", {
|
||||
tabs: {
|
||||
get: vi.fn(async () => tab),
|
||||
query: vi.fn(async () => [tab]),
|
||||
sendMessage: vi.fn(async () => undefined),
|
||||
},
|
||||
});
|
||||
const sessions = new SessionManager({
|
||||
agentWindow: {
|
||||
create: async () => 4242,
|
||||
remove: async () => {},
|
||||
ensureActiveTab: async () => 7,
|
||||
},
|
||||
});
|
||||
const ctx = await sessions.start("aa11");
|
||||
ctx.refStore.set("e1", 12, { tabId: 7 });
|
||||
const { transport, sent, deliver } = fakeTransport();
|
||||
const onBrowserControlResumed = vi.fn();
|
||||
let resolveNode: ((value: object) => void) | undefined;
|
||||
const cdp = {
|
||||
send: vi.fn(async (_tabId: number, method: string) => {
|
||||
if (method === "DOM.resolveNode")
|
||||
return new Promise((resolve) => {
|
||||
resolveNode = resolve;
|
||||
});
|
||||
if (method === "Runtime.callFunctionOn") return { result: { value: true } };
|
||||
return {};
|
||||
}),
|
||||
} as unknown as TestDispatcherCdp;
|
||||
const dispatcher = new ToolDispatcher({ transport, sessions, cdp, onBrowserControlResumed });
|
||||
const hover = dispatcher as unknown as {
|
||||
rememberHover: (sessionId: string, result: object) => void;
|
||||
setHoverBypass: (sessionId: string, tabId: number, enabled: boolean) => Promise<void>;
|
||||
};
|
||||
hover.rememberHover("aa11", { tab_id: 7, x: 10, y: 20 });
|
||||
await hover.setHoverBypass("aa11", 7, true);
|
||||
dispatcher.start();
|
||||
deliver(makeRequest(`tool.${action}`, { session_id: "aa11", ref: "e1" }));
|
||||
await vi.waitFor(() => expect(resolveNode).toBeDefined());
|
||||
expect(onBrowserControlResumed).toHaveBeenCalledWith("aa11");
|
||||
deliver({ id: "cancel-focus", method: "cancel", params: { rpc_id: "r-1" } });
|
||||
resolveNode!({ object: { objectId: "focus-target" } });
|
||||
await vi.waitFor(() => expect(sent).toHaveLength(2));
|
||||
expect(sent).toContainEqual({ id: "cancel-focus", result: { cancelled: true } });
|
||||
expect(sent).toContainEqual({
|
||||
id: "r-1",
|
||||
error: expect.objectContaining({ code: "cancelled" }),
|
||||
});
|
||||
expect(cdp.send).not.toHaveBeenCalledWith(7, "DOM.focus", expect.anything());
|
||||
expect(cdp.send).not.toHaveBeenCalledWith(7, "Runtime.callFunctionOn", expect.anything());
|
||||
if (action === "scroll_to") {
|
||||
expect(cdp.send).toHaveBeenCalledWith(7, "Runtime.releaseObjectGroup", {
|
||||
objectGroup: expect.any(String),
|
||||
});
|
||||
} else {
|
||||
expect(cdp.send).toHaveBeenCalledWith(7, "Runtime.releaseObject", {
|
||||
objectId: "focus-target",
|
||||
});
|
||||
}
|
||||
expect(chrome.tabs.sendMessage).toHaveBeenCalledWith(
|
||||
7,
|
||||
expect.objectContaining({ enabled: false }),
|
||||
);
|
||||
expect(dispatcher.inflightAbortControllers.size).toBe(0);
|
||||
dispatcher.stop();
|
||||
});
|
||||
|
||||
it("invokes onBrowserControlResumed for browser-control tools but not passive reads", async () => {
|
||||
vi.stubGlobal("chrome", {
|
||||
tabs: {
|
||||
create: vi.fn(async (props: chrome.tabs.CreateProperties) => ({
|
||||
id: 7,
|
||||
windowId: props.windowId,
|
||||
url: props.url,
|
||||
active: props.active,
|
||||
})),
|
||||
},
|
||||
});
|
||||
const { transport, sent, deliver } = fakeTransport();
|
||||
const sessions = new SessionManager({
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 1),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const onBrowserControlResumed = vi.fn();
|
||||
const onAgentTabClaimed = vi.fn();
|
||||
const dispatcher = new ToolDispatcher({
|
||||
transport,
|
||||
sessions,
|
||||
onBrowserControlResumed,
|
||||
onAgentTabClaimed,
|
||||
});
|
||||
const dispatcher = new ToolDispatcher({ transport, sessions, onBrowserControlResumed });
|
||||
dispatcher.start();
|
||||
|
||||
deliver(makeRequest("tool.session_start", { session_id: "aa11" }));
|
||||
@@ -715,7 +544,6 @@ describe("ToolDispatcher", () => {
|
||||
});
|
||||
await flushMicrotasks();
|
||||
expect(onBrowserControlResumed).toHaveBeenCalledWith("aa11");
|
||||
expect(onAgentTabClaimed).toHaveBeenCalledWith(7, 1);
|
||||
});
|
||||
|
||||
it("reasserts remembered hover before follow-up work and releases only after actions", async () => {
|
||||
@@ -729,7 +557,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 1),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const order: string[] = [];
|
||||
@@ -811,7 +639,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 1),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const cdp = {
|
||||
@@ -861,135 +689,6 @@ describe("ToolDispatcher", () => {
|
||||
);
|
||||
});
|
||||
|
||||
it.each([
|
||||
{ tab_id: 7, code: "not_found" },
|
||||
{ tab_id: undefined, code: "invalid_params" },
|
||||
])("keeps hover when tab_return is rejected with $code", async ({ tab_id, code }) => {
|
||||
const sendMessage = vi.fn(async () => undefined);
|
||||
vi.stubGlobal("chrome", {
|
||||
tabs: {
|
||||
sendMessage,
|
||||
get: vi.fn(async () => ({ id: 7, windowId: 100, active: true })),
|
||||
query: vi.fn(async () => [{ id: 7, windowId: 100, active: true }]),
|
||||
},
|
||||
});
|
||||
const { transport, sent, deliver } = fakeTransport();
|
||||
const sessions = new SessionManager({
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 100),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
},
|
||||
});
|
||||
await sessions.start("aa11");
|
||||
const cdp = {
|
||||
send: vi.fn(async <T>() => ({}) as T),
|
||||
detachSession: vi.fn(async () => {}),
|
||||
releaseSessionTab: vi.fn(async () => {}),
|
||||
};
|
||||
const dispatcher = new ToolDispatcher({
|
||||
transport,
|
||||
sessions,
|
||||
cdp: cdp as unknown as TestDispatcherCdp,
|
||||
});
|
||||
const helpers = dispatcher as unknown as {
|
||||
rememberHover: (sessionId: string, result: unknown) => unknown;
|
||||
setHoverBypass: (sessionId: string, tabId: number, enabled: boolean) => Promise<void>;
|
||||
withHoverReassert: <T>(
|
||||
params: { session_id: string; tab_id?: number },
|
||||
work: () => Promise<T>,
|
||||
) => Promise<T>;
|
||||
};
|
||||
helpers.rememberHover("aa11", { tab_id: 7, x: 10, y: 20 });
|
||||
await helpers.setHoverBypass("aa11", 7, true);
|
||||
dispatcher.start();
|
||||
deliver(makeRequest("tool.tab_return", { session_id: "aa11", tab_id }));
|
||||
await vi.waitFor(() => expect(sent).toHaveLength(1));
|
||||
|
||||
expect(sent[0]).toMatchObject({ error: { code } });
|
||||
expect(cdp.releaseSessionTab).not.toHaveBeenCalled();
|
||||
expect(sendMessage).not.toHaveBeenCalledWith(7, expect.objectContaining({ enabled: false }));
|
||||
await helpers.withHoverReassert({ session_id: "aa11", tab_id: 7 }, async () => ({}));
|
||||
expect(cdp.send).toHaveBeenCalledExactlyOnceWith(7, "Input.dispatchMouseEvent", {
|
||||
type: "mouseMoved",
|
||||
x: 10,
|
||||
y: 20,
|
||||
});
|
||||
dispatcher.stop();
|
||||
});
|
||||
|
||||
it("releases the returned tab's hover before moving it and leaves other tabs alone", async () => {
|
||||
const sendMessage = vi.fn(async () => undefined);
|
||||
const move = vi.fn(async () => {
|
||||
expect(sendMessage).toHaveBeenCalledWith(7, expect.objectContaining({ enabled: false }));
|
||||
return { id: 7, windowId: 200, index: 4 };
|
||||
});
|
||||
vi.stubGlobal("chrome", {
|
||||
tabs: { sendMessage, move },
|
||||
windows: { get: vi.fn(async () => ({ id: 200 })) },
|
||||
});
|
||||
const { transport, sent, deliver } = fakeTransport();
|
||||
const sessions = new SessionManager({
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 100),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
},
|
||||
});
|
||||
const ctx = await sessions.start("aa11");
|
||||
ctx.borrowedTabs.set(7, { tabId: 7, originalWindowId: 200, originalIndex: 4 });
|
||||
const cdp = {
|
||||
send: vi.fn(async <T>() => ({}) as T),
|
||||
detachSession: vi.fn(async () => {}),
|
||||
releaseSessionTab: vi.fn(async () => {}),
|
||||
};
|
||||
const dispatcher = new ToolDispatcher({
|
||||
transport,
|
||||
sessions,
|
||||
cdp: cdp as unknown as TestDispatcherCdp,
|
||||
});
|
||||
const helpers = dispatcher as unknown as {
|
||||
rememberHover: (sessionId: string, result: unknown) => unknown;
|
||||
setHoverBypass: (sessionId: string, tabId: number, enabled: boolean) => Promise<void>;
|
||||
withHoverReassert: <T>(
|
||||
params: { session_id: string; tab_id?: number },
|
||||
work: () => Promise<T>,
|
||||
) => Promise<T>;
|
||||
};
|
||||
for (const [sessionId, tabId] of [
|
||||
["aa11", 7],
|
||||
["aa11", 8],
|
||||
["bb22", 9],
|
||||
] as const) {
|
||||
helpers.rememberHover(sessionId, { tab_id: tabId, x: 10, y: 20 });
|
||||
await helpers.setHoverBypass(sessionId, tabId, true);
|
||||
}
|
||||
dispatcher.start();
|
||||
deliver(makeRequest("tool.tab_return", { session_id: "aa11", tab_id: 7 }));
|
||||
await vi.waitFor(() => expect(sent).toHaveLength(1));
|
||||
|
||||
expect(sent[0]).toMatchObject({ result: { tab_id: 7, returned_to_window_id: 200 } });
|
||||
expect(cdp.releaseSessionTab).toHaveBeenCalledExactlyOnceWith("aa11", 7);
|
||||
await helpers.withHoverReassert({ session_id: "aa11", tab_id: 7 }, async () => ({}));
|
||||
expect(cdp.send).not.toHaveBeenCalled();
|
||||
for (const [sessionId, tabId] of [
|
||||
["aa11", 8],
|
||||
["bb22", 9],
|
||||
] as const) {
|
||||
expect(sendMessage).not.toHaveBeenCalledWith(
|
||||
tabId,
|
||||
expect.objectContaining({ enabled: false }),
|
||||
);
|
||||
await helpers.withHoverReassert({ session_id: sessionId, tab_id: tabId }, async () => ({}));
|
||||
expect(cdp.send).toHaveBeenLastCalledWith(tabId, "Input.dispatchMouseEvent", {
|
||||
type: "mouseMoved",
|
||||
x: 10,
|
||||
y: 20,
|
||||
});
|
||||
}
|
||||
dispatcher.stop();
|
||||
});
|
||||
|
||||
it("transfers hover overlay bypass ownership between sessions", async () => {
|
||||
vi.stubGlobal("chrome", {
|
||||
tabs: {
|
||||
@@ -1001,7 +700,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 1),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const dispatcher = new ToolDispatcher({ transport, sessions });
|
||||
@@ -1038,7 +737,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 4242),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
await sessions.start("aa11");
|
||||
@@ -1090,7 +789,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 1),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const dispatcher = new ToolDispatcher({ transport, sessions });
|
||||
@@ -1124,7 +823,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 4242),
|
||||
remove: vi.fn(),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
transport.send = () => {
|
||||
@@ -1146,7 +845,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 5555),
|
||||
remove,
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
transport.send = () => {
|
||||
@@ -1174,7 +873,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(() => createPromise),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const dispatcher = new ToolDispatcher({ transport, sessions });
|
||||
@@ -1225,7 +924,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 1),
|
||||
remove: vi.fn(),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const dispatcher = new ToolDispatcher({ transport, sessions });
|
||||
@@ -1246,7 +945,7 @@ describe("ToolDispatcher", () => {
|
||||
agentWindow: {
|
||||
create: vi.fn(() => createPromise),
|
||||
remove: vi.fn(),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
const dispatcher = new ToolDispatcher({ transport, sessions });
|
||||
|
||||
@@ -20,7 +20,7 @@ function fakeAgentWindow(ids: number[]) {
|
||||
return id;
|
||||
}),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
@@ -1,39 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import type { RpcError } from "@/transport/types";
|
||||
import { cdpError, classifyCdpError } from "../errors";
|
||||
|
||||
const denied = "Cannot access a chrome-extension:// URL of different extension";
|
||||
|
||||
describe("CDP extension access errors", () => {
|
||||
it("classifies both Chrome Error instances and string failures", () => {
|
||||
for (const error of [new Error(denied), denied]) {
|
||||
expect(cdpError(error)).toEqual({
|
||||
code: "cdp_failed",
|
||||
message: denied,
|
||||
data: { reason: "cdp_extension_access_denied" },
|
||||
});
|
||||
}
|
||||
});
|
||||
|
||||
it("preserves transfer outcome and cleanup instructions when CDP was denied", () => {
|
||||
const error: RpcError = {
|
||||
code: "cdp_failed",
|
||||
message: denied,
|
||||
data: {
|
||||
reason: "transfer_outcome_unknown",
|
||||
effect_state: "unknown",
|
||||
cleanup_state: "failed",
|
||||
},
|
||||
};
|
||||
expect(classifyCdpError(error)).toBe(error);
|
||||
});
|
||||
|
||||
it("leaves other error codes and unrelated debugger failures unchanged", () => {
|
||||
for (const error of [
|
||||
{ code: "permission_denied", message: denied },
|
||||
{ code: "cdp_failed", message: "Another debugger is already attached" },
|
||||
] satisfies RpcError[]) {
|
||||
expect(classifyCdpError(error)).toBe(error);
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -12,7 +12,7 @@ function fakeAgentWindow(ids: number[]) {
|
||||
return id;
|
||||
}),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
@@ -2,7 +2,6 @@ import { describe, expect, it, vi } from "vitest";
|
||||
import { SessionManager } from "@/session-manager/manager";
|
||||
import { type DownloadsApi, handleDownload } from "../download";
|
||||
import { captureBrowserDownload } from "../download-capture";
|
||||
import { uploadThroughFileDrop } from "../file-drop-transaction";
|
||||
import { uploadThroughActivatedFileInput } from "../file-input-transaction";
|
||||
import type { ResolvedActionTarget } from "../interaction";
|
||||
import type { CdpRunner } from "../shared";
|
||||
@@ -13,7 +12,7 @@ function sessions() {
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 100),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
},
|
||||
});
|
||||
}
|
||||
@@ -38,20 +37,16 @@ function fakeEvent<T extends (...args: never[]) => unknown>() {
|
||||
};
|
||||
}
|
||||
|
||||
function actionTarget(frameId?: string, sessionId?: string): ResolvedActionTarget {
|
||||
function actionTarget(frameId?: string): ResolvedActionTarget {
|
||||
return {
|
||||
tab: { tabId: 4, windowId: 100, active: true },
|
||||
backendNodeId: 123,
|
||||
cdpTarget: { tabId: 4, ...(sessionId ? { sessionId } : {}) },
|
||||
cdpTarget: { tabId: 4 },
|
||||
...(frameId ? { frameId } : {}),
|
||||
usedRef: "e3",
|
||||
};
|
||||
}
|
||||
|
||||
function withoutOverlay<T>(operation: () => Promise<T>): Promise<T> {
|
||||
return operation();
|
||||
}
|
||||
|
||||
function uploadCdp(
|
||||
options: {
|
||||
inputCount?: number;
|
||||
@@ -64,7 +59,6 @@ function uploadCdp(
|
||||
let cdpEvent: Parameters<NonNullable<CdpRunner["onEvent"]>>[0] | undefined;
|
||||
const send = vi.fn(async (_tabId: number, method: string, params?: object) => {
|
||||
calls.push({ method, params });
|
||||
if (method === "DOM.scrollIntoViewIfNeeded") return {};
|
||||
if (method === "Page.setInterceptFileChooserDialog") return {};
|
||||
if (method === "Page.getLayoutMetrics")
|
||||
return { cssLayoutViewport: { clientWidth: 1280, clientHeight: 720 } };
|
||||
@@ -116,50 +110,6 @@ function uploadCdp(
|
||||
};
|
||||
}
|
||||
|
||||
function dropCdp(
|
||||
options: {
|
||||
targetContainsPoint?: boolean;
|
||||
dispatchError?: (type: string) => Error | Promise<never> | undefined;
|
||||
onCall?: (method: string) => void;
|
||||
} = {},
|
||||
) {
|
||||
const calls: Array<{ method: string; params?: object }> = [];
|
||||
const detach = vi.fn(async () => {});
|
||||
const send = vi.fn(async (_tabId: number, method: string, params?: object) => {
|
||||
calls.push({ method, params });
|
||||
options.onCall?.(method);
|
||||
if (method === "DOM.scrollIntoViewIfNeeded") return {};
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return { cssLayoutViewport: { clientWidth: 1280, clientHeight: 720 } };
|
||||
}
|
||||
if (method === "DOM.getContentQuads") {
|
||||
return { quads: [[10, 20, 210, 20, 210, 120, 10, 120]] };
|
||||
}
|
||||
if (method === "DOM.getNodeForLocation") return { backendNodeId: 124 };
|
||||
if (method === "DOM.resolveNode") {
|
||||
const id = (params as { backendNodeId?: number }).backendNodeId;
|
||||
return { object: { objectId: id === 123 ? "drop-target" : "hit-target" } };
|
||||
}
|
||||
if (method === "Runtime.callFunctionOn") {
|
||||
return { result: { value: options.targetContainsPoint ?? true } };
|
||||
}
|
||||
if (method === "Input.dispatchDragEvent") {
|
||||
const type = (params as { type?: string }).type ?? "";
|
||||
const error = options.dispatchError?.(type);
|
||||
if (error instanceof Promise) return error;
|
||||
if (error) throw error;
|
||||
return {};
|
||||
}
|
||||
if (method === "Runtime.releaseObjectGroup") return {};
|
||||
throw new Error(`unexpected drop CDP command ${method}`);
|
||||
});
|
||||
const cdp: CdpRunner = {
|
||||
send: send as unknown as CdpRunner["send"],
|
||||
detach,
|
||||
};
|
||||
return { calls, cdp, detach };
|
||||
}
|
||||
|
||||
describe("file transfer tools", () => {
|
||||
it("captures the file input activated by the requested click and injects only staged paths", async () => {
|
||||
const manager = sessions();
|
||||
@@ -296,6 +246,104 @@ describe("file transfer tools", () => {
|
||||
});
|
||||
});
|
||||
|
||||
it("does not dispatch browser work when upload is already cancelled", async () => {
|
||||
const controller = new AbortController();
|
||||
controller.abort();
|
||||
const { cdp, calls } = uploadCdp();
|
||||
|
||||
const result = await uploadThroughActivatedFileInput({
|
||||
cdp,
|
||||
actionTarget: actionTarget(),
|
||||
files: ["/private/stage/one"],
|
||||
timeoutMs: 100,
|
||||
signal: controller.signal,
|
||||
trigger: vi.fn(),
|
||||
});
|
||||
|
||||
expect(result).toMatchObject({
|
||||
code: "cancelled",
|
||||
data: { effect_state: "none", phase: "arm_interception" },
|
||||
});
|
||||
expect(calls).not.toContainEqual({
|
||||
method: "Page.setInterceptFileChooserDialog",
|
||||
params: { enabled: true },
|
||||
});
|
||||
expect(calls.some((call) => call.method === "DOM.setFileInputFiles")).toBe(false);
|
||||
});
|
||||
|
||||
it("stops before file assignment when cancellation interrupts input resolution", async () => {
|
||||
const controller = new AbortController();
|
||||
const fixture = uploadCdp();
|
||||
const originalSend = fixture.cdp.send;
|
||||
let markProbeStarted!: () => void;
|
||||
const probeStarted = new Promise<void>((resolve) => {
|
||||
markProbeStarted = resolve;
|
||||
});
|
||||
fixture.cdp.send = vi.fn((tabId: number, method: string, params?: object) => {
|
||||
const declaration = (params as { functionDeclaration?: string } | undefined)
|
||||
?.functionDeclaration;
|
||||
if (
|
||||
method === "Runtime.callFunctionOn" &&
|
||||
declaration?.includes("count: state.inputs.length")
|
||||
) {
|
||||
markProbeStarted();
|
||||
return new Promise<never>(() => {});
|
||||
}
|
||||
return originalSend(tabId, method, params);
|
||||
}) as CdpRunner["send"];
|
||||
|
||||
const transaction = uploadThroughActivatedFileInput({
|
||||
cdp: fixture.cdp,
|
||||
actionTarget: actionTarget(),
|
||||
files: ["/private/stage/one"],
|
||||
timeoutMs: 1_000,
|
||||
signal: controller.signal,
|
||||
trigger: async () => ({ tab_id: 4, x: 10, y: 10 }),
|
||||
});
|
||||
await probeStarted;
|
||||
controller.abort();
|
||||
const result = await transaction;
|
||||
|
||||
expect(result).toMatchObject({
|
||||
code: "cancelled",
|
||||
data: { effect_state: "none", phase: "resolve_input" },
|
||||
});
|
||||
expect(fixture.calls.some((call) => call.method === "DOM.setFileInputFiles")).toBe(false);
|
||||
});
|
||||
|
||||
it("disarms chooser interception when its enable response times out", async () => {
|
||||
const calls: Array<{ method: string; params?: object }> = [];
|
||||
const cdp: CdpRunner = {
|
||||
send: vi.fn(async (_tabId: number, method: string, params?: object) => {
|
||||
calls.push({ method, params });
|
||||
if (
|
||||
method === "Page.setInterceptFileChooserDialog" &&
|
||||
(params as { enabled?: boolean }).enabled
|
||||
) {
|
||||
return new Promise<never>(() => {});
|
||||
}
|
||||
return {};
|
||||
}) as CdpRunner["send"],
|
||||
};
|
||||
|
||||
const result = await uploadThroughActivatedFileInput({
|
||||
cdp,
|
||||
actionTarget: actionTarget(),
|
||||
files: ["/private/stage/one"],
|
||||
timeoutMs: 5,
|
||||
trigger: vi.fn(),
|
||||
});
|
||||
|
||||
expect(result).toMatchObject({
|
||||
code: "timeout",
|
||||
data: { effect_state: "none", phase: "arm_interception" },
|
||||
});
|
||||
expect(calls).toContainEqual({
|
||||
method: "Page.setInterceptFileChooserDialog",
|
||||
params: { enabled: false, cancel: true },
|
||||
});
|
||||
});
|
||||
|
||||
it("marks a timed-out file assignment unknown and detaches browser state", async () => {
|
||||
const fixture = uploadCdp();
|
||||
const originalSend = fixture.cdp.send;
|
||||
@@ -321,238 +369,6 @@ describe("file transfer tools", () => {
|
||||
expect(detach).toHaveBeenCalledWith(4);
|
||||
});
|
||||
|
||||
it("delivers staged files through one explicit native drop without clicking", async () => {
|
||||
const manager = sessions();
|
||||
const ctx = await manager.start("s1");
|
||||
ctx.refStore.set("e3", 123, { tabId: 4 });
|
||||
const lifecycle: string[] = [];
|
||||
const { cdp, calls } = dropCdp({ onCall: (method) => lifecycle.push(method) });
|
||||
const overlayPhases: string[] = [];
|
||||
|
||||
const result = await handleUpload(
|
||||
manager,
|
||||
{
|
||||
session_id: "s1",
|
||||
ref: "@e3",
|
||||
mode: "drop",
|
||||
files: [{ transfer_id: "tr_1", name: "one.png", staged_path: "/stage/one.png" }],
|
||||
},
|
||||
{
|
||||
cdp,
|
||||
tabsApi: tabsApi(),
|
||||
sendToTab: vi.fn(async (_tabId, message) => {
|
||||
overlayPhases.push(message.phase);
|
||||
lifecycle.push(`overlay:${message.phase}`);
|
||||
}),
|
||||
},
|
||||
);
|
||||
|
||||
expect(result).toMatchObject({ tab_id: 4, used_ref: "e3", file_names: ["one.png"] });
|
||||
expect(calls.filter((call) => call.method === "Input.dispatchDragEvent")).toEqual([
|
||||
{
|
||||
method: "Input.dispatchDragEvent",
|
||||
params: {
|
||||
type: "dragEnter",
|
||||
x: 110,
|
||||
y: 70,
|
||||
data: { items: [], files: ["/stage/one.png"], dragOperationsMask: 1 },
|
||||
},
|
||||
},
|
||||
{
|
||||
method: "Input.dispatchDragEvent",
|
||||
params: {
|
||||
type: "dragOver",
|
||||
x: 110,
|
||||
y: 70,
|
||||
data: { items: [], files: ["/stage/one.png"], dragOperationsMask: 1 },
|
||||
},
|
||||
},
|
||||
{
|
||||
method: "Input.dispatchDragEvent",
|
||||
params: {
|
||||
type: "drop",
|
||||
x: 110,
|
||||
y: 70,
|
||||
data: { items: [], files: ["/stage/one.png"], dragOperationsMask: 1 },
|
||||
},
|
||||
},
|
||||
]);
|
||||
expect(calls.some((call) => call.method === "Input.dispatchMouseEvent")).toBe(false);
|
||||
expect(overlayPhases).toEqual(["begin", "end"]);
|
||||
expect(lifecycle.indexOf("DOM.getContentQuads")).toBeLessThan(
|
||||
lifecycle.indexOf("overlay:begin"),
|
||||
);
|
||||
expect(lifecycle.indexOf("overlay:begin")).toBeLessThan(
|
||||
lifecycle.indexOf("DOM.getNodeForLocation"),
|
||||
);
|
||||
expect(lifecycle.lastIndexOf("Input.dispatchDragEvent")).toBeLessThan(
|
||||
lifecycle.indexOf("overlay:end"),
|
||||
);
|
||||
expect(lifecycle.indexOf("overlay:end")).toBeLessThan(
|
||||
lifecycle.indexOf("Runtime.releaseObjectGroup"),
|
||||
);
|
||||
});
|
||||
|
||||
it("fails closed before dragging when another element owns the action point", async () => {
|
||||
const { cdp, calls } = dropCdp({ targetContainsPoint: false });
|
||||
const result = await uploadThroughFileDrop({
|
||||
cdp,
|
||||
actionTarget: actionTarget(),
|
||||
files: ["/stage/one.png"],
|
||||
timeoutMs: 100,
|
||||
withOverlayHidden: withoutOverlay,
|
||||
});
|
||||
|
||||
expect(result).toMatchObject({
|
||||
code: "permission_denied",
|
||||
data: {
|
||||
reason: "file_drop_target_unavailable",
|
||||
mechanism: "drop",
|
||||
effect_state: "none",
|
||||
phase: "resolve_target",
|
||||
},
|
||||
});
|
||||
expect(calls.some((call) => call.method === "Input.dispatchDragEvent")).toBe(false);
|
||||
});
|
||||
|
||||
it("dispatches an OOPIF file drop in the child target's local coordinates", async () => {
|
||||
const rootCalls: Array<{ method: string; params?: object }> = [];
|
||||
const childCalls: Array<{ method: string; params?: object }> = [];
|
||||
const cdp: CdpRunner = {
|
||||
send: vi.fn(async (_tabId, method, params) => {
|
||||
rootCalls.push({ method, params });
|
||||
if (method === "DOM.scrollIntoViewIfNeeded") return {};
|
||||
if (method === "DOM.getBoxModel") {
|
||||
return { model: { content: [100, 100, 300, 100, 300, 200, 100, 200] } };
|
||||
}
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return { cssLayoutViewport: { clientWidth: 800, clientHeight: 600 } };
|
||||
}
|
||||
throw new Error(`unexpected root command ${method}`);
|
||||
}) as CdpRunner["send"],
|
||||
sendToTarget: vi.fn(async (_target, method, params) => {
|
||||
childCalls.push({ method, params });
|
||||
if (method === "DOM.scrollIntoViewIfNeeded") return {};
|
||||
if (method === "DOM.getContentQuads") {
|
||||
return { quads: [[10, 20, 210, 20, 210, 120, 10, 120]] };
|
||||
}
|
||||
if (method === "Runtime.evaluate")
|
||||
return { result: { value: { width: 400, height: 300 } } };
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return { cssLayoutViewport: { clientWidth: 400, clientHeight: 300 } };
|
||||
}
|
||||
if (method === "DOM.getNodeForLocation") {
|
||||
return { backendNodeId: 124, frameId: "child" };
|
||||
}
|
||||
if (method === "DOM.resolveNode") {
|
||||
const id = (params as { backendNodeId?: number }).backendNodeId;
|
||||
return { object: { objectId: id === 123 ? "drop-target" : "hit-target" } };
|
||||
}
|
||||
if (method === "Runtime.callFunctionOn") return { result: { value: true } };
|
||||
if (method === "Input.dispatchDragEvent" || method === "Runtime.releaseObjectGroup") {
|
||||
return {};
|
||||
}
|
||||
throw new Error(`unexpected child command ${method}`);
|
||||
}) as CdpRunner["sendToTarget"],
|
||||
getFrameGraph: vi.fn(async () => ({
|
||||
rootFrameId: "main",
|
||||
frames: [
|
||||
{ frameId: "main", target: { tabId: 4 } },
|
||||
{
|
||||
frameId: "child",
|
||||
parentFrameId: "main",
|
||||
ownerBackendNodeId: 10,
|
||||
target: { tabId: 4, sessionId: "child-session" },
|
||||
},
|
||||
],
|
||||
})),
|
||||
};
|
||||
|
||||
const result = await uploadThroughFileDrop({
|
||||
cdp,
|
||||
actionTarget: actionTarget("child", "child-session"),
|
||||
files: ["/stage/one.png"],
|
||||
timeoutMs: 100,
|
||||
withOverlayHidden: withoutOverlay,
|
||||
});
|
||||
|
||||
expect(result).toMatchObject({ x: 110, y: 70 });
|
||||
expect(
|
||||
childCalls
|
||||
.filter((call) => call.method === "Input.dispatchDragEvent")
|
||||
.map((call) => call.params),
|
||||
).toEqual([
|
||||
expect.objectContaining({ type: "dragEnter", x: 110, y: 70 }),
|
||||
expect.objectContaining({ type: "dragOver", x: 110, y: 70 }),
|
||||
expect.objectContaining({ type: "drop", x: 110, y: 70 }),
|
||||
]);
|
||||
expect(rootCalls.some((call) => call.method === "Input.dispatchDragEvent")).toBe(false);
|
||||
});
|
||||
|
||||
it("reports a missing native drag command as unsupported before commit", async () => {
|
||||
const { cdp } = dropCdp({
|
||||
dispatchError: (type) =>
|
||||
type === "dragEnter" ? new Error("'Input.dispatchDragEvent' wasn't found") : undefined,
|
||||
});
|
||||
const result = await uploadThroughFileDrop({
|
||||
cdp,
|
||||
actionTarget: actionTarget(),
|
||||
files: ["/stage/one.png"],
|
||||
timeoutMs: 100,
|
||||
withOverlayHidden: withoutOverlay,
|
||||
});
|
||||
|
||||
expect(result).toMatchObject({
|
||||
code: "unsupported",
|
||||
data: {
|
||||
reason: "upload_mechanism_unsupported",
|
||||
effect_state: "none",
|
||||
phase: "drag_enter",
|
||||
},
|
||||
});
|
||||
});
|
||||
|
||||
it("cancels an unresolved drag before returning a pre-commit timeout", async () => {
|
||||
const { cdp, calls } = dropCdp({
|
||||
dispatchError: (type) => (type === "dragEnter" ? new Promise<never>(() => {}) : undefined),
|
||||
});
|
||||
const result = await uploadThroughFileDrop({
|
||||
cdp,
|
||||
actionTarget: actionTarget(),
|
||||
files: ["/stage/one.png"],
|
||||
timeoutMs: 10,
|
||||
withOverlayHidden: withoutOverlay,
|
||||
});
|
||||
|
||||
expect(result).toMatchObject({
|
||||
code: "timeout",
|
||||
data: { reason: "file_drop_failed", effect_state: "none", phase: "drag_enter" },
|
||||
});
|
||||
expect(calls).toContainEqual({
|
||||
method: "Input.dispatchDragEvent",
|
||||
params: expect.objectContaining({ type: "dragCancel" }),
|
||||
});
|
||||
});
|
||||
|
||||
it("marks an unresolved drop unknown and detaches browser state", async () => {
|
||||
const { cdp, detach } = dropCdp({
|
||||
dispatchError: (type) => (type === "drop" ? new Promise<never>(() => {}) : undefined),
|
||||
});
|
||||
const result = await uploadThroughFileDrop({
|
||||
cdp,
|
||||
actionTarget: actionTarget(),
|
||||
files: ["/stage/one.png"],
|
||||
timeoutMs: 10,
|
||||
withOverlayHidden: withoutOverlay,
|
||||
});
|
||||
|
||||
expect(result).toMatchObject({
|
||||
code: "timeout",
|
||||
data: { reason: "file_drop_failed", effect_state: "unknown", phase: "drop" },
|
||||
});
|
||||
expect(detach).toHaveBeenCalledWith(4);
|
||||
});
|
||||
|
||||
it("routes one exact-target download through a browser-relative capability", async () => {
|
||||
const manager = sessions();
|
||||
const ctx = await manager.start("s1");
|
||||
@@ -849,7 +665,10 @@ describe("file transfer tools", () => {
|
||||
expect(downloads.cancel).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("reconciles a download that completes while cancellation is being requested", async () => {
|
||||
it.each([
|
||||
["cancel resolves", false],
|
||||
["cancel reports that completion won", true],
|
||||
])("reconciles a download that completes while %s", async (_label, cancelThrows) => {
|
||||
const onCreated = fakeEvent<(item: chrome.downloads.DownloadItem) => void>();
|
||||
const onChanged = fakeEvent<(delta: chrome.downloads.DownloadDelta) => void>();
|
||||
const onDeterminingFilename =
|
||||
@@ -883,7 +702,7 @@ describe("file transfer tools", () => {
|
||||
onDeterminingFilename,
|
||||
search: vi.fn().mockResolvedValueOnce([initial]).mockResolvedValueOnce([complete]),
|
||||
cancel: vi.fn(async () => {
|
||||
throw new Error("download already complete");
|
||||
if (cancelThrows) throw new Error("download already complete");
|
||||
}),
|
||||
removeFile: vi.fn(async () => {}),
|
||||
};
|
||||
|
||||
@@ -1,573 +0,0 @@
|
||||
import { afterEach, describe, expect, it, vi } from "vitest";
|
||||
import { SessionManager } from "@/session-manager/manager";
|
||||
import type { CdpRunner } from "@/tools/shared";
|
||||
import { handleFill } from "../interaction";
|
||||
|
||||
interface ScriptParams {
|
||||
functionDeclaration: string;
|
||||
arguments?: Array<{ value: unknown }>;
|
||||
}
|
||||
|
||||
async function setup(markup = '<input value="old">') {
|
||||
document.body.innerHTML = markup;
|
||||
const element = document.body.firstElementChild as HTMLInputElement;
|
||||
const manager = new SessionManager({
|
||||
agentWindow: {
|
||||
create: async () => 100,
|
||||
remove: async () => {},
|
||||
ensureActiveTab: async () => 4,
|
||||
},
|
||||
});
|
||||
const ctx = await manager.start("aa11");
|
||||
ctx.refStore.set("e1", 12, { tabId: 4 });
|
||||
const script = vi.fn(async (params: ScriptParams): Promise<unknown> => {
|
||||
try {
|
||||
const fn = new Function(`return (${params.functionDeclaration})`)();
|
||||
return {
|
||||
result: {
|
||||
value: await fn.apply(
|
||||
element,
|
||||
(params.arguments ?? []).map((arg) => arg.value),
|
||||
),
|
||||
},
|
||||
};
|
||||
} catch {
|
||||
return { exceptionDetails: { text: "test page script failed" } };
|
||||
}
|
||||
});
|
||||
// Number/email controls have a browser caret even though their selection
|
||||
// getters return null. Model that caret instead of assuming it is at the end.
|
||||
const hiddenCaret = { start: 0, end: 0 };
|
||||
const moveToEnd = vi.fn(async () => {
|
||||
if (typeof element.selectionStart === "number") {
|
||||
element.setSelectionRange(element.value.length, element.value.length);
|
||||
} else {
|
||||
hiddenCaret.start = hiddenCaret.end = element.value.length;
|
||||
}
|
||||
});
|
||||
const insert = vi.fn(async (text: string) => {
|
||||
const focused = document.activeElement as HTMLInputElement;
|
||||
if (focused.readOnly || focused.disabled) return;
|
||||
const start = focused.selectionStart ?? hiddenCaret.start;
|
||||
const end = focused.selectionEnd ?? hiddenCaret.end;
|
||||
const value = focused.value.slice(0, start) + text + focused.value.slice(end);
|
||||
focused.value = focused.maxLength >= 0 ? value.slice(0, focused.maxLength) : value;
|
||||
hiddenCaret.start = hiddenCaret.end = Math.min(start + text.length, focused.value.length);
|
||||
focused.dispatchEvent(new Event("input", { bubbles: true }));
|
||||
});
|
||||
const release = vi.fn(async () => ({}));
|
||||
const send = vi.fn(async (_tabId: number, method: string, params?: object) => {
|
||||
switch (method) {
|
||||
case "DOM.describeNode":
|
||||
return {
|
||||
node: {
|
||||
nodeName: element.tagName,
|
||||
attributes: Array.from(element.attributes).flatMap((attr) => [attr.name, attr.value]),
|
||||
},
|
||||
};
|
||||
case "DOM.scrollIntoViewIfNeeded":
|
||||
return {};
|
||||
case "DOM.focus":
|
||||
element.focus();
|
||||
return {};
|
||||
case "DOM.resolveNode":
|
||||
return { object: { objectId: "fill-target" } };
|
||||
case "Runtime.callFunctionOn":
|
||||
return script(params as ScriptParams);
|
||||
case "Input.insertText":
|
||||
await insert((params as { text: string }).text);
|
||||
return {};
|
||||
case "Input.dispatchKeyEvent":
|
||||
if ((params as { commands?: string[] }).commands?.includes("moveToEndOfDocument")) {
|
||||
await moveToEnd();
|
||||
}
|
||||
return {};
|
||||
case "Runtime.releaseObject":
|
||||
return release();
|
||||
default:
|
||||
throw new Error(`unexpected ${method}`);
|
||||
}
|
||||
});
|
||||
return {
|
||||
element,
|
||||
hiddenCaret,
|
||||
moveToEnd,
|
||||
script,
|
||||
insert,
|
||||
release,
|
||||
send,
|
||||
fill: (value = "hello", clearBefore = true, signal?: AbortSignal) =>
|
||||
handleFill(
|
||||
manager,
|
||||
{ session_id: "aa11", ref: "e1", value, clear_before: clearBefore },
|
||||
{
|
||||
cdp: { send: send as CdpRunner["send"] },
|
||||
tabsApi: {
|
||||
get: async (id) => ({ id, windowId: 100, active: true }) as chrome.tabs.Tab,
|
||||
query: async () => [{ id: 4, windowId: 100, active: true } as chrome.tabs.Tab],
|
||||
},
|
||||
signal,
|
||||
},
|
||||
),
|
||||
};
|
||||
}
|
||||
|
||||
afterEach(() => {
|
||||
vi.restoreAllMocks();
|
||||
document.body.innerHTML = "";
|
||||
});
|
||||
|
||||
describe("fill result verification", () => {
|
||||
it.each([
|
||||
"readonly",
|
||||
"disabled",
|
||||
])("preserves a %s field before rejecting it", async (attribute) => {
|
||||
const h = await setup(`<input ${attribute} value="old">`);
|
||||
expect(await h.fill()).toMatchObject({
|
||||
code: "invalid_params",
|
||||
data: { reason: "target_not_fillable" },
|
||||
});
|
||||
expect(h.element.value).toBe("old");
|
||||
expect(h.insert).not.toHaveBeenCalled();
|
||||
expect(h.release).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it.each([
|
||||
"checkbox",
|
||||
"radio",
|
||||
"range",
|
||||
"date",
|
||||
"file",
|
||||
])("rejects an unsupported %s input before clearing", async (type) => {
|
||||
const h = await setup(`<input type="${type}">`);
|
||||
const before = h.element.value;
|
||||
expect(await h.fill()).toMatchObject({
|
||||
code: "invalid_params",
|
||||
data: { reason: "target_not_fillable" },
|
||||
});
|
||||
expect(h.element.value).toBe(before);
|
||||
expect(h.insert).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("rejects an overlong value before clearing", async () => {
|
||||
const h = await setup('<input maxlength="3" value="old">');
|
||||
expect(await h.fill()).toMatchObject({
|
||||
code: "invalid_params",
|
||||
message: /maxlength/,
|
||||
data: { reason: "fill_value_invalid" },
|
||||
});
|
||||
expect(h.element.value).toBe("old");
|
||||
expect(h.insert).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it.each([
|
||||
true,
|
||||
false,
|
||||
])("classifies a DOM.focus rejection on a disabled=%s target", async (disabled) => {
|
||||
const h = await setup(`<input ${disabled ? "disabled" : ""} value="old">`);
|
||||
const send = h.send.getMockImplementation()!;
|
||||
h.send.mockImplementation(async (tabId, method, params) => {
|
||||
if (method === "DOM.focus") throw new Error("Element is not focusable");
|
||||
return send(tabId, method, params);
|
||||
});
|
||||
expect(await h.fill()).toMatchObject({
|
||||
code: disabled ? "invalid_params" : "cdp_failed",
|
||||
data: { reason: disabled ? "target_not_fillable" : "fill_failed" },
|
||||
});
|
||||
expect(h.element.value).toBe("old");
|
||||
expect(h.insert).not.toHaveBeenCalled();
|
||||
expect(h.release).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it("fills a background document without requiring foreground browser focus", async () => {
|
||||
const h = await setup();
|
||||
vi.spyOn(document, "hasFocus").mockReturnValue(false);
|
||||
expect(await h.fill()).toMatchObject({ value_length: 5 });
|
||||
expect(h.element.value).toBe("hello");
|
||||
});
|
||||
|
||||
it("restores focus once after clearing without typing into another field", async () => {
|
||||
const h = await setup();
|
||||
const other = document.createElement("input");
|
||||
document.body.append(other);
|
||||
h.element.addEventListener("input", () => other.focus());
|
||||
expect(await h.fill()).toMatchObject({ value_length: 5 });
|
||||
expect(h.element.value).toBe("hello");
|
||||
expect(other.value).toBe("");
|
||||
expect(h.send.mock.calls.filter(([, method]) => method === "DOM.focus")).toHaveLength(2);
|
||||
});
|
||||
|
||||
it.each([
|
||||
"focus",
|
||||
"value",
|
||||
])("rechecks %s after restoring focus, without retrying again", async (action) => {
|
||||
const h = await setup();
|
||||
const other = document.createElement("input");
|
||||
document.body.append(other);
|
||||
h.element.addEventListener(
|
||||
"input",
|
||||
() => {
|
||||
other.focus();
|
||||
h.element.addEventListener("focus", () => {
|
||||
if (action === "focus") queueMicrotask(() => other.focus());
|
||||
else h.element.value = "changed";
|
||||
});
|
||||
},
|
||||
{ once: true },
|
||||
);
|
||||
expect(await h.fill()).toMatchObject({
|
||||
code: "cdp_failed",
|
||||
data: { reason: action === "focus" ? "fill_focus_lost" : "fill_target_changed" },
|
||||
});
|
||||
expect(other.value).toBe("");
|
||||
expect(h.insert).not.toHaveBeenCalled();
|
||||
expect(h.send.mock.calls.filter(([, method]) => method === "DOM.focus")).toHaveLength(2);
|
||||
});
|
||||
|
||||
it.each([
|
||||
"remove",
|
||||
"readonly",
|
||||
"restore",
|
||||
"microtask-restore",
|
||||
])("stops when clearing causes the page to %s the target", async (action) => {
|
||||
const h = await setup();
|
||||
h.element.addEventListener("input", () => {
|
||||
if (action === "remove") h.element.remove();
|
||||
if (action === "readonly") h.element.readOnly = true;
|
||||
if (action === "restore") h.element.value = "restored";
|
||||
if (action === "microtask-restore")
|
||||
queueMicrotask(() => {
|
||||
h.element.value = "restored";
|
||||
});
|
||||
});
|
||||
expect(await h.fill()).toMatchObject({
|
||||
code: "cdp_failed",
|
||||
data: { reason: "fill_target_changed" },
|
||||
});
|
||||
expect(h.insert).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("fails when insertText is acknowledged without changing the value", async () => {
|
||||
const h = await setup();
|
||||
h.insert.mockImplementation(async () => {});
|
||||
expect(await h.fill()).toMatchObject({
|
||||
code: "cdp_failed",
|
||||
data: { reason: "fill_value_mismatch" },
|
||||
});
|
||||
expect(h.release).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it("detects truncation when maxlength changes after preparation", async () => {
|
||||
const h = await setup();
|
||||
h.element.addEventListener(
|
||||
"input",
|
||||
() => {
|
||||
h.element.maxLength = 3;
|
||||
},
|
||||
{ once: true },
|
||||
);
|
||||
expect(await h.fill()).toMatchObject({
|
||||
code: "cdp_failed",
|
||||
data: { reason: "fill_value_mismatch" },
|
||||
});
|
||||
expect(h.element.value).toBe("hel");
|
||||
});
|
||||
|
||||
it.each([
|
||||
"input",
|
||||
"change",
|
||||
"microtask-change",
|
||||
])("detects a value reverted by the %s handler", async (event) => {
|
||||
const h = await setup();
|
||||
h.element.addEventListener(event === "microtask-change" ? "change" : event, () => {
|
||||
if (event === "microtask-change")
|
||||
queueMicrotask(() => {
|
||||
h.element.value = "";
|
||||
});
|
||||
else h.element.value = "";
|
||||
});
|
||||
expect(await h.fill()).toMatchObject({ code: "cdp_failed", message: /expected value/ });
|
||||
});
|
||||
|
||||
it("compares content rather than length without including field values in the error", async () => {
|
||||
const h = await setup('<input type="password">');
|
||||
h.element.addEventListener("change", () => {
|
||||
h.element.value = "other-secret";
|
||||
});
|
||||
const result = await h.fill("given-secret");
|
||||
expect(result).toMatchObject({ code: "cdp_failed", message: /expected value/ });
|
||||
expect(JSON.stringify(result)).not.toMatch(/given-secret|other-secret/);
|
||||
});
|
||||
|
||||
it("does not report success for a target replaced by a change handler", async () => {
|
||||
const h = await setup();
|
||||
h.element.addEventListener("change", () => h.element.replaceWith(h.element.cloneNode()));
|
||||
expect(await h.fill()).toMatchObject({
|
||||
code: "cdp_failed",
|
||||
data: { reason: "fill_target_changed" },
|
||||
});
|
||||
});
|
||||
|
||||
it.each([
|
||||
1, 2, 3, 4, 5,
|
||||
])("rejects script exceptions at phase %s and releases the target", async (phase) => {
|
||||
const h = await setup();
|
||||
vi.spyOn(document, "hasFocus").mockReturnValue(false);
|
||||
const run = h.script.getMockImplementation()!;
|
||||
let count = 0;
|
||||
h.script.mockImplementation(async (params) =>
|
||||
++count === phase ? { exceptionDetails: { text: "page secret" } } : run(params),
|
||||
);
|
||||
const result = await h.fill();
|
||||
expect(result).toMatchObject({ code: "cdp_failed", data: { reason: "fill_failed" } });
|
||||
expect(JSON.stringify(result)).not.toContain("page secret");
|
||||
if (phase <= 3) expect(h.insert).not.toHaveBeenCalled();
|
||||
expect(h.release).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it.each([1, 2, 3, 5])("rejects missing results at phase %s", async (phase) => {
|
||||
const h = await setup();
|
||||
vi.spyOn(document, "hasFocus").mockReturnValue(false);
|
||||
const run = h.script.getMockImplementation()!;
|
||||
let count = 0;
|
||||
h.script.mockImplementation(async (params) =>
|
||||
++count === phase ? { result: { type: "undefined" } } : run(params),
|
||||
);
|
||||
expect(await h.fill()).toMatchObject({ code: "cdp_failed" });
|
||||
if (phase <= 3) expect(h.insert).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it.each(["input", "change"])("checks state after nested microtasks from %s", async (event) => {
|
||||
const h = await setup();
|
||||
h.element.addEventListener(event, () => {
|
||||
queueMicrotask(() =>
|
||||
queueMicrotask(() => {
|
||||
h.element.value = "reverted";
|
||||
}),
|
||||
);
|
||||
});
|
||||
expect(await h.fill()).toMatchObject({ code: "cdp_failed" });
|
||||
if (event === "input") expect(h.insert).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it.each([
|
||||
"<input>",
|
||||
'<input type="password">',
|
||||
"<textarea></textarea>",
|
||||
])("verifies successful text in %s", async (markup) => {
|
||||
const h = await setup(markup);
|
||||
expect(await h.fill("你好🙂")).toMatchObject({ value_length: 4 });
|
||||
expect(h.element.value).toBe("你好🙂");
|
||||
expect(h.release).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it("verifies append against the old value plus the requested text", async () => {
|
||||
const h = await setup();
|
||||
h.element.focus();
|
||||
h.element.setSelectionRange(3, 3);
|
||||
expect(await h.fill("!", false)).toMatchObject({ value_length: 4 });
|
||||
expect(h.element.value).toBe("old!");
|
||||
});
|
||||
|
||||
it.each([
|
||||
["<textarea></textarea>", "a\r\nb", "a\nb"],
|
||||
["<input>", "a\nb", "a b"],
|
||||
["<input>", "a\r\nb", "a b"],
|
||||
[
|
||||
'<input type="email" multiple>',
|
||||
" a@example.com , b@example.com ",
|
||||
"a@example.com,b@example.com",
|
||||
],
|
||||
])("accepts native normalization for %s", async (markup, requested, normalized) => {
|
||||
if (markup.startsWith("<textarea")) {
|
||||
// Happy DOM does not implement Chrome's textarea line-ending normalization.
|
||||
const setter = Object.getOwnPropertyDescriptor(HTMLTextAreaElement.prototype, "value")!.set!;
|
||||
vi.spyOn(HTMLTextAreaElement.prototype, "value", "set").mockImplementation(function (
|
||||
this: HTMLTextAreaElement,
|
||||
value,
|
||||
) {
|
||||
setter.call(this, value.replace(/\r\n?/g, "\n"));
|
||||
});
|
||||
}
|
||||
const h = await setup(markup);
|
||||
h.insert.mockImplementation(async () => {
|
||||
h.element.value = normalized;
|
||||
});
|
||||
expect(await h.fill(requested)).toMatchObject({ value_length: normalized.length });
|
||||
});
|
||||
|
||||
it("does not count an editable padding break as an extra typed character", async () => {
|
||||
const h = await setup('<div contenteditable="true" tabindex="0"></div>');
|
||||
// These two layout/editability properties are missing in Happy DOM.
|
||||
let innerText = "";
|
||||
Object.defineProperty(h.element, "isContentEditable", { get: () => true });
|
||||
Object.defineProperty(h.element, "innerText", { get: () => innerText });
|
||||
h.insert.mockImplementation(async () => {
|
||||
h.element.innerHTML = "one<div><br></div>";
|
||||
innerText = "one\n\n";
|
||||
});
|
||||
expect(await h.fill("one\n")).toMatchObject({ value_length: 4 });
|
||||
});
|
||||
|
||||
it.each([
|
||||
[0, 0],
|
||||
[1, 1],
|
||||
[0, 3],
|
||||
])("appends after moving selection %s:%s to the end", async (start, end) => {
|
||||
const h = await setup();
|
||||
h.element.focus();
|
||||
h.element.setSelectionRange(start, end);
|
||||
expect(await h.fill("🙂", false)).toMatchObject({ value_length: 5 });
|
||||
expect(h.element.value).toBe("old🙂");
|
||||
});
|
||||
|
||||
it.each(
|
||||
["number", "email"].flatMap((type) =>
|
||||
[
|
||||
[0, 0],
|
||||
[1, 1],
|
||||
[0, 2],
|
||||
].map(([start, end]) => ({ type, start, end })),
|
||||
),
|
||||
)("appends to $type from selection $start:$end without using its unsupported API", async ({
|
||||
type,
|
||||
start,
|
||||
end,
|
||||
}) => {
|
||||
const h = await setup(`<input type="${type}" value="12">`);
|
||||
Object.assign(h.hiddenCaret, { start, end });
|
||||
vi.spyOn(h.element, "selectionStart", "get").mockReturnValue(null);
|
||||
vi.spyOn(h.element, "selectionEnd", "get").mockReturnValue(null);
|
||||
const selection = vi.spyOn(h.element, "setSelectionRange").mockImplementation(() => {
|
||||
throw new DOMException("unsupported", "InvalidStateError");
|
||||
});
|
||||
expect(await h.fill("3", false)).toMatchObject({ value_length: 3 });
|
||||
expect(h.element.value).toBe("123");
|
||||
expect(selection).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it.each([
|
||||
"number",
|
||||
"email",
|
||||
])("does not report successful %s append when the caret command is ignored", async (type) => {
|
||||
const h = await setup(`<input type="${type}" value="12">`);
|
||||
vi.spyOn(h.element, "selectionStart", "get").mockReturnValue(null);
|
||||
vi.spyOn(h.element, "selectionEnd", "get").mockReturnValue(null);
|
||||
h.moveToEnd.mockResolvedValueOnce(undefined);
|
||||
expect(await h.fill("3", false)).toMatchObject({
|
||||
code: "cdp_failed",
|
||||
data: { reason: "fill_value_mismatch" },
|
||||
});
|
||||
expect(h.element.value).toBe("312");
|
||||
expect(h.insert).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it("rejects invalid number text before clearing", async () => {
|
||||
const h = await setup('<input type="number" value="12">');
|
||||
expect(await h.fill("abc")).toMatchObject({
|
||||
code: "invalid_params",
|
||||
data: { reason: "fill_value_invalid" },
|
||||
});
|
||||
expect(h.element.value).toBe("12");
|
||||
expect(h.insert).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("reports page formatting as unconfirmed without retrying the write", async () => {
|
||||
const h = await setup();
|
||||
h.element.addEventListener("change", () => {
|
||||
h.element.value = h.element.value.toUpperCase();
|
||||
});
|
||||
expect(await h.fill()).toMatchObject({
|
||||
code: "cdp_failed",
|
||||
data: { reason: "fill_value_mismatch" },
|
||||
});
|
||||
expect(h.element.value).toBe("HELLO");
|
||||
expect(h.insert).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it.each([
|
||||
["focus", false],
|
||||
["focus", true],
|
||||
["value", false],
|
||||
["value", true],
|
||||
["cancel", false],
|
||||
["cancel", true],
|
||||
["throw", false],
|
||||
["throw", true],
|
||||
] as const)("stops when positioning triggers %s (clear=%s) and releases the key", async (action, clearBefore) => {
|
||||
const h = await setup();
|
||||
vi.spyOn(document, "hasFocus").mockReturnValue(false);
|
||||
const controller = new AbortController();
|
||||
const other = document.createElement("input");
|
||||
document.body.append(other);
|
||||
const send = h.send.getMockImplementation()!;
|
||||
h.send.mockImplementation(async (tabId, method, params) => {
|
||||
const reply = await send(tabId, method, params);
|
||||
if (
|
||||
method === "Input.dispatchKeyEvent" &&
|
||||
(params as { type: string }).type === "rawKeyDown"
|
||||
) {
|
||||
if (action === "focus") other.focus();
|
||||
if (action === "value") h.element.value = "changed";
|
||||
if (action === "cancel") controller.abort();
|
||||
if (action === "throw") throw new Error("dispatch failed");
|
||||
}
|
||||
return reply;
|
||||
});
|
||||
const result = await h.fill("!", clearBefore, controller.signal);
|
||||
expect(result).toMatchObject({ code: action === "cancel" ? "cancelled" : "cdp_failed" });
|
||||
expect(h.insert).not.toHaveBeenCalled();
|
||||
expect(other.value).toBe("");
|
||||
expect(h.send).toHaveBeenCalledWith(
|
||||
4,
|
||||
"Input.dispatchKeyEvent",
|
||||
expect.objectContaining({ type: "keyUp" }),
|
||||
);
|
||||
expect(h.release).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it.each([true, false])("verifies an empty request with clear_before=%s", async (clearBefore) => {
|
||||
const h = await setup();
|
||||
expect(await h.fill("", clearBefore)).toMatchObject({ value_length: clearBefore ? 0 : 3 });
|
||||
expect(h.element.value).toBe(clearBefore ? "" : "old");
|
||||
expect(h.insert).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("cancels after insertion without sending change events", async () => {
|
||||
const h = await setup();
|
||||
const controller = new AbortController();
|
||||
h.insert.mockImplementation(async () => controller.abort());
|
||||
expect(await h.fill("hello", true, controller.signal)).toMatchObject({ code: "cancelled" });
|
||||
expect(h.script).toHaveBeenCalledTimes(2);
|
||||
expect(h.release).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it("cancels after resolving the remote object without clearing the field", async () => {
|
||||
const h = await setup();
|
||||
const controller = new AbortController();
|
||||
const send = h.send.getMockImplementation()!;
|
||||
h.send.mockImplementation(async (tabId, method, params) => {
|
||||
const result = await send(tabId, method, params);
|
||||
if (method === "DOM.resolveNode") controller.abort();
|
||||
return result;
|
||||
});
|
||||
expect(await h.fill("hello", true, controller.signal)).toMatchObject({ code: "cancelled" });
|
||||
expect(h.element.value).toBe("old");
|
||||
expect(h.script).not.toHaveBeenCalled();
|
||||
expect(h.release).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it("honors cancellation during verification", async () => {
|
||||
const h = await setup();
|
||||
const controller = new AbortController();
|
||||
h.element.addEventListener("change", () => controller.abort());
|
||||
expect(await h.fill("hello", true, controller.signal)).toMatchObject({ code: "cancelled" });
|
||||
expect(h.release).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it("keeps the verified outcome when releasing the remote object fails", async () => {
|
||||
const h = await setup();
|
||||
h.release.mockRejectedValueOnce(new Error("target closed"));
|
||||
expect(await h.fill()).toMatchObject({ value_length: 5 });
|
||||
});
|
||||
});
|
||||
@@ -1,166 +0,0 @@
|
||||
// @vitest-environment node
|
||||
// Opt in with BSK_FOCUS_CHROME=/path/to/chrome; each test owns its browser/profile.
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { SessionManager } from "@/session-manager/manager";
|
||||
import { handleBlur, handleFocus } from "../interaction";
|
||||
import type { CdpRunner } from "../shared";
|
||||
|
||||
type Send = <T = Record<string, unknown>>(
|
||||
method: string,
|
||||
params?: object,
|
||||
sessionId?: string,
|
||||
) => Promise<T>;
|
||||
|
||||
async function withFocusBrowser(
|
||||
run: (h: {
|
||||
evaluate: (expression: string) => Promise<unknown>;
|
||||
ref: () => Promise<void>;
|
||||
focus: (signal?: AbortSignal) => ReturnType<typeof handleFocus>;
|
||||
blur: (signal?: AbortSignal) => ReturnType<typeof handleBlur>;
|
||||
calls: string[];
|
||||
afterCommand: { current: (method: string) => void };
|
||||
}) => Promise<void>,
|
||||
) {
|
||||
// Reuse the existing isolated Chrome launcher; no new browser dependency.
|
||||
const { withChrome } = await import(
|
||||
new URL(
|
||||
"../../../../../evals/browser/cases/regression/snapshot-coordinates/chrome.mjs",
|
||||
import.meta.url,
|
||||
).href
|
||||
);
|
||||
await withChrome(
|
||||
{ executable: process.env.BSK_FOCUS_CHROME, deviceScale: 1, zoom: 1 },
|
||||
async (send: Send) => {
|
||||
const { targetId } = await send<{ targetId: string }>("Target.createTarget", {
|
||||
url: "about:blank",
|
||||
});
|
||||
const { sessionId } = await send<{ sessionId: string }>("Target.attachToTarget", {
|
||||
targetId,
|
||||
flatten: true,
|
||||
});
|
||||
await send("Page.bringToFront", {}, sessionId);
|
||||
const evaluate = async (expression: string) => {
|
||||
const reply = await send<{ result: { value: unknown }; exceptionDetails?: unknown }>(
|
||||
"Runtime.evaluate",
|
||||
{ expression, returnByValue: true },
|
||||
sessionId,
|
||||
);
|
||||
expect(reply.exceptionDetails).toBeUndefined();
|
||||
return reply.result.value;
|
||||
};
|
||||
await evaluate(
|
||||
`document.body.innerHTML = '<input id="target"><input id="other">'; window.probe = document.querySelector('#target');`,
|
||||
);
|
||||
const manager = new SessionManager({
|
||||
agentWindow: {
|
||||
create: async () => 100,
|
||||
remove: async () => {},
|
||||
ensureActiveTab: async () => 4,
|
||||
},
|
||||
});
|
||||
const ctx = await manager.start("aa11");
|
||||
const calls: string[] = [];
|
||||
const afterCommand = { current: (_method: string) => {} };
|
||||
const cdp: CdpRunner = {
|
||||
send: async (_tabId, method, params) => {
|
||||
calls.push(method);
|
||||
const result = await send(method, params, sessionId);
|
||||
afterCommand.current(method);
|
||||
return result as never;
|
||||
},
|
||||
};
|
||||
const deps = {
|
||||
cdp,
|
||||
tabsApi: {
|
||||
get: async (id: number) => ({ id, windowId: 100, active: true }) as chrome.tabs.Tab,
|
||||
query: async () => [{ id: 4, windowId: 100, active: true } as chrome.tabs.Tab],
|
||||
},
|
||||
};
|
||||
await run({
|
||||
evaluate,
|
||||
calls,
|
||||
afterCommand,
|
||||
ref: async () => {
|
||||
const { result } = await send<{ result: { objectId: string } }>(
|
||||
"Runtime.evaluate",
|
||||
{ expression: "window.probe" },
|
||||
sessionId,
|
||||
);
|
||||
const { node } = await send<{ node: { backendNodeId: number } }>(
|
||||
"DOM.describeNode",
|
||||
{ objectId: result.objectId },
|
||||
sessionId,
|
||||
);
|
||||
await send("Runtime.releaseObject", { objectId: result.objectId }, sessionId);
|
||||
ctx.refStore.set("e1", node.backendNodeId, { tabId: 4 });
|
||||
},
|
||||
focus: (signal) =>
|
||||
handleFocus(manager, { session_id: "aa11", ref: "e1" }, { ...deps, signal }),
|
||||
blur: (signal) =>
|
||||
handleBlur(manager, { session_id: "aa11", ref: "e1" }, { ...deps, signal }),
|
||||
});
|
||||
},
|
||||
);
|
||||
}
|
||||
|
||||
describe.skipIf(!process.env.BSK_FOCUS_CHROME)("real browser focus and blur", () => {
|
||||
it.each(["light", "open", "closed"])("verifies focus and blur in %s DOM", async (mode) => {
|
||||
await withFocusBrowser(async (h) => {
|
||||
if (mode !== "light")
|
||||
await h.evaluate(`(() => {
|
||||
const host = document.createElement('div'); document.body.append(host);
|
||||
const nested = document.createElement('div'); host.attachShadow({mode:'${mode}'}).append(nested);
|
||||
const input = document.createElement('input'); nested.attachShadow({mode:'${mode}'}).append(input);
|
||||
window.probe = input;
|
||||
})()`);
|
||||
await h.ref();
|
||||
expect(await h.focus()).toMatchObject({ focused: true });
|
||||
expect(await h.evaluate("window.probe.matches(':focus')")).toBe(true);
|
||||
expect(await h.blur()).toMatchObject({ was_focused: true, focused: false });
|
||||
expect(await h.evaluate("window.probe.matches(':focus')")).toBe(false);
|
||||
expect(h.calls.filter((method) => method === "Runtime.releaseObject")).toHaveLength(2);
|
||||
});
|
||||
});
|
||||
|
||||
it("detects focus changes from event-handler microtasks", async () => {
|
||||
await withFocusBrowser(async (h) => {
|
||||
await h.ref();
|
||||
await h.evaluate(
|
||||
"window.probe.addEventListener('focus', () => queueMicrotask(() => document.querySelector('#other').focus()), {once:true})",
|
||||
);
|
||||
expect(await h.focus()).toMatchObject({ code: "cdp_failed" });
|
||||
expect(await h.focus()).toMatchObject({ focused: true });
|
||||
await h.evaluate(
|
||||
"window.probe.addEventListener('blur', () => queueMicrotask(() => window.probe.focus()), {once:true})",
|
||||
);
|
||||
expect(await h.blur()).toMatchObject({ code: "cdp_failed" });
|
||||
expect(await h.evaluate("window.probe.matches(':focus')")).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
it("cancels before blur while still releasing the resolved object", async () => {
|
||||
await withFocusBrowser(async (h) => {
|
||||
await h.ref();
|
||||
await h.focus();
|
||||
const abort = new AbortController();
|
||||
h.afterCommand.current = (method) => {
|
||||
if (method === "DOM.resolveNode") abort.abort();
|
||||
};
|
||||
expect(await h.blur(abort.signal)).toMatchObject({ code: "cancelled" });
|
||||
expect(await h.evaluate("window.probe.matches(':focus')")).toBe(true);
|
||||
expect(h.calls.at(-1)).toBe("Runtime.releaseObject");
|
||||
});
|
||||
});
|
||||
|
||||
it("reports a page exception with its cause", async () => {
|
||||
await withFocusBrowser(async (h) => {
|
||||
await h.ref();
|
||||
await h.evaluate("window.probe.blur = () => { throw new Error('page blur failed'); }");
|
||||
expect(await h.blur()).toMatchObject({
|
||||
code: "cdp_failed",
|
||||
message: expect.stringContaining("page blur failed"),
|
||||
});
|
||||
expect(h.calls.at(-1)).toBe("Runtime.releaseObject");
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -1,293 +0,0 @@
|
||||
import { afterEach, describe, expect, it, vi } from "vitest";
|
||||
import type { CdpTarget } from "@/browser-driver/frame-graph";
|
||||
import { SessionManager } from "@/session-manager/manager";
|
||||
import { handleBlur, handleFocus } from "../interaction";
|
||||
import type { CdpRunner } from "../shared";
|
||||
|
||||
interface ScriptParams {
|
||||
functionDeclaration: string;
|
||||
}
|
||||
interface Call {
|
||||
target: CdpTarget;
|
||||
method: string;
|
||||
}
|
||||
|
||||
async function setup(element?: HTMLElement, childSession = false) {
|
||||
if (!element) {
|
||||
document.body.innerHTML = '<input id="target"><input id="other">';
|
||||
element = document.querySelector<HTMLInputElement>("#target")!;
|
||||
}
|
||||
const targetElement = element;
|
||||
const manager = new SessionManager({
|
||||
agentWindow: {
|
||||
create: async () => 100,
|
||||
remove: async () => {},
|
||||
ensureActiveTab: async () => 4,
|
||||
},
|
||||
});
|
||||
const ctx = await manager.start("aa11");
|
||||
ctx.refStore.set("e1", 12, {
|
||||
tabId: 4,
|
||||
...(childSession ? { frameId: "child", cdpSessionId: "child-session" } : {}),
|
||||
});
|
||||
const calls: Call[] = [];
|
||||
const afterCommand = vi.fn<(call: Call) => void>();
|
||||
const script = vi.fn(async (params: ScriptParams) => {
|
||||
try {
|
||||
const fn = new Function(`return (${params.functionDeclaration})`)();
|
||||
return { result: { value: await fn.call(targetElement) } };
|
||||
} catch (error) {
|
||||
return { exceptionDetails: { text: "Uncaught", exception: { description: String(error) } } };
|
||||
}
|
||||
});
|
||||
const focus = vi.fn(() => targetElement.focus());
|
||||
const release = vi.fn(async () => ({}));
|
||||
const send = async (target: CdpTarget, method: string, params?: object) => {
|
||||
const call = { target, method };
|
||||
calls.push(call);
|
||||
try {
|
||||
switch (method) {
|
||||
case "DOM.getDocument":
|
||||
return { root: { nodeId: 1 } };
|
||||
case "DOM.querySelector":
|
||||
return { nodeId: 2 };
|
||||
case "DOM.describeNode":
|
||||
return { node: { backendNodeId: 12 } };
|
||||
case "DOM.scrollIntoViewIfNeeded":
|
||||
return {};
|
||||
case "DOM.resolveNode":
|
||||
return { object: { objectId: "focus-target" } };
|
||||
case "DOM.focus":
|
||||
focus();
|
||||
return {};
|
||||
case "Runtime.callFunctionOn":
|
||||
return await script(params as ScriptParams);
|
||||
case "Runtime.releaseObject":
|
||||
return await release();
|
||||
default:
|
||||
throw new Error(`unexpected ${method}`);
|
||||
}
|
||||
} finally {
|
||||
afterCommand(call);
|
||||
}
|
||||
};
|
||||
const cdp: CdpRunner = {
|
||||
send: (tabId, method, params) => send({ tabId }, method, params) as never,
|
||||
sendToTarget: send as CdpRunner["sendToTarget"],
|
||||
getFrameGraph: vi.fn(async () => ({
|
||||
rootFrameId: "main",
|
||||
frames: [
|
||||
{ frameId: "main", target: { tabId: 4 } },
|
||||
...(childSession
|
||||
? [
|
||||
{
|
||||
frameId: "child",
|
||||
parentFrameId: "main",
|
||||
ownerBackendNodeId: 99,
|
||||
target: { tabId: 4, sessionId: "child-session" },
|
||||
},
|
||||
]
|
||||
: []),
|
||||
],
|
||||
})),
|
||||
};
|
||||
const tabsApi = {
|
||||
get: vi.fn(async (id: number) => ({ id, windowId: 100, active: true }) as chrome.tabs.Tab),
|
||||
query: vi.fn(async () => [{ id: 4, windowId: 100, active: true } as chrome.tabs.Tab]),
|
||||
};
|
||||
return {
|
||||
element: targetElement,
|
||||
calls,
|
||||
afterCommand,
|
||||
script,
|
||||
focus,
|
||||
release,
|
||||
cdp,
|
||||
tabsApi,
|
||||
run: (
|
||||
action: "focus" | "blur",
|
||||
signal?: AbortSignal,
|
||||
params: { ref?: string; selector?: string; tab_id?: number } = { ref: "e1" },
|
||||
) =>
|
||||
(action === "focus" ? handleFocus : handleBlur)(
|
||||
manager,
|
||||
{ session_id: "aa11", ...params },
|
||||
{ cdp, tabsApi, signal },
|
||||
),
|
||||
};
|
||||
}
|
||||
|
||||
afterEach(() => {
|
||||
vi.restoreAllMocks();
|
||||
document.body.innerHTML = "";
|
||||
});
|
||||
|
||||
describe("focus and blur state verification", () => {
|
||||
it.each(["open", "closed"] as const)("handles nested %s shadow roots", async (mode) => {
|
||||
const host = document.createElement("div");
|
||||
document.body.append(host);
|
||||
const outer = host.attachShadow({ mode });
|
||||
const innerHost = document.createElement("div");
|
||||
outer.append(innerHost);
|
||||
const inner = innerHost.attachShadow({ mode });
|
||||
const element = document.createElement("input");
|
||||
inner.append(element);
|
||||
const h = await setup(element);
|
||||
expect(await h.run("focus")).toMatchObject({ focused: true });
|
||||
expect(inner.activeElement).toBe(element);
|
||||
expect(await h.run("blur")).toMatchObject({ was_focused: true, focused: false });
|
||||
expect(inner.activeElement).toBeNull();
|
||||
expect(h.release).toHaveBeenCalledTimes(2);
|
||||
});
|
||||
|
||||
it("keeps DOM focus usable when the document is in the background", async () => {
|
||||
const h = await setup();
|
||||
vi.spyOn(document, "hasFocus").mockReturnValue(false);
|
||||
expect(await h.run("focus")).toMatchObject({ focused: true });
|
||||
expect(await h.run("blur")).toMatchObject({ was_focused: true, focused: false });
|
||||
});
|
||||
|
||||
it("blurring an unfocused target preserves the other element's focus", async () => {
|
||||
const h = await setup();
|
||||
const other = document.querySelector<HTMLInputElement>("#other")!;
|
||||
other.focus();
|
||||
expect(await h.run("blur")).toMatchObject({ was_focused: false, focused: false });
|
||||
expect(document.activeElement).toBe(other);
|
||||
});
|
||||
|
||||
it("detects focus redirected by a focus handler's microtask", async () => {
|
||||
const h = await setup();
|
||||
h.element.addEventListener("focus", () =>
|
||||
queueMicrotask(() => document.querySelector<HTMLInputElement>("#other")!.focus()),
|
||||
);
|
||||
expect(await h.run("focus")).toMatchObject({
|
||||
code: "cdp_failed",
|
||||
message: "target element did not become focused",
|
||||
});
|
||||
expect(h.release).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it("does not report blur success when a microtask restores focus", async () => {
|
||||
const h = await setup();
|
||||
h.element.focus();
|
||||
h.element.addEventListener("blur", () => queueMicrotask(() => h.element.focus()));
|
||||
expect(await h.run("blur")).toMatchObject({
|
||||
code: "cdp_failed",
|
||||
message: "target element remained focused after blur()",
|
||||
});
|
||||
expect(document.activeElement).toBe(h.element);
|
||||
expect(h.release).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it.each(["focus", "blur"] as const)("rejects a detached %s target", async (action) => {
|
||||
const h = await setup();
|
||||
h.element.remove();
|
||||
expect(await h.run(action)).toMatchObject({ code: "cdp_failed" });
|
||||
expect(h.release).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it("preserves a script exception's cause", async () => {
|
||||
const h = await setup();
|
||||
vi.spyOn(h.element, "blur").mockImplementation(() => {
|
||||
throw new Error("page blur failed");
|
||||
});
|
||||
expect(await h.run("blur")).toMatchObject({
|
||||
code: "cdp_failed",
|
||||
message: expect.stringContaining("page blur failed"),
|
||||
});
|
||||
expect(h.release).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it.each(["focus", "blur"] as const)("rejects malformed %s script results", async (action) => {
|
||||
const h = await setup();
|
||||
h.script.mockResolvedValueOnce({ result: { value: null } });
|
||||
expect(await h.run(action)).toMatchObject({
|
||||
code: "cdp_failed",
|
||||
message: expect.stringContaining("unexpected result"),
|
||||
});
|
||||
expect(h.release).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it.each([
|
||||
"focus",
|
||||
"blur",
|
||||
] as const)("keeps %s, verification and cleanup in the OOPIF session", async (action) => {
|
||||
const h = await setup(undefined, true);
|
||||
if (action === "blur") h.element.focus();
|
||||
expect(await h.run(action)).toMatchObject({ focused: action === "focus" });
|
||||
const targetCalls = h.calls.filter((call) => call.method !== "DOM.scrollIntoViewIfNeeded");
|
||||
expect(targetCalls.every((call) => call.target.sessionId === "child-session")).toBe(true);
|
||||
expect(targetCalls.at(-1)?.method).toBe("Runtime.releaseObject");
|
||||
});
|
||||
|
||||
it.each(["focus", "blur"] as const)("rejects %s on a user tab before CDP", async (action) => {
|
||||
const h = await setup();
|
||||
h.tabsApi.get.mockResolvedValue({ id: 9, windowId: 200, active: true } as chrome.tabs.Tab);
|
||||
expect(await h.run(action, undefined, { ref: "e1", tab_id: 9 })).toMatchObject({
|
||||
code: "permission_denied",
|
||||
});
|
||||
expect(h.calls).toEqual([]);
|
||||
});
|
||||
|
||||
it("does not replace a successful result when navigation disposed the remote object", async () => {
|
||||
const h = await setup();
|
||||
h.release.mockRejectedValue(new Error("Cannot find context"));
|
||||
expect(await h.run("focus")).toMatchObject({ focused: true });
|
||||
});
|
||||
});
|
||||
|
||||
describe("focus and blur cancellation", () => {
|
||||
const boundaries = [
|
||||
"DOM.getDocument",
|
||||
"DOM.querySelector",
|
||||
"DOM.describeNode",
|
||||
"DOM.resolveNode",
|
||||
"Runtime.callFunctionOn",
|
||||
];
|
||||
for (const action of ["focus", "blur"] as const) {
|
||||
it.each(
|
||||
action === "focus" ? [...boundaries, "DOM.scrollIntoViewIfNeeded", "DOM.focus"] : boundaries,
|
||||
)(`${action} stops after cancellation during %s`, async (method) => {
|
||||
const h = await setup();
|
||||
const abort = new AbortController();
|
||||
let cancelledAfter = 0;
|
||||
h.afterCommand.mockImplementation((call) => {
|
||||
if (call.method === method && !abort.signal.aborted) {
|
||||
cancelledAfter = h.calls.length;
|
||||
abort.abort();
|
||||
}
|
||||
});
|
||||
expect(await h.run(action, abort.signal, { selector: "#target" })).toMatchObject({
|
||||
code: "cancelled",
|
||||
});
|
||||
expect(abort.signal.aborted).toBe(true);
|
||||
expect(
|
||||
h.calls.slice(cancelledAfter).every((call) => call.method === "Runtime.releaseObject"),
|
||||
).toBe(true);
|
||||
if (h.calls.some((call) => call.method === "DOM.resolveNode"))
|
||||
expect(h.release).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it(`${action} stops if cancellation arrives while resolving the tab`, async () => {
|
||||
const h = await setup();
|
||||
const abort = new AbortController();
|
||||
h.tabsApi.query.mockImplementation(async () => {
|
||||
abort.abort();
|
||||
return [{ id: 4, windowId: 100, active: true } as chrome.tabs.Tab];
|
||||
});
|
||||
expect(await h.run(action, abort.signal)).toMatchObject({ code: "cancelled" });
|
||||
expect(h.calls).toEqual([]);
|
||||
});
|
||||
}
|
||||
|
||||
it("does not scroll frame owners after cancellation in an OOPIF", async () => {
|
||||
const h = await setup(undefined, true);
|
||||
const abort = new AbortController();
|
||||
h.afterCommand.mockImplementation((call) => {
|
||||
if (call.method === "DOM.scrollIntoViewIfNeeded") abort.abort();
|
||||
});
|
||||
expect(await h.run("focus", abort.signal)).toMatchObject({ code: "cancelled" });
|
||||
expect(h.calls.filter((call) => call.method === "DOM.scrollIntoViewIfNeeded")).toHaveLength(1);
|
||||
expect(h.focus).not.toHaveBeenCalled();
|
||||
});
|
||||
});
|
||||
@@ -1,5 +1,5 @@
|
||||
import { describe, expect, it, vi } from "vitest";
|
||||
import { resolveNodeGeometry } from "../frame-geometry";
|
||||
import { resolveFrameProjection, resolveNodeGeometry } from "../frame-geometry";
|
||||
import {
|
||||
clipPolygon,
|
||||
polygonArea,
|
||||
@@ -10,141 +10,9 @@ import {
|
||||
rectPolygon,
|
||||
regionBounds,
|
||||
} from "../geometry";
|
||||
import { GeometryContext } from "../geometry/frame-context";
|
||||
import type { CdpRunner } from "../shared";
|
||||
|
||||
function scrollbarDriver(
|
||||
visible = { width: 185, height: 89 },
|
||||
frameSize: unknown = { width: 200, height: 100 },
|
||||
) {
|
||||
const send = vi.fn(async (target: { sessionId?: string }, method: string) => {
|
||||
if (method === "Runtime.evaluate") return { result: { value: frameSize } };
|
||||
if (method === "Page.getLayoutMetrics")
|
||||
return {
|
||||
cssLayoutViewport: {
|
||||
clientWidth: target.sessionId ? visible.width : 800,
|
||||
clientHeight: target.sessionId ? visible.height : 600,
|
||||
},
|
||||
};
|
||||
if (method === "DOM.getBoxModel")
|
||||
return {
|
||||
model: {
|
||||
content: target.sessionId
|
||||
? [0, 0, 200, 0, 200, 100, 0, 100]
|
||||
: [100, 100, 500, 100, 500, 300, 100, 300],
|
||||
},
|
||||
};
|
||||
if (method === "DOM.getContentQuads")
|
||||
return { quads: [[180, 80, 230, 80, 230, 120, 180, 120]] };
|
||||
throw new Error(`unexpected ${method}`);
|
||||
});
|
||||
const cdp: CdpRunner = {
|
||||
send: (tabId, method) => send({ tabId } as never, method) as never,
|
||||
sendToTarget: send as CdpRunner["sendToTarget"],
|
||||
getFrameGraph: async () => ({
|
||||
rootFrameId: "main",
|
||||
frames: [
|
||||
{ frameId: "main", target: { tabId: 4 } },
|
||||
{
|
||||
frameId: "child",
|
||||
parentFrameId: "main",
|
||||
ownerBackendNodeId: 10,
|
||||
target: { tabId: 4, sessionId: "child" },
|
||||
},
|
||||
{
|
||||
frameId: "same-child",
|
||||
parentFrameId: "child",
|
||||
ownerBackendNodeId: 20,
|
||||
target: { tabId: 4, sessionId: "child" },
|
||||
},
|
||||
],
|
||||
}),
|
||||
};
|
||||
return { cdp, send };
|
||||
}
|
||||
|
||||
describe("frame geometry projection", () => {
|
||||
it.each([
|
||||
{ width: 200, height: 100 },
|
||||
{ width: 185, height: 100 },
|
||||
{ width: 200, height: 89 },
|
||||
{ width: 185, height: 89 },
|
||||
])("preserves scale and clips scrollbar strips for visible viewport $width × $height", async (visible) => {
|
||||
const { cdp, send } = scrollbarDriver(visible);
|
||||
const geometry = await resolveNodeGeometry(cdp, 4, {
|
||||
target: { tabId: 4, sessionId: "child" },
|
||||
frameId: "child",
|
||||
backendNodeId: 101,
|
||||
});
|
||||
expect(geometry).toMatchObject({
|
||||
topBounds: {
|
||||
x: 460,
|
||||
y: 260,
|
||||
width: (visible.width - 180) * 2,
|
||||
height: (visible.height - 80) * 2,
|
||||
},
|
||||
actionPoint: { x: 460 + visible.width - 180, y: 260 + visible.height - 80 },
|
||||
targetActionPoint: { x: (180 + visible.width) / 2, y: (80 + visible.height) / 2 },
|
||||
});
|
||||
expect(send.mock.calls.filter(([, method]) => method === "Runtime.evaluate")).toHaveLength(1);
|
||||
expect(send.mock.calls.filter(([, method]) => method === "Page.getLayoutMetrics")).toHaveLength(
|
||||
2,
|
||||
);
|
||||
});
|
||||
|
||||
it("shares the full viewport read across same-target frames, and refreshes it next operation", async () => {
|
||||
const { cdp, send } = scrollbarDriver();
|
||||
const context = new GeometryContext(cdp, 4);
|
||||
await Promise.all([context.targetProjection("child"), context.targetProjection("same-child")]);
|
||||
expect(send.mock.calls.filter(([, method]) => method === "Runtime.evaluate")).toHaveLength(1);
|
||||
await new GeometryContext(cdp, 4).targetProjection("child");
|
||||
expect(send.mock.calls.filter(([, method]) => method === "Runtime.evaluate")).toHaveLength(2);
|
||||
});
|
||||
|
||||
it.each([
|
||||
null,
|
||||
{},
|
||||
{ width: 0, height: 100 },
|
||||
{ width: 200, height: NaN },
|
||||
])("rejects unavailable full viewport dimensions: %j", async (size) => {
|
||||
const { cdp } = scrollbarDriver(undefined, size);
|
||||
expect(await new GeometryContext(cdp, 4).targetProjection("child")).toBeNull();
|
||||
});
|
||||
|
||||
it("clips an inner OOPIF against an intermediate OOPIF's occupied scrollbar strips", async () => {
|
||||
const { cdp } = scrollbarDriver();
|
||||
const outer = cdp.sendToTarget!;
|
||||
cdp.sendToTarget = async (target, method, params) => {
|
||||
if (method === "DOM.getBoxModel")
|
||||
return { model: { content: [150, 60, 250, 60, 250, 120, 150, 120] } } as never;
|
||||
if (target.sessionId !== "inner") return outer(target, method, params);
|
||||
if (method === "Runtime.evaluate")
|
||||
return { result: { value: { width: 100, height: 60 } } } as never;
|
||||
if (method === "Page.getLayoutMetrics")
|
||||
return { cssLayoutViewport: { clientWidth: 90, clientHeight: 50 } } as never;
|
||||
if (method === "DOM.getContentQuads")
|
||||
return { quads: [[0, 0, 100, 0, 100, 60, 0, 60]] } as never;
|
||||
throw new Error(`unexpected ${method}`);
|
||||
};
|
||||
const graph = await cdp.getFrameGraph!(4);
|
||||
graph.frames[2] = {
|
||||
frameId: "inner",
|
||||
parentFrameId: "child",
|
||||
ownerBackendNodeId: 20,
|
||||
target: { tabId: 4, sessionId: "inner" },
|
||||
};
|
||||
cdp.getFrameGraph = async () => graph;
|
||||
expect(
|
||||
await resolveNodeGeometry(cdp, 4, {
|
||||
target: { tabId: 4, sessionId: "inner" },
|
||||
frameId: "inner",
|
||||
backendNodeId: 101,
|
||||
}),
|
||||
).toMatchObject({
|
||||
topBounds: { x: 400, y: 220, width: 70, height: 58 },
|
||||
});
|
||||
});
|
||||
|
||||
it("keeps region bounds separate from polygon area", () => {
|
||||
const region = [
|
||||
rectPolygon({ x: 0, y: 0, w: 10, h: 10 }),
|
||||
@@ -208,32 +76,34 @@ describe("frame geometry projection", () => {
|
||||
const cdp: CdpRunner = {
|
||||
send: send as CdpRunner["send"],
|
||||
sendToTarget: vi.fn(async (_target, method) => {
|
||||
if (method === "Runtime.evaluate")
|
||||
return { result: { value: { width: 200, height: 100 } } };
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return { cssLayoutViewport: { clientWidth: 200, clientHeight: 100 } };
|
||||
}
|
||||
throw new Error(`unexpected child command ${method}`);
|
||||
}) as CdpRunner["sendToTarget"],
|
||||
};
|
||||
const projection = await new GeometryContext(cdp, 4, {
|
||||
rootFrameId: "main",
|
||||
frames: [
|
||||
{ frameId: "main", target: { tabId: 4 } },
|
||||
{
|
||||
frameId: "same-process-parent",
|
||||
parentFrameId: "main",
|
||||
ownerBackendNodeId: 10,
|
||||
target: { tabId: 4 },
|
||||
},
|
||||
{
|
||||
frameId: "oopif",
|
||||
parentFrameId: "same-process-parent",
|
||||
ownerBackendNodeId: 20,
|
||||
target: { tabId: 4, sessionId: "oopif-session" },
|
||||
},
|
||||
],
|
||||
}).targetProjection("oopif");
|
||||
const projection = await resolveFrameProjection(
|
||||
cdp,
|
||||
{
|
||||
rootFrameId: "main",
|
||||
frames: [
|
||||
{ frameId: "main", target: { tabId: 4 } },
|
||||
{
|
||||
frameId: "same-process-parent",
|
||||
parentFrameId: "main",
|
||||
ownerBackendNodeId: 10,
|
||||
target: { tabId: 4 },
|
||||
},
|
||||
{
|
||||
frameId: "oopif",
|
||||
parentFrameId: "same-process-parent",
|
||||
ownerBackendNodeId: 20,
|
||||
target: { tabId: 4, sessionId: "oopif-session" },
|
||||
},
|
||||
],
|
||||
},
|
||||
"oopif",
|
||||
);
|
||||
|
||||
expect(projection?.edges).toEqual([
|
||||
{
|
||||
@@ -268,8 +138,6 @@ describe("frame geometry projection", () => {
|
||||
throw new Error(`unexpected root command ${method}`);
|
||||
}) as CdpRunner["send"],
|
||||
sendToTarget: vi.fn(async (_target, method) => {
|
||||
if (method === "Runtime.evaluate")
|
||||
return { result: { value: { width: 200, height: 100 } } };
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return { cssLayoutViewport: { clientWidth: 200, clientHeight: 100 } };
|
||||
}
|
||||
@@ -301,7 +169,6 @@ describe("frame geometry projection", () => {
|
||||
expect(geometry).toMatchObject({
|
||||
topBounds: { x: 100, y: 100, width: 200, height: 100 },
|
||||
actionPoint: { x: 200, y: 150 },
|
||||
targetActionPoint: { x: 100, y: 50 },
|
||||
});
|
||||
});
|
||||
|
||||
@@ -331,8 +198,6 @@ describe("frame geometry projection", () => {
|
||||
}) as CdpRunner["send"],
|
||||
sendToTarget: vi.fn(async (_target, method) => {
|
||||
if (method === "DOM.scrollIntoViewIfNeeded") return {};
|
||||
if (method === "Runtime.evaluate")
|
||||
return { result: { value: { width: 200, height: 100 } } };
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return { cssLayoutViewport: { clientWidth: 200, clientHeight: 100 } };
|
||||
}
|
||||
@@ -396,7 +261,6 @@ describe("frame geometry projection", () => {
|
||||
expect(geometry).toMatchObject({
|
||||
topBounds: { x: 100, y: 100, width: 200, height: 100 },
|
||||
actionPoint: { x: 200, y: 150 },
|
||||
targetActionPoint: { x: 200, y: 150 },
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
@@ -1,464 +0,0 @@
|
||||
import { describe, expect, it, vi } from "vitest";
|
||||
import type { CdpFrameGraph } from "@/browser-driver/frame-graph";
|
||||
import { resolveNodeGeometry } from "../frame-geometry";
|
||||
import { rectPolygon } from "../geometry";
|
||||
import {
|
||||
projectSnapshotRect,
|
||||
screenshotPageRect,
|
||||
snapshotCoordinates,
|
||||
snapshotViewportRect,
|
||||
} from "../geometry/coordinate-types";
|
||||
import { GeometryContext, snapshotLayoutScale } from "../geometry/frame-context";
|
||||
import type { CdpRunner } from "../shared";
|
||||
|
||||
const target = { tabId: 4 };
|
||||
const graph: CdpFrameGraph = {
|
||||
rootFrameId: "main",
|
||||
frames: [
|
||||
{ frameId: "main", target },
|
||||
{ frameId: "child", parentFrameId: "main", ownerBackendNodeId: 10, target },
|
||||
],
|
||||
};
|
||||
|
||||
function driver() {
|
||||
const send = vi.fn(async (_tab: number, method: string): Promise<object> => {
|
||||
if (method === "Page.getLayoutMetrics")
|
||||
return {
|
||||
visualViewport: { clientWidth: 1000 },
|
||||
cssVisualViewport: { clientWidth: 1000 },
|
||||
cssLayoutViewport: { clientWidth: 1000, clientHeight: 1000 },
|
||||
};
|
||||
if (method === "DOM.getBoxModel")
|
||||
return { model: { content: [52.5, 612.5, 427.5, 612.5, 427.5, 862.5, 52.5, 862.5] } };
|
||||
if (method === "DOM.resolveNode") return { object: { objectId: "owner" } };
|
||||
if (method === "Runtime.callFunctionOn")
|
||||
return { result: { value: { width: 300, height: 200 } } };
|
||||
if (method === "Runtime.releaseObject") return {};
|
||||
throw new Error(method);
|
||||
});
|
||||
return { send: send as CdpRunner["send"], getFrameGraph: vi.fn(async () => graph), calls: send };
|
||||
}
|
||||
|
||||
describe("measurement geometry context", () => {
|
||||
it.each([0.8, 1, 1.25, 2])("normalizes snapshot layout units at scale %s", (scale) => {
|
||||
const measured = snapshotLayoutScale({
|
||||
visualViewport: { clientWidth: 997.25, zoom: 1.1 },
|
||||
cssVisualViewport: { clientWidth: 997.25 / scale, zoom: 1.1 },
|
||||
// Rounded layout dimensions must not supply the scale.
|
||||
layoutViewport: { clientWidth: 997 },
|
||||
cssLayoutViewport: { clientWidth: Math.floor(997.25 / scale) },
|
||||
});
|
||||
expect(measured).toBeCloseTo(scale, 12);
|
||||
const coordinates = snapshotCoordinates(
|
||||
{ scrollOffsetX: 80 * scale, scrollOffsetY: 200 * scale },
|
||||
measured,
|
||||
{ x: 999, y: 999 },
|
||||
);
|
||||
expect(
|
||||
snapshotViewportRect(
|
||||
[160 * scale, 320 * scale, 120 * scale, 40 * scale],
|
||||
{ target },
|
||||
coordinates,
|
||||
)?.rect,
|
||||
).toEqual({ x: 80, y: 120, width: 120, height: 40 });
|
||||
});
|
||||
|
||||
it("uses CSS root scroll only for missing snapshot offsets, without scaling it twice", () => {
|
||||
const coordinates = snapshotCoordinates({ scrollOffsetX: 80 }, 2, { x: 999, y: 100 });
|
||||
expect(snapshotViewportRect([200, 800, 240, 80], { target }, coordinates)?.rect).toEqual({
|
||||
x: 60,
|
||||
y: 300,
|
||||
width: 120,
|
||||
height: 40,
|
||||
});
|
||||
expect(snapshotCoordinates({ scrollOffsetX: 0 }, 2)).toBeNull();
|
||||
expect(
|
||||
snapshotCoordinates({ scrollOffsetX: NaN, scrollOffsetY: 0 }, 2, { x: 0, y: 0 }),
|
||||
).toBeNull();
|
||||
});
|
||||
|
||||
it("does not infer snapshot units from missing, invalid, or CSS-only metrics", () => {
|
||||
expect(snapshotLayoutScale({ cssLayoutViewport: { clientWidth: 800 } })).toBeNull();
|
||||
for (const raw of [0, -1, NaN, Infinity]) {
|
||||
expect(
|
||||
snapshotLayoutScale({
|
||||
visualViewport: { clientWidth: raw },
|
||||
cssVisualViewport: { clientWidth: 800 },
|
||||
}),
|
||||
).toBeNull();
|
||||
}
|
||||
expect(
|
||||
snapshotLayoutScale({
|
||||
visualViewport: { clientWidth: 0, clientHeight: 600 },
|
||||
cssVisualViewport: { clientWidth: 0, clientHeight: 300 },
|
||||
}),
|
||||
).toBe(2);
|
||||
expect(snapshotCoordinates({ scrollOffsetX: 0, scrollOffsetY: 0 }, null)).toBeNull();
|
||||
expect(snapshotViewportRect([10, 20, 120, 40], { target }, null)).toBeNull();
|
||||
});
|
||||
|
||||
it("shares in-flight frame measurements, but never shares them with the next context", async () => {
|
||||
const cdp = driver();
|
||||
const context = new GeometryContext(cdp, 4);
|
||||
const results = await Promise.all(
|
||||
Array.from({ length: 20 }, () => context.targetProjection("child")),
|
||||
);
|
||||
expect(results.every((value) => value === results[0])).toBe(true);
|
||||
expect(cdp.getFrameGraph).toHaveBeenCalledTimes(1);
|
||||
expect(cdp.calls.mock.calls.map(([, method]) => method)).toEqual([
|
||||
"Page.getLayoutMetrics",
|
||||
"DOM.getBoxModel",
|
||||
]);
|
||||
await new GeometryContext(cdp, 4).targetProjection("child");
|
||||
expect(cdp.getFrameGraph).toHaveBeenCalledTimes(2);
|
||||
expect(cdp.calls.mock.calls).toHaveLength(4);
|
||||
});
|
||||
|
||||
it("projects frame-local snapshot CSS bounds through the scaled owner content quad", async () => {
|
||||
const cdp = driver();
|
||||
const context = new GeometryContext(cdp, 4);
|
||||
const source = { target, frameId: "child" };
|
||||
const projection = await context.snapshotProjection(source, 10, [], {
|
||||
width: 1000,
|
||||
height: 1000,
|
||||
});
|
||||
if (projection.status !== "available") throw new Error("expected available projection");
|
||||
const input = snapshotViewportRect([17, 23, 120, 40], source, {
|
||||
layoutUnitsPerCssPixel: 1,
|
||||
scrollCss: { x: 0, y: 0 },
|
||||
});
|
||||
expect(projectSnapshotRect(input!, projection.projection)).toEqual({
|
||||
x: 73.75,
|
||||
y: 641.25,
|
||||
width: 150,
|
||||
height: 50,
|
||||
});
|
||||
const scrolled = snapshotViewportRect([17, 23, 120, 40], source, {
|
||||
layoutUnitsPerCssPixel: 1,
|
||||
scrollCss: { x: 0, y: 10 },
|
||||
});
|
||||
expect(projectSnapshotRect(scrolled!, projection.projection)?.y).toBe(628.75);
|
||||
await context.snapshotProjection(source, 10, [], { width: 1000, height: 1000 });
|
||||
expect(cdp.calls.mock.calls.filter(([, method]) => method === "DOM.resolveNode")).toHaveLength(
|
||||
1,
|
||||
);
|
||||
expect(
|
||||
cdp.calls.mock.calls.filter(([, method]) => method === "Runtime.releaseObject"),
|
||||
).toHaveLength(1);
|
||||
});
|
||||
|
||||
it("falls back only for missing or invalid batch entries and does not reuse sizes across contexts", async () => {
|
||||
const cdp = driver();
|
||||
const original = cdp.send;
|
||||
const calls: string[] = [];
|
||||
cdp.send = async (tabId, method, params) => {
|
||||
calls.push(method);
|
||||
if (method === "Runtime.evaluate")
|
||||
return {
|
||||
result: {
|
||||
deepSerializedValue: {
|
||||
type: "array",
|
||||
value: [
|
||||
{
|
||||
type: "array",
|
||||
value: [
|
||||
{ type: "node", value: { backendNodeId: 10 } },
|
||||
{ type: "string", value: '{"width":300,"height":200}' },
|
||||
],
|
||||
},
|
||||
{
|
||||
type: "array",
|
||||
value: [
|
||||
{ type: "node", value: { backendNodeId: 11 } },
|
||||
{ type: "string", value: '{"width":0,"height":200}' },
|
||||
],
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
} as never;
|
||||
if (method === "Runtime.releaseObjectGroup") return {} as never;
|
||||
return original(tabId, method, params);
|
||||
};
|
||||
const context = new GeometryContext(cdp, 4);
|
||||
context.registerSnapshotOwners(target, new Set([10, 11]));
|
||||
const values = await Promise.all(
|
||||
[10, 11].map((id) =>
|
||||
context.snapshotProjection({ target, frameId: String(id) }, id, [], {
|
||||
width: 1000,
|
||||
height: 1000,
|
||||
}),
|
||||
),
|
||||
);
|
||||
expect(values.every((value) => value.status === "available")).toBe(true);
|
||||
expect(calls.filter((method) => method === "DOM.resolveNode")).toHaveLength(1);
|
||||
expect(calls.filter((method) => method === "Runtime.evaluate")).toHaveLength(1);
|
||||
await new GeometryContext(cdp, 4).snapshotProjection({ target, frameId: "child" }, 10, [], {
|
||||
width: 1000,
|
||||
height: 1000,
|
||||
});
|
||||
expect(calls.filter((method) => method === "DOM.resolveNode")).toHaveLength(2);
|
||||
});
|
||||
|
||||
it("waits for batch object cleanup and propagates cancellation", async () => {
|
||||
const cdp = driver();
|
||||
const original = cdp.send;
|
||||
const controller = new AbortController();
|
||||
let release!: () => void;
|
||||
let cleanup!: () => void;
|
||||
const started = new Promise<void>((resolve) => {
|
||||
cleanup = resolve;
|
||||
});
|
||||
cdp.send = async (tabId, method, params) => {
|
||||
if (method === "Runtime.evaluate") return {} as never;
|
||||
if (method === "Runtime.releaseObjectGroup") {
|
||||
cleanup();
|
||||
await new Promise<void>((resolve) => {
|
||||
release = resolve;
|
||||
});
|
||||
return {} as never;
|
||||
}
|
||||
return original(tabId, method, params);
|
||||
};
|
||||
const context = new GeometryContext(cdp, 4, undefined, controller.signal);
|
||||
context.registerSnapshotOwners(target, new Set([10, 11]));
|
||||
let settled = false;
|
||||
const operation = context
|
||||
.snapshotProjection({ target, frameId: "child" }, 10, [], { width: 1000, height: 1000 })
|
||||
.finally(() => {
|
||||
settled = true;
|
||||
});
|
||||
const rejected = expect(operation).rejects.toMatchObject({ name: "AbortError" });
|
||||
await started;
|
||||
controller.abort();
|
||||
expect(settled).toBe(false);
|
||||
release();
|
||||
await rejected;
|
||||
expect(cdp.calls.mock.calls.some(([, method]) => method === "DOM.resolveNode")).toBe(false);
|
||||
});
|
||||
|
||||
it("rejects owner mismatches and invalid numeric bounds", () => {
|
||||
const input = snapshotViewportRect(
|
||||
[30, 50, 120, 40],
|
||||
{ target, frameId: "main" },
|
||||
{ layoutUnitsPerCssPixel: 1, scrollCss: { x: 10, y: 20 } },
|
||||
)!;
|
||||
const projection = {
|
||||
source: { target, frameId: "main" },
|
||||
geometry: { sourceClips: [], edges: [], topViewport: { width: 800, height: 600 } },
|
||||
};
|
||||
expect(projectSnapshotRect(input, projection)).toEqual({
|
||||
x: 20,
|
||||
y: 30,
|
||||
width: 120,
|
||||
height: 40,
|
||||
});
|
||||
expect(
|
||||
projectSnapshotRect(input, { ...projection, source: { target, frameId: "other" } }),
|
||||
).toBeNull();
|
||||
expect(
|
||||
projectSnapshotRect(input, {
|
||||
...projection,
|
||||
source: { target: { tabId: 5 }, frameId: "main" },
|
||||
}),
|
||||
).toBeNull();
|
||||
expect(
|
||||
snapshotViewportRect(
|
||||
[0, 0, NaN, 40],
|
||||
{ target },
|
||||
{ layoutUnitsPerCssPixel: 1, scrollCss: { x: 0, y: 0 } },
|
||||
),
|
||||
).toBeNull();
|
||||
expect(
|
||||
snapshotViewportRect(
|
||||
[0, 0, 10, 40],
|
||||
{ target },
|
||||
{ layoutUnitsPerCssPixel: 1, scrollCss: { x: Infinity, y: 0 } },
|
||||
),
|
||||
).toBeNull();
|
||||
});
|
||||
|
||||
it("does not turn a border quad or a failed owner read into a content projection", async () => {
|
||||
const cdp: CdpRunner = {
|
||||
send: vi.fn(async () => ({
|
||||
model: { border: [0, 0, 100, 0, 100, 100, 0, 100] },
|
||||
})) as CdpRunner["send"],
|
||||
};
|
||||
expect(
|
||||
await new GeometryContext(cdp, 4).snapshotProjection({ target, frameId: "child" }, 10, [], {
|
||||
width: 100,
|
||||
height: 100,
|
||||
}),
|
||||
).toEqual({
|
||||
status: "unavailable",
|
||||
source: { target, frameId: "child" },
|
||||
ownerBackendNodeId: 10,
|
||||
});
|
||||
});
|
||||
|
||||
it("keeps ancestor clips in target coordinates instead of applying nested offsets twice", async () => {
|
||||
const cdp = driver();
|
||||
const projection = await new GeometryContext(cdp, 4).snapshotProjection(
|
||||
{ target, frameId: "nested" },
|
||||
10,
|
||||
[rectPolygon({ x: 60, y: 620, w: 100, h: 100 })],
|
||||
{ width: 1000, height: 1000 },
|
||||
);
|
||||
if (projection.status !== "available") throw new Error("expected available projection");
|
||||
const input = snapshotViewportRect(
|
||||
[0, 0, 300, 200],
|
||||
{ target, frameId: "nested" },
|
||||
{ layoutUnitsPerCssPixel: 1, scrollCss: { x: 0, y: 0 } },
|
||||
);
|
||||
expect(projectSnapshotRect(input!, projection.projection)).toEqual({
|
||||
x: 60,
|
||||
y: 620,
|
||||
width: 100,
|
||||
height: 100,
|
||||
});
|
||||
});
|
||||
|
||||
it("rejects malformed frame ancestry without looping", async () => {
|
||||
const cdp = driver();
|
||||
const cycle: CdpFrameGraph = {
|
||||
rootFrameId: "a",
|
||||
frames: [
|
||||
{ frameId: "a", parentFrameId: "b", target },
|
||||
{ frameId: "b", parentFrameId: "a", target },
|
||||
],
|
||||
};
|
||||
expect(await new GeometryContext(cdp, 4, cycle).targetProjection("a")).toBeNull();
|
||||
expect(cdp.calls).not.toHaveBeenCalled();
|
||||
const orphan: CdpFrameGraph = {
|
||||
rootFrameId: "a",
|
||||
frames: [{ frameId: "a", parentFrameId: "missing", target }],
|
||||
};
|
||||
expect(await new GeometryContext(cdp, 4, orphan).targetProjection("a")).toBeNull();
|
||||
});
|
||||
|
||||
it("rejects a live node whose frame belongs to another target before any DOM input", async () => {
|
||||
const cdp = driver();
|
||||
expect(
|
||||
await resolveNodeGeometry(
|
||||
cdp,
|
||||
4,
|
||||
{ target: { tabId: 4, sessionId: "wrong" }, frameId: "child", backendNodeId: 20 },
|
||||
{ scrollIntoView: true },
|
||||
),
|
||||
).toMatchObject({ code: "cdp_failed" });
|
||||
expect(cdp.calls).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("bounds concurrent measurements and does not dispatch queued reads after cancellation", async () => {
|
||||
let active = 0;
|
||||
let peak = 0;
|
||||
const release: Array<() => void> = [];
|
||||
const send = vi.fn(async () => {
|
||||
active++;
|
||||
peak = Math.max(peak, active);
|
||||
await new Promise<void>((resolve) => release.push(resolve));
|
||||
active--;
|
||||
return {
|
||||
visualViewport: { clientWidth: 1000 },
|
||||
cssVisualViewport: { clientWidth: 1000 },
|
||||
cssLayoutViewport: { clientWidth: 100, clientHeight: 100 },
|
||||
};
|
||||
});
|
||||
const controller = new AbortController();
|
||||
const context = new GeometryContext(
|
||||
{ send: send as CdpRunner["send"] },
|
||||
4,
|
||||
undefined,
|
||||
controller.signal,
|
||||
);
|
||||
const tasks = Array.from({ length: 8 }, (_, index) =>
|
||||
context.viewport({ tabId: 4, sessionId: String(index) }),
|
||||
);
|
||||
const settled = Promise.allSettled(tasks);
|
||||
expect(send).toHaveBeenCalledTimes(4);
|
||||
controller.abort();
|
||||
for (const done of release) done();
|
||||
const results = await settled;
|
||||
expect(peak).toBe(4);
|
||||
expect(send).toHaveBeenCalledTimes(4);
|
||||
expect(results.filter((item) => item.status === "rejected")).toHaveLength(4);
|
||||
});
|
||||
|
||||
it("releases an owner object even when cancellation arrives before its viewport read", async () => {
|
||||
const controller = new AbortController();
|
||||
const cdp = driver();
|
||||
const original = cdp.calls.getMockImplementation()!;
|
||||
cdp.calls.mockImplementation(async (tab, method) => {
|
||||
const result = await original(tab, method);
|
||||
if (method === "DOM.resolveNode") controller.abort();
|
||||
return result;
|
||||
});
|
||||
const context = new GeometryContext(cdp, 4, undefined, controller.signal);
|
||||
await expect(
|
||||
context.snapshotProjection({ target, frameId: "child" }, 10, [], {
|
||||
width: 1000,
|
||||
height: 1000,
|
||||
}),
|
||||
).rejects.toMatchObject({ name: "AbortError" });
|
||||
expect(cdp.calls.mock.calls.map(([, method]) => method)).toEqual([
|
||||
"DOM.getBoxModel",
|
||||
"DOM.resolveNode",
|
||||
"Runtime.releaseObject",
|
||||
]);
|
||||
});
|
||||
|
||||
it("reads live owner geometry only after scrolling", async () => {
|
||||
const cdp = driver();
|
||||
const original = cdp.calls.getMockImplementation()!;
|
||||
let scrolled = false;
|
||||
cdp.calls.mockImplementation(async (tab, method) => {
|
||||
if (method === "DOM.scrollIntoViewIfNeeded") {
|
||||
scrolled = true;
|
||||
return {};
|
||||
}
|
||||
if (method === "DOM.getContentQuads") {
|
||||
expect(scrolled).toBe(true);
|
||||
return { quads: [[60, 620, 100, 620, 100, 640, 60, 640]] };
|
||||
}
|
||||
if (method === "DOM.getBoxModel") expect(scrolled).toBe(true);
|
||||
return original(tab, method);
|
||||
});
|
||||
expect(
|
||||
await resolveNodeGeometry(
|
||||
cdp,
|
||||
4,
|
||||
{ target, frameId: "child", backendNodeId: 20 },
|
||||
{ scrollIntoView: true },
|
||||
),
|
||||
).toMatchObject({ topBounds: { x: 60, y: 620, width: 40, height: 20 } });
|
||||
expect(cdp.getFrameGraph).toHaveBeenCalledTimes(1);
|
||||
expect(cdp.calls.mock.calls.filter(([, method]) => method === "DOM.getBoxModel")).toHaveLength(
|
||||
1,
|
||||
);
|
||||
});
|
||||
|
||||
it("adapts viewport CSS bounds to page DIP with scroll and browser zoom, never raster DPR", () => {
|
||||
const viewport = { width: 1600, height: 1000, scrollX: 10, scrollY: 100, cssToDip: 0.9 };
|
||||
const clip = screenshotPageRect({ x: 20, y: 30, width: 120, height: 40 }, viewport);
|
||||
expect(clip).toEqual({ space: "page-dip", rect: { x: 27, y: 117, width: 108, height: 36 } });
|
||||
expect(
|
||||
screenshotPageRect({ x: 20, y: 30, width: 120, height: 40 }, { ...viewport, cssToDip: NaN }),
|
||||
).toBeNull();
|
||||
expect(
|
||||
screenshotPageRect({ x: 20, y: 30, width: 120, height: 40 }, { ...viewport, cssToDip: 0 }),
|
||||
).toBeNull();
|
||||
});
|
||||
|
||||
it("retries a rejected measurement only in a new operation", async () => {
|
||||
const cdp = driver();
|
||||
cdp.calls.mockRejectedValueOnce(new Error("unavailable"));
|
||||
const context = new GeometryContext(cdp, 4);
|
||||
await expect(context.viewport(target)).rejects.toThrow("unavailable");
|
||||
await expect(context.viewport(target)).rejects.toThrow("unavailable");
|
||||
expect(cdp.calls).toHaveBeenCalledTimes(1);
|
||||
expect(await new GeometryContext(cdp, 4).viewport(target)).toEqual({
|
||||
width: 1000,
|
||||
height: 1000,
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -405,7 +405,6 @@ describe("handleRequestHelp", () => {
|
||||
agentWindowId: 99,
|
||||
refStore: {
|
||||
resolveEntry: () => ({
|
||||
kind: "dom",
|
||||
backendNodeId: 42,
|
||||
tabId: 5,
|
||||
frameId: "child",
|
||||
@@ -434,7 +433,6 @@ describe("handleRequestHelp", () => {
|
||||
if (method === "DOM.getContentQuads") {
|
||||
return { quads: [[10, 20, 110, 20, 110, 60, 10, 60]] };
|
||||
}
|
||||
if (method === "Runtime.evaluate") return { result: { value: { width: 200, height: 100 } } };
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return { cssLayoutViewport: { clientWidth: 200, clientHeight: 100 } };
|
||||
}
|
||||
|
||||
@@ -2,10 +2,8 @@ import { describe, expect, it, vi } from "vitest";
|
||||
import { SessionManager } from "@/session-manager/manager";
|
||||
import type { CdpRunner } from "@/tools/shared";
|
||||
import {
|
||||
handleBlur,
|
||||
handleClick,
|
||||
handleFill,
|
||||
handleFocus,
|
||||
handleHover,
|
||||
handlePress,
|
||||
handleSelect,
|
||||
@@ -23,7 +21,7 @@ function fakeAgentWindow(ids: number[]) {
|
||||
return id;
|
||||
}),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
};
|
||||
}
|
||||
|
||||
@@ -125,6 +123,29 @@ describe("handleClick", () => {
|
||||
expect(fake.cdp.send).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("rejects screenshot-only visual surface refs before issuing CDP calls", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.refStore.set("e3", 1234, {
|
||||
tabId: 4,
|
||||
kind: "surface",
|
||||
capabilities: ["screenshot"],
|
||||
});
|
||||
const fake = makeFakeCdp({});
|
||||
|
||||
const res = await handleClick(
|
||||
sm,
|
||||
{ session_id: "aa11", ref: "@e3" },
|
||||
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
|
||||
);
|
||||
|
||||
expect(res).toMatchObject({
|
||||
code: "permission_denied",
|
||||
data: { reason: "ref_capability_denied", required_capability: "interact" },
|
||||
});
|
||||
expect(fake.cdp.send).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("clicks by ref, computes the quad centre, dispatches three mouse events", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
const ctx = await sm.start("aa11");
|
||||
@@ -203,7 +224,6 @@ describe("handleClick", () => {
|
||||
if (method === "DOM.getContentQuads") {
|
||||
return { quads: [[10, 20, 110, 20, 110, 60, 10, 60]] };
|
||||
}
|
||||
if (method === "Runtime.evaluate") return { result: { value: { width: 200, height: 100 } } };
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return { cssLayoutViewport: { clientWidth: 200, clientHeight: 100 } };
|
||||
}
|
||||
@@ -223,7 +243,6 @@ describe("handleClick", () => {
|
||||
{ sessionId: "child-session", method: "DOM.scrollIntoViewIfNeeded" },
|
||||
{ sessionId: "child-session", method: "DOM.getContentQuads" },
|
||||
{ sessionId: "child-session", method: "Page.getLayoutMetrics" },
|
||||
{ sessionId: "child-session", method: "Runtime.evaluate" },
|
||||
]);
|
||||
expect(fake.sent.filter((call) => call.method === "Input.dispatchMouseEvent")).toHaveLength(3);
|
||||
});
|
||||
@@ -544,176 +563,6 @@ describe("handleHover", () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe("handleFocus and handleBlur", () => {
|
||||
it("focuses a ref and verifies the deep active element", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.refStore.set("e3", 1234, { tabId: 4 });
|
||||
const fake = makeFakeCdp({
|
||||
"DOM.scrollIntoViewIfNeeded": () => ({}),
|
||||
"DOM.focus": () => ({}),
|
||||
"DOM.resolveNode": () => ({ object: { objectId: "focus-target" } }),
|
||||
"Runtime.callFunctionOn": () => ({ result: { value: true } }),
|
||||
});
|
||||
|
||||
const res = await handleFocus(
|
||||
sm,
|
||||
{ session_id: "aa11", ref: "@e3" },
|
||||
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
|
||||
);
|
||||
|
||||
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
|
||||
expect(res).toMatchObject({ tab_id: 4, used_ref: "e3", focused: true });
|
||||
expect(fake.sent.map((call) => call.method)).toEqual([
|
||||
"DOM.scrollIntoViewIfNeeded",
|
||||
"DOM.resolveNode",
|
||||
"DOM.focus",
|
||||
"Runtime.callFunctionOn",
|
||||
"Runtime.releaseObject",
|
||||
]);
|
||||
});
|
||||
|
||||
it("focuses an OOPIF ref in its CDP session", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.refStore.set("e3", 1234, {
|
||||
tabId: 4,
|
||||
frameId: "child-frame",
|
||||
cdpSessionId: "child-session",
|
||||
});
|
||||
const fake = makeFakeCdp({
|
||||
"DOM.scrollIntoViewIfNeeded": () => ({}),
|
||||
});
|
||||
fake.cdp.getFrameGraph = vi.fn(async () => ({
|
||||
rootFrameId: "main",
|
||||
frames: [
|
||||
{ frameId: "main", target: { tabId: 4 } },
|
||||
{
|
||||
frameId: "child-frame",
|
||||
parentFrameId: "main",
|
||||
ownerBackendNodeId: 99,
|
||||
target: { tabId: 4, sessionId: "child-session" },
|
||||
},
|
||||
],
|
||||
}));
|
||||
const targetCalls: Array<{ sessionId?: string; method: string }> = [];
|
||||
fake.cdp.sendToTarget = vi.fn(async (target, method) => {
|
||||
targetCalls.push({ sessionId: target.sessionId, method });
|
||||
if (method === "DOM.scrollIntoViewIfNeeded") return {};
|
||||
if (method === "DOM.focus" || method === "Runtime.releaseObject") return {};
|
||||
if (method === "DOM.resolveNode") return { object: { objectId: "focus-target" } };
|
||||
if (method === "Runtime.callFunctionOn") return { result: { value: true } };
|
||||
throw new Error(`unexpected child CDP call ${method}`);
|
||||
}) as CdpRunner["sendToTarget"];
|
||||
|
||||
const res = await handleFocus(
|
||||
sm,
|
||||
{ session_id: "aa11", ref: "@e3" },
|
||||
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
|
||||
);
|
||||
|
||||
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
|
||||
expect(res.focused).toBe(true);
|
||||
expect(targetCalls).toEqual([
|
||||
{ sessionId: "child-session", method: "DOM.scrollIntoViewIfNeeded" },
|
||||
{ sessionId: "child-session", method: "DOM.resolveNode" },
|
||||
{ sessionId: "child-session", method: "DOM.focus" },
|
||||
{ sessionId: "child-session", method: "Runtime.callFunctionOn" },
|
||||
{ sessionId: "child-session", method: "Runtime.releaseObject" },
|
||||
]);
|
||||
});
|
||||
|
||||
it("does not focus after cancellation during scrolling", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.refStore.set("e3", 1234, { tabId: 4 });
|
||||
const abort = new AbortController();
|
||||
const fake = makeFakeCdp({
|
||||
"DOM.scrollIntoViewIfNeeded": () => {
|
||||
abort.abort();
|
||||
return {};
|
||||
},
|
||||
});
|
||||
|
||||
const res = await handleFocus(
|
||||
sm,
|
||||
{ session_id: "aa11", ref: "@e3" },
|
||||
{ cdp: fake.cdp, tabsApi: fake.tabsApi, signal: abort.signal },
|
||||
);
|
||||
|
||||
expect(res).toMatchObject({ code: "cancelled" });
|
||||
expect(fake.sent.some((call) => call.method === "DOM.focus")).toBe(false);
|
||||
});
|
||||
|
||||
it("blurs a ref and returns its previous focus state", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.refStore.set("e3", 1234, { tabId: 4 });
|
||||
const fake = makeFakeCdp({
|
||||
"DOM.resolveNode": () => ({ object: { objectId: "focus-target" } }),
|
||||
"Runtime.callFunctionOn": vi
|
||||
.fn()
|
||||
.mockResolvedValueOnce({ result: { value: { ok: true, was_focused: true } } })
|
||||
.mockResolvedValueOnce({ result: { value: false } }),
|
||||
});
|
||||
|
||||
const res = await handleBlur(
|
||||
sm,
|
||||
{ session_id: "aa11", ref: "@e3" },
|
||||
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
|
||||
);
|
||||
|
||||
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
|
||||
expect(res).toMatchObject({
|
||||
tab_id: 4,
|
||||
used_ref: "e3",
|
||||
was_focused: true,
|
||||
focused: false,
|
||||
});
|
||||
expect(fake.sent.map((call) => call.method)).toEqual([
|
||||
"DOM.resolveNode",
|
||||
"Runtime.callFunctionOn",
|
||||
"Runtime.callFunctionOn",
|
||||
"Runtime.releaseObject",
|
||||
]);
|
||||
});
|
||||
|
||||
it("rejects a target that does not implement blur", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.refStore.set("e3", 1234, { tabId: 4 });
|
||||
const fake = makeFakeCdp({
|
||||
"DOM.resolveNode": () => ({ object: { objectId: "focus-target" } }),
|
||||
"Runtime.callFunctionOn": () => ({
|
||||
result: { value: { ok: false, was_focused: false, focused: false } },
|
||||
}),
|
||||
});
|
||||
|
||||
const res = await handleBlur(
|
||||
sm,
|
||||
{ session_id: "aa11", ref: "@e3" },
|
||||
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
|
||||
);
|
||||
|
||||
expect(res).toMatchObject({ code: "invalid_params", message: /does not support blur/ });
|
||||
});
|
||||
});
|
||||
|
||||
function successfulFillScript(params: unknown) {
|
||||
const script = params as { arguments?: Array<{ value: unknown }>; functionDeclaration: string };
|
||||
const args = script.arguments ?? [];
|
||||
return {
|
||||
result: {
|
||||
value:
|
||||
args.length === 2
|
||||
? { before: "", expected: args[0].value }
|
||||
: script.functionDeclaration.startsWith("function(expected)")
|
||||
? { connected: true, matches: true, valueLength: String(args[0].value).length }
|
||||
: "ready",
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
describe("handleFill", () => {
|
||||
it("returns not_found for unknown ref", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
@@ -760,8 +609,7 @@ describe("handleFill", () => {
|
||||
"DOM.scrollIntoViewIfNeeded": () => ({}),
|
||||
"DOM.focus": () => ({}),
|
||||
"DOM.resolveNode": () => ({ object: { objectId: "obj-1" } }),
|
||||
"Runtime.callFunctionOn": successfulFillScript,
|
||||
"Runtime.releaseObject": () => ({}),
|
||||
"Runtime.callFunctionOn": () => ({ result: { type: "undefined" } }),
|
||||
"Input.insertText": () => ({}),
|
||||
});
|
||||
const res = await handleFill(
|
||||
@@ -775,12 +623,13 @@ describe("handleFill", () => {
|
||||
expect(res.used_ref).toBe("e1");
|
||||
const insert = fake.sent.find((c) => c.method === "Input.insertText");
|
||||
expect(insert?.params).toEqual({ text: "hello" });
|
||||
// Foreground replacement needs no extra caret-positioning round trip.
|
||||
// clear_before defaults to true → callFunctionOn invoked once to
|
||||
// clear, once to fire input/change after typing.
|
||||
const callFns = fake.sent.filter((c) => c.method === "Runtime.callFunctionOn");
|
||||
expect(callFns).toHaveLength(4);
|
||||
expect(callFns.length).toBeGreaterThanOrEqual(2);
|
||||
});
|
||||
|
||||
it("passes clear_before=false to preparation and verifies the result", async () => {
|
||||
it("clear_before=false skips the wipe call", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.refStore.set("e1", 1, { tabId: 4 });
|
||||
@@ -792,12 +641,12 @@ describe("handleFill", () => {
|
||||
"DOM.focus": () => ({}),
|
||||
"DOM.resolveNode": () => ({ object: { objectId: "obj-2" } }),
|
||||
"Runtime.callFunctionOn": (p) => {
|
||||
const args = (p as { arguments?: Array<{ value: unknown }> }).arguments ?? [];
|
||||
if (args.length === 2) expect(args[1].value).toBe(false);
|
||||
return successfulFillScript(p);
|
||||
const fn = (p as { functionDeclaration?: string }).functionDeclaration ?? "";
|
||||
// No "this.value = ''" clearing on a no-clear path; only the
|
||||
// post-input dispatchEvent.
|
||||
expect(fn).not.toMatch(/this\.value\s*=\s*''/);
|
||||
return { result: { type: "undefined" } };
|
||||
},
|
||||
"Input.dispatchKeyEvent": () => ({}),
|
||||
"Runtime.releaseObject": () => ({}),
|
||||
"Input.insertText": () => ({}),
|
||||
});
|
||||
const res = await handleFill(
|
||||
@@ -824,8 +673,7 @@ describe("handleFill", () => {
|
||||
"DOM.scrollIntoViewIfNeeded": () => ({}),
|
||||
"DOM.focus": () => ({}),
|
||||
"DOM.resolveNode": () => ({ object: { objectId: "obj-3" } }),
|
||||
"Runtime.callFunctionOn": successfulFillScript,
|
||||
"Runtime.releaseObject": () => ({}),
|
||||
"Runtime.callFunctionOn": () => ({ result: { type: "undefined" } }),
|
||||
"Input.insertText": () => ({}),
|
||||
});
|
||||
const res = await handleFill(
|
||||
|
||||
@@ -1,266 +0,0 @@
|
||||
import { describe, expect, it, vi } from "vitest";
|
||||
import { SessionManager } from "@/session-manager/manager";
|
||||
import type { BrowserNavigationApi } from "../browser-navigation";
|
||||
import { handleNavigate, handleReload } from "../navigation";
|
||||
import type { CdpRunner } from "../shared";
|
||||
|
||||
const denied = "Cannot access a chrome-extension:// URL of different extension";
|
||||
const url = "https://example.test/recovered";
|
||||
|
||||
function event<T extends (...args: never[]) => void>() {
|
||||
const listeners = new Set<T>();
|
||||
return {
|
||||
listeners,
|
||||
addListener: (listener: T) => listeners.add(listener),
|
||||
removeListener: (listener: T) => listeners.delete(listener),
|
||||
fire: (...args: Parameters<T>) => {
|
||||
for (const listener of [...listeners]) listener(...args);
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
async function fixture() {
|
||||
const manager = new SessionManager({
|
||||
agentWindow: {
|
||||
create: vi.fn(async () => 100),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 4),
|
||||
},
|
||||
});
|
||||
await manager.start("test");
|
||||
type Listener = Parameters<BrowserNavigationApi["onCommitted"]["addListener"]>[0];
|
||||
const events = {
|
||||
onCommitted: event<Listener>(),
|
||||
onDOMContentLoaded: event<Listener>(),
|
||||
onCompleted: event<Listener>(),
|
||||
onErrorOccurred: event<Listener>(),
|
||||
};
|
||||
const cdpEvents = event<Parameters<NonNullable<CdpRunner["onEvent"]>>[0]>();
|
||||
const state = { blocked: true, destinationBlocked: false, emitIdle: true };
|
||||
const send = vi.fn(async (_tabId: number, method: string) => {
|
||||
if (state.blocked) throw new Error(denied);
|
||||
if (method === "Page.getFrameTree") {
|
||||
return { frameTree: { frame: { id: "main", loaderId: "new-loader" } } };
|
||||
}
|
||||
if (method === "Runtime.evaluate") return { result: { value: "complete" } };
|
||||
if (method === "Page.setLifecycleEventsEnabled" && state.emitIdle) {
|
||||
cdpEvents.fire({ tabId: 4 }, "Page.lifecycleEvent", {
|
||||
frameId: "main",
|
||||
loaderId: "new-loader",
|
||||
name: "networkIdle",
|
||||
});
|
||||
}
|
||||
if (method === "Page.navigate") return { frameId: "main", loaderId: "new-loader" };
|
||||
return {};
|
||||
});
|
||||
const cdp: CdpRunner = {
|
||||
send: send as CdpRunner["send"],
|
||||
onEvent: (listener) => {
|
||||
cdpEvents.addListener(listener);
|
||||
return { dispose: () => cdpEvents.removeListener(listener) };
|
||||
},
|
||||
};
|
||||
const main = { tabId: 4, frameId: 0, documentId: "new-document" };
|
||||
const navigate = async () => {
|
||||
state.blocked = state.destinationBlocked;
|
||||
events.onCommitted.fire(main);
|
||||
events.onDOMContentLoaded.fire(main);
|
||||
events.onCompleted.fire(main);
|
||||
};
|
||||
const browserNavigation = { ...events, update: vi.fn(navigate), reload: vi.fn(navigate) };
|
||||
const tab = { id: 4, windowId: 100, active: true, url } as chrome.tabs.Tab;
|
||||
const tabsApi = { get: vi.fn(async () => tab), query: vi.fn(async () => [tab]) };
|
||||
const deps = { cdp, tabsApi, browserNavigation, defaultTimeoutMs: 1000 };
|
||||
const expectCleanedUp = () => {
|
||||
for (const entry of Object.values(events)) expect(entry.listeners.size).toBe(0);
|
||||
expect(cdpEvents.listeners.size).toBe(0);
|
||||
};
|
||||
return { manager, deps, state, send, events, main, cdpEvents, expectCleanedUp };
|
||||
}
|
||||
|
||||
describe("navigation after Chrome denies extension-frame access", () => {
|
||||
it.each([
|
||||
"load",
|
||||
"commit",
|
||||
"domcontentloaded",
|
||||
"networkidle",
|
||||
] as const)("recovers the same tab with the requested %s checkpoint", async (waitUntil) => {
|
||||
const f = await fixture();
|
||||
const result = await handleNavigate(
|
||||
f.manager,
|
||||
{
|
||||
session_id: "test",
|
||||
url,
|
||||
wait_until: waitUntil,
|
||||
},
|
||||
f.deps,
|
||||
);
|
||||
|
||||
expect(result).toMatchObject({ tab_id: 4, final_url: url, reached: waitUntil });
|
||||
expect(f.deps.browserNavigation.update).toHaveBeenCalledExactlyOnceWith(4, { url });
|
||||
expect(f.send.mock.calls.some(([, method]) => method === "Page.navigate")).toBe(false);
|
||||
expect(f.send).toHaveBeenCalledWith(4, "Page.enable", {});
|
||||
f.expectCleanedUp();
|
||||
});
|
||||
|
||||
it("recovers reload through tabs.reload and preserves hard reload", async () => {
|
||||
const f = await fixture();
|
||||
const result = await handleReload(f.manager, { session_id: "test", hard: true }, f.deps);
|
||||
expect(result).toMatchObject({ tab_id: 4, reached: "load" });
|
||||
expect(f.deps.browserNavigation.reload).toHaveBeenCalledExactlyOnceWith(4, {
|
||||
bypassCache: true,
|
||||
});
|
||||
expect(f.deps.browserNavigation.update).not.toHaveBeenCalled();
|
||||
f.expectCleanedUp();
|
||||
});
|
||||
|
||||
it("reports the restriction when reload leaves the conflicting frame present", async () => {
|
||||
const f = await fixture();
|
||||
f.state.destinationBlocked = true;
|
||||
const result = await handleReload(f.manager, { session_id: "test" }, f.deps);
|
||||
expect(result).toMatchObject({
|
||||
code: "cdp_failed",
|
||||
data: { reason: "cdp_extension_access_denied" },
|
||||
});
|
||||
expect(f.deps.browserNavigation.reload).toHaveBeenCalledOnce();
|
||||
f.expectCleanedUp();
|
||||
});
|
||||
|
||||
it("does not fall back for unrelated debugger failures", async () => {
|
||||
const f = await fixture();
|
||||
f.send.mockRejectedValue(new Error("Another debugger is already attached"));
|
||||
const result = await handleNavigate(f.manager, { session_id: "test", url }, f.deps);
|
||||
expect(result).toMatchObject({
|
||||
code: "cdp_failed",
|
||||
message: "Another debugger is already attached",
|
||||
});
|
||||
expect(f.deps.browserNavigation.update).not.toHaveBeenCalled();
|
||||
f.expectCleanedUp();
|
||||
});
|
||||
|
||||
it("does not replay navigation when a dispatched CDP command fails", async () => {
|
||||
const f = await fixture();
|
||||
f.state.blocked = false;
|
||||
const send = f.send.getMockImplementation()!;
|
||||
f.send.mockImplementation(async (tabId, method) => {
|
||||
if (method === "Page.navigate") throw new Error(denied);
|
||||
return send(tabId, method);
|
||||
});
|
||||
const result = await handleNavigate(f.manager, { session_id: "test", url }, f.deps);
|
||||
expect(result).toMatchObject({
|
||||
code: "cdp_failed",
|
||||
data: { reason: "cdp_extension_access_denied" },
|
||||
});
|
||||
expect(f.deps.browserNavigation.update).not.toHaveBeenCalled();
|
||||
f.expectCleanedUp();
|
||||
});
|
||||
|
||||
it("keeps the Agent Window guard in front of the recovery", async () => {
|
||||
const f = await fixture();
|
||||
f.deps.tabsApi.get.mockResolvedValue({
|
||||
id: 4,
|
||||
windowId: 200,
|
||||
active: true,
|
||||
url,
|
||||
} as chrome.tabs.Tab);
|
||||
const result = await handleNavigate(f.manager, { session_id: "test", tab_id: 4, url }, f.deps);
|
||||
expect(result).toMatchObject({ code: "permission_denied" });
|
||||
expect(f.send).not.toHaveBeenCalled();
|
||||
expect(f.deps.browserNavigation.update).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("ignores old-document, subframe, and other-tab completion events", async () => {
|
||||
const f = await fixture();
|
||||
f.deps.browserNavigation.update.mockImplementation(async () => {});
|
||||
let settled = false;
|
||||
const work = handleNavigate(f.manager, { session_id: "test", url }, f.deps).then((result) => {
|
||||
settled = true;
|
||||
return result;
|
||||
});
|
||||
await vi.waitFor(() => expect(f.deps.browserNavigation.update).toHaveBeenCalledOnce());
|
||||
f.events.onCompleted.fire(f.main);
|
||||
f.events.onCommitted.fire({ ...f.main, tabId: 9 });
|
||||
f.events.onCommitted.fire({ ...f.main, frameId: 1 });
|
||||
f.events.onCompleted.fire(f.main);
|
||||
await Promise.resolve();
|
||||
expect(settled).toBe(false);
|
||||
f.events.onCommitted.fire(f.main);
|
||||
f.events.onCompleted.fire({ ...f.main, documentId: "old-document" });
|
||||
await Promise.resolve();
|
||||
expect(settled).toBe(false);
|
||||
f.state.blocked = false;
|
||||
f.events.onCompleted.fire(f.main);
|
||||
expect(await work).toMatchObject({ reached: "load" });
|
||||
f.expectCleanedUp();
|
||||
});
|
||||
|
||||
it("does not infer network idle from a browser load event", async () => {
|
||||
const f = await fixture();
|
||||
f.state.emitIdle = false;
|
||||
const result = await handleNavigate(
|
||||
f.manager,
|
||||
{
|
||||
session_id: "test",
|
||||
url,
|
||||
wait_until: "networkidle",
|
||||
timeout_ms: 10,
|
||||
},
|
||||
f.deps,
|
||||
);
|
||||
expect(result).toMatchObject({ reached: "timeout" });
|
||||
f.expectCleanedUp();
|
||||
});
|
||||
|
||||
it("cleans up browser listeners on timeout", async () => {
|
||||
const f = await fixture();
|
||||
f.deps.browserNavigation.update.mockImplementation(async () => {});
|
||||
const result = await handleNavigate(
|
||||
f.manager,
|
||||
{ session_id: "test", url, timeout_ms: 10 },
|
||||
f.deps,
|
||||
);
|
||||
expect(result).toMatchObject({ reached: "timeout" });
|
||||
f.expectCleanedUp();
|
||||
});
|
||||
|
||||
it("does not navigate an already-cancelled request", async () => {
|
||||
const f = await fixture();
|
||||
const result = await handleNavigate(
|
||||
f.manager,
|
||||
{ session_id: "test", url },
|
||||
{
|
||||
...f.deps,
|
||||
signal: AbortSignal.abort(),
|
||||
},
|
||||
);
|
||||
expect(result).toMatchObject({ code: "cancelled" });
|
||||
expect(f.deps.browserNavigation.update).not.toHaveBeenCalled();
|
||||
f.expectCleanedUp();
|
||||
});
|
||||
|
||||
it("cleans up browser listeners when cancelled after dispatch", async () => {
|
||||
const f = await fixture();
|
||||
const ac = new AbortController();
|
||||
f.deps.browserNavigation.update.mockImplementation(async () => {
|
||||
ac.abort();
|
||||
});
|
||||
const result = await handleNavigate(
|
||||
f.manager,
|
||||
{ session_id: "test", url },
|
||||
{ ...f.deps, signal: ac.signal },
|
||||
);
|
||||
expect(result).toMatchObject({ code: "cancelled" });
|
||||
expect(f.deps.browserNavigation.update).toHaveBeenCalledOnce();
|
||||
f.expectCleanedUp();
|
||||
});
|
||||
|
||||
it("reports browser navigation errors and releases listeners", async () => {
|
||||
const f = await fixture();
|
||||
f.deps.browserNavigation.update.mockImplementation(async () => {
|
||||
f.events.onErrorOccurred.fire({ ...f.main, error: "net::ERR_NAME_NOT_RESOLVED" });
|
||||
});
|
||||
const result = await handleNavigate(f.manager, { session_id: "test", url }, f.deps);
|
||||
expect(result).toMatchObject({ code: "cdp_failed", message: "net::ERR_NAME_NOT_RESOLVED" });
|
||||
f.expectCleanedUp();
|
||||
});
|
||||
});
|
||||
@@ -21,7 +21,7 @@ function fakeAgentWindow(ids: number[]) {
|
||||
return id;
|
||||
}),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
@@ -12,7 +12,7 @@ function fakeAgentWindow(ids: number[]) {
|
||||
return id;
|
||||
}),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,348 +0,0 @@
|
||||
// @vitest-environment node
|
||||
// Opt in with BSK_SCROLL_CHROME=/path/to/chrome. Uses an isolated browser/profile.
|
||||
import { describe, expect, it } from "vitest";
|
||||
import type { CdpFrame, CdpFrameGraph, CdpTarget } from "@/browser-driver/frame-graph";
|
||||
import { SessionManager } from "@/session-manager/manager";
|
||||
import type { ViewportRect } from "../geometry";
|
||||
import { handleScrollTo } from "../scroll";
|
||||
import type { CdpRunner } from "../shared";
|
||||
|
||||
type Send = <T = Record<string, unknown>>(
|
||||
method: string,
|
||||
params?: object,
|
||||
sessionId?: string,
|
||||
) => Promise<T>;
|
||||
type Tree = { frame: { id: string; parentId?: string; name?: string }; childFrames?: Tree[] };
|
||||
|
||||
async function withBrowser(
|
||||
run: (h: Awaited<ReturnType<typeof harness>>) => Promise<void>,
|
||||
zoom = 1,
|
||||
) {
|
||||
const { withChrome } = await import(
|
||||
new URL(
|
||||
"../../../../../evals/browser/cases/regression/snapshot-coordinates/chrome.mjs",
|
||||
import.meta.url,
|
||||
).href
|
||||
);
|
||||
await withChrome(
|
||||
{ executable: process.env.BSK_SCROLL_CHROME, deviceScale: 1, zoom },
|
||||
async (send: Send) => run(await harness(send)),
|
||||
);
|
||||
}
|
||||
|
||||
async function harness(send: Send) {
|
||||
const { targetId } = await send<{ targetId: string }>("Target.createTarget", {
|
||||
url: "about:blank",
|
||||
});
|
||||
const { sessionId: rootSession } = await send<{ sessionId: string }>("Target.attachToTarget", {
|
||||
targetId,
|
||||
flatten: true,
|
||||
});
|
||||
await send("Page.bringToFront", {}, rootSession);
|
||||
const manager = new SessionManager({
|
||||
agentWindow: {
|
||||
create: async () => 100,
|
||||
remove: async () => {},
|
||||
ensureActiveTab: async () => 4,
|
||||
},
|
||||
});
|
||||
const ctx = await manager.start("aa11");
|
||||
const calls: { method: string; sessionId?: string }[] = [];
|
||||
const after = { command: (_method: string) => {} };
|
||||
const sessionFor = (target: CdpTarget) => target.sessionId ?? rootSession;
|
||||
const forward = async <T>(target: CdpTarget, method: string, params?: object): Promise<T> => {
|
||||
calls.push({ method, sessionId: target.sessionId });
|
||||
const result = await send<T>(method, params, sessionFor(target));
|
||||
after.command(method);
|
||||
return result;
|
||||
};
|
||||
const cdp: CdpRunner = {
|
||||
send: (_tab, method, params) => forward({ tabId: 4 }, method, params),
|
||||
sendToTarget: forward,
|
||||
};
|
||||
const evaluate = async <T>(expression: string, frame?: CdpFrame): Promise<T> => {
|
||||
const session = frame ? sessionFor(frame.target) : rootSession;
|
||||
const world = frame
|
||||
? await send<{ executionContextId: number }>(
|
||||
"Page.createIsolatedWorld",
|
||||
{
|
||||
frameId: frame.frameId,
|
||||
worldName: "scroll-oracle",
|
||||
},
|
||||
session,
|
||||
)
|
||||
: undefined;
|
||||
const reply = await send<{ result: { value: T }; exceptionDetails?: unknown }>(
|
||||
"Runtime.evaluate",
|
||||
{
|
||||
expression,
|
||||
contextId: world?.executionContextId,
|
||||
returnByValue: true,
|
||||
awaitPromise: true,
|
||||
},
|
||||
session,
|
||||
);
|
||||
expect(reply.exceptionDetails).toBeUndefined();
|
||||
return reply.result.value;
|
||||
};
|
||||
const rememberRef = (frame: CdpFrame, backendNodeId: number) =>
|
||||
ctx.refStore.set("e1", backendNodeId, {
|
||||
tabId: 4,
|
||||
frameId: frame.frameId,
|
||||
cdpSessionId: frame.target.sessionId,
|
||||
});
|
||||
const ref = async (frame: CdpFrame, selector = "#probe") => {
|
||||
const { executionContextId } = await send<{ executionContextId: number }>(
|
||||
"Page.createIsolatedWorld",
|
||||
{
|
||||
frameId: frame.frameId,
|
||||
worldName: "scroll-oracle",
|
||||
},
|
||||
sessionFor(frame.target),
|
||||
);
|
||||
const { result } = await send<{ result: { objectId: string } }>(
|
||||
"Runtime.evaluate",
|
||||
{
|
||||
expression: `document.querySelector(${JSON.stringify(selector)})`,
|
||||
contextId: executionContextId,
|
||||
},
|
||||
sessionFor(frame.target),
|
||||
);
|
||||
const { node } = await send<{ node: { backendNodeId: number } }>(
|
||||
"DOM.describeNode",
|
||||
{ objectId: result.objectId },
|
||||
sessionFor(frame.target),
|
||||
);
|
||||
await send("Runtime.releaseObject", { objectId: result.objectId }, sessionFor(frame.target));
|
||||
rememberRef(frame, node.backendNodeId);
|
||||
};
|
||||
const scroll = (target: { selector: string } | { ref: string }, signal?: AbortSignal) =>
|
||||
handleScrollTo(
|
||||
manager,
|
||||
{ session_id: "aa11", ...target },
|
||||
{
|
||||
cdp,
|
||||
signal,
|
||||
tabsApi: {
|
||||
get: async (id) => ({ id, windowId: 100, active: true }) as chrome.tabs.Tab,
|
||||
query: async () => [{ id: 4, windowId: 100, active: true } as chrome.tabs.Tab],
|
||||
},
|
||||
},
|
||||
);
|
||||
const loadFrames = async () => {
|
||||
const { targetInfos } = await send<{ targetInfos: { targetId: string; type: string }[] }>(
|
||||
"Target.getTargets",
|
||||
);
|
||||
const sessions = [rootSession];
|
||||
for (const target of targetInfos.filter((t) => t.type === "iframe")) {
|
||||
const { sessionId } = await send<{ sessionId: string }>("Target.attachToTarget", {
|
||||
targetId: target.targetId,
|
||||
flatten: true,
|
||||
});
|
||||
sessions.push(sessionId);
|
||||
}
|
||||
const frames: (CdpFrame & { name: string })[] = [];
|
||||
for (const session of sessions) {
|
||||
const { frameTree } = await send<{ frameTree: Tree }>("Page.getFrameTree", {}, session);
|
||||
const target = { tabId: 4, ...(session !== rootSession ? { sessionId: session } : {}) };
|
||||
const visit = (tree: Tree, parentFrameId = tree.frame.parentId) => {
|
||||
frames.push({ frameId: tree.frame.id, parentFrameId, target, name: tree.frame.name ?? "" });
|
||||
for (const child of tree.childFrames ?? []) visit(child, tree.frame.id);
|
||||
};
|
||||
visit(frameTree);
|
||||
}
|
||||
for (const frame of frames) {
|
||||
if (!frame.parentFrameId) continue;
|
||||
const parent = frames.find((f) => f.frameId === frame.parentFrameId)!;
|
||||
const owner = await send<{ backendNodeId: number }>(
|
||||
"DOM.getFrameOwner",
|
||||
{ frameId: frame.frameId },
|
||||
sessionFor(parent.target),
|
||||
);
|
||||
frame.ownerBackendNodeId = owner.backendNodeId;
|
||||
}
|
||||
const graph: CdpFrameGraph = { rootFrameId: frames[0].frameId, frames };
|
||||
cdp.getFrameGraph = async () => graph;
|
||||
return frames;
|
||||
};
|
||||
return { send, rootSession, evaluate, ref, rememberRef, scroll, loadFrames, calls, after };
|
||||
}
|
||||
|
||||
function intersection(a: ViewportRect, b: ViewportRect): ViewportRect | null {
|
||||
const x = Math.max(a.x, b.x),
|
||||
y = Math.max(a.y, b.y);
|
||||
const right = Math.min(a.x + a.width, b.x + b.width),
|
||||
bottom = Math.min(a.y + a.height, b.y + b.height);
|
||||
return right > x && bottom > y ? { x, y, width: right - x, height: bottom - y } : null;
|
||||
}
|
||||
|
||||
function expectRect(actual: unknown, expected: ViewportRect) {
|
||||
expect(actual).not.toHaveProperty("code");
|
||||
for (const key of ["x", "y", "width", "height"] as const)
|
||||
expect(Math.abs((actual as ViewportRect)[key] - expected[key]), key).toBeLessThan(2);
|
||||
}
|
||||
|
||||
describe.skipIf(!process.env.BSK_SCROLL_CHROME)("real browser scroll-to", () => {
|
||||
it("scrolls ordinary elements and reports the clipped portion of nested scrollers", async () => {
|
||||
await withBrowser(async (h) => {
|
||||
for (const html of [
|
||||
'<div style="height:2200px"></div><div id="target" style="width:100px;height:40px"></div>',
|
||||
'<div style="height:200px"></div><div id="clip" style="height:80px;width:200px;overflow:auto"><div id="target" style="width:100px;height:400px"></div></div>',
|
||||
'<div style="height:200px"></div><div id="clip" style="height:80px;width:200px;overflow:auto;transform:scale(1.25);transform-origin:0 0"><div id="target" style="width:100px;height:400px"></div></div>',
|
||||
]) {
|
||||
await h.evaluate(`document.body.innerHTML = ${JSON.stringify(html)}`);
|
||||
const result = await h.scroll({ selector: "#target" });
|
||||
const oracle = await h.evaluate<{ rect: ViewportRect; clip?: ViewportRect }>(`({
|
||||
rect: document.querySelector('#target').getBoundingClientRect().toJSON(),
|
||||
clip: document.querySelector('#clip')?.getBoundingClientRect().toJSON()
|
||||
})`);
|
||||
expectRect(result, oracle.clip ? intersection(oracle.rect, oracle.clip)! : oracle.rect);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
it.each([
|
||||
"visibility:hidden",
|
||||
"opacity:0",
|
||||
"display:none",
|
||||
"content-visibility:hidden",
|
||||
])("rejects %s targets", async (style) => {
|
||||
await withBrowser(async (h) => {
|
||||
await h.evaluate(
|
||||
`document.body.innerHTML = '<div style="${style}"><button id="target">Target</button></div>'`,
|
||||
);
|
||||
expect(await h.scroll({ selector: "#target" })).toMatchObject({
|
||||
code: "permission_denied",
|
||||
data: { reason: "element_not_visible" },
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
it("rejects targets fully outside an overflow:clip ancestor", async () => {
|
||||
await withBrowser(async (h) => {
|
||||
await h.evaluate(
|
||||
`document.body.innerHTML = '<div style="height:80px;overflow:clip"><div style="height:150px"></div><button id="target">Target</button></div>'`,
|
||||
);
|
||||
expect(await h.scroll({ selector: "#target" })).toMatchObject({ code: "permission_denied" });
|
||||
});
|
||||
});
|
||||
|
||||
it.each(["open", "closed"])("clips %s shadow-root refs", async (mode) => {
|
||||
await withBrowser(async (h) => {
|
||||
await h.evaluate(`(() => {
|
||||
const host = document.createElement('div'); document.body.append(host);
|
||||
const root = host.attachShadow({mode:'${mode}'});
|
||||
root.innerHTML = '<div style="height:60px;overflow:auto"><button id="probe" style="height:200px;width:100px">Target</button></div>';
|
||||
window.probe = root.querySelector('#probe');
|
||||
})()`);
|
||||
const frames = await h.loadFrames();
|
||||
const { result } = await h.send<{ result: { objectId: string } }>(
|
||||
"Runtime.evaluate",
|
||||
{ expression: "window.probe" },
|
||||
h.rootSession,
|
||||
);
|
||||
// Build the ref from the actual closed-root node, as an observation does.
|
||||
const { node } = await h.send<{ node: { backendNodeId: number } }>(
|
||||
"DOM.describeNode",
|
||||
{ objectId: result.objectId },
|
||||
h.rootSession,
|
||||
);
|
||||
await h.send("Runtime.releaseObject", { objectId: result.objectId }, h.rootSession);
|
||||
h.rememberRef(frames[0], node.backendNodeId);
|
||||
expect(await h.scroll({ ref: "e1" })).toMatchObject({ height: 60 });
|
||||
});
|
||||
});
|
||||
|
||||
it("cancels after scrolling and releases the measurement object without follow-up reads", async () => {
|
||||
await withBrowser(async (h) => {
|
||||
await h.evaluate("document.body.innerHTML = '<button id=target>Target</button>'");
|
||||
const abort = new AbortController();
|
||||
h.after.command = (method) => {
|
||||
if (method === "DOM.resolveNode") abort.abort();
|
||||
};
|
||||
expect(await h.scroll({ selector: "#target" }, abort.signal)).toMatchObject({
|
||||
code: "cancelled",
|
||||
});
|
||||
expect(h.calls.at(-1)!.method).toBe("Runtime.releaseObjectGroup");
|
||||
expect(h.calls.some((call) => call.method === "Runtime.callFunctionOn")).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
it.each([
|
||||
{ fixture: "snapshot-coordinates", zoom: 1 },
|
||||
{ fixture: "snapshot-coordinates", zoom: 1.25 },
|
||||
{ fixture: "oopif-scrollbars", zoom: 1 },
|
||||
{ fixture: "oopif-scrollbars", zoom: 0.8 },
|
||||
])("scrolls nested frames: $fixture at zoom $zoom", async ({ fixture, zoom }) => {
|
||||
const { createEvalServer } = await import(
|
||||
new URL("../../../../../evals/browser/lib/server.mjs", import.meta.url).href
|
||||
);
|
||||
const server = createEvalServer();
|
||||
const { baseUrl } = await server.start();
|
||||
try {
|
||||
await withBrowser(async (h) => {
|
||||
await h.send("Page.navigate", { url: `${baseUrl}/${fixture}?run=scroll` }, h.rootSession);
|
||||
await expect
|
||||
.poll(
|
||||
() =>
|
||||
server
|
||||
.snapshot("scroll")
|
||||
.events.some(
|
||||
(e: { type: string; data: { root?: boolean } }) =>
|
||||
e.type === "geometry.ready" && e.data.root,
|
||||
),
|
||||
{ timeout: 10_000 },
|
||||
)
|
||||
.toBe(true);
|
||||
const frames = await h.loadFrames();
|
||||
expect(frames.length).toBe(fixture === "snapshot-coordinates" ? 5 : 3);
|
||||
for (const frame of frames) {
|
||||
await h.ref(frame);
|
||||
const result = await h.scroll({ ref: "e1" });
|
||||
// Independent DOM oracle: CSS border boxes plus this fixture's known
|
||||
// axis-aligned iframe scales. Re-read after each scroll changes layout.
|
||||
let rect = await h.evaluate<ViewportRect>(
|
||||
"document.querySelector('#probe').getBoundingClientRect().toJSON()",
|
||||
frame,
|
||||
);
|
||||
let current = frame;
|
||||
while (true) {
|
||||
const viewport = await h.evaluate<ViewportRect>(
|
||||
"({ x:0, y:0, width:document.documentElement.clientWidth, height:document.documentElement.clientHeight })",
|
||||
current,
|
||||
);
|
||||
rect = intersection(rect, viewport)!;
|
||||
if (!current.parentFrameId) break;
|
||||
const parent = frames.find((f) => f.frameId === current.parentFrameId)!;
|
||||
const owner = await h.evaluate<{ x: number; y: number; scale: number }>(
|
||||
`(() => {
|
||||
const iframe = document.querySelector('iframe[name="${current.name}"]');
|
||||
const r = iframe.getBoundingClientRect(); const s = getComputedStyle(iframe);
|
||||
const scale = r.width / iframe.offsetWidth;
|
||||
return { x:r.x + (iframe.clientLeft + parseFloat(s.paddingLeft))*scale,
|
||||
y:r.y + (iframe.clientTop + parseFloat(s.paddingTop))*scale, scale };
|
||||
})()`,
|
||||
parent,
|
||||
);
|
||||
rect = {
|
||||
x: owner.x + rect.x * owner.scale,
|
||||
y: owner.y + rect.y * owner.scale,
|
||||
width: rect.width * owner.scale,
|
||||
height: rect.height * owner.scale,
|
||||
};
|
||||
current = parent;
|
||||
}
|
||||
expectRect(result, rect);
|
||||
}
|
||||
const child = frames.find((frame) => frame.parentFrameId === frames[0].frameId)!;
|
||||
await h.ref(child);
|
||||
await h.evaluate(
|
||||
`document.querySelector('iframe[name="${child.name}"]').style.opacity = '0'`,
|
||||
);
|
||||
expect(await h.scroll({ ref: "e1" })).toMatchObject({ code: "permission_denied" });
|
||||
}, zoom);
|
||||
} finally {
|
||||
await server.stop();
|
||||
}
|
||||
}, 30_000);
|
||||
});
|
||||
@@ -1,310 +0,0 @@
|
||||
import { afterEach, describe, expect, it, vi } from "vitest";
|
||||
import type { CdpFrameGraph, CdpTarget } from "@/browser-driver/frame-graph";
|
||||
import { SessionManager } from "@/session-manager/manager";
|
||||
import type { JavaScriptDialogInfo, ScrollToParams } from "@/transport/types";
|
||||
import type { ViewportRect } from "../geometry";
|
||||
import { handleScrollTo } from "../scroll";
|
||||
import type { CdpRunner } from "../shared";
|
||||
|
||||
interface Call {
|
||||
target: CdpTarget;
|
||||
method: string;
|
||||
params?: Record<string, unknown>;
|
||||
aborted: boolean;
|
||||
}
|
||||
|
||||
async function fixture(frame: "top" | "same-target" | "oopif" = "top") {
|
||||
const manager = new SessionManager({
|
||||
agentWindow: {
|
||||
create: async () => 100,
|
||||
remove: async () => {},
|
||||
ensureActiveTab: async () => 4,
|
||||
},
|
||||
});
|
||||
const ctx = await manager.start("aa11");
|
||||
ctx.refStore.set("e3", 1234, {
|
||||
tabId: 4,
|
||||
...(frame !== "top" ? { frameId: "child" } : {}),
|
||||
...(frame === "oopif" ? { cdpSessionId: "child-session" } : {}),
|
||||
});
|
||||
const abort = new AbortController();
|
||||
const graph: CdpFrameGraph = {
|
||||
rootFrameId: "main",
|
||||
frames: [
|
||||
{ frameId: "main", target: { tabId: 4 } },
|
||||
{
|
||||
frameId: "child",
|
||||
parentFrameId: "main",
|
||||
ownerBackendNodeId: 99,
|
||||
target: { tabId: 4, ...(frame === "oopif" ? { sessionId: "child-session" } : {}) },
|
||||
},
|
||||
],
|
||||
};
|
||||
const rectangles = new Map<number, ViewportRect | null>([
|
||||
[1234, { x: 10, y: 20, width: 100, height: 40 }],
|
||||
[99, { x: 204, y: 306, width: 400, height: 200 }],
|
||||
]);
|
||||
const calls: Call[] = [];
|
||||
const hooks = {
|
||||
after: (_call: Call) => {},
|
||||
reply: (_call: Call): object | undefined => undefined,
|
||||
};
|
||||
const send = async <T>(target: CdpTarget, method: string, params?: object): Promise<T> => {
|
||||
const call = {
|
||||
target,
|
||||
method,
|
||||
params: params as Call["params"],
|
||||
aborted: abort.signal.aborted,
|
||||
};
|
||||
calls.push(call);
|
||||
const override = hooks.reply(call);
|
||||
hooks.after(call);
|
||||
if (override) return override as T;
|
||||
const args = call.params ?? {};
|
||||
const replies: Record<string, unknown> = {
|
||||
"DOM.getDocument": { root: { nodeId: 1 } },
|
||||
"DOM.querySelector": { nodeId: 2 },
|
||||
"DOM.describeNode": { node: { backendNodeId: 1234 } },
|
||||
"DOM.scrollIntoViewIfNeeded": {},
|
||||
"DOM.resolveNode": { object: { objectId: String(args.backendNodeId) } },
|
||||
"Runtime.callFunctionOn": {
|
||||
result: {
|
||||
value: String(args.functionDeclaration).includes("IntersectionObserver")
|
||||
? rectangles.get(Number(args.objectId))
|
||||
: { width: 200, height: 100 },
|
||||
},
|
||||
},
|
||||
"Runtime.releaseObject": {},
|
||||
"Runtime.releaseObjectGroup": {},
|
||||
"Runtime.evaluate": { result: { value: { width: 200, height: 100 } } },
|
||||
"Page.getLayoutMetrics": {
|
||||
cssLayoutViewport: {
|
||||
clientWidth: target.sessionId ? 185 : 1280,
|
||||
clientHeight: target.sessionId ? 89 : 720,
|
||||
},
|
||||
},
|
||||
"DOM.getBoxModel": { model: { content: [204, 306, 604, 306, 604, 506, 204, 506] } },
|
||||
};
|
||||
if (!(method in replies)) throw new Error(`unexpected CDP call ${method}`);
|
||||
return replies[method] as T;
|
||||
};
|
||||
const cdp: CdpRunner = {
|
||||
send: (tabId, method, params) => send({ tabId }, method, params),
|
||||
sendToTarget: send,
|
||||
getFrameGraph: vi.fn(async () => {
|
||||
hooks.after({ target: { tabId: 4 }, method: "getFrameGraph", aborted: abort.signal.aborted });
|
||||
return graph;
|
||||
}),
|
||||
trackSessionTab: vi.fn(),
|
||||
};
|
||||
const tabsApi = {
|
||||
get: vi.fn(async (id: number) => ({ id, windowId: 100, active: true }) as chrome.tabs.Tab),
|
||||
query: vi.fn(async () => [{ id: 4, windowId: 100, active: true } as chrome.tabs.Tab]),
|
||||
};
|
||||
const run = (params: Partial<ScrollToParams> = {}) =>
|
||||
handleScrollTo(
|
||||
manager,
|
||||
{ session_id: "aa11", ref: "@e3", ...params },
|
||||
{ cdp, tabsApi, signal: abort.signal },
|
||||
);
|
||||
return { ctx, cdp, graph, rectangles, calls, hooks, abort, tabsApi, run };
|
||||
}
|
||||
|
||||
afterEach(() => vi.restoreAllMocks());
|
||||
|
||||
describe("handleScrollTo", () => {
|
||||
it("scrolls a ref and returns renderer-clipped bounds", async () => {
|
||||
const f = await fixture();
|
||||
expect(await f.run()).toMatchObject({
|
||||
tab_id: 4,
|
||||
used_ref: "e3",
|
||||
x: 10,
|
||||
y: 20,
|
||||
width: 100,
|
||||
height: 40,
|
||||
});
|
||||
expect(f.calls[0]).toMatchObject({
|
||||
method: "DOM.scrollIntoViewIfNeeded",
|
||||
params: { backendNodeId: 1234 },
|
||||
});
|
||||
const group = f.calls.find((call) => call.method === "DOM.resolveNode")!.params!.objectGroup;
|
||||
expect(f.calls.at(-1)).toMatchObject({
|
||||
method: "Runtime.releaseObjectGroup",
|
||||
params: { objectGroup: group },
|
||||
});
|
||||
});
|
||||
|
||||
it("resolves a selector and tracks the attached tab even when it is missing", async () => {
|
||||
const f = await fixture();
|
||||
expect(await f.run({ ref: undefined, selector: "#target" })).toMatchObject({
|
||||
used_selector: "#target",
|
||||
});
|
||||
f.hooks.reply = ({ method }) => (method === "DOM.querySelector" ? { nodeId: 0 } : undefined);
|
||||
expect(await f.run({ ref: undefined, selector: "#missing" })).toMatchObject({
|
||||
code: "not_found",
|
||||
data: { reason: "selector_not_found" },
|
||||
});
|
||||
expect(f.cdp.trackSessionTab).toHaveBeenCalledWith("aa11", 4);
|
||||
});
|
||||
|
||||
it.each([
|
||||
"same-target",
|
||||
"oopif",
|
||||
] as const)("projects %s refs and scrolls their owners", async (frame) => {
|
||||
const f = await fixture(frame);
|
||||
expect(await f.run()).toMatchObject({ x: 224, y: 346, width: 200, height: 80 });
|
||||
expect(
|
||||
f.calls
|
||||
.filter((call) => call.method === "DOM.scrollIntoViewIfNeeded")
|
||||
.map((call) => call.params!.backendNodeId),
|
||||
).toEqual([99, 1234]);
|
||||
expect(f.cdp.getFrameGraph).toHaveBeenCalledTimes(1);
|
||||
if (frame === "oopif")
|
||||
expect(f.calls.find((call) => call.params?.backendNodeId === 1234)!.target.sessionId).toBe(
|
||||
"child-session",
|
||||
);
|
||||
});
|
||||
|
||||
it("clips OOPIF bounds to occupied scrollbars without changing the frame scale", async () => {
|
||||
const f = await fixture("oopif");
|
||||
f.rectangles.set(1234, { x: 180, y: 80, width: 5, height: 9 });
|
||||
expect(await f.run()).toMatchObject({ x: 564, y: 466, width: 10, height: 18 });
|
||||
});
|
||||
|
||||
it("clips against the iframe owner's ordinary DOM ancestors", async () => {
|
||||
const f = await fixture("oopif");
|
||||
f.rectangles.set(99, { x: 204, y: 306, width: 400, height: 80 });
|
||||
expect(await f.run()).toMatchObject({ x: 224, y: 346, width: 200, height: 40 });
|
||||
});
|
||||
|
||||
it.each([1234, 99])("rejects a hidden or fully clipped node %i", async (node) => {
|
||||
const f = await fixture("oopif");
|
||||
f.rectangles.set(node, null);
|
||||
expect(await f.run()).toMatchObject({
|
||||
code: "permission_denied",
|
||||
data: { reason: "element_not_visible" },
|
||||
});
|
||||
expect(f.calls.at(-1)!.method).toBe("Runtime.releaseObjectGroup");
|
||||
});
|
||||
|
||||
it.each([
|
||||
{ ref: undefined },
|
||||
{ selector: "#target" },
|
||||
{ timeout_ms: 0 },
|
||||
])("rejects invalid params %j", async (params) => {
|
||||
const f = await fixture();
|
||||
expect(await f.run(params)).toMatchObject({ code: "invalid_params" });
|
||||
expect(f.calls).toEqual([]);
|
||||
});
|
||||
|
||||
it.each(["stale", "other-tab"])("rejects %s refs before scrolling", async (mode) => {
|
||||
const f = await fixture();
|
||||
if (mode === "stale") f.ctx.refStore.clear();
|
||||
else f.ctx.refStore.set("e3", 1234, { tabId: 8 });
|
||||
expect(await f.run()).toMatchObject({ code: "not_found", data: { reason: "ref_not_found" } });
|
||||
expect(f.calls).toEqual([]);
|
||||
});
|
||||
|
||||
it("enforces the Agent Window boundary", async () => {
|
||||
const f = await fixture();
|
||||
f.tabsApi.query.mockResolvedValue([{ id: 4, windowId: 200, active: true } as chrome.tabs.Tab]);
|
||||
f.tabsApi.get.mockResolvedValue({ id: 4, windowId: 200, active: true } as chrome.tabs.Tab);
|
||||
expect(await f.run({ tab_id: 4 })).toMatchObject({ code: "permission_denied" });
|
||||
expect(f.calls).toEqual([]);
|
||||
});
|
||||
|
||||
it.each([
|
||||
"getFrameGraph",
|
||||
"DOM.scrollIntoViewIfNeeded",
|
||||
"DOM.resolveNode",
|
||||
"Runtime.callFunctionOn",
|
||||
"Page.getLayoutMetrics",
|
||||
"Runtime.evaluate",
|
||||
"DOM.getBoxModel",
|
||||
])("honors cancellation during %s and only cleans up afterwards", async (method) => {
|
||||
const f = await fixture("oopif");
|
||||
f.hooks.after = (call) => {
|
||||
if (call.method === method) f.abort.abort();
|
||||
};
|
||||
expect(await f.run()).toMatchObject({ code: "cancelled" });
|
||||
expect(
|
||||
f.calls.filter((call) => call.aborted && call.method !== "Runtime.releaseObjectGroup"),
|
||||
).toEqual([]);
|
||||
});
|
||||
|
||||
it.each([
|
||||
"DOM.getDocument",
|
||||
"DOM.querySelector",
|
||||
"DOM.describeNode",
|
||||
])("cancels selector resolution during %s", async (method) => {
|
||||
const f = await fixture();
|
||||
f.hooks.after = (call) => {
|
||||
if (call.method === method) f.abort.abort();
|
||||
};
|
||||
expect(await f.run({ ref: undefined, selector: "#target" })).toMatchObject({
|
||||
code: "cancelled",
|
||||
});
|
||||
expect(f.calls.filter((call) => call.aborted)).toEqual([]);
|
||||
});
|
||||
|
||||
it("does not start after early cancellation", async () => {
|
||||
const f = await fixture();
|
||||
f.abort.abort();
|
||||
expect(await f.run()).toMatchObject({ code: "cancelled" });
|
||||
expect(f.calls).toEqual([]);
|
||||
expect(f.tabsApi.query).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("does not issue fallback scrolling after cancellation", async () => {
|
||||
const f = await fixture();
|
||||
f.hooks.reply = ({ method }) => {
|
||||
if (method === "DOM.scrollIntoViewIfNeeded") {
|
||||
f.abort.abort();
|
||||
throw new Error("scroll failed");
|
||||
}
|
||||
return undefined;
|
||||
};
|
||||
expect(await f.run()).toMatchObject({ code: "cancelled" });
|
||||
expect(f.calls.map((call) => call.method)).toEqual(["DOM.scrollIntoViewIfNeeded"]);
|
||||
});
|
||||
|
||||
it("stops target scrolling after a deadline expires while scrolling its owner", async () => {
|
||||
const f = await fixture("oopif");
|
||||
const now = vi.spyOn(Date, "now").mockReturnValue(100);
|
||||
f.hooks.after = ({ method }) => {
|
||||
if (method === "DOM.scrollIntoViewIfNeeded") now.mockReturnValue(201);
|
||||
};
|
||||
expect(await f.run({ timeout_ms: 100 })).toMatchObject({ code: "timeout" });
|
||||
expect(f.calls.filter((call) => call.method === "DOM.scrollIntoViewIfNeeded")).toHaveLength(1);
|
||||
});
|
||||
|
||||
it("reports measurement exceptions and releases objects even if cleanup fails", async () => {
|
||||
const f = await fixture();
|
||||
f.hooks.reply = ({ method }) => {
|
||||
if (method === "Runtime.callFunctionOn")
|
||||
return { exceptionDetails: { text: "measurement failed" } };
|
||||
if (method === "Runtime.releaseObjectGroup") throw new Error("target closed");
|
||||
return undefined;
|
||||
};
|
||||
expect(await f.run()).toMatchObject({ code: "cdp_failed", message: "measurement failed" });
|
||||
expect(f.calls.at(-1)!.method).toBe("Runtime.releaseObjectGroup");
|
||||
});
|
||||
|
||||
it("attaches dialogs observed during scrolling", async () => {
|
||||
const f = await fixture();
|
||||
f.cdp.dialogCursor = () => 5;
|
||||
const dialogs: JavaScriptDialogInfo[] = [
|
||||
{
|
||||
sequence: 6,
|
||||
tab_id: 4,
|
||||
type: "alert",
|
||||
message: "scrolled",
|
||||
handled: "accepted",
|
||||
url: "https://example.test",
|
||||
},
|
||||
];
|
||||
f.cdp.dialogsSince = vi.fn(() => dialogs);
|
||||
expect(await f.run()).toHaveProperty("dialogs", dialogs);
|
||||
expect(f.cdp.dialogsSince).toHaveBeenCalledWith(4, 5);
|
||||
});
|
||||
});
|
||||
@@ -1,26 +1,8 @@
|
||||
import { describe, expect, it, vi } from "vitest";
|
||||
import { SessionManager } from "@/session-manager/manager";
|
||||
import { handleSessionStop } from "../session";
|
||||
import type { ChromeTabsApi } from "../shared";
|
||||
import { type AgentOverlayResetApi, type ChromeWindowsApi, type TabMutationApi } from "../tabs";
|
||||
|
||||
/** Build a read-only query api over a FakeState. */
|
||||
function makeQuery(state: FakeState): ChromeTabsApi {
|
||||
return {
|
||||
get: vi.fn(async (id) => {
|
||||
const t = state.tabs.get(id);
|
||||
if (!t) throw new Error(`tab ${id} not found`);
|
||||
return t;
|
||||
}),
|
||||
query: vi.fn(async (q: chrome.tabs.QueryInfo) => {
|
||||
const w = q.windowId;
|
||||
return Array.from(state.tabs.values()).filter(
|
||||
(t) => typeof w !== "number" || t.windowId === w,
|
||||
);
|
||||
}),
|
||||
};
|
||||
}
|
||||
|
||||
function fakeAgentWindow(ids: number[]) {
|
||||
let i = 0;
|
||||
const create = vi.fn(async () => {
|
||||
@@ -29,7 +11,7 @@ function fakeAgentWindow(ids: number[]) {
|
||||
return id;
|
||||
});
|
||||
const remove = vi.fn(async () => {});
|
||||
const ensureActiveTab = vi.fn(async () => 0);
|
||||
const ensureActiveTab = vi.fn(async () => {});
|
||||
return { create, remove, ensureActiveTab };
|
||||
}
|
||||
|
||||
@@ -48,9 +30,7 @@ function makeApis(
|
||||
} {
|
||||
const tabs: TabMutationApi = {
|
||||
create: vi.fn(),
|
||||
remove: vi.fn(async (id: number) => {
|
||||
state.tabs.delete(id);
|
||||
}),
|
||||
remove: vi.fn(async () => {}),
|
||||
update: vi.fn(async (_id, _p) => undefined),
|
||||
get: vi.fn(async (id) => {
|
||||
const t = state.tabs.get(id);
|
||||
@@ -257,15 +237,11 @@ describe("handleSessionStop with auto-return", () => {
|
||||
moves: [],
|
||||
};
|
||||
const { tabs, windows } = makeApis(state, { moveThrowsFor: new Set([1]) });
|
||||
const cdp = {
|
||||
detachSession: vi.fn(async () => {}),
|
||||
releaseSessionTab: vi.fn(async () => {}),
|
||||
};
|
||||
|
||||
const res = await handleSessionStop(
|
||||
sm,
|
||||
{ session_id: "aa11" },
|
||||
{ cdp, tabManagement: { tabs, windows } },
|
||||
{ tabManagement: { tabs, windows } },
|
||||
);
|
||||
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
|
||||
expect(res.return_failures?.map((f) => f.tab_id)).toEqual([1]);
|
||||
@@ -273,8 +249,6 @@ describe("handleSessionStop with auto-return", () => {
|
||||
expect(sm.has("aa11")).toBe(true);
|
||||
expect(ctx.borrowedTabs.has(1)).toBe(true);
|
||||
expect(ctx.borrowedTabs.has(2)).toBe(false);
|
||||
expect(cdp.releaseSessionTab).toHaveBeenCalledExactlyOnceWith("aa11", 2);
|
||||
expect(cdp.detachSession).not.toHaveBeenCalled();
|
||||
expect(aw.remove).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
@@ -293,275 +267,4 @@ describe("handleSessionStop with auto-return", () => {
|
||||
await handleSessionStop(sm, { session_id: "aa11" }, { tabManagement: { tabs, windows } });
|
||||
expect(ctx.refStore.isEmpty()).toBe(true);
|
||||
});
|
||||
|
||||
it.each([
|
||||
"before teardown",
|
||||
"during its return",
|
||||
"after its return failed",
|
||||
"before its turn in the return loop",
|
||||
])("finishes stopping when a borrowed tab closes %s", async (timing) => {
|
||||
const aw = fakeAgentWindow([100]);
|
||||
const sm = new SessionManager({ agentWindow: aw });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.borrowedTabs.set(1, { tabId: 1, originalWindowId: 200, originalIndex: 0 });
|
||||
ctx.borrowedTabs.set(2, { tabId: 2, originalWindowId: 200, originalIndex: 1 });
|
||||
const state: FakeState = {
|
||||
tabs: new Map([
|
||||
[1, { id: 1, windowId: 100 } as chrome.tabs.Tab],
|
||||
[2, { id: 2, windowId: 100 } as chrome.tabs.Tab],
|
||||
]),
|
||||
windowsClosed: new Set(),
|
||||
moves: [],
|
||||
};
|
||||
const { tabs, windows } = makeApis(state);
|
||||
const cdp = { detachSession: vi.fn(async () => {}) };
|
||||
const closeTab = (tabId: number) => {
|
||||
state.tabs.delete(tabId);
|
||||
sm.forgetClosedTab(tabId);
|
||||
};
|
||||
const baseMove = tabs.move;
|
||||
tabs.move = vi.fn(async (tabId, props) => {
|
||||
if (tabId === 1 && timing === "during its return") closeTab(1);
|
||||
if (tabId === 1 && timing === "after its return failed") {
|
||||
throw new Error("simulated move failure");
|
||||
}
|
||||
if (tabId === 2 && timing === "after its return failed") closeTab(1);
|
||||
if (tabId === 1 && timing === "before its turn in the return loop") closeTab(2);
|
||||
if (!state.tabs.has(tabId)) throw new Error(`tab ${tabId} not found`);
|
||||
return baseMove(tabId, props);
|
||||
});
|
||||
if (timing === "before teardown") closeTab(1);
|
||||
|
||||
const res = await handleSessionStop(
|
||||
sm,
|
||||
{ session_id: "aa11" },
|
||||
{
|
||||
cdp,
|
||||
tabManagement: {
|
||||
tabs,
|
||||
windows,
|
||||
agentOverlayReset: { resetAgentOverlays: vi.fn(async () => {}) },
|
||||
},
|
||||
tabsQuery: makeQuery(state),
|
||||
},
|
||||
);
|
||||
|
||||
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
|
||||
const closedTabId = timing === "before its turn in the return loop" ? 2 : 1;
|
||||
expect(res.returned_tab_ids).toEqual([closedTabId === 1 ? 2 : 1]);
|
||||
expect(res.return_failures).toBeUndefined();
|
||||
expect(ctx.borrowedTabs.size).toBe(0);
|
||||
expect(sm.has("aa11")).toBe(false);
|
||||
expect(cdp.detachSession).toHaveBeenCalledWith("aa11");
|
||||
expect(aw.remove).toHaveBeenCalledWith(100);
|
||||
if (timing === "before teardown" || timing === "before its turn in the return loop") {
|
||||
expect(tabs.move).not.toHaveBeenCalledWith(closedTabId, expect.anything());
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
describe("handleSessionStop window release (issue #57)", () => {
|
||||
const agentWindowId = 100;
|
||||
|
||||
it("releases the window when user-created tabs remain", async () => {
|
||||
const aw = fakeAgentWindow([agentWindowId]);
|
||||
// ensureActiveTab returns the home tab id (10). We override the fake to
|
||||
// return a known id.
|
||||
aw.ensureActiveTab = vi.fn(async () => 10);
|
||||
const sm = new SessionManager({ agentWindow: aw });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.agentCreatedTabs.add(11);
|
||||
ctx.agentCreatedTabs.add(12);
|
||||
// user tab 99 (created via Chrome UI, NOT in agentCreatedTabs)
|
||||
const state: FakeState = {
|
||||
tabs: new Map([
|
||||
[10, { id: 10, windowId: agentWindowId } as chrome.tabs.Tab],
|
||||
[11, { id: 11, windowId: agentWindowId } as chrome.tabs.Tab],
|
||||
[12, { id: 12, windowId: agentWindowId } as chrome.tabs.Tab],
|
||||
[99, { id: 99, windowId: agentWindowId } as chrome.tabs.Tab],
|
||||
]),
|
||||
windowsClosed: new Set(),
|
||||
moves: [],
|
||||
};
|
||||
const { tabs, windows } = makeApis(state);
|
||||
const query = makeQuery(state);
|
||||
|
||||
const res = await handleSessionStop(
|
||||
sm,
|
||||
{ session_id: "aa11" },
|
||||
{ tabManagement: { tabs, windows }, tabsQuery: query },
|
||||
);
|
||||
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
|
||||
expect(res.window_released).toBe(true);
|
||||
// agent tabs + home removed, user tab 99 kept
|
||||
expect((tabs.remove as ReturnType<typeof vi.fn>).mock.calls.map((c) => c[0]).sort()).toEqual([
|
||||
10, 11, 12,
|
||||
]);
|
||||
expect(state.tabs.has(99)).toBe(true);
|
||||
// window released (dropOnly), not closed
|
||||
expect(aw.remove).not.toHaveBeenCalled();
|
||||
expect(sm.has("aa11")).toBe(false);
|
||||
});
|
||||
|
||||
it("closes the window (not release) when no user tabs remain", async () => {
|
||||
const aw = fakeAgentWindow([agentWindowId]);
|
||||
aw.ensureActiveTab = vi.fn(async () => 10);
|
||||
const sm = new SessionManager({ agentWindow: aw });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.agentCreatedTabs.add(11);
|
||||
const state: FakeState = {
|
||||
tabs: new Map([
|
||||
[10, { id: 10, windowId: agentWindowId } as chrome.tabs.Tab],
|
||||
[11, { id: 11, windowId: agentWindowId } as chrome.tabs.Tab],
|
||||
]),
|
||||
windowsClosed: new Set(),
|
||||
moves: [],
|
||||
};
|
||||
const { tabs, windows } = makeApis(state);
|
||||
const query = makeQuery(state);
|
||||
|
||||
const res = await handleSessionStop(
|
||||
sm,
|
||||
{ session_id: "aa11" },
|
||||
{ tabManagement: { tabs, windows }, tabsQuery: query },
|
||||
);
|
||||
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
|
||||
expect(res.window_released).toBeFalsy();
|
||||
expect(aw.remove).toHaveBeenCalledWith(agentWindowId);
|
||||
expect(sm.has("aa11")).toBe(false);
|
||||
});
|
||||
|
||||
it("is non-fatal when an agent tab is already gone", async () => {
|
||||
const aw = fakeAgentWindow([agentWindowId]);
|
||||
aw.ensureActiveTab = vi.fn(async () => 10);
|
||||
const sm = new SessionManager({ agentWindow: aw });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.agentCreatedTabs.add(11); // no longer in state → remove throws
|
||||
const state: FakeState = {
|
||||
tabs: new Map([[10, { id: 10, windowId: agentWindowId } as chrome.tabs.Tab]]),
|
||||
windowsClosed: new Set(),
|
||||
moves: [],
|
||||
};
|
||||
const { tabs, windows } = makeApis(state);
|
||||
(tabs.remove as ReturnType<typeof vi.fn>).mockImplementation(async (id: number) => {
|
||||
if (id === 11) throw new Error("tab 11 already closed");
|
||||
state.tabs.delete(id); // home (10) removed normally
|
||||
});
|
||||
const query = makeQuery(state);
|
||||
|
||||
const res = await handleSessionStop(
|
||||
sm,
|
||||
{ session_id: "aa11" },
|
||||
{ tabManagement: { tabs, windows }, tabsQuery: query },
|
||||
);
|
||||
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
|
||||
// user tab 10? no — 10 is home, removed. window would be empty → close.
|
||||
expect(res.window_released).toBeFalsy();
|
||||
expect(aw.remove).toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("degrades to close-window when tabsQuery is missing", async () => {
|
||||
const aw = fakeAgentWindow([agentWindowId]);
|
||||
aw.ensureActiveTab = vi.fn(async () => 10);
|
||||
const sm = new SessionManager({ agentWindow: aw });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.agentCreatedTabs.add(11);
|
||||
const state: FakeState = {
|
||||
tabs: new Map([
|
||||
[10, { id: 10, windowId: agentWindowId } as chrome.tabs.Tab],
|
||||
[11, { id: 11, windowId: agentWindowId } as chrome.tabs.Tab],
|
||||
]),
|
||||
windowsClosed: new Set(),
|
||||
moves: [],
|
||||
};
|
||||
const { tabs, windows } = makeApis(state);
|
||||
|
||||
const res = await handleSessionStop(
|
||||
sm,
|
||||
{ session_id: "aa11" },
|
||||
{ tabManagement: { tabs, windows } }, // no tabsQuery
|
||||
);
|
||||
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
|
||||
// No query available → conservatively close the window.
|
||||
expect(res.window_released).toBeFalsy();
|
||||
expect(aw.remove).toHaveBeenCalledWith(agentWindowId);
|
||||
});
|
||||
|
||||
it("degrades to close-window when tabsQuery.query throws", async () => {
|
||||
const aw = fakeAgentWindow([agentWindowId]);
|
||||
aw.ensureActiveTab = vi.fn(async () => 10);
|
||||
const sm = new SessionManager({ agentWindow: aw });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.agentCreatedTabs.add(11);
|
||||
const state: FakeState = {
|
||||
tabs: new Map([[11, { id: 11, windowId: agentWindowId } as chrome.tabs.Tab]]),
|
||||
windowsClosed: new Set(),
|
||||
moves: [],
|
||||
};
|
||||
const { tabs, windows } = makeApis(state);
|
||||
const query = makeQuery(state);
|
||||
(query.query as ReturnType<typeof vi.fn>).mockImplementation(async () => {
|
||||
throw new Error("query failed");
|
||||
});
|
||||
|
||||
const res = await handleSessionStop(
|
||||
sm,
|
||||
{ session_id: "aa11" },
|
||||
{ tabManagement: { tabs, windows }, tabsQuery: query },
|
||||
);
|
||||
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
|
||||
expect(res.window_released).toBeFalsy();
|
||||
expect(aw.remove).toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("tracks agentCreatedTabs across tab_create / tab_close", async () => {
|
||||
const aw = fakeAgentWindow([agentWindowId]);
|
||||
aw.ensureActiveTab = vi.fn(async () => 10);
|
||||
const sm = new SessionManager({ agentWindow: aw });
|
||||
const ctx = await sm.start("aa11");
|
||||
// Simulate handleTabCreate adding, then handleTabClose removing.
|
||||
ctx.agentCreatedTabs.add(11);
|
||||
expect(ctx.agentCreatedTabs.has(11)).toBe(true);
|
||||
ctx.agentCreatedTabs.delete(11); // as handleTabClose does on success
|
||||
expect(ctx.agentCreatedTabs.has(11)).toBe(false);
|
||||
// Unknown id delete is a safe no-op (user-closed tab).
|
||||
expect(() => ctx.agentCreatedTabs.delete(999)).not.toThrow();
|
||||
});
|
||||
|
||||
it("closes the window (not release) when an agent tab fails to close", async () => {
|
||||
// Regression: a leaked agent tab (still in agentCreatedTabs, but
|
||||
// still present because Step 4 remove() threw) must NOT be mistaken
|
||||
// for a user tab. Otherwise the window would be released (dropOnly)
|
||||
// and the agent tab would leak (issue #57 regression).
|
||||
const aw = fakeAgentWindow([agentWindowId]);
|
||||
aw.ensureActiveTab = vi.fn(async () => 10);
|
||||
const sm = new SessionManager({ agentWindow: aw });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.agentCreatedTabs.add(11); // Step 4 remove() will throw for this tab
|
||||
const state: FakeState = {
|
||||
tabs: new Map([
|
||||
[10, { id: 10, windowId: agentWindowId } as chrome.tabs.Tab],
|
||||
[11, { id: 11, windowId: agentWindowId } as chrome.tabs.Tab],
|
||||
]),
|
||||
windowsClosed: new Set(),
|
||||
moves: [],
|
||||
};
|
||||
const { tabs, windows } = makeApis(state);
|
||||
(tabs.remove as ReturnType<typeof vi.fn>).mockImplementation(async (id: number) => {
|
||||
if (id === 11) throw new Error("tab 11 failed to close");
|
||||
state.tabs.delete(id); // home (10) removed normally; 11 lingers
|
||||
});
|
||||
const query = makeQuery(state);
|
||||
|
||||
const res = await handleSessionStop(
|
||||
sm,
|
||||
{ session_id: "aa11" },
|
||||
{ tabManagement: { tabs, windows }, tabsQuery: query },
|
||||
);
|
||||
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
|
||||
// The leaked agent tab must NOT keep the window open.
|
||||
expect(res.window_released).toBeFalsy();
|
||||
expect(aw.remove).toHaveBeenCalledWith(agentWindowId);
|
||||
expect(sm.has("aa11")).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -12,7 +12,7 @@ function fakeAgentWindow() {
|
||||
return {
|
||||
create: vi.fn(async () => 100),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
@@ -1,355 +0,0 @@
|
||||
// @vitest-environment node
|
||||
import { describe, expect, it } from "vitest";
|
||||
import type { CdpFrame, CdpFrameGraph, CdpTarget } from "@/browser-driver/frame-graph";
|
||||
import { resolveNodeGeometry } from "../frame-geometry";
|
||||
import type { CdpRunner } from "../shared";
|
||||
import { captureObservationFacts } from "../vom/capture-coordinator";
|
||||
|
||||
type Send = <T = Record<string, unknown>>(
|
||||
method: string,
|
||||
params?: object,
|
||||
sessionId?: string,
|
||||
) => Promise<T>;
|
||||
type Tree = { frame: { id: string; parentId?: string; name?: string }; childFrames?: Tree[] };
|
||||
type Rect = { x: number; y: number; w: number; h: number };
|
||||
type Oracle = {
|
||||
probes: Record<string, Rect>;
|
||||
viewport: { width: number; height: number };
|
||||
owners: Record<string, { x: number; y: number; scale: number }>;
|
||||
};
|
||||
|
||||
function clip(rect: Rect, viewport: Oracle["viewport"]): Rect | null {
|
||||
const x = Math.max(0, rect.x),
|
||||
y = Math.max(0, rect.y);
|
||||
const right = Math.min(viewport.width, rect.x + rect.w);
|
||||
const bottom = Math.min(viewport.height, rect.y + rect.h);
|
||||
return right > x && bottom > y ? { x, y, w: right - x, h: bottom - y } : null;
|
||||
}
|
||||
|
||||
// The independent oracle uses DOM border boxes and this fixture's axis-aligned
|
||||
// iframe transforms. No production snapshot conversion/projection builds expectations.
|
||||
const oracleExpression = `(() => {
|
||||
const probes = {};
|
||||
for (const node of document.querySelectorAll('[data-geometry-probe]')) {
|
||||
const box = node.getBoundingClientRect();
|
||||
probes[node.id] = { x: box.x, y: box.y, w: box.width, h: box.height };
|
||||
}
|
||||
const owners = {};
|
||||
for (const frame of document.querySelectorAll('iframe')) {
|
||||
const rect = frame.getBoundingClientRect();
|
||||
const style = getComputedStyle(frame);
|
||||
const scale = rect.width / frame.offsetWidth;
|
||||
owners[frame.name] = {
|
||||
x: rect.x + (frame.clientLeft + parseFloat(style.paddingLeft)) * scale,
|
||||
y: rect.y + (frame.clientTop + parseFloat(style.paddingTop)) * scale,
|
||||
scale,
|
||||
};
|
||||
}
|
||||
return { probes, viewport: { width: document.documentElement.clientWidth, height: document.documentElement.clientHeight }, owners };
|
||||
})()`;
|
||||
|
||||
describe.skipIf(!process.env.BSK_GEOMETRY_CHROME)("real DOMSnapshot coordinate contract", () => {
|
||||
it.each(
|
||||
[
|
||||
{ deviceScale: 1, zoom: 1 },
|
||||
{ deviceScale: 0.8, zoom: 1 },
|
||||
{ deviceScale: 1, zoom: 1.25 },
|
||||
{ deviceScale: 2, zoom: 1 },
|
||||
{ deviceScale: 2, zoom: 0.8 },
|
||||
]
|
||||
.flatMap((configuration) => [
|
||||
{ ...configuration, fixture: "snapshot-coordinates", scrollbars: "none" },
|
||||
{ ...configuration, fixture: "oopif-scrollbars", scrollbars: "both" },
|
||||
])
|
||||
.concat(
|
||||
["vertical", "horizontal", "none"].map((scrollbars) => ({
|
||||
deviceScale: 1,
|
||||
zoom: 1,
|
||||
fixture: "oopif-scrollbars",
|
||||
scrollbars,
|
||||
})),
|
||||
),
|
||||
)("$fixture: device scale $deviceScale, zoom $zoom, scrollbars $scrollbars", async (configuration) => {
|
||||
const evalRoot = new URL("../../../../../evals/browser/", import.meta.url);
|
||||
const { createEvalServer } = await import(new URL("lib/server.mjs", evalRoot).href);
|
||||
const { withChrome } = await import(
|
||||
new URL("cases/regression/snapshot-coordinates/chrome.mjs", evalRoot).href
|
||||
);
|
||||
const server = createEvalServer();
|
||||
const { baseUrl } = await server.start();
|
||||
try {
|
||||
await withChrome(
|
||||
{ executable: process.env.BSK_GEOMETRY_CHROME, ...configuration },
|
||||
async (send: Send) => {
|
||||
const { targetId } = await send<{ targetId: string }>("Target.createTarget", {
|
||||
url: "about:blank",
|
||||
});
|
||||
const { sessionId: rootSession } = await send<{ sessionId: string }>(
|
||||
"Target.attachToTarget",
|
||||
{ targetId, flatten: true },
|
||||
);
|
||||
await send(
|
||||
"Page.navigate",
|
||||
{
|
||||
url: `${baseUrl}/${configuration.fixture}?run=coordinates&scrollbars=${configuration.scrollbars}`,
|
||||
},
|
||||
rootSession,
|
||||
);
|
||||
await expect
|
||||
.poll(
|
||||
() =>
|
||||
server
|
||||
.snapshot("coordinates")
|
||||
.events.some(
|
||||
(event: { type: string; data: { root?: boolean } }) =>
|
||||
event.type === "geometry.ready" && event.data.root,
|
||||
),
|
||||
{ timeout: 10_000 },
|
||||
)
|
||||
.toBe(true);
|
||||
|
||||
const targets = await send<{ targetInfos: { targetId: string; type: string }[] }>(
|
||||
"Target.getTargets",
|
||||
);
|
||||
const sessions = [rootSession];
|
||||
for (const target of targets.targetInfos.filter((target) => target.type === "iframe")) {
|
||||
const { sessionId } = await send<{ sessionId: string }>("Target.attachToTarget", {
|
||||
targetId: target.targetId,
|
||||
flatten: true,
|
||||
});
|
||||
sessions.push(sessionId);
|
||||
}
|
||||
expect(sessions.length).toBe(configuration.fixture === "oopif-scrollbars" ? 3 : 2);
|
||||
const frames: CdpFrame[] = [];
|
||||
const names = new Map<string, string>();
|
||||
const sessionFor = (target: CdpTarget) => target.sessionId ?? rootSession;
|
||||
for (const sessionId of sessions) {
|
||||
const { frameTree } = await send<{ frameTree: Tree }>(
|
||||
"Page.getFrameTree",
|
||||
{},
|
||||
sessionId,
|
||||
);
|
||||
const target: CdpTarget = {
|
||||
tabId: 1,
|
||||
...(sessionId === rootSession ? {} : { sessionId }),
|
||||
};
|
||||
const visit = (tree: Tree, parentFrameId = tree.frame.parentId) => {
|
||||
frames.push({ frameId: tree.frame.id, parentFrameId, target });
|
||||
names.set(tree.frame.id, tree.frame.name ?? "");
|
||||
for (const child of tree.childFrames ?? []) visit(child, tree.frame.id);
|
||||
};
|
||||
visit(frameTree);
|
||||
}
|
||||
expect(frames).toHaveLength(configuration.fixture === "oopif-scrollbars" ? 3 : 5);
|
||||
for (const frame of frames) {
|
||||
if (!frame.parentFrameId) continue;
|
||||
const parent = frames.find((item) => item.frameId === frame.parentFrameId)!;
|
||||
const owner = await send<{ backendNodeId: number }>(
|
||||
"DOM.getFrameOwner",
|
||||
{ frameId: frame.frameId },
|
||||
sessionFor(parent.target),
|
||||
);
|
||||
frame.ownerBackendNodeId = owner.backendNodeId;
|
||||
}
|
||||
const graph: CdpFrameGraph = { rootFrameId: frames[0].frameId, frames };
|
||||
const calls: string[] = [];
|
||||
const cdp: CdpRunner = {
|
||||
send: (tabId, method, params) => {
|
||||
calls.push(`${tabId}:${method}`);
|
||||
return send(method, params, rootSession);
|
||||
},
|
||||
sendToTarget: (target, method, params) => {
|
||||
calls.push(`${target.sessionId ?? target.tabId}:${method}`);
|
||||
if (
|
||||
method === "Runtime.evaluate" &&
|
||||
(params as { expression?: string })?.expression?.includes("window.innerWidth")
|
||||
)
|
||||
calls.push(`${target.sessionId ?? target.tabId}:viewport-size`);
|
||||
return send(method, params, sessionFor(target));
|
||||
},
|
||||
getFrameGraph: async () => graph,
|
||||
getAttachmentId: () => rootSession,
|
||||
};
|
||||
const oracles = new Map<string, Oracle>();
|
||||
for (const frame of frames) {
|
||||
const session = sessionFor(frame.target);
|
||||
const { executionContextId } = await send<{ executionContextId: number }>(
|
||||
"Page.createIsolatedWorld",
|
||||
{ frameId: frame.frameId, worldName: "coordinate-oracle" },
|
||||
session,
|
||||
);
|
||||
await expect
|
||||
.poll(
|
||||
async () => {
|
||||
const ready = await send<{ result: { value: boolean } }>(
|
||||
"Runtime.evaluate",
|
||||
{
|
||||
expression: 'document.documentElement.dataset.geometryReady === "true"',
|
||||
contextId: executionContextId,
|
||||
returnByValue: true,
|
||||
},
|
||||
session,
|
||||
);
|
||||
return ready.result.value;
|
||||
},
|
||||
{ timeout: 5_000 },
|
||||
)
|
||||
.toBe(true);
|
||||
// Establish scroll after cross-process target creation/layout settles.
|
||||
const scroll = frame.parentFrameId
|
||||
? names.get(frame.frameId) === "nested"
|
||||
? [10, 20]
|
||||
: [40, 100]
|
||||
: [80, 240];
|
||||
await send(
|
||||
"Runtime.evaluate",
|
||||
{
|
||||
expression: `(async () => { scrollTo(${scroll.join(",")}); await new Promise(resolve => requestAnimationFrame(() => requestAnimationFrame(resolve))); })()`,
|
||||
contextId: executionContextId,
|
||||
awaitPromise: true,
|
||||
},
|
||||
session,
|
||||
);
|
||||
const reply = await send<{ result: { value: Oracle } }>(
|
||||
"Runtime.evaluate",
|
||||
{ expression: oracleExpression, contextId: executionContextId, returnByValue: true },
|
||||
session,
|
||||
);
|
||||
oracles.set(frame.frameId, reply.result.value);
|
||||
}
|
||||
const childViewport = await send<{
|
||||
result: {
|
||||
value: { width: number; height: number; clientWidth: number; clientHeight: number };
|
||||
};
|
||||
}>(
|
||||
"Runtime.evaluate",
|
||||
{
|
||||
expression:
|
||||
"({ width: innerWidth, height: innerHeight, clientWidth: document.documentElement.clientWidth, clientHeight: document.documentElement.clientHeight })",
|
||||
returnByValue: true,
|
||||
},
|
||||
sessions[1],
|
||||
);
|
||||
for (const dimension of ["Width", "Height"] as const) {
|
||||
const occupied =
|
||||
childViewport.result.value[dimension === "Width" ? "width" : "height"] -
|
||||
childViewport.result.value[`client${dimension}`];
|
||||
if (
|
||||
configuration.scrollbars === "both" ||
|
||||
configuration.scrollbars === (dimension === "Width" ? "vertical" : "horizontal")
|
||||
)
|
||||
expect(occupied).toBeGreaterThan(0);
|
||||
else expect(occupied).toBe(0);
|
||||
}
|
||||
const facts = await captureObservationFacts(cdp, 1);
|
||||
expect(facts.issues).toEqual([]);
|
||||
expect(calls.filter((call) => call.endsWith(":Page.getLayoutMetrics"))).toHaveLength(
|
||||
sessions.length,
|
||||
);
|
||||
// Identity verification also uses Runtime.evaluate; count the full viewport reads separately.
|
||||
const viewportReadsBeforeLive = calls.filter((call) => call.endsWith(":viewport-size"));
|
||||
expect(new Set(viewportReadsBeforeLive).size).toBe(viewportReadsBeforeLive.length);
|
||||
expect(viewportReadsBeforeLive.length).toBeLessThanOrEqual(sessions.length - 1);
|
||||
for (const frame of frames) {
|
||||
for (const [id, local] of Object.entries(oracles.get(frame.frameId)!.probes)) {
|
||||
const node = facts.documents
|
||||
.find((doc) => doc.frame.frameId === frame.frameId)
|
||||
?.domNodes.find((node) => node.attrs.id === id);
|
||||
expect(node, `missing ${id} in ${names.get(frame.frameId) || "root"}`).toBeDefined();
|
||||
let top = clip(local, oracles.get(frame.frameId)!.viewport);
|
||||
let current = frame;
|
||||
while (top && current.parentFrameId) {
|
||||
const parentOracle = oracles.get(current.parentFrameId)!;
|
||||
const owner = parentOracle.owners[names.get(current.frameId)!];
|
||||
top = clip(
|
||||
{
|
||||
x: owner.x + top.x * owner.scale,
|
||||
y: owner.y + top.y * owner.scale,
|
||||
w: top.w * owner.scale,
|
||||
h: top.h * owner.scale,
|
||||
},
|
||||
parentOracle.viewport,
|
||||
);
|
||||
current = frames.find((item) => item.frameId === current.parentFrameId)!;
|
||||
}
|
||||
for (const key of ["x", "y", "w", "h"] as const)
|
||||
expect(
|
||||
Math.abs(node!.localRect![key] - local[key]),
|
||||
`${names.get(frame.frameId)} ${id} local ${key}`,
|
||||
).toBeLessThan(2);
|
||||
if (!top) {
|
||||
expect(node!.rect, `${id} must be clipped out`).toBeNull();
|
||||
if (configuration.fixture === "oopif-scrollbars")
|
||||
expect(
|
||||
await resolveNodeGeometry(cdp, 1, {
|
||||
target: frame.target,
|
||||
frameId: frame.frameId,
|
||||
backendNodeId: node!.backendNodeId,
|
||||
}),
|
||||
).toMatchObject({ code: "permission_denied" });
|
||||
continue;
|
||||
}
|
||||
expect(node!.rect).not.toBeNull();
|
||||
for (const key of ["x", "y", "w", "h"] as const)
|
||||
expect(
|
||||
Math.abs(node!.rect![key] - top[key]),
|
||||
`${names.get(frame.frameId)} ${id} top ${key}`,
|
||||
).toBeLessThan(2);
|
||||
if (configuration.fixture !== "oopif-scrollbars") continue;
|
||||
const live = await resolveNodeGeometry(cdp, 1, {
|
||||
target: frame.target,
|
||||
frameId: frame.frameId,
|
||||
backendNodeId: node!.backendNodeId,
|
||||
});
|
||||
if ("code" in live) throw new Error(live.message);
|
||||
for (const [key, liveKey] of [
|
||||
["x", "x"],
|
||||
["y", "y"],
|
||||
["w", "width"],
|
||||
["h", "height"],
|
||||
] as const)
|
||||
expect(
|
||||
Math.abs(live.topBounds[liveKey] - top[key]),
|
||||
`${id} live ${key}`,
|
||||
).toBeLessThan(2);
|
||||
const before = server.snapshot("coordinates").events.length;
|
||||
for (const type of ["mousePressed", "mouseReleased"])
|
||||
await send(
|
||||
"Input.dispatchMouseEvent",
|
||||
{ type, ...live.actionPoint, button: "left", clickCount: 1 },
|
||||
rootSession,
|
||||
);
|
||||
await expect
|
||||
.poll(
|
||||
() =>
|
||||
server
|
||||
.snapshot("coordinates")
|
||||
.events.slice(before)
|
||||
.some(
|
||||
(event: { type: string; path: string; data: { probe?: string } }) =>
|
||||
event.type === "geometry.clicked" &&
|
||||
event.data.probe === id &&
|
||||
event.path ===
|
||||
(frame.parentFrameId
|
||||
? names.get(frame.frameId) === "nested"
|
||||
? "/oopif-scrollbars/nested"
|
||||
: "/oopif-scrollbars/frame"
|
||||
: "/oopif-scrollbars"),
|
||||
),
|
||||
{ timeout: 3000 },
|
||||
)
|
||||
.toBe(true);
|
||||
}
|
||||
}
|
||||
const metrics = await send<{
|
||||
cssVisualViewport: { zoom: number };
|
||||
visualViewport: { clientWidth: number };
|
||||
}>("Page.getLayoutMetrics", {}, rootSession);
|
||||
expect(metrics.cssVisualViewport.zoom).toBeCloseTo(configuration.zoom, 4);
|
||||
},
|
||||
);
|
||||
} finally {
|
||||
await server.stop();
|
||||
}
|
||||
}, 30_000);
|
||||
});
|
||||
@@ -11,7 +11,7 @@ function fakeAgentWindow(ids: number[]) {
|
||||
return id;
|
||||
},
|
||||
remove: async () => {},
|
||||
ensureActiveTab: async () => 1,
|
||||
ensureActiveTab: async () => {},
|
||||
};
|
||||
}
|
||||
|
||||
@@ -24,10 +24,14 @@ describe("lookupSnapshotRef", () => {
|
||||
expect(lookupSnapshotRef(ctx, "@e3", 4)).toEqual({
|
||||
backendNodeId: 1234,
|
||||
refKey: "e3",
|
||||
kind: "dom",
|
||||
capabilities: ["interact", "screenshot"],
|
||||
});
|
||||
expect(lookupSnapshotRef(ctx, "e3", 4)).toEqual({
|
||||
backendNodeId: 1234,
|
||||
refKey: "e3",
|
||||
kind: "dom",
|
||||
capabilities: ["interact", "screenshot"],
|
||||
});
|
||||
});
|
||||
|
||||
@@ -53,6 +57,8 @@ describe("resolveSnapshotRef", () => {
|
||||
tabId: 4,
|
||||
frameId: "child-frame",
|
||||
cdpSessionId: "child-session",
|
||||
kind: "dom",
|
||||
capabilities: ["interact", "screenshot"],
|
||||
});
|
||||
|
||||
const expected = {
|
||||
@@ -60,6 +66,8 @@ describe("resolveSnapshotRef", () => {
|
||||
refKey: "e3",
|
||||
frameId: "child-frame",
|
||||
cdpSessionId: "child-session",
|
||||
kind: "dom" as const,
|
||||
capabilities: ["interact", "screenshot"] as const,
|
||||
};
|
||||
expect(lookupSnapshotRef(ctx, "@e3", 4)).toEqual(expected);
|
||||
expect(resolveSnapshotRef(ctx, "@e3", 4)).toEqual(expected);
|
||||
@@ -105,6 +113,28 @@ describe("resolveSnapshotRef", () => {
|
||||
expect(resolveSnapshotRef(ctx, "@e3", 4)).toEqual({
|
||||
backendNodeId: 1234,
|
||||
refKey: "e3",
|
||||
kind: "dom",
|
||||
capabilities: ["interact", "screenshot"],
|
||||
});
|
||||
});
|
||||
|
||||
it("rejects an operation outside the ref's declared capabilities", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.refStore.set("e3", 1234, {
|
||||
tabId: 4,
|
||||
kind: "surface",
|
||||
capabilities: ["screenshot"],
|
||||
});
|
||||
|
||||
expect(resolveSnapshotRef(ctx, "@e3", 4, "interact")).toMatchObject({
|
||||
code: "permission_denied",
|
||||
message: "ref @e3 does not support interact",
|
||||
data: {
|
||||
reason: "ref_capability_denied",
|
||||
required_capability: "interact",
|
||||
kind: "surface",
|
||||
},
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,7 +1,5 @@
|
||||
import { describe, expect, it, vi } from "vitest";
|
||||
import { type CdpDebuggerApi, ChromiumCdp } from "@/browser-driver/chromium-cdp";
|
||||
import { SessionManager } from "@/session-manager/manager";
|
||||
import { handleHover } from "../interaction";
|
||||
import {
|
||||
type AgentOverlayResetApi,
|
||||
type ChromeWindowsApi,
|
||||
@@ -25,7 +23,7 @@ function fakeAgentWindow(ids: number[]) {
|
||||
return id;
|
||||
}),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
};
|
||||
}
|
||||
|
||||
@@ -223,7 +221,6 @@ describe("handleTabCreate", () => {
|
||||
active: true,
|
||||
});
|
||||
expect(res).toMatchObject({ tab_id: 10, window_id: 100 });
|
||||
expect(sm.get("aa11")?.agentCreatedTabs.has(10)).toBe(true);
|
||||
});
|
||||
|
||||
it("forwards explicit url + index + active=false", async () => {
|
||||
@@ -259,41 +256,6 @@ describe("handleTabCreate", () => {
|
||||
const res = await handleTabCreate(sm, { session_id: "aa11", index: -1 }, { tabs: api });
|
||||
expect(res).toMatchObject({ code: "invalid_params" });
|
||||
});
|
||||
|
||||
it("does not claim any tab when chrome.tabs.create fails", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
await sm.start("aa11");
|
||||
const state: FakeTabState = { tabs: new Map(), nextTabId: 10, windowsClosed: new Set() };
|
||||
const { api, spies } = makeTabMutationApi(state);
|
||||
spies.create.mockRejectedValueOnce(new Error("chrome.tabs.create failed"));
|
||||
|
||||
const res = await handleTabCreate(sm, { session_id: "aa11" }, { tabs: api });
|
||||
expect(res).toMatchObject({ code: "protocol_error" });
|
||||
|
||||
expect(sm.get("aa11")?.agentCreatedTabs).toEqual(new Set([1]));
|
||||
});
|
||||
|
||||
it("claims the returned id even when a user tab appears during tab creation", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
const ctx = await sm.start("aa11");
|
||||
const state: FakeTabState = { tabs: new Map(), nextTabId: 10, windowsClosed: new Set() };
|
||||
const { api, spies } = makeTabMutationApi(state);
|
||||
let resolveCreate!: (tab: chrome.tabs.Tab) => void;
|
||||
const createResult = new Promise<chrome.tabs.Tab>((resolve) => {
|
||||
resolveCreate = resolve;
|
||||
});
|
||||
spies.create.mockImplementationOnce(() => createResult);
|
||||
|
||||
const pending = handleTabCreate(sm, { session_id: "aa11" }, { tabs: api });
|
||||
// A user can create an unrelated same-window tab while Chrome is still
|
||||
// resolving the agent request. There is no pending slot for it to steal.
|
||||
expect(ctx.agentCreatedTabs.has(99)).toBe(false);
|
||||
resolveCreate({ id: 10, windowId: 100, active: true } as chrome.tabs.Tab);
|
||||
|
||||
await expect(pending).resolves.toMatchObject({ tab_id: 10 });
|
||||
expect(ctx.agentCreatedTabs.has(10)).toBe(true);
|
||||
expect(ctx.agentCreatedTabs.has(99)).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("handleTabClose", () => {
|
||||
@@ -549,148 +511,6 @@ describe("handleTabBorrow", () => {
|
||||
});
|
||||
|
||||
describe("handleTabReturn", () => {
|
||||
it.each([
|
||||
"not_found",
|
||||
"cdp_failed",
|
||||
])("detaches after selector resolution fails with %s", async (code) => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.borrowedTabs.set(7, { tabId: 7, originalWindowId: 200, originalIndex: 4 });
|
||||
const state: FakeTabState = {
|
||||
tabs: new Map([[7, { id: 7, windowId: 100 } as chrome.tabs.Tab]]),
|
||||
nextTabId: 50,
|
||||
windowsClosed: new Set(),
|
||||
};
|
||||
const { api } = makeTabMutationApi(state);
|
||||
const { api: windows } = makeWindowsApi(state);
|
||||
const debuggerApi = {
|
||||
attach: vi.fn(async () => {}),
|
||||
detach: vi.fn(async () => {}),
|
||||
sendCommand: vi.fn(async (_target: unknown, method: string) => {
|
||||
if (method === "DOM.getDocument") return { root: { nodeId: 1 } };
|
||||
if (method === "DOM.querySelector") {
|
||||
if (code === "cdp_failed") throw new Error("selector query failed");
|
||||
return { nodeId: 0 };
|
||||
}
|
||||
return {};
|
||||
}),
|
||||
onEvent: { addListener: vi.fn(), removeListener: vi.fn() },
|
||||
onDetach: { addListener: vi.fn(), removeListener: vi.fn() },
|
||||
};
|
||||
const cdp = new ChromiumCdp(debuggerApi as unknown as CdpDebuggerApi);
|
||||
|
||||
const hover = await handleHover(
|
||||
sm,
|
||||
{ session_id: "aa11", tab_id: 7, selector: "#missing" },
|
||||
{
|
||||
cdp,
|
||||
tabsApi: { get: api.get, query: vi.fn(async () => []) },
|
||||
},
|
||||
);
|
||||
expect(hover).toMatchObject({ code });
|
||||
expect(cdp.isAttached(7)).toBe(true);
|
||||
|
||||
const returned = await handleTabReturn(
|
||||
sm,
|
||||
{ session_id: "aa11", tab_id: 7 },
|
||||
{
|
||||
tabs: api,
|
||||
windows,
|
||||
cdp,
|
||||
agentOverlayReset: { resetAgentOverlays: vi.fn(async () => {}) },
|
||||
},
|
||||
);
|
||||
expect(returned).toMatchObject({ returned_to_window_id: 200 });
|
||||
expect(ctx.borrowedTabs.has(7)).toBe(false);
|
||||
expect(cdp.isAttached(7)).toBe(false);
|
||||
expect(debuggerApi.detach).toHaveBeenCalledExactlyOnceWith({ tabId: 7 });
|
||||
cdp.dispose();
|
||||
});
|
||||
|
||||
it("honours cancellation while preparing a validated return", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.borrowedTabs.set(7, { tabId: 7, originalWindowId: 200, originalIndex: 4 });
|
||||
const state: FakeTabState = {
|
||||
tabs: new Map([[7, { id: 7, windowId: 100 } as chrome.tabs.Tab]]),
|
||||
nextTabId: 50,
|
||||
windowsClosed: new Set(),
|
||||
};
|
||||
const { api, spies } = makeTabMutationApi(state);
|
||||
const { api: windows } = makeWindowsApi(state);
|
||||
const controller = new AbortController();
|
||||
const beforeReturn = vi.fn(async () => {
|
||||
controller.abort();
|
||||
});
|
||||
const result = await handleTabReturn(
|
||||
sm,
|
||||
{ session_id: "aa11", tab_id: 7 },
|
||||
{
|
||||
tabs: api,
|
||||
windows,
|
||||
signal: controller.signal,
|
||||
beforeReturn,
|
||||
},
|
||||
);
|
||||
|
||||
expect(result).toMatchObject({ code: "cancelled" });
|
||||
expect(beforeReturn).toHaveBeenCalledExactlyOnceWith("aa11", 7);
|
||||
expect(spies.move).not.toHaveBeenCalled();
|
||||
expect(ctx.borrowedTabs.has(7)).toBe(true);
|
||||
});
|
||||
|
||||
it.each([
|
||||
"original",
|
||||
"fallback",
|
||||
"cleanup_failed",
|
||||
"failed",
|
||||
"cancelled",
|
||||
])("releases CDP only after a successful return (%s)", async (mode) => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
const ctx = await sm.start("aa11");
|
||||
ctx.borrowedTabs.set(7, { tabId: 7, originalWindowId: 200, originalIndex: 4 });
|
||||
const state: FakeTabState = {
|
||||
tabs: new Map([[7, { id: 7, windowId: 100 } as chrome.tabs.Tab]]),
|
||||
nextTabId: 50,
|
||||
windowsClosed: new Set(),
|
||||
};
|
||||
const { api, spies } = makeTabMutationApi(state);
|
||||
const { api: windowsApi } = makeWindowsApi(state, { lastFocused: 500 });
|
||||
const success = mode !== "failed" && mode !== "cancelled";
|
||||
if (mode === "fallback") spies.move.mockRejectedValueOnce(new Error("original move failed"));
|
||||
if (mode === "failed") spies.move.mockRejectedValue(new Error("move failed"));
|
||||
let windowAtRelease: number | undefined;
|
||||
const cdp = {
|
||||
releaseSessionTab: vi.fn(async () => {
|
||||
windowAtRelease = state.tabs.get(7)?.windowId;
|
||||
if (mode === "cleanup_failed") throw new Error("debugger release failed");
|
||||
}),
|
||||
};
|
||||
const controller = new AbortController();
|
||||
if (mode === "cancelled") controller.abort();
|
||||
|
||||
const result = await handleTabReturn(
|
||||
sm,
|
||||
{ session_id: "aa11", tab_id: 7 },
|
||||
{
|
||||
tabs: api,
|
||||
windows: windowsApi,
|
||||
cdp,
|
||||
signal: controller.signal,
|
||||
agentOverlayReset: { resetAgentOverlays: vi.fn(async () => {}) },
|
||||
},
|
||||
);
|
||||
|
||||
expect("code" in result).toBe(!success);
|
||||
expect(ctx.borrowedTabs.has(7)).toBe(!success);
|
||||
expect(cdp.releaseSessionTab).toHaveBeenCalledTimes(success ? 1 : 0);
|
||||
if (success) {
|
||||
expect(cdp.releaseSessionTab).toHaveBeenCalledWith("aa11", 7);
|
||||
expect(windowAtRelease).toBe(mode === "fallback" ? 500 : 200);
|
||||
expect(spies.move).toHaveBeenCalledTimes(mode === "fallback" ? 2 : 1);
|
||||
}
|
||||
});
|
||||
|
||||
it("returns the tab to its original window/index and clears borrowedTabs", async () => {
|
||||
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
|
||||
const ctx = await sm.start("aa11");
|
||||
|
||||
@@ -1,208 +0,0 @@
|
||||
import { afterEach, describe, expect, it, vi } from "vitest";
|
||||
import { SessionManager } from "@/session-manager/manager";
|
||||
import { RefStore, type VisualRefInput } from "@/session-manager/ref-store";
|
||||
import { handleDownload } from "../download";
|
||||
import { handleRequestHelp, resetHelpLifecycleForTests } from "../human-loop";
|
||||
import { handleClick, handleFill, handleHover, handlePress, handleSelect } from "../interaction";
|
||||
import { handleGetHtml, handleScreenshot } from "../observation";
|
||||
import type { CdpRunner } from "../shared";
|
||||
import { lookupRefTarget, lookupSnapshotRef, resolveSnapshotRef } from "../snapshot-ref";
|
||||
import { handleUpload } from "../upload";
|
||||
|
||||
function visual(): VisualRefInput {
|
||||
return {
|
||||
kind: "visual-region",
|
||||
candidate: {
|
||||
document: {
|
||||
attachmentId: "a",
|
||||
target: { tabId: 4, sessionId: "child" },
|
||||
frameId: "frame",
|
||||
documentElementBackendNodeId: 1,
|
||||
},
|
||||
backendNodeId: 42,
|
||||
parentBackendNodeId: 1,
|
||||
region: {
|
||||
status: "available",
|
||||
borderBox: { x: 0, y: 0, width: 100, height: 50 },
|
||||
crop: { x: 0, y: 0, width: 100, height: 50 },
|
||||
},
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
async function setup() {
|
||||
const manager = new SessionManager({
|
||||
agentWindow: {
|
||||
create: async () => 100,
|
||||
remove: async () => {},
|
||||
ensureActiveTab: async () => 4,
|
||||
},
|
||||
});
|
||||
const ctx = await manager.start("test");
|
||||
ctx.refStore.replace([
|
||||
["e1", visual()],
|
||||
["e2", { backendNodeId: 43, tabId: 4 }],
|
||||
]);
|
||||
const send = vi.fn(async () => {
|
||||
throw new Error("unexpected target operation");
|
||||
});
|
||||
const cdp = { send, sendToTarget: send, trackSessionTab: vi.fn() } as unknown as CdpRunner;
|
||||
const tab = { id: 4, windowId: 100, active: true, url: "https://example.com" } as chrome.tabs.Tab;
|
||||
const tabsApi = { get: vi.fn(async () => tab), query: vi.fn(async () => [tab]) };
|
||||
return { manager, ctx, send, cdp, tabsApi };
|
||||
}
|
||||
|
||||
describe("typed visual refs", () => {
|
||||
afterEach(() => resetHelpLifecycleForTests());
|
||||
|
||||
it("keeps candidate evidence and cannot resolve a visual anchor as a bare DOM node", () => {
|
||||
const store = new RefStore();
|
||||
const input = visual();
|
||||
store.replace([
|
||||
["@e1", input],
|
||||
["e2", { backendNodeId: 43, tabId: 4 }],
|
||||
]);
|
||||
const entry = store.resolveEntry("e1");
|
||||
expect(entry?.kind).toBe("visual-region");
|
||||
if (entry?.kind !== "visual-region") throw new Error("missing visual ref");
|
||||
expect(entry.candidate).toBe(input.candidate);
|
||||
expect(entry.generation).toBe(1);
|
||||
expect(store.resolve("@e1")).toBeNull();
|
||||
expect(store.resolve("e2")).toBe(43);
|
||||
// The latest observation replaces both target kinds; eN strings carry no generation.
|
||||
store.replace([["e1", { backendNodeId: 99, tabId: 4 }]]);
|
||||
expect(store.resolve("e1")).toBe(99);
|
||||
expect(store.resolveEntry("e1")).toMatchObject({ kind: "dom", generation: 2 });
|
||||
expect(store.resolveEntry("e2")).toBeNull();
|
||||
});
|
||||
|
||||
it("rejects missing visual identity without partially publishing a replacement", () => {
|
||||
const store = new RefStore();
|
||||
store.set("e1", 10, { tabId: 4 });
|
||||
const invalid = visual();
|
||||
invalid.candidate.document.attachmentId = "";
|
||||
expect(() =>
|
||||
store.replace([
|
||||
["e2", 20],
|
||||
["e3", invalid],
|
||||
]),
|
||||
).toThrow(TypeError);
|
||||
expect(store.resolveEntry("e1")).toMatchObject({ generation: 0, backendNodeId: 10 });
|
||||
expect(store.size()).toBe(1);
|
||||
store.replace([["e1", visual()]]);
|
||||
expect(store.resolveEntry("e1")?.generation).toBe(1);
|
||||
});
|
||||
|
||||
it("isolates tabs/sessions and distinguishes unsupported targets from missing refs", async () => {
|
||||
const { ctx } = await setup();
|
||||
expect(lookupRefTarget(ctx, "@e1", 4)?.kind).toBe("visual-region");
|
||||
expect(lookupRefTarget(ctx, "e1", 5)).toBeNull();
|
||||
expect(lookupSnapshotRef(ctx, "e1", 4)).toBeNull();
|
||||
expect(resolveSnapshotRef(ctx, "e1", 4)).toMatchObject({
|
||||
code: "unsupported",
|
||||
data: { reason: "ref_kind_unsupported" },
|
||||
});
|
||||
expect(resolveSnapshotRef(ctx, "e1", 5)).toMatchObject({
|
||||
code: "not_found",
|
||||
data: { reason: "ref_not_found" },
|
||||
});
|
||||
expect(lookupRefTarget({ ...ctx, refStore: new RefStore() }, "e1", 4)).toBeNull();
|
||||
expect(lookupSnapshotRef(ctx, "e2", 4)).toMatchObject({ backendNodeId: 43 });
|
||||
});
|
||||
|
||||
it.each([
|
||||
"click",
|
||||
"fill",
|
||||
"hover",
|
||||
"press",
|
||||
"select",
|
||||
"get_html",
|
||||
"screenshot",
|
||||
])("rejects visual refs in %s before target effects", async (tool) => {
|
||||
const { manager, send, cdp, tabsApi } = await setup();
|
||||
const params = { session_id: "test", tab_id: 4, ref: "@e1" };
|
||||
const deps = { cdp, tabsApi };
|
||||
const captureVisibleTab = vi.fn();
|
||||
let result: unknown;
|
||||
switch (tool) {
|
||||
case "click":
|
||||
result = await handleClick(manager, params, deps);
|
||||
break;
|
||||
case "fill":
|
||||
result = await handleFill(manager, { ...params, value: "hello" }, deps);
|
||||
break;
|
||||
case "hover":
|
||||
result = await handleHover(manager, params, deps);
|
||||
break;
|
||||
case "press":
|
||||
result = await handlePress(manager, { ...params, key: "Enter" }, deps);
|
||||
break;
|
||||
case "select":
|
||||
result = await handleSelect(manager, { ...params, values: ["one"] }, deps);
|
||||
break;
|
||||
case "get_html":
|
||||
result = await handleGetHtml(manager, params, deps);
|
||||
break;
|
||||
case "screenshot":
|
||||
result = await handleScreenshot(manager, params, {
|
||||
...deps,
|
||||
captureApi: { ...tabsApi, captureVisibleTab },
|
||||
});
|
||||
break;
|
||||
}
|
||||
expect(result).toMatchObject({ code: "unsupported", data: { reason: "ref_kind_unsupported" } });
|
||||
expect(send).not.toHaveBeenCalled();
|
||||
expect(captureVisibleTab).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it.each([
|
||||
"input",
|
||||
"drop",
|
||||
"download",
|
||||
] as const)("rejects visual refs before %s file-transfer setup", async (mode) => {
|
||||
const { manager, send, cdp, tabsApi } = await setup();
|
||||
const params = { session_id: "test", tab_id: 4, ref: "e1" };
|
||||
const result =
|
||||
mode === "download"
|
||||
? await handleDownload(
|
||||
manager,
|
||||
{ ...params, browser_relative_dir: "test" },
|
||||
{ cdp, tabsApi },
|
||||
)
|
||||
: await handleUpload(
|
||||
manager,
|
||||
{
|
||||
...params,
|
||||
mode,
|
||||
files: [{ transfer_id: "test", name: "test.txt", staged_path: "/unused/test.txt" }],
|
||||
},
|
||||
{ cdp, tabsApi },
|
||||
);
|
||||
expect(result).toMatchObject({ code: "unsupported", data: { reason: "ref_kind_unsupported" } });
|
||||
expect(send).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("does not scroll or highlight a visual anchor in human help", async () => {
|
||||
const { manager, cdp, tabsApi, send } = await setup();
|
||||
const sendToTab = vi.fn(async (_tab: number, _message: unknown) => ({
|
||||
type: "bsk-help-response",
|
||||
outcome: "continued",
|
||||
}));
|
||||
const result = await handleRequestHelp(
|
||||
manager,
|
||||
{ session_id: "test", tab_id: 4, prompt: "help", targets: [{ ref: "@e1" }] },
|
||||
{
|
||||
cdp,
|
||||
tabsApi,
|
||||
sendToTab,
|
||||
windows: { update: vi.fn(async () => ({}) as never) },
|
||||
activateTab: vi.fn(async () => {}),
|
||||
notifications: null,
|
||||
autoAttachLifecycle: false,
|
||||
},
|
||||
);
|
||||
expect(result).toMatchObject({ resolved_targets: [{ ref: "@e1", matched: false }] });
|
||||
expect(send).not.toHaveBeenCalled();
|
||||
expect(sendToTab.mock.calls[0][1]).toMatchObject({ rects: [], selectors: [] });
|
||||
});
|
||||
});
|
||||
@@ -12,7 +12,7 @@ function fakeAgentWindow(ids: number[]) {
|
||||
return id;
|
||||
}),
|
||||
remove: vi.fn(async () => {}),
|
||||
ensureActiveTab: vi.fn(async () => 1),
|
||||
ensureActiveTab: vi.fn(async () => {}),
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
@@ -11,7 +11,7 @@ function fakeAgentWindow(ids: number[]) {
|
||||
return id;
|
||||
});
|
||||
const remove = vi.fn(async () => {});
|
||||
const ensureActiveTab = vi.fn(async () => 1);
|
||||
const ensureActiveTab = vi.fn(async () => {});
|
||||
return { create, remove, ensureActiveTab };
|
||||
}
|
||||
|
||||
|
||||
@@ -1,110 +0,0 @@
|
||||
import type { RpcError, WaitUntil } from "@/transport/types";
|
||||
import { cdpError } from "./errors";
|
||||
|
||||
interface NavigationEvent {
|
||||
tabId: number;
|
||||
frameId: number;
|
||||
documentId?: string;
|
||||
error?: string;
|
||||
}
|
||||
|
||||
interface NavigationEvents {
|
||||
addListener(listener: (details: NavigationEvent) => void): void;
|
||||
removeListener(listener: (details: NavigationEvent) => void): void;
|
||||
}
|
||||
|
||||
/** Normal browser navigation remains available when chrome.debugger is denied. */
|
||||
export interface BrowserNavigationApi {
|
||||
update(tabId: number, props: { url: string }): Promise<unknown>;
|
||||
reload(tabId: number, props: { bypassCache: boolean }): Promise<void>;
|
||||
onCommitted: NavigationEvents;
|
||||
onDOMContentLoaded: NavigationEvents;
|
||||
onCompleted: NavigationEvents;
|
||||
onErrorOccurred: NavigationEvents;
|
||||
}
|
||||
|
||||
export const chromeBrowserNavigationApi: BrowserNavigationApi = {
|
||||
update: (tabId, props) => chrome.tabs.update(tabId, props),
|
||||
reload: (tabId, props) => chrome.tabs.reload(tabId, props),
|
||||
get onCommitted() {
|
||||
return chrome.webNavigation.onCommitted;
|
||||
},
|
||||
get onDOMContentLoaded() {
|
||||
return chrome.webNavigation.onDOMContentLoaded;
|
||||
},
|
||||
get onCompleted() {
|
||||
return chrome.webNavigation.onCompleted;
|
||||
},
|
||||
get onErrorOccurred() {
|
||||
return chrome.webNavigation.onErrorOccurred;
|
||||
},
|
||||
};
|
||||
|
||||
export type NavigationOutcome =
|
||||
| { reached: "match" | "timeout" | "cancelled"; lastLifecycle?: string }
|
||||
| { reached: "failed"; error: RpcError };
|
||||
|
||||
/** Subscribe before dispatch and ignore the departing document's load events. */
|
||||
export async function navigateWithBrowserApi(
|
||||
api: BrowserNavigationApi,
|
||||
tabId: number,
|
||||
action: () => Promise<unknown>,
|
||||
waitUntil: Exclude<WaitUntil, "networkidle">,
|
||||
timeoutMs: number,
|
||||
signal?: AbortSignal,
|
||||
): Promise<NavigationOutcome> {
|
||||
if (signal?.aborted) return { reached: "cancelled" };
|
||||
if (timeoutMs <= 0) return { reached: "timeout" };
|
||||
let committed = false;
|
||||
let documentId: string | undefined;
|
||||
let lastLifecycle: string | undefined;
|
||||
let finish!: (outcome: NavigationOutcome) => void;
|
||||
const outcome = new Promise<NavigationOutcome>((resolve) => {
|
||||
finish = resolve;
|
||||
});
|
||||
const isMainFrame = (details: NavigationEvent) =>
|
||||
details.tabId === tabId && details.frameId === 0;
|
||||
const onCommitted = (details: NavigationEvent) => {
|
||||
if (!isMainFrame(details)) return;
|
||||
committed = true;
|
||||
documentId = details.documentId;
|
||||
lastLifecycle = "commit";
|
||||
if (waitUntil === "commit") finish({ reached: "match", lastLifecycle });
|
||||
};
|
||||
const onDOMContentLoaded = (details: NavigationEvent) => {
|
||||
if (!isMainFrame(details) || !committed || (documentId && details.documentId !== documentId))
|
||||
return;
|
||||
lastLifecycle = "DOMContentLoaded";
|
||||
if (waitUntil === "domcontentloaded") finish({ reached: "match", lastLifecycle });
|
||||
};
|
||||
const onCompleted = (details: NavigationEvent) => {
|
||||
if (!isMainFrame(details) || !committed || (documentId && details.documentId !== documentId))
|
||||
return;
|
||||
finish({ reached: "match", lastLifecycle: "load" });
|
||||
};
|
||||
const onError = (details: NavigationEvent) => {
|
||||
if (!isMainFrame(details)) return;
|
||||
finish({ reached: "failed", error: cdpError(details.error ?? "browser navigation failed") });
|
||||
};
|
||||
const onAbort = () => finish({ reached: "cancelled", lastLifecycle });
|
||||
const subscriptions = [
|
||||
[api.onCommitted, onCommitted],
|
||||
[api.onDOMContentLoaded, onDOMContentLoaded],
|
||||
[api.onCompleted, onCompleted],
|
||||
[api.onErrorOccurred, onError],
|
||||
] as const;
|
||||
for (const [event, listener] of subscriptions) event.addListener(listener);
|
||||
signal?.addEventListener("abort", onAbort, { once: true });
|
||||
const timer = setTimeout(() => finish({ reached: "timeout", lastLifecycle }), timeoutMs);
|
||||
try {
|
||||
if (signal?.aborted) return { reached: "cancelled" };
|
||||
await action();
|
||||
return await outcome;
|
||||
} catch (error) {
|
||||
return { reached: "failed", error: cdpError(error) };
|
||||
} finally {
|
||||
clearTimeout(timer);
|
||||
signal?.removeEventListener("abort", onAbort);
|
||||
for (const [event, listener] of subscriptions) event.removeListener(listener);
|
||||
}
|
||||
}
|
||||
@@ -2,14 +2,12 @@ import { OVERLAY_AUTOMATION_BYPASS } from "@/lib/overlay-bridge";
|
||||
import type { SessionManager } from "@/session-manager/manager";
|
||||
import type { Transport } from "@/transport/transport";
|
||||
import type {
|
||||
BlurParams,
|
||||
ClickParams,
|
||||
ConsoleParams,
|
||||
DownloadParams,
|
||||
EmulateParams,
|
||||
EvaluateParams,
|
||||
FillParams,
|
||||
FocusParams,
|
||||
GetHtmlParams,
|
||||
HoverParams,
|
||||
HoverResult,
|
||||
@@ -29,7 +27,6 @@ import type {
|
||||
ResponseFrame,
|
||||
RpcError,
|
||||
ScreenshotParams,
|
||||
ScrollToParams,
|
||||
SelectParams,
|
||||
SnapshotParams,
|
||||
UploadParams,
|
||||
@@ -39,18 +36,9 @@ import { isRequestFrame } from "@/transport/types";
|
||||
import { handleConsole } from "./console";
|
||||
import { handleDownload } from "./download";
|
||||
import { type EmulateCdpRunner, handleEmulate } from "./emulate";
|
||||
import { classifyCdpError } from "./errors";
|
||||
import { handleEvaluate } from "./evaluate";
|
||||
import { handleRequestHelp } from "./human-loop";
|
||||
import {
|
||||
handleBlur,
|
||||
handleClick,
|
||||
handleFill,
|
||||
handleFocus,
|
||||
handleHover,
|
||||
handlePress,
|
||||
handleSelect,
|
||||
} from "./interaction";
|
||||
import { handleClick, handleFill, handleHover, handlePress, handleSelect } from "./interaction";
|
||||
import {
|
||||
handleNavigate,
|
||||
handleNavigateBack,
|
||||
@@ -72,7 +60,6 @@ import {
|
||||
handleRecordStop,
|
||||
type RecordRuntimeDeps,
|
||||
} from "./record";
|
||||
import { handleScrollTo } from "./scroll";
|
||||
import {
|
||||
handleSessionStart,
|
||||
handleSessionStop,
|
||||
@@ -82,7 +69,6 @@ import {
|
||||
import { chromeTabsApi, lookupSession, resolveTargetTab } from "./shared";
|
||||
import {
|
||||
type BorrowConfirmationApprover,
|
||||
chromeTabMutationApi,
|
||||
handleTabBorrow,
|
||||
handleTabClose,
|
||||
handleTabCreate,
|
||||
@@ -132,8 +118,6 @@ export interface DispatcherDeps {
|
||||
onSessionsChanged?: () => void;
|
||||
/** Invoked before a tool that dispatches page input or mutates browser state is forwarded. */
|
||||
onBrowserControlResumed?: (sessionId: string) => void;
|
||||
/** Invoked after a tab is explicitly claimed so its overlay can be refreshed immediately. */
|
||||
onAgentTabClaimed?: (tabId: number, windowId: number) => void;
|
||||
/** User approval for `tool.tab_borrow` (overlay in content script). */
|
||||
approveBorrow?: BorrowConfirmationApprover;
|
||||
/** i18n notification copy for `tool.request_help` (resolved per-call). */
|
||||
@@ -163,7 +147,6 @@ export class ToolDispatcher {
|
||||
private readonly recording?: RecordRuntimeDeps;
|
||||
private readonly onSessionsChanged?: () => void;
|
||||
private readonly onBrowserControlResumed?: (sessionId: string) => void;
|
||||
private readonly onAgentTabClaimed?: (tabId: number, windowId: number) => void;
|
||||
private readonly approveBorrow?: BorrowConfirmationApprover;
|
||||
private readonly helpNotificationCopy?: () => { title: string; body: string };
|
||||
private subscription: { dispose(): void } | null = null;
|
||||
@@ -184,7 +167,6 @@ export class ToolDispatcher {
|
||||
this.recording = deps.recording;
|
||||
this.onSessionsChanged = deps.onSessionsChanged;
|
||||
this.onBrowserControlResumed = deps.onBrowserControlResumed;
|
||||
this.onAgentTabClaimed = deps.onAgentTabClaimed;
|
||||
this.approveBorrow = deps.approveBorrow;
|
||||
this.helpNotificationCopy = deps.helpNotificationCopy;
|
||||
}
|
||||
@@ -252,7 +234,7 @@ export class ToolDispatcher {
|
||||
if (sessionId) this.onBrowserControlResumed?.(sessionId);
|
||||
const result = await this.invoke(req, ac.signal);
|
||||
if (isRpcError(result)) {
|
||||
body = { id: req.id, error: classifyCdpError(result) };
|
||||
body = { id: req.id, error: result };
|
||||
} else {
|
||||
body = { id: req.id, result };
|
||||
if (req.method === "tool.session_start") {
|
||||
@@ -320,25 +302,13 @@ export class ToolDispatcher {
|
||||
await this.releaseHoverLatch((req.params as SessionStopParams).session_id);
|
||||
return handleSessionStop(this.sessions, req.params as SessionStopParams, {
|
||||
cdp: this.cdp,
|
||||
// Must be wired in production: the agent-tab cleanup and the
|
||||
// window-release decision (issue #57) read these deps directly
|
||||
// and silently no-op when they are absent.
|
||||
tabManagement: { tabs: chromeTabMutationApi },
|
||||
tabsQuery: chromeTabsApi,
|
||||
signal,
|
||||
});
|
||||
}
|
||||
case "tool.tab_list":
|
||||
return handleTabList(this.sessions, req.params as TabListParams, chromeTabsApi, signal);
|
||||
case "tool.tab_create": {
|
||||
const result = await handleTabCreate(this.sessions, req.params as TabCreateParams, {
|
||||
signal,
|
||||
});
|
||||
if (!isRpcError(result)) {
|
||||
this.onAgentTabClaimed?.(result.tab_id, result.window_id);
|
||||
}
|
||||
return result;
|
||||
}
|
||||
case "tool.tab_create":
|
||||
return handleTabCreate(this.sessions, req.params as TabCreateParams, { signal });
|
||||
case "tool.tab_close":
|
||||
return this.withHoverReleaseForRequest(
|
||||
req.params as TabCloseParams,
|
||||
@@ -347,22 +317,13 @@ export class ToolDispatcher {
|
||||
);
|
||||
case "tool.tab_select":
|
||||
return handleTabSelect(this.sessions, req.params as TabSelectParams, { signal });
|
||||
case "tool.tab_borrow": {
|
||||
const result = await handleTabBorrow(this.sessions, req.params as TabBorrowParams, {
|
||||
case "tool.tab_borrow":
|
||||
return handleTabBorrow(this.sessions, req.params as TabBorrowParams, {
|
||||
signal,
|
||||
approveBorrow: this.approveBorrow,
|
||||
});
|
||||
if (!isRpcError(result)) {
|
||||
this.onAgentTabClaimed?.(result.tab_id, result.agent_window_id);
|
||||
}
|
||||
return result;
|
||||
}
|
||||
case "tool.tab_return":
|
||||
return handleTabReturn(this.sessions, req.params as TabReturnParams, {
|
||||
signal,
|
||||
cdp: this.cdp,
|
||||
beforeReturn: (sessionId, tabId) => this.releaseHoverLatch(sessionId, tabId),
|
||||
});
|
||||
return handleTabReturn(this.sessions, req.params as TabReturnParams, { signal });
|
||||
case "tool.window_resize":
|
||||
return handleWindowResize(
|
||||
this.sessions,
|
||||
@@ -527,39 +488,6 @@ export class ToolDispatcher {
|
||||
);
|
||||
return this.rememberHover((req.params as HoverParams).session_id, result);
|
||||
}
|
||||
case "tool.scroll_to":
|
||||
return this.withHoverReleaseForRequest(
|
||||
req.params as ScrollToParams,
|
||||
() =>
|
||||
handleScrollTo(
|
||||
this.sessions,
|
||||
req.params as ScrollToParams,
|
||||
this.cdp ? { cdp: this.cdp, tabsApi: chromeTabsApi, signal } : undefined,
|
||||
),
|
||||
signal,
|
||||
);
|
||||
case "tool.focus":
|
||||
return this.withHoverReleaseForRequest(
|
||||
req.params as FocusParams,
|
||||
() =>
|
||||
handleFocus(
|
||||
this.sessions,
|
||||
req.params as FocusParams,
|
||||
this.cdp ? { cdp: this.cdp, tabsApi: chromeTabsApi, signal } : undefined,
|
||||
),
|
||||
signal,
|
||||
);
|
||||
case "tool.blur":
|
||||
return this.withHoverReleaseForRequest(
|
||||
req.params as BlurParams,
|
||||
() =>
|
||||
handleBlur(
|
||||
this.sessions,
|
||||
req.params as BlurParams,
|
||||
this.cdp ? { cdp: this.cdp, tabsApi: chromeTabsApi, signal } : undefined,
|
||||
),
|
||||
signal,
|
||||
);
|
||||
case "tool.fill":
|
||||
return this.withHoverReleaseForRequest(
|
||||
req.params as FillParams,
|
||||
@@ -830,9 +758,6 @@ function sessionIdForBrowserControlMethod(req: RequestFrame): string | null {
|
||||
case "tool.reload":
|
||||
case "tool.click":
|
||||
case "tool.hover":
|
||||
case "tool.scroll_to":
|
||||
case "tool.focus":
|
||||
case "tool.blur":
|
||||
case "tool.fill":
|
||||
case "tool.press":
|
||||
case "tool.select":
|
||||
|
||||
@@ -9,6 +9,8 @@ import { type CdpRunner, isRpcError } from "./shared";
|
||||
|
||||
const CORRELATION_GRACE_MS = 750;
|
||||
const UNIQUE_SETTLE_MS = 50;
|
||||
const CLEANUP_RECONCILE_MS = 1_000;
|
||||
const CLEANUP_POLL_MS = 25;
|
||||
const SIZE_POLL_MS = 250;
|
||||
|
||||
type DeterminingFilenameListener = (
|
||||
@@ -110,26 +112,35 @@ function captureError(
|
||||
|
||||
async function cleanupClaimedDownload(downloads: DownloadsApi, downloadId: number): Promise<void> {
|
||||
const lookup = async () => (await downloads.search({ id: downloadId }))[0];
|
||||
const item = await lookup();
|
||||
let item = await lookup();
|
||||
if (!item || item.state === "interrupted") return;
|
||||
if (item.state === "complete") {
|
||||
await downloads.removeFile(downloadId);
|
||||
return;
|
||||
}
|
||||
|
||||
let cancelError: unknown;
|
||||
try {
|
||||
await downloads.cancel(downloadId);
|
||||
} catch (cancelError) {
|
||||
// Completion can win the race after the lookup but before cancellation.
|
||||
// Reconcile against Chrome's authoritative state before declaring cleanup
|
||||
// failed so every terminal state has one explicit cleanup path.
|
||||
const reconciled = await lookup();
|
||||
if (!reconciled || reconciled.state === "interrupted") return;
|
||||
if (reconciled.state === "complete") {
|
||||
} catch (error) {
|
||||
cancelError = error;
|
||||
}
|
||||
|
||||
const deadline = Date.now() + CLEANUP_RECONCILE_MS;
|
||||
while (true) {
|
||||
item = await lookup();
|
||||
if (!item || item.state === "interrupted") return;
|
||||
if (item.state === "complete") {
|
||||
await downloads.removeFile(downloadId);
|
||||
return;
|
||||
}
|
||||
throw cancelError;
|
||||
if (Date.now() >= deadline) {
|
||||
if (cancelError instanceof Error) throw cancelError;
|
||||
throw new Error("download remained in progress after cancellation");
|
||||
}
|
||||
await new Promise((resolve) =>
|
||||
setTimeout(resolve, Math.min(CLEANUP_POLL_MS, Math.max(1, deadline - Date.now()))),
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -13,34 +13,6 @@ import type {
|
||||
|
||||
export type { RpcErrorData, RpcErrorReason };
|
||||
|
||||
/** Chrome checks the whole tab's frame tree, including other extensions' frames. */
|
||||
export function isCdpExtensionAccessDenied(error: unknown): boolean {
|
||||
const message = error instanceof Error ? error.message : String(error);
|
||||
return message.includes("Cannot access a chrome-extension:// URL of different extension");
|
||||
}
|
||||
|
||||
/** Preserve more specific reasons, especially file-transfer outcome/cleanup details. */
|
||||
export function classifyCdpError(error: RpcError): RpcError {
|
||||
if (
|
||||
error.code !== "cdp_failed" ||
|
||||
error.data?.reason ||
|
||||
!isCdpExtensionAccessDenied(error.message)
|
||||
) {
|
||||
return error;
|
||||
}
|
||||
return {
|
||||
...error,
|
||||
data: { ...error.data, reason: "cdp_extension_access_denied" },
|
||||
};
|
||||
}
|
||||
|
||||
export function cdpError(error: unknown): RpcError {
|
||||
return classifyCdpError({
|
||||
code: "cdp_failed",
|
||||
message: error instanceof Error ? error.message : String(error),
|
||||
});
|
||||
}
|
||||
|
||||
export interface TransferErrorOptions {
|
||||
effectState: TransferEffectState;
|
||||
phase: string;
|
||||
|
||||
@@ -1,319 +0,0 @@
|
||||
// One native file-drop transaction bound to an explicit page target. CDP drag
|
||||
// events are sent to the target that owns the node: root targets use top-level
|
||||
// coordinates, while OOPIF targets require coordinates local to their session.
|
||||
|
||||
import type { RpcError, TransferEffectState } from "@/transport/types";
|
||||
import { transferError } from "./errors";
|
||||
import { resolveNodeGeometry } from "./frame-geometry";
|
||||
import type { ResolvedActionTarget } from "./interaction";
|
||||
import { type CdpRunner, isRpcError, sendToCdpTarget } from "./shared";
|
||||
import { BoundedWaitError, waitBounded } from "./transfer-transaction";
|
||||
|
||||
const CLEANUP_TIMEOUT_MS = 1_000;
|
||||
|
||||
type FileDropPhase = "resolve_target" | "drag_enter" | "drag_over" | "drop" | "cleanup";
|
||||
|
||||
interface RuntimeReply {
|
||||
result?: { value?: unknown; objectId?: string };
|
||||
exceptionDetails?: { text?: string; exception?: { description?: string } };
|
||||
}
|
||||
|
||||
interface DragData {
|
||||
items: [];
|
||||
files: string[];
|
||||
dragOperationsMask: number;
|
||||
}
|
||||
|
||||
export interface FileDropTransactionOptions {
|
||||
cdp: CdpRunner;
|
||||
actionTarget: ResolvedActionTarget;
|
||||
files: string[];
|
||||
timeoutMs: number;
|
||||
signal?: AbortSignal;
|
||||
withOverlayHidden: <T>(operation: () => Promise<T>) => Promise<T>;
|
||||
}
|
||||
|
||||
export interface FileDropTransactionResult {
|
||||
x: number;
|
||||
y: number;
|
||||
}
|
||||
|
||||
function failure(
|
||||
code: RpcError["code"],
|
||||
reason: "upload_mechanism_unsupported" | "file_drop_target_unavailable" | "file_drop_failed",
|
||||
message: string,
|
||||
effectState: TransferEffectState,
|
||||
phase: FileDropPhase,
|
||||
): RpcError {
|
||||
const error = transferError(code, reason, message, { effectState, phase });
|
||||
error.data = { ...error.data, mechanism: "drop" };
|
||||
return error;
|
||||
}
|
||||
|
||||
function enrichFailure(
|
||||
error: RpcError,
|
||||
effectState: TransferEffectState,
|
||||
phase: FileDropPhase,
|
||||
): RpcError {
|
||||
return {
|
||||
...error,
|
||||
data: {
|
||||
...error.data,
|
||||
mechanism: "drop",
|
||||
effect_state: effectState,
|
||||
phase,
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
function messageOf(error: unknown): string {
|
||||
return error instanceof Error ? error.message : String(error);
|
||||
}
|
||||
|
||||
function methodUnavailable(error: unknown): boolean {
|
||||
return /(?:method|command).*(?:not found|wasn't found|unsupported)|wasn't found|-32601/i.test(
|
||||
messageOf(error),
|
||||
);
|
||||
}
|
||||
|
||||
function runtimeError(reply: RuntimeReply, fallback: string): Error | null {
|
||||
if (!reply.exceptionDetails) return null;
|
||||
return new Error(
|
||||
reply.exceptionDetails.exception?.description ?? reply.exceptionDetails.text ?? fallback,
|
||||
);
|
||||
}
|
||||
|
||||
async function pointBelongsToTarget(
|
||||
options: FileDropTransactionOptions,
|
||||
x: number,
|
||||
y: number,
|
||||
objectGroup: string,
|
||||
): Promise<boolean> {
|
||||
const target = options.actionTarget.cdpTarget;
|
||||
const hit = await sendToCdpTarget<{ backendNodeId?: number; frameId?: string }>(
|
||||
options.cdp,
|
||||
target,
|
||||
"DOM.getNodeForLocation",
|
||||
{ x: Math.round(x), y: Math.round(y), includeUserAgentShadowDOM: true },
|
||||
);
|
||||
if (typeof hit.backendNodeId !== "number") return false;
|
||||
if (options.actionTarget.frameId && hit.frameId !== options.actionTarget.frameId) return false;
|
||||
|
||||
const [resolvedTarget, resolvedHit] = await Promise.all([
|
||||
sendToCdpTarget<{ object?: { objectId?: string } }>(options.cdp, target, "DOM.resolveNode", {
|
||||
backendNodeId: options.actionTarget.backendNodeId,
|
||||
objectGroup,
|
||||
}),
|
||||
sendToCdpTarget<{ object?: { objectId?: string } }>(options.cdp, target, "DOM.resolveNode", {
|
||||
backendNodeId: hit.backendNodeId,
|
||||
objectGroup,
|
||||
}),
|
||||
]);
|
||||
const targetObjectId = resolvedTarget.object?.objectId;
|
||||
const hitObjectId = resolvedHit.object?.objectId;
|
||||
if (!targetObjectId || !hitObjectId) return false;
|
||||
|
||||
const reply = await sendToCdpTarget<RuntimeReply>(options.cdp, target, "Runtime.callFunctionOn", {
|
||||
objectId: targetObjectId,
|
||||
functionDeclaration: `function(hit) {
|
||||
for (let node = hit; node; ) {
|
||||
if (node === this) return true;
|
||||
if (this.contains?.(node)) return true;
|
||||
const root = node.getRootNode?.();
|
||||
node = node.parentNode || (root && root !== node ? root.host : null);
|
||||
}
|
||||
return false;
|
||||
}`,
|
||||
arguments: [{ objectId: hitObjectId }],
|
||||
returnByValue: true,
|
||||
});
|
||||
const error = runtimeError(reply, "failed to verify file-drop target");
|
||||
if (error) throw error;
|
||||
return reply.result?.value === true;
|
||||
}
|
||||
|
||||
export async function uploadThroughFileDrop(
|
||||
options: FileDropTransactionOptions,
|
||||
): Promise<FileDropTransactionResult | RpcError> {
|
||||
const deadline = Date.now() + options.timeoutMs;
|
||||
const target = options.actionTarget.cdpTarget;
|
||||
const objectGroup = `bsk-file-drop-${crypto.randomUUID()}`;
|
||||
const dragData: DragData = {
|
||||
items: [],
|
||||
files: options.files,
|
||||
dragOperationsMask: 1,
|
||||
};
|
||||
let dragStarted = false;
|
||||
let dropSent = false;
|
||||
let dragPoint = { x: 0, y: 0 };
|
||||
let cleanupFailed = false;
|
||||
let outcome: FileDropTransactionResult | RpcError = failure(
|
||||
"protocol_error",
|
||||
"file_drop_failed",
|
||||
"file-drop transaction ended without an outcome",
|
||||
"none",
|
||||
"cleanup",
|
||||
);
|
||||
|
||||
try {
|
||||
const geometry = await waitBounded(
|
||||
resolveNodeGeometry(
|
||||
options.cdp,
|
||||
options.actionTarget.tab.tabId,
|
||||
{
|
||||
target,
|
||||
backendNodeId: options.actionTarget.backendNodeId,
|
||||
...(options.actionTarget.frameId ? { frameId: options.actionTarget.frameId } : {}),
|
||||
},
|
||||
{ scrollIntoView: true },
|
||||
),
|
||||
deadline,
|
||||
options.signal,
|
||||
"resolving file-drop target timed out",
|
||||
);
|
||||
if (isRpcError(geometry)) {
|
||||
outcome = enrichFailure(geometry, "none", "resolve_target");
|
||||
return outcome;
|
||||
}
|
||||
const point = geometry.targetActionPoint;
|
||||
dragPoint = point;
|
||||
|
||||
outcome = await options.withOverlayHidden(async () => {
|
||||
try {
|
||||
try {
|
||||
const belongs = await waitBounded(
|
||||
pointBelongsToTarget(options, point.x, point.y, objectGroup),
|
||||
deadline,
|
||||
options.signal,
|
||||
"verifying file-drop target timed out",
|
||||
);
|
||||
if (!belongs) {
|
||||
return failure(
|
||||
"permission_denied",
|
||||
"file_drop_target_unavailable",
|
||||
"file-drop target is not the topmost element at its action point",
|
||||
"none",
|
||||
"resolve_target",
|
||||
);
|
||||
}
|
||||
} catch (error) {
|
||||
return failure(
|
||||
error instanceof BoundedWaitError ? "timeout" : "cdp_failed",
|
||||
"file_drop_target_unavailable",
|
||||
messageOf(error),
|
||||
"none",
|
||||
"resolve_target",
|
||||
);
|
||||
}
|
||||
|
||||
for (const [type, phase] of [
|
||||
["dragEnter", "drag_enter"],
|
||||
["dragOver", "drag_over"],
|
||||
] as const) {
|
||||
try {
|
||||
if (type === "dragEnter") dragStarted = true;
|
||||
await waitBounded(
|
||||
sendToCdpTarget(options.cdp, target, "Input.dispatchDragEvent", {
|
||||
type,
|
||||
x: point.x,
|
||||
y: point.y,
|
||||
data: dragData,
|
||||
}),
|
||||
deadline,
|
||||
options.signal,
|
||||
`${type} timed out`,
|
||||
);
|
||||
} catch (error) {
|
||||
const unsupported = methodUnavailable(error);
|
||||
if (type === "dragEnter" && unsupported) dragStarted = false;
|
||||
return failure(
|
||||
unsupported
|
||||
? "unsupported"
|
||||
: error instanceof BoundedWaitError
|
||||
? "timeout"
|
||||
: "cdp_failed",
|
||||
unsupported ? "upload_mechanism_unsupported" : "file_drop_failed",
|
||||
messageOf(error),
|
||||
"none",
|
||||
phase,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
try {
|
||||
dropSent = true;
|
||||
await waitBounded(
|
||||
sendToCdpTarget(options.cdp, target, "Input.dispatchDragEvent", {
|
||||
type: "drop",
|
||||
x: point.x,
|
||||
y: point.y,
|
||||
data: dragData,
|
||||
}),
|
||||
deadline,
|
||||
options.signal,
|
||||
"file drop timed out",
|
||||
);
|
||||
return { x: point.x, y: point.y };
|
||||
} catch (error) {
|
||||
outcome = failure(
|
||||
error instanceof BoundedWaitError ? "timeout" : "cdp_failed",
|
||||
"file_drop_failed",
|
||||
messageOf(error),
|
||||
"unknown",
|
||||
"drop",
|
||||
);
|
||||
return outcome;
|
||||
}
|
||||
} finally {
|
||||
if (dragStarted && !dropSent) {
|
||||
try {
|
||||
await waitBounded(
|
||||
sendToCdpTarget(options.cdp, target, "Input.dispatchDragEvent", {
|
||||
type: "dragCancel",
|
||||
x: dragPoint.x,
|
||||
y: dragPoint.y,
|
||||
data: dragData,
|
||||
}),
|
||||
Date.now() + CLEANUP_TIMEOUT_MS,
|
||||
undefined,
|
||||
"cancelling file drag timed out",
|
||||
);
|
||||
} catch {
|
||||
cleanupFailed = true;
|
||||
}
|
||||
}
|
||||
}
|
||||
});
|
||||
return outcome;
|
||||
} catch (error) {
|
||||
outcome = failure(
|
||||
error instanceof BoundedWaitError ? "timeout" : "cdp_failed",
|
||||
"file_drop_target_unavailable",
|
||||
messageOf(error),
|
||||
"none",
|
||||
"resolve_target",
|
||||
);
|
||||
return outcome;
|
||||
} finally {
|
||||
try {
|
||||
await waitBounded(
|
||||
sendToCdpTarget(options.cdp, target, "Runtime.releaseObjectGroup", { objectGroup }),
|
||||
Date.now() + CLEANUP_TIMEOUT_MS,
|
||||
undefined,
|
||||
"releasing file-drop object group timed out",
|
||||
);
|
||||
} catch {
|
||||
cleanupFailed = true;
|
||||
}
|
||||
|
||||
const effect = isRpcError(outcome)
|
||||
? (outcome.data?.effect_state as TransferEffectState | undefined)
|
||||
: "committed";
|
||||
if (effect === "unknown" || cleanupFailed) {
|
||||
await options.cdp.detach?.(target.tabId);
|
||||
}
|
||||
if (cleanupFailed && isRpcError(outcome)) {
|
||||
outcome.data = { ...outcome.data, cleanup_state: "failed" };
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -7,9 +7,9 @@ import type { ClickResult, RpcError, TransferEffectState } from "@/transport/typ
|
||||
import { transferError } from "./errors";
|
||||
import type { ResolvedActionTarget } from "./interaction";
|
||||
import { type CdpRunner, isRpcError, sendToCdpTarget } from "./shared";
|
||||
import { BoundedWaitError, remainingMs, waitBounded } from "./transfer-transaction";
|
||||
|
||||
const CLEANUP_TIMEOUT_MS = 1_000;
|
||||
const DETACH_TIMEOUT_MS = 500;
|
||||
const ACTIVATION_GRACE_MS = 1_000;
|
||||
const PROBE_INTERVAL_MS = 20;
|
||||
|
||||
@@ -46,6 +46,51 @@ export interface FileInputTransactionResult {
|
||||
multiple: boolean;
|
||||
}
|
||||
|
||||
class BoundedWaitError extends Error {
|
||||
constructor(
|
||||
readonly kind: "timeout" | "aborted",
|
||||
message: string,
|
||||
) {
|
||||
super(message);
|
||||
}
|
||||
}
|
||||
|
||||
function remainingMs(deadline: number): number {
|
||||
return Math.max(0, deadline - Date.now());
|
||||
}
|
||||
|
||||
async function waitBounded<T>(
|
||||
operation: () => Promise<T>,
|
||||
deadline: number,
|
||||
signal: AbortSignal | undefined,
|
||||
timeoutMessage: string,
|
||||
): Promise<T> {
|
||||
const remaining = remainingMs(deadline);
|
||||
if (signal?.aborted) throw new BoundedWaitError("aborted", "upload transaction aborted");
|
||||
if (remaining === 0) throw new BoundedWaitError("timeout", timeoutMessage);
|
||||
|
||||
let timer: ReturnType<typeof setTimeout> | undefined;
|
||||
let onAbort: (() => void) | undefined;
|
||||
const boundary = new Promise<never>((_resolve, reject) => {
|
||||
timer = setTimeout(() => reject(new BoundedWaitError("timeout", timeoutMessage)), remaining);
|
||||
if (signal) {
|
||||
onAbort = () => reject(new BoundedWaitError("aborted", "upload transaction aborted"));
|
||||
signal.addEventListener("abort", onAbort, { once: true });
|
||||
}
|
||||
});
|
||||
try {
|
||||
const work = Promise.resolve().then(() => {
|
||||
if (signal?.aborted) throw new BoundedWaitError("aborted", "upload transaction aborted");
|
||||
if (remainingMs(deadline) === 0) throw new BoundedWaitError("timeout", timeoutMessage);
|
||||
return operation();
|
||||
});
|
||||
return await Promise.race([work, boundary]);
|
||||
} finally {
|
||||
if (timer) clearTimeout(timer);
|
||||
if (signal && onAbort) signal.removeEventListener("abort", onAbort);
|
||||
}
|
||||
}
|
||||
|
||||
function runtimeError(reply: RuntimeReply, fallback: string): Error | null {
|
||||
if (!reply.exceptionDetails) return null;
|
||||
return new Error(
|
||||
@@ -83,13 +128,18 @@ function sameTarget(
|
||||
|
||||
async function delay(ms: number, signal?: AbortSignal): Promise<void> {
|
||||
await waitBounded(
|
||||
new Promise((resolve) => setTimeout(resolve, ms)),
|
||||
() => new Promise((resolve) => setTimeout(resolve, ms)),
|
||||
Date.now() + ms + 1,
|
||||
signal,
|
||||
"upload activation probe timed out",
|
||||
);
|
||||
}
|
||||
|
||||
function waitErrorCode(error: unknown): RpcError["code"] {
|
||||
if (!(error instanceof BoundedWaitError)) return "cdp_failed";
|
||||
return error.kind === "aborted" ? "cancelled" : "timeout";
|
||||
}
|
||||
|
||||
async function callOnTrigger<T = RuntimeReply>(
|
||||
options: FileInputTransactionOptions,
|
||||
objectId: string,
|
||||
@@ -114,8 +164,8 @@ export async function uploadThroughActivatedFileInput(
|
||||
const objectGroup = `bsk-upload-${crypto.randomUUID()}`;
|
||||
const stateKey = `__bskUpload_${crypto.randomUUID().replaceAll("-", "")}`;
|
||||
const chooserEvents: ChooserEvent[] = [];
|
||||
let interceptionArmed = false;
|
||||
let probeArmed = false;
|
||||
let interceptionState: "not_started" | "possibly_active" | "active" = "not_started";
|
||||
let probeState: "not_started" | "possibly_active" | "active" = "not_started";
|
||||
let triggerObjectId: string | undefined;
|
||||
let outcome: FileInputTransactionResult | RpcError = transferFailure(
|
||||
"protocol_error",
|
||||
@@ -133,18 +183,20 @@ export async function uploadThroughActivatedFileInput(
|
||||
|
||||
try {
|
||||
try {
|
||||
interceptionState = "possibly_active";
|
||||
await waitBounded(
|
||||
sendToCdpTarget(options.cdp, target, "Page.setInterceptFileChooserDialog", {
|
||||
enabled: true,
|
||||
}),
|
||||
() =>
|
||||
sendToCdpTarget(options.cdp, target, "Page.setInterceptFileChooserDialog", {
|
||||
enabled: true,
|
||||
}),
|
||||
deadline,
|
||||
options.signal,
|
||||
"arming native file chooser interception timed out",
|
||||
);
|
||||
interceptionArmed = true;
|
||||
interceptionState = "active";
|
||||
} catch (err) {
|
||||
outcome = transferFailure(
|
||||
err instanceof BoundedWaitError ? "timeout" : "cdp_failed",
|
||||
waitErrorCode(err),
|
||||
"file_input_probe_failed",
|
||||
err instanceof Error ? err.message : String(err),
|
||||
"none",
|
||||
@@ -155,15 +207,16 @@ export async function uploadThroughActivatedFileInput(
|
||||
|
||||
try {
|
||||
const resolved = await waitBounded(
|
||||
sendToCdpTarget<{ object?: { objectId?: string } }>(
|
||||
options.cdp,
|
||||
target,
|
||||
"DOM.resolveNode",
|
||||
{
|
||||
backendNodeId: options.actionTarget.backendNodeId,
|
||||
objectGroup,
|
||||
},
|
||||
),
|
||||
() =>
|
||||
sendToCdpTarget<{ object?: { objectId?: string } }>(
|
||||
options.cdp,
|
||||
target,
|
||||
"DOM.resolveNode",
|
||||
{
|
||||
backendNodeId: options.actionTarget.backendNodeId,
|
||||
objectGroup,
|
||||
},
|
||||
),
|
||||
deadline,
|
||||
options.signal,
|
||||
"resolving upload trigger timed out",
|
||||
@@ -171,11 +224,13 @@ export async function uploadThroughActivatedFileInput(
|
||||
triggerObjectId = resolved.object?.objectId;
|
||||
if (!triggerObjectId) throw new Error("DOM.resolveNode returned no trigger objectId");
|
||||
|
||||
probeState = "possibly_active";
|
||||
const armed = await waitBounded(
|
||||
callOnTrigger<RuntimeReply>(
|
||||
options,
|
||||
triggerObjectId,
|
||||
`function(key) {
|
||||
() =>
|
||||
callOnTrigger<RuntimeReply>(
|
||||
options,
|
||||
triggerObjectId as string,
|
||||
`function(key) {
|
||||
const doc = this.ownerDocument;
|
||||
const owner = doc.defaultView;
|
||||
if (!owner) return false;
|
||||
@@ -193,9 +248,9 @@ export async function uploadThroughActivatedFileInput(
|
||||
doc.addEventListener("click", state.listener, true);
|
||||
return true;
|
||||
}`,
|
||||
[stateKey],
|
||||
true,
|
||||
),
|
||||
[stateKey],
|
||||
true,
|
||||
),
|
||||
deadline,
|
||||
options.signal,
|
||||
"arming frame-scoped file input probe timed out",
|
||||
@@ -204,10 +259,10 @@ export async function uploadThroughActivatedFileInput(
|
||||
if (armError || armed.result?.value !== true) {
|
||||
throw armError ?? new Error("file input probe did not arm");
|
||||
}
|
||||
probeArmed = true;
|
||||
probeState = "active";
|
||||
} catch (err) {
|
||||
outcome = transferFailure(
|
||||
err instanceof BoundedWaitError ? "timeout" : "cdp_failed",
|
||||
waitErrorCode(err),
|
||||
"file_input_probe_failed",
|
||||
err instanceof Error ? err.message : String(err),
|
||||
"none",
|
||||
@@ -219,14 +274,14 @@ export async function uploadThroughActivatedFileInput(
|
||||
let click: ClickResult | RpcError;
|
||||
try {
|
||||
click = await waitBounded(
|
||||
options.trigger(),
|
||||
options.trigger,
|
||||
deadline,
|
||||
options.signal,
|
||||
"upload trigger timed out",
|
||||
);
|
||||
} catch (err) {
|
||||
outcome = transferFailure(
|
||||
err instanceof BoundedWaitError ? "timeout" : "cdp_failed",
|
||||
waitErrorCode(err),
|
||||
"file_input_probe_failed",
|
||||
err instanceof Error ? err.message : String(err),
|
||||
"none",
|
||||
@@ -244,17 +299,23 @@ export async function uploadThroughActivatedFileInput(
|
||||
let summary: { count: number; multiple: boolean } = { count: 0, multiple: false };
|
||||
while (Date.now() < activationDeadline) {
|
||||
if (chooserEvents.length > 0) break;
|
||||
const reply = await callOnTrigger<RuntimeReply>(
|
||||
options,
|
||||
triggerObjectId,
|
||||
`function(key) {
|
||||
const reply = await waitBounded(
|
||||
() =>
|
||||
callOnTrigger<RuntimeReply>(
|
||||
options,
|
||||
triggerObjectId as string,
|
||||
`function(key) {
|
||||
const state = this.ownerDocument.defaultView?.[key];
|
||||
return state
|
||||
? { count: state.inputs.length, multiple: state.inputs[0]?.multiple === true }
|
||||
: { count: 0, multiple: false };
|
||||
}`,
|
||||
[stateKey],
|
||||
true,
|
||||
[stateKey],
|
||||
true,
|
||||
),
|
||||
activationDeadline,
|
||||
options.signal,
|
||||
"inspecting activated file input timed out",
|
||||
);
|
||||
const summaryError = runtimeError(reply, "failed to inspect activated file input");
|
||||
if (summaryError) throw summaryError;
|
||||
@@ -317,21 +378,33 @@ export async function uploadThroughActivatedFileInput(
|
||||
);
|
||||
return outcome;
|
||||
}
|
||||
const input = await callOnTrigger<RuntimeReply>(
|
||||
options,
|
||||
triggerObjectId,
|
||||
`function(key) { return this.ownerDocument.defaultView?.[key]?.inputs[0]; }`,
|
||||
[stateKey],
|
||||
false,
|
||||
const input = await waitBounded(
|
||||
() =>
|
||||
callOnTrigger<RuntimeReply>(
|
||||
options,
|
||||
triggerObjectId as string,
|
||||
`function(key) { return this.ownerDocument.defaultView?.[key]?.inputs[0]; }`,
|
||||
[stateKey],
|
||||
false,
|
||||
),
|
||||
deadline,
|
||||
options.signal,
|
||||
"resolving activated file input timed out",
|
||||
);
|
||||
const inputError = runtimeError(input, "failed to resolve activated file input object");
|
||||
if (inputError) throw inputError;
|
||||
if (!input.result?.objectId) throw new Error("activated file input returned no objectId");
|
||||
const described = await sendToCdpTarget<{ node?: { backendNodeId?: number } }>(
|
||||
options.cdp,
|
||||
target,
|
||||
"DOM.describeNode",
|
||||
{ objectId: input.result.objectId },
|
||||
const described = await waitBounded(
|
||||
() =>
|
||||
sendToCdpTarget<{ node?: { backendNodeId?: number } }>(
|
||||
options.cdp,
|
||||
target,
|
||||
"DOM.describeNode",
|
||||
{ objectId: input.result?.objectId },
|
||||
),
|
||||
deadline,
|
||||
options.signal,
|
||||
"describing activated file input timed out",
|
||||
);
|
||||
backendNodeId = described.node?.backendNodeId;
|
||||
if (typeof backendNodeId !== "number") {
|
||||
@@ -350,17 +423,18 @@ export async function uploadThroughActivatedFileInput(
|
||||
|
||||
try {
|
||||
await waitBounded(
|
||||
sendToCdpTarget(options.cdp, target, "DOM.setFileInputFiles", {
|
||||
files: options.files,
|
||||
backendNodeId,
|
||||
}),
|
||||
() =>
|
||||
sendToCdpTarget(options.cdp, target, "DOM.setFileInputFiles", {
|
||||
files: options.files,
|
||||
backendNodeId,
|
||||
}),
|
||||
deadline,
|
||||
options.signal,
|
||||
"setting file input files timed out",
|
||||
);
|
||||
} catch (err) {
|
||||
outcome = transferFailure(
|
||||
err instanceof BoundedWaitError ? "timeout" : "cdp_failed",
|
||||
waitErrorCode(err),
|
||||
"set_file_input_failed",
|
||||
err instanceof Error ? err.message : String(err),
|
||||
"unknown",
|
||||
@@ -372,7 +446,7 @@ export async function uploadThroughActivatedFileInput(
|
||||
return outcome;
|
||||
} catch (err) {
|
||||
outcome = transferFailure(
|
||||
err instanceof BoundedWaitError ? "timeout" : "cdp_failed",
|
||||
waitErrorCode(err),
|
||||
"file_input_probe_failed",
|
||||
err instanceof Error ? err.message : String(err),
|
||||
"none",
|
||||
@@ -382,61 +456,70 @@ export async function uploadThroughActivatedFileInput(
|
||||
}
|
||||
} finally {
|
||||
chooserSubscription?.dispose();
|
||||
let cleanupFailed = false;
|
||||
if (probeArmed && triggerObjectId) {
|
||||
const cleanupDeadline = Date.now() + CLEANUP_TIMEOUT_MS;
|
||||
const cleanupTasks: Promise<boolean>[] = [];
|
||||
const cleanup = async (operation: () => Promise<unknown>, message: string) => {
|
||||
try {
|
||||
await waitBounded(
|
||||
callOnTrigger(
|
||||
options,
|
||||
triggerObjectId,
|
||||
`function(key) {
|
||||
await waitBounded(operation, cleanupDeadline, undefined, message);
|
||||
return true;
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
};
|
||||
if (probeState !== "not_started" && triggerObjectId) {
|
||||
cleanupTasks.push(
|
||||
cleanup(
|
||||
() =>
|
||||
callOnTrigger(
|
||||
options,
|
||||
triggerObjectId as string,
|
||||
`function(key) {
|
||||
const owner = this.ownerDocument.defaultView;
|
||||
const state = owner?.[key];
|
||||
if (state?.listener) this.ownerDocument.removeEventListener("click", state.listener, true);
|
||||
if (owner) delete owner[key];
|
||||
}`,
|
||||
[stateKey],
|
||||
true,
|
||||
),
|
||||
Date.now() + CLEANUP_TIMEOUT_MS,
|
||||
undefined,
|
||||
[stateKey],
|
||||
true,
|
||||
),
|
||||
"cleaning file input probe timed out",
|
||||
);
|
||||
} catch {
|
||||
cleanupFailed = true;
|
||||
}
|
||||
}
|
||||
if (interceptionArmed) {
|
||||
try {
|
||||
await waitBounded(
|
||||
sendToCdpTarget(options.cdp, target, "Page.setInterceptFileChooserDialog", {
|
||||
enabled: false,
|
||||
cancel: true,
|
||||
}),
|
||||
Date.now() + CLEANUP_TIMEOUT_MS,
|
||||
undefined,
|
||||
"disabling file chooser interception timed out",
|
||||
);
|
||||
} catch {
|
||||
cleanupFailed = true;
|
||||
}
|
||||
}
|
||||
try {
|
||||
await waitBounded(
|
||||
sendToCdpTarget(options.cdp, target, "Runtime.releaseObjectGroup", { objectGroup }),
|
||||
Date.now() + CLEANUP_TIMEOUT_MS,
|
||||
undefined,
|
||||
"releasing upload object group timed out",
|
||||
),
|
||||
);
|
||||
} catch {
|
||||
cleanupFailed = true;
|
||||
}
|
||||
if (interceptionState !== "not_started") {
|
||||
cleanupTasks.push(
|
||||
cleanup(
|
||||
() =>
|
||||
sendToCdpTarget(options.cdp, target, "Page.setInterceptFileChooserDialog", {
|
||||
enabled: false,
|
||||
cancel: true,
|
||||
}),
|
||||
"disabling file chooser interception timed out",
|
||||
),
|
||||
);
|
||||
}
|
||||
let cleanupFailed = (await Promise.all(cleanupTasks)).some((completed) => !completed);
|
||||
if (!cleanupFailed) {
|
||||
cleanupFailed = !(await cleanup(
|
||||
() => sendToCdpTarget(options.cdp, target, "Runtime.releaseObjectGroup", { objectGroup }),
|
||||
"releasing upload object group timed out",
|
||||
));
|
||||
}
|
||||
|
||||
const effect = isRpcError(outcome)
|
||||
? (outcome.data?.effect_state as TransferEffectState | undefined)
|
||||
: "committed";
|
||||
if (effect === "unknown" || cleanupFailed) {
|
||||
await options.cdp.detach?.(target.tabId);
|
||||
try {
|
||||
await waitBounded(
|
||||
() => options.cdp.detach?.(target.tabId) ?? Promise.resolve(),
|
||||
Date.now() + DETACH_TIMEOUT_MS,
|
||||
undefined,
|
||||
"detaching upload target timed out",
|
||||
);
|
||||
} catch {
|
||||
cleanupFailed = true;
|
||||
}
|
||||
}
|
||||
if (cleanupFailed && isRpcError(outcome)) {
|
||||
outcome.data = { ...outcome.data, cleanup_state: "failed" };
|
||||
|
||||
@@ -1,21 +1,24 @@
|
||||
import { type CdpTarget, cdpTargetKey } from "@/browser-driver/frame-graph";
|
||||
import { type CdpFrame, type CdpFrameGraph, type CdpTarget } from "@/browser-driver/frame-graph";
|
||||
import type { RpcError } from "@/transport/types";
|
||||
import { nodeContentRegion, scrollNodeIntoView } from "./element-geometry";
|
||||
import {
|
||||
clipPolygon,
|
||||
type GeometryProjection,
|
||||
type Point,
|
||||
type Polygon,
|
||||
type ProjectiveEdge,
|
||||
parseCdpQuad,
|
||||
polygonArea,
|
||||
polygonCentroid,
|
||||
projectRegionToViewport,
|
||||
type Quad,
|
||||
type Region,
|
||||
rectPolygon,
|
||||
regionBounds,
|
||||
type Size,
|
||||
type ViewportRect,
|
||||
} from "./geometry";
|
||||
import type { CssViewport } from "./geometry/coordinate-types";
|
||||
import { cssViewport, GeometryContext } from "./geometry/frame-context";
|
||||
import { type CdpRunner, cdpRunnerForTarget, isRpcError } from "./shared";
|
||||
import { type CdpRunner, cdpRunnerForTarget, isRpcError, sendToCdpTarget } from "./shared";
|
||||
|
||||
export interface NodeAddress {
|
||||
target: CdpTarget;
|
||||
@@ -24,30 +27,154 @@ export interface NodeAddress {
|
||||
}
|
||||
|
||||
export interface ResolvedNodeGeometry {
|
||||
/** The same top-level measurement used by projection, for screenshot coordinate adaptation. */
|
||||
topViewport: CssViewport;
|
||||
topVisibleRegions: Region;
|
||||
topBounds: ViewportRect;
|
||||
/** Point in the top-level tab viewport, used by root-target input events. */
|
||||
actionPoint: Point;
|
||||
/** Point in the addressed CDP target's viewport, used by OOPIF-local input events. */
|
||||
targetActionPoint: Point;
|
||||
}
|
||||
|
||||
function geometryError(message: string): RpcError {
|
||||
return { code: "cdp_failed", message };
|
||||
}
|
||||
|
||||
function frameMap(graph: CdpFrameGraph): Map<string, CdpFrame> {
|
||||
return new Map(graph.frames.map((frame) => [frame.frameId, frame]));
|
||||
}
|
||||
|
||||
function targetRootFrame(byId: Map<string, CdpFrame>, frame: CdpFrame): CdpFrame | null {
|
||||
const seen = new Set<string>();
|
||||
let current = frame;
|
||||
while (current.parentFrameId) {
|
||||
if (seen.has(current.frameId)) return null;
|
||||
seen.add(current.frameId);
|
||||
const parent = byId.get(current.parentFrameId);
|
||||
if (!parent || parent.target.sessionId !== current.target.sessionId) break;
|
||||
current = parent;
|
||||
}
|
||||
return current;
|
||||
}
|
||||
|
||||
function frameAncestry(graph: CdpFrameGraph, frameId: string): CdpFrame[] | null {
|
||||
const byId = frameMap(graph);
|
||||
const path: CdpFrame[] = [];
|
||||
const seen = new Set<string>();
|
||||
let current = byId.get(frameId);
|
||||
if (!current) return null;
|
||||
while (current.parentFrameId) {
|
||||
if (seen.has(current.frameId)) return null;
|
||||
seen.add(current.frameId);
|
||||
path.push(current);
|
||||
const parent = byId.get(current.parentFrameId);
|
||||
if (!parent) return null;
|
||||
current = parent;
|
||||
}
|
||||
return path;
|
||||
}
|
||||
|
||||
async function targetViewport(cdp: CdpRunner, target: CdpTarget): Promise<Size | null> {
|
||||
const metrics = await sendToCdpTarget<{
|
||||
cssLayoutViewport?: { clientWidth?: number; clientHeight?: number };
|
||||
layoutViewport?: { clientWidth?: number; clientHeight?: number };
|
||||
}>(cdp, target, "Page.getLayoutMetrics", {});
|
||||
const viewport = metrics.cssLayoutViewport ?? metrics.layoutViewport ?? {};
|
||||
const width = viewport.clientWidth ?? 0;
|
||||
const height = viewport.clientHeight ?? 0;
|
||||
return width > 0 && height > 0 ? { width, height } : null;
|
||||
}
|
||||
|
||||
async function ownerContentQuad(
|
||||
cdp: CdpRunner,
|
||||
parent: CdpFrame,
|
||||
ownerBackendNodeId: number,
|
||||
): Promise<Quad | null> {
|
||||
const result = await sendToCdpTarget<{ model?: { content?: number[] } }>(
|
||||
cdp,
|
||||
parent.target,
|
||||
"DOM.getBoxModel",
|
||||
{ backendNodeId: ownerBackendNodeId },
|
||||
);
|
||||
return parseCdpQuad(result.model?.content);
|
||||
}
|
||||
|
||||
async function sameTargetFrameClips(
|
||||
cdp: CdpRunner,
|
||||
byId: Map<string, CdpFrame>,
|
||||
frame: CdpFrame,
|
||||
targetRoot: CdpFrame,
|
||||
): Promise<Polygon[] | null> {
|
||||
const clips: Polygon[] = [];
|
||||
let current = frame;
|
||||
const seen = new Set<string>();
|
||||
while (current.frameId !== targetRoot.frameId) {
|
||||
if (seen.has(current.frameId) || !current.parentFrameId) return null;
|
||||
seen.add(current.frameId);
|
||||
const parent = byId.get(current.parentFrameId);
|
||||
if (!parent || current.ownerBackendNodeId === undefined) return null;
|
||||
const clip = await ownerContentQuad(cdp, parent, current.ownerBackendNodeId);
|
||||
if (!clip) return null;
|
||||
clips.push(clip);
|
||||
current = parent;
|
||||
}
|
||||
return clips;
|
||||
}
|
||||
|
||||
export async function resolveFrameProjection(
|
||||
cdp: CdpRunner,
|
||||
graph: CdpFrameGraph,
|
||||
frameId: string,
|
||||
): Promise<GeometryProjection | null> {
|
||||
const byId = frameMap(graph);
|
||||
const frame = byId.get(frameId);
|
||||
if (!frame) return null;
|
||||
let targetRoot = targetRootFrame(byId, frame);
|
||||
if (!targetRoot) return null;
|
||||
const sourceViewport = await targetViewport(cdp, targetRoot.target);
|
||||
if (!sourceViewport) return null;
|
||||
const sourceClips = await sameTargetFrameClips(cdp, byId, frame, targetRoot);
|
||||
if (!sourceClips) return null;
|
||||
|
||||
const edges: ProjectiveEdge[] = [];
|
||||
while (targetRoot.parentFrameId) {
|
||||
const parent = byId.get(targetRoot.parentFrameId);
|
||||
if (!parent || targetRoot.ownerBackendNodeId === undefined) return null;
|
||||
const destinationQuad = await ownerContentQuad(cdp, parent, targetRoot.ownerBackendNodeId);
|
||||
if (!destinationQuad) return null;
|
||||
const source =
|
||||
edges.length === 0 ? sourceViewport : await targetViewport(cdp, targetRoot.target);
|
||||
if (!source) return null;
|
||||
const parentTargetRoot = targetRootFrame(byId, parent);
|
||||
if (!parentTargetRoot) return null;
|
||||
const destinationClips = await sameTargetFrameClips(cdp, byId, parent, parentTargetRoot);
|
||||
if (!destinationClips) return null;
|
||||
edges.push({ sourceViewport: source, destinationQuad, destinationClips });
|
||||
targetRoot = parentTargetRoot;
|
||||
}
|
||||
|
||||
const topViewport =
|
||||
edges.length === 0 ? sourceViewport : await targetViewport(cdp, targetRoot.target);
|
||||
return topViewport ? { sourceClips, edges, topViewport } : null;
|
||||
}
|
||||
|
||||
async function loadFrameGraph(cdp: CdpRunner, tabId: number): Promise<CdpFrameGraph | null> {
|
||||
if (!cdp.getFrameGraph) return null;
|
||||
try {
|
||||
return await cdp.getFrameGraph(tabId);
|
||||
} catch (error) {
|
||||
console.debug("[bsk frame-geometry] frame graph resolution failed", error);
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
async function scrollFrameOwners(
|
||||
cdp: CdpRunner,
|
||||
tabId: number,
|
||||
context: GeometryContext,
|
||||
graph: CdpFrameGraph,
|
||||
frameId: string,
|
||||
): Promise<RpcError | null> {
|
||||
const ancestry = await context.ancestry(frameId);
|
||||
const byId = frameMap(graph);
|
||||
const ancestry = frameAncestry(graph, frameId);
|
||||
if (!ancestry) return geometryError(`could not resolve frame ancestry for ${frameId}`);
|
||||
for (const child of [...ancestry].reverse()) {
|
||||
const parent = child.parentFrameId ? await context.frame(child.parentFrameId) : undefined;
|
||||
const parent = child.parentFrameId ? byId.get(child.parentFrameId) : undefined;
|
||||
if (!parent || child.ownerBackendNodeId === undefined) {
|
||||
return geometryError(`could not resolve frame owner for ${child.frameId}`);
|
||||
}
|
||||
@@ -61,20 +188,17 @@ async function scrollFrameOwners(
|
||||
return null;
|
||||
}
|
||||
|
||||
async function scrollElementWithContext(
|
||||
async function scrollElementWithFrameGraph(
|
||||
cdp: CdpRunner,
|
||||
tabId: number,
|
||||
target: CdpTarget,
|
||||
backendNodeId: number,
|
||||
frameId: string | undefined,
|
||||
context: GeometryContext,
|
||||
graph: CdpFrameGraph | null,
|
||||
): Promise<RpcError | null> {
|
||||
if (frameId) {
|
||||
const frame = await context.frame(frameId);
|
||||
if (!frame || cdpTargetKey(frame.target) !== cdpTargetKey(target)) {
|
||||
return geometryError("node frame does not belong to its target");
|
||||
}
|
||||
const error = await scrollFrameOwners(cdp, tabId, context, frameId);
|
||||
if (!graph) return geometryError(`could not resolve frame graph for ${frameId}`);
|
||||
const error = await scrollFrameOwners(cdp, tabId, graph, frameId);
|
||||
if (error) return error;
|
||||
} else if (target.sessionId) {
|
||||
return geometryError("an OOPIF node address requires frameId");
|
||||
@@ -89,15 +213,8 @@ export async function scrollElementAndFramesIntoView(
|
||||
backendNodeId: number,
|
||||
frameId?: string,
|
||||
): Promise<RpcError | null> {
|
||||
if (target.tabId !== tabId) return geometryError("node target belongs to another tab");
|
||||
return scrollElementWithContext(
|
||||
cdp,
|
||||
tabId,
|
||||
target,
|
||||
backendNodeId,
|
||||
frameId,
|
||||
new GeometryContext(cdp, tabId),
|
||||
);
|
||||
const graph = frameId ? await loadFrameGraph(cdp, tabId) : null;
|
||||
return scrollElementWithFrameGraph(cdp, tabId, target, backendNodeId, frameId, graph);
|
||||
}
|
||||
|
||||
function largestRegion(regions: Region): Polygon | null {
|
||||
@@ -120,32 +237,23 @@ export async function resolveNodeGeometry(
|
||||
if (address.target.sessionId && !address.frameId) {
|
||||
return geometryError("an OOPIF node address requires frameId");
|
||||
}
|
||||
if (address.target.tabId !== tabId) return geometryError("node target belongs to another tab");
|
||||
const context = new GeometryContext(cdp, tabId);
|
||||
const graph = address.frameId ? await context.graph() : null;
|
||||
if (address.frameId && graph) {
|
||||
const frame = await context.frame(address.frameId);
|
||||
if (!frame || cdpTargetKey(frame.target) !== cdpTargetKey(address.target)) {
|
||||
return geometryError("node frame does not belong to its target");
|
||||
}
|
||||
}
|
||||
const graph = address.frameId ? await loadFrameGraph(cdp, tabId) : null;
|
||||
if (address.frameId && !graph) {
|
||||
return geometryError(`could not resolve frame graph for ${address.frameId}`);
|
||||
}
|
||||
|
||||
if (options.scrollIntoView) {
|
||||
const scrollError = await scrollElementWithContext(
|
||||
const scrollError = await scrollElementWithFrameGraph(
|
||||
cdp,
|
||||
tabId,
|
||||
address.target,
|
||||
address.backendNodeId,
|
||||
address.frameId,
|
||||
context,
|
||||
graph,
|
||||
);
|
||||
if (scrollError) return scrollError;
|
||||
}
|
||||
|
||||
// Only topology was read above. Begin live measurements after scrolling.
|
||||
const localRegion = await nodeContentRegion(
|
||||
cdpRunnerForTarget(cdp, address.target),
|
||||
tabId,
|
||||
@@ -154,33 +262,13 @@ export async function resolveNodeGeometry(
|
||||
if (isRpcError(localRegion)) return localRegion;
|
||||
|
||||
let topVisibleRegions: Region;
|
||||
let targetActionPoint: Point | null = null;
|
||||
if (address.frameId && graph) {
|
||||
const projection = await context.targetProjection(address.frameId);
|
||||
const projection = await resolveFrameProjection(cdp, graph, address.frameId);
|
||||
if (!projection)
|
||||
return geometryError(`could not resolve frame geometry for ${address.frameId}`);
|
||||
topVisibleRegions = projectRegionToViewport(localRegion, projection);
|
||||
if (address.target.sessionId) {
|
||||
const localViewport = await context.viewport(address.target);
|
||||
if (!localViewport) return geometryError("could not resolve target viewport geometry");
|
||||
const localVisibleRegions = localRegion
|
||||
.map((polygon) =>
|
||||
clipPolygon(
|
||||
polygon,
|
||||
rectPolygon({
|
||||
x: 0,
|
||||
y: 0,
|
||||
w: localViewport.width,
|
||||
h: localViewport.height,
|
||||
}),
|
||||
),
|
||||
)
|
||||
.filter((polygon) => polygon.length >= 3);
|
||||
const localActionRegion = largestRegion(localVisibleRegions);
|
||||
targetActionPoint = localActionRegion ? polygonCentroid(localActionRegion) : null;
|
||||
}
|
||||
} else {
|
||||
const viewport = await context.viewport(address.target);
|
||||
const viewport = await targetViewport(cdp, address.target);
|
||||
if (!viewport) return geometryError("could not resolve top viewport geometry");
|
||||
topVisibleRegions = localRegion
|
||||
.map((polygon) =>
|
||||
@@ -195,17 +283,7 @@ export async function resolveNodeGeometry(
|
||||
if (!topBounds || !actionPoint) {
|
||||
return { code: "permission_denied", message: "element not visible" };
|
||||
}
|
||||
if (address.target.sessionId && !targetActionPoint) {
|
||||
return { code: "permission_denied", message: "element not visible in its target" };
|
||||
}
|
||||
targetActionPoint ??= actionPoint;
|
||||
return {
|
||||
topVisibleRegions,
|
||||
topBounds,
|
||||
actionPoint,
|
||||
targetActionPoint,
|
||||
topViewport: cssViewport(await context.layoutMetrics({ tabId })),
|
||||
};
|
||||
return { topVisibleRegions, topBounds, actionPoint };
|
||||
} catch (error) {
|
||||
return geometryError(error instanceof Error ? error.message : String(error));
|
||||
}
|
||||
|
||||
@@ -245,3 +245,22 @@ export function projectRectToViewport(
|
||||
if (!rect) return null;
|
||||
return regionBounds(projectRegionToViewport([rectPolygon(rect)], projection));
|
||||
}
|
||||
|
||||
export function childFrameProjection(
|
||||
parent: GeometryProjection,
|
||||
ownerRectInParent: { x: number; y: number; w: number; h: number },
|
||||
): GeometryProjection {
|
||||
const destinationQuad = rectPolygon(ownerRectInParent);
|
||||
return {
|
||||
sourceClips: [],
|
||||
edges: [
|
||||
{
|
||||
sourceViewport: { width: ownerRectInParent.w, height: ownerRectInParent.h },
|
||||
destinationQuad,
|
||||
destinationClips: parent.sourceClips,
|
||||
},
|
||||
...parent.edges,
|
||||
],
|
||||
topViewport: parent.topViewport,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -1,157 +0,0 @@
|
||||
import { type CdpTarget, cdpTargetKey } from "@/browser-driver/frame-graph";
|
||||
import type { GeometryProjection, ViewportRect } from "../geometry";
|
||||
import { projectRectToViewport } from "../geometry";
|
||||
|
||||
export interface CoordinateOwner {
|
||||
target: CdpTarget;
|
||||
frameId?: string;
|
||||
}
|
||||
|
||||
export interface FrameViewportRect {
|
||||
space: "frame-viewport-css";
|
||||
owner: CoordinateOwner;
|
||||
rect: ViewportRect;
|
||||
}
|
||||
|
||||
export interface SnapshotProjection {
|
||||
source: CoordinateOwner;
|
||||
geometry: GeometryProjection;
|
||||
}
|
||||
|
||||
/** A failed owner read is different from a successfully projected, clipped-out rect. */
|
||||
export interface UnavailableFrameProjection {
|
||||
status: "unavailable";
|
||||
source: CoordinateOwner;
|
||||
ownerBackendNodeId: number;
|
||||
}
|
||||
|
||||
export interface UnavailableSnapshotCoordinates {
|
||||
status: "unavailable";
|
||||
source: CoordinateOwner;
|
||||
reason: "snapshot-coordinates-unavailable";
|
||||
}
|
||||
|
||||
export type SnapshotProjectionResult =
|
||||
| { status: "available"; projection: SnapshotProjection }
|
||||
| UnavailableFrameProjection;
|
||||
|
||||
/** Descendants inherit the failed boundary without attempting another owner read. */
|
||||
export type FrameProjectionIssue =
|
||||
| UnavailableFrameProjection
|
||||
| UnavailableSnapshotCoordinates
|
||||
| {
|
||||
status: "blocked";
|
||||
source: CoordinateOwner;
|
||||
cause: UnavailableFrameProjection | UnavailableSnapshotCoordinates;
|
||||
};
|
||||
|
||||
export type FrameProjectionState = SnapshotProjectionResult | FrameProjectionIssue;
|
||||
|
||||
export interface SnapshotCoordinates {
|
||||
layoutUnitsPerCssPixel: number;
|
||||
scrollCss: { x: number; y: number };
|
||||
}
|
||||
|
||||
/** Snapshot scroll offsets share the raw layout units of its bounds. Only a
|
||||
* target's root document may fall back to that target's CSS layout viewport. */
|
||||
export function snapshotCoordinates(
|
||||
document: { scrollOffsetX?: number; scrollOffsetY?: number },
|
||||
layoutUnitsPerCssPixel: number | null,
|
||||
rootScrollCss?: { x?: number; y?: number },
|
||||
): SnapshotCoordinates | null {
|
||||
if (
|
||||
layoutUnitsPerCssPixel === null ||
|
||||
!Number.isFinite(layoutUnitsPerCssPixel) ||
|
||||
layoutUnitsPerCssPixel <= 0
|
||||
)
|
||||
return null;
|
||||
const x =
|
||||
document.scrollOffsetX === undefined
|
||||
? rootScrollCss?.x
|
||||
: document.scrollOffsetX / layoutUnitsPerCssPixel;
|
||||
const y =
|
||||
document.scrollOffsetY === undefined
|
||||
? rootScrollCss?.y
|
||||
: document.scrollOffsetY / layoutUnitsPerCssPixel;
|
||||
if (x === undefined || y === undefined || !Number.isFinite(x) || !Number.isFinite(y)) return null;
|
||||
return { layoutUnitsPerCssPixel, scrollCss: { x, y } };
|
||||
}
|
||||
|
||||
/** Convert raw document-relative Blink layout units exactly once, before any
|
||||
* CSS viewport clipping or frame projection. This scale is not screenshot zoom. */
|
||||
export function snapshotViewportRect(
|
||||
bounds: number[],
|
||||
owner: CoordinateOwner,
|
||||
coordinates: SnapshotCoordinates | null,
|
||||
): FrameViewportRect | null {
|
||||
if (!coordinates || bounds.length < 4 || !bounds.slice(0, 4).every(Number.isFinite)) return null;
|
||||
const { layoutUnitsPerCssPixel: scale, scrollCss: scroll } = coordinates;
|
||||
const [x, y, width, height] = bounds;
|
||||
if (
|
||||
!Number.isFinite(scale) ||
|
||||
scale <= 0 ||
|
||||
width <= 0 ||
|
||||
height <= 0 ||
|
||||
!Number.isFinite(scroll.x) ||
|
||||
!Number.isFinite(scroll.y)
|
||||
) {
|
||||
return null;
|
||||
}
|
||||
return {
|
||||
space: "frame-viewport-css",
|
||||
owner,
|
||||
rect: {
|
||||
x: x / scale - scroll.x,
|
||||
y: y / scale - scroll.y,
|
||||
width: width / scale,
|
||||
height: height / scale,
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
export function projectSnapshotRect(
|
||||
input: FrameViewportRect,
|
||||
projection: SnapshotProjection,
|
||||
): ViewportRect | null {
|
||||
if (
|
||||
input.owner.frameId !== projection.source.frameId ||
|
||||
cdpTargetKey(input.owner.target) !== cdpTargetKey(projection.source.target)
|
||||
) {
|
||||
return null;
|
||||
}
|
||||
const { x, y, width: w, height: h } = input.rect;
|
||||
return projectRectToViewport({ x, y, w, h }, projection.geometry);
|
||||
}
|
||||
|
||||
/** CSS viewport metadata; browser zoom is distinct from raster devicePixelRatio. */
|
||||
export interface CssViewport {
|
||||
width: number;
|
||||
height: number;
|
||||
scrollX: number;
|
||||
scrollY: number;
|
||||
cssToDip: number;
|
||||
}
|
||||
|
||||
/** Page.captureScreenshot takes page-relative DIP, not viewport-relative CSS pixels. */
|
||||
export function screenshotPageRect(
|
||||
rect: ViewportRect,
|
||||
viewport: CssViewport,
|
||||
): { space: "page-dip"; rect: ViewportRect } | null {
|
||||
const { cssToDip, scrollX, scrollY } = viewport;
|
||||
if (
|
||||
![rect.x, rect.y, rect.width, rect.height, cssToDip, scrollX, scrollY].every(Number.isFinite) ||
|
||||
cssToDip <= 0 ||
|
||||
rect.width <= 0 ||
|
||||
rect.height <= 0
|
||||
)
|
||||
return null;
|
||||
return {
|
||||
space: "page-dip",
|
||||
rect: {
|
||||
x: (rect.x + scrollX) * cssToDip,
|
||||
y: (rect.y + scrollY) * cssToDip,
|
||||
width: rect.width * cssToDip,
|
||||
height: rect.height * cssToDip,
|
||||
},
|
||||
};
|
||||
}
|
||||
@@ -1,400 +0,0 @@
|
||||
import {
|
||||
type CdpFrame,
|
||||
type CdpFrameGraph,
|
||||
type CdpTarget,
|
||||
cdpTargetKey,
|
||||
} from "@/browser-driver/frame-graph";
|
||||
import {
|
||||
type GeometryProjection,
|
||||
type Polygon,
|
||||
type ProjectiveEdge,
|
||||
parseCdpQuad,
|
||||
projectPolygon,
|
||||
type Quad,
|
||||
type Size,
|
||||
viewportPolygon,
|
||||
} from "../geometry";
|
||||
import { type CdpRunner, sendToCdpTarget } from "../shared";
|
||||
import type { CoordinateOwner, CssViewport, SnapshotProjectionResult } from "./coordinate-types";
|
||||
|
||||
import { readSnapshotOwnerSizes } from "./snapshot-owner-sizes";
|
||||
|
||||
export interface LayoutMetrics {
|
||||
cssVisualViewport?: {
|
||||
zoom?: number;
|
||||
scale?: number;
|
||||
clientWidth?: number;
|
||||
clientHeight?: number;
|
||||
};
|
||||
visualViewport?: { zoom?: number; scale?: number; clientWidth?: number; clientHeight?: number };
|
||||
cssLayoutViewport?: {
|
||||
clientWidth?: number;
|
||||
clientHeight?: number;
|
||||
pageX?: number;
|
||||
pageY?: number;
|
||||
};
|
||||
layoutViewport?: { clientWidth?: number; clientHeight?: number; pageX?: number; pageY?: number };
|
||||
}
|
||||
|
||||
/** Chromium emits these paired floating-point dimensions before/after dividing
|
||||
* by LayoutZoomFactor. Integer layout viewport dimensions lose precision at
|
||||
* fractional zoom. Neither visualViewport.scale nor .zoom is this conversion.
|
||||
* See InspectorPageAgent::getLayoutMetrics in Chromium. */
|
||||
export function snapshotLayoutScale(metrics: LayoutMetrics): number | null {
|
||||
for (const dimension of ["clientWidth", "clientHeight"] as const) {
|
||||
const raw = metrics.visualViewport?.[dimension];
|
||||
const css = metrics.cssVisualViewport?.[dimension];
|
||||
if (
|
||||
raw !== undefined &&
|
||||
css !== undefined &&
|
||||
Number.isFinite(raw) &&
|
||||
Number.isFinite(css) &&
|
||||
raw > 0 &&
|
||||
css > 0
|
||||
) {
|
||||
const scale = raw / css;
|
||||
if (Number.isFinite(scale) && scale > 0) return scale;
|
||||
}
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
/** The legacy field is a compatibility fallback, never a source of raster DPR. */
|
||||
export function cssViewport(metrics: LayoutMetrics): CssViewport {
|
||||
const value = metrics.cssLayoutViewport ?? metrics.layoutViewport;
|
||||
return {
|
||||
width: value?.clientWidth ?? 0,
|
||||
height: value?.clientHeight ?? 0,
|
||||
scrollX: value?.pageX ?? 0,
|
||||
scrollY: value?.pageY ?? 0,
|
||||
cssToDip: metrics.cssVisualViewport?.zoom ?? metrics.visualViewport?.zoom ?? 1,
|
||||
};
|
||||
}
|
||||
|
||||
/** One read-only measurement phase. Discard after scrolling or any later operation. */
|
||||
export class GeometryContext {
|
||||
private readonly metrics = new Map<string, Promise<LayoutMetrics>>();
|
||||
private readonly frameViewports = new Map<string, Promise<Size | null>>();
|
||||
private readonly owners = new Map<string, Promise<Quad | null>>();
|
||||
private readonly projections = new Map<string, Promise<GeometryProjection | null>>();
|
||||
private readonly snapshotOwners = new Map<string, Promise<{ quad: Quad; size: Size } | null>>();
|
||||
private readonly sizeBatches = new Map<string, () => Promise<Map<number, Size>>>();
|
||||
private active = 0;
|
||||
private readonly waiting: Array<() => void> = [];
|
||||
private graphPromise?: Promise<CdpFrameGraph | null>;
|
||||
private framesPromise?: Promise<Map<string, CdpFrame>>;
|
||||
|
||||
constructor(
|
||||
private readonly cdp: CdpRunner,
|
||||
private readonly tabId: number,
|
||||
graph?: CdpFrameGraph,
|
||||
private readonly signal?: AbortSignal,
|
||||
) {
|
||||
if (graph) this.graphPromise = Promise.resolve(graph);
|
||||
}
|
||||
|
||||
private async request<T>(
|
||||
target: CdpTarget,
|
||||
method: string,
|
||||
params: object,
|
||||
cleanup = false,
|
||||
): Promise<T> {
|
||||
if (!cleanup && this.signal?.aborted) throw new DOMException("geometry aborted", "AbortError");
|
||||
if (this.active >= 4) await new Promise<void>((resolve) => this.waiting.push(resolve));
|
||||
else this.active++;
|
||||
try {
|
||||
if (!cleanup && this.signal?.aborted)
|
||||
throw new DOMException("geometry aborted", "AbortError");
|
||||
return await sendToCdpTarget<T>(this.cdp, target, method, params);
|
||||
} finally {
|
||||
const next = this.waiting.shift();
|
||||
if (next) next();
|
||||
else this.active--;
|
||||
}
|
||||
}
|
||||
|
||||
graph(): Promise<CdpFrameGraph | null> {
|
||||
this.graphPromise ??=
|
||||
this.cdp.getFrameGraph?.(this.tabId).catch(() => null) ?? Promise.resolve(null);
|
||||
return this.graphPromise;
|
||||
}
|
||||
|
||||
private frames(): Promise<Map<string, CdpFrame>> {
|
||||
this.framesPromise ??= this.graph().then(
|
||||
(graph) => new Map(graph?.frames.map((frame) => [frame.frameId, frame]) ?? []),
|
||||
);
|
||||
return this.framesPromise;
|
||||
}
|
||||
|
||||
async frame(frameId: string): Promise<CdpFrame | undefined> {
|
||||
return (await this.frames()).get(frameId);
|
||||
}
|
||||
|
||||
/** Topology only: safe to resolve before the caller scrolls frame owners. */
|
||||
async ancestry(frameId: string): Promise<CdpFrame[] | null> {
|
||||
const frames = await this.frames();
|
||||
const path: CdpFrame[] = [];
|
||||
const seen = new Set<string>();
|
||||
let current = frames.get(frameId);
|
||||
if (!current) return null;
|
||||
while (current.parentFrameId) {
|
||||
if (seen.has(current.frameId)) return null;
|
||||
seen.add(current.frameId);
|
||||
path.push(current);
|
||||
const parent = frames.get(current.parentFrameId);
|
||||
if (!parent) return null;
|
||||
current = parent;
|
||||
}
|
||||
return path;
|
||||
}
|
||||
|
||||
layoutMetrics(target: CdpTarget): Promise<LayoutMetrics> {
|
||||
const key = cdpTargetKey(target);
|
||||
let promise = this.metrics.get(key);
|
||||
if (!promise) {
|
||||
promise = this.request<LayoutMetrics>(target, "Page.getLayoutMetrics", {});
|
||||
this.metrics.set(key, promise);
|
||||
}
|
||||
return promise;
|
||||
}
|
||||
|
||||
async viewport(target: CdpTarget): Promise<Size | null> {
|
||||
const { width, height } = cssViewport(await this.layoutMetrics(target));
|
||||
return Number.isFinite(width) && Number.isFinite(height) && width > 0 && height > 0
|
||||
? { width, height }
|
||||
: null;
|
||||
}
|
||||
|
||||
/** The full OOPIF viewport maps to its owner's content quad. Layout metrics
|
||||
* exclude occupied scrollbars and remain the clipping boundary, not the scale. */
|
||||
private frameViewport(target: CdpTarget): Promise<Size | null> {
|
||||
const key = cdpTargetKey(target);
|
||||
let promise = this.frameViewports.get(key);
|
||||
if (!promise) {
|
||||
promise = this.request<{ result?: { value?: Size }; exceptionDetails?: unknown }>(
|
||||
target,
|
||||
"Runtime.evaluate",
|
||||
{
|
||||
expression: "({ width: window.innerWidth, height: window.innerHeight })",
|
||||
returnByValue: true,
|
||||
},
|
||||
).then(({ result, exceptionDetails }) => {
|
||||
const size = result?.value;
|
||||
return !exceptionDetails &&
|
||||
size &&
|
||||
Number.isFinite(size.width) &&
|
||||
Number.isFinite(size.height) &&
|
||||
size.width > 0 &&
|
||||
size.height > 0
|
||||
? size
|
||||
: null;
|
||||
});
|
||||
this.frameViewports.set(key, promise);
|
||||
}
|
||||
return promise;
|
||||
}
|
||||
|
||||
ownerContent(target: CdpTarget, backendNodeId: number): Promise<Quad | null> {
|
||||
const key = `${cdpTargetKey(target)}:${backendNodeId}`;
|
||||
let promise = this.owners.get(key);
|
||||
if (!promise) {
|
||||
promise = this.request<{ model?: { content?: number[] } }>(target, "DOM.getBoxModel", {
|
||||
backendNodeId,
|
||||
}).then((reply) => parseCdpQuad(reply.model?.content));
|
||||
this.owners.set(key, promise);
|
||||
}
|
||||
return promise;
|
||||
}
|
||||
|
||||
/** Same-target owner quads are already target-relative, including nested owners. */
|
||||
async snapshotProjection(
|
||||
source: CoordinateOwner,
|
||||
ownerBackendNodeId: number,
|
||||
ancestorClips: Polygon[],
|
||||
viewport: Size,
|
||||
): Promise<SnapshotProjectionResult> {
|
||||
const key = `${cdpTargetKey(source.target)}:${ownerBackendNodeId}`;
|
||||
let promise = this.snapshotOwners.get(key);
|
||||
if (!promise) {
|
||||
promise = this.snapshotOwner(source.target, ownerBackendNodeId);
|
||||
this.snapshotOwners.set(key, promise);
|
||||
}
|
||||
let owner: { quad: Quad; size: Size } | null;
|
||||
try {
|
||||
owner = await promise;
|
||||
} catch (error) {
|
||||
if (error && typeof error === "object" && "name" in error && error.name === "AbortError")
|
||||
throw error;
|
||||
console.debug("[bsk geometry] frame owner unavailable", error);
|
||||
owner = null;
|
||||
}
|
||||
return owner
|
||||
? {
|
||||
status: "available",
|
||||
projection: {
|
||||
source,
|
||||
geometry: {
|
||||
sourceClips: [],
|
||||
edges: [
|
||||
{
|
||||
sourceViewport: owner.size,
|
||||
destinationQuad: owner.quad,
|
||||
destinationClips: ancestorClips,
|
||||
},
|
||||
],
|
||||
topViewport: viewport,
|
||||
},
|
||||
},
|
||||
}
|
||||
: { status: "unavailable", source, ownerBackendNodeId };
|
||||
}
|
||||
|
||||
/** Register one target's snapshot owners; the batch starts only when a
|
||||
* projection actually needs a size. Single owners keep the cheaper old path. */
|
||||
registerSnapshotOwners(target: CdpTarget, owners: ReadonlySet<number>): void {
|
||||
const key = cdpTargetKey(target);
|
||||
if (owners.size < 2 || this.sizeBatches.has(key)) return;
|
||||
let pending: Promise<Map<number, Size>> | undefined;
|
||||
this.sizeBatches.set(key, () => {
|
||||
pending ??= readSnapshotOwnerSizes(
|
||||
(method, params, cleanup) => this.request(target, method, params, cleanup),
|
||||
owners,
|
||||
).catch((error) => {
|
||||
if (error && typeof error === "object" && "name" in error && error.name === "AbortError")
|
||||
throw error;
|
||||
return new Map<number, Size>();
|
||||
});
|
||||
return pending;
|
||||
});
|
||||
}
|
||||
|
||||
private async snapshotOwner(
|
||||
target: CdpTarget,
|
||||
backendNodeId: number,
|
||||
): Promise<{ quad: Quad; size: Size } | null> {
|
||||
const quad = await this.ownerContent(target, backendNodeId);
|
||||
if (!quad) return null;
|
||||
const batchSize = (await this.sizeBatches.get(cdpTargetKey(target))?.())?.get(backendNodeId);
|
||||
if (this.signal?.aborted) throw new DOMException("geometry aborted", "AbortError");
|
||||
if (batchSize) return { quad, size: batchSize };
|
||||
const resolved = await this.request<{ object?: { objectId?: string } }>(
|
||||
target,
|
||||
"DOM.resolveNode",
|
||||
{ backendNodeId },
|
||||
);
|
||||
const objectId = resolved.object?.objectId;
|
||||
if (!objectId) return null;
|
||||
try {
|
||||
const reply = await this.request<{ result?: { value?: Size }; exceptionDetails?: unknown }>(
|
||||
target,
|
||||
"Runtime.callFunctionOn",
|
||||
{
|
||||
objectId,
|
||||
functionDeclaration: `function() {
|
||||
if (!this.isConnected) return null;
|
||||
const style = getComputedStyle(this);
|
||||
return {
|
||||
width: this.clientWidth - parseFloat(style.paddingLeft) - parseFloat(style.paddingRight),
|
||||
height: this.clientHeight - parseFloat(style.paddingTop) - parseFloat(style.paddingBottom)
|
||||
};
|
||||
}`,
|
||||
returnByValue: true,
|
||||
},
|
||||
);
|
||||
const size = reply.result?.value;
|
||||
return !reply.exceptionDetails &&
|
||||
size &&
|
||||
Number.isFinite(size.width) &&
|
||||
Number.isFinite(size.height) &&
|
||||
size.width > 0 &&
|
||||
size.height > 0
|
||||
? { quad, size }
|
||||
: null;
|
||||
} finally {
|
||||
// Cleanup must still run if cancellation arrived after resolving the object.
|
||||
await this.request(target, "Runtime.releaseObject", { objectId }, true).catch(() => {});
|
||||
}
|
||||
}
|
||||
|
||||
private targetRoot(frames: Map<string, CdpFrame>, frame: CdpFrame): CdpFrame | null {
|
||||
const seen = new Set<string>();
|
||||
let current = frame;
|
||||
while (current.parentFrameId) {
|
||||
if (seen.has(current.frameId)) return null;
|
||||
seen.add(current.frameId);
|
||||
const parent = frames.get(current.parentFrameId);
|
||||
if (!parent) return null;
|
||||
if (cdpTargetKey(parent.target) !== cdpTargetKey(current.target)) break;
|
||||
current = parent;
|
||||
}
|
||||
return current;
|
||||
}
|
||||
|
||||
private async clips(
|
||||
frames: Map<string, CdpFrame>,
|
||||
frame: CdpFrame,
|
||||
root: CdpFrame,
|
||||
): Promise<Polygon[] | null> {
|
||||
const clips: Polygon[] = [];
|
||||
let current = frame;
|
||||
const seen = new Set<string>();
|
||||
while (current.frameId !== root.frameId) {
|
||||
if (seen.has(current.frameId) || !current.parentFrameId) return null;
|
||||
seen.add(current.frameId);
|
||||
const parent = frames.get(current.parentFrameId);
|
||||
if (!parent || current.ownerBackendNodeId === undefined) return null;
|
||||
const quad = await this.ownerContent(parent.target, current.ownerBackendNodeId);
|
||||
if (!quad) return null;
|
||||
clips.push(quad);
|
||||
current = parent;
|
||||
}
|
||||
return clips;
|
||||
}
|
||||
|
||||
/** Input is already in the frame's CDP target viewport, not its local viewport. */
|
||||
targetProjection(frameId: string): Promise<GeometryProjection | null> {
|
||||
let promise = this.projections.get(frameId);
|
||||
if (!promise) {
|
||||
promise = this.buildTargetProjection(frameId);
|
||||
this.projections.set(frameId, promise);
|
||||
}
|
||||
return promise;
|
||||
}
|
||||
|
||||
private async buildTargetProjection(frameId: string): Promise<GeometryProjection | null> {
|
||||
const frames = await this.frames();
|
||||
const frame = frames.get(frameId);
|
||||
if (!frame) return null;
|
||||
let root = this.targetRoot(frames, frame);
|
||||
if (!root) return null;
|
||||
const sourceViewport = await this.viewport(root.target);
|
||||
if (!sourceViewport) return null;
|
||||
const sourceClips = await this.clips(frames, frame, root);
|
||||
if (!sourceClips) return null;
|
||||
const edges: ProjectiveEdge[] = [];
|
||||
const seen = new Set<string>();
|
||||
while (root.parentFrameId) {
|
||||
if (seen.has(root.frameId)) return null;
|
||||
seen.add(root.frameId);
|
||||
const parent = frames.get(root.parentFrameId);
|
||||
if (!parent || root.ownerBackendNodeId === undefined) return null;
|
||||
const destinationQuad = await this.ownerContent(parent.target, root.ownerBackendNodeId);
|
||||
if (!destinationQuad) return null;
|
||||
const source = await this.frameViewport(root.target);
|
||||
const visible = await this.viewport(root.target);
|
||||
const parentRoot = this.targetRoot(frames, parent);
|
||||
if (!source || !visible || !parentRoot) return null;
|
||||
const destinationClips = await this.clips(frames, parent, parentRoot);
|
||||
if (!destinationClips) return null;
|
||||
const edge = { sourceViewport: source, destinationQuad, destinationClips };
|
||||
// Keep scrollbar strips clipped at every target boundary, including
|
||||
// intermediate OOPIFs. Project the clip with the same full-viewport scale.
|
||||
if (source.width !== visible.width || source.height !== visible.height)
|
||||
destinationClips.push(projectPolygon(viewportPolygon(visible), edge));
|
||||
edges.push(edge);
|
||||
root = parentRoot;
|
||||
}
|
||||
const topViewport = await this.viewport(root.target);
|
||||
return topViewport ? { sourceClips, edges, topViewport } : null;
|
||||
}
|
||||
}
|
||||
@@ -1,74 +0,0 @@
|
||||
import type { Size } from "../geometry";
|
||||
|
||||
interface SerializedValue {
|
||||
type: string;
|
||||
value?: unknown;
|
||||
}
|
||||
|
||||
type Send = <T>(method: string, params: object, cleanup?: boolean) => Promise<T>;
|
||||
|
||||
/** Batch only accessible frame owners. Missing/shadow/cross-origin owners keep
|
||||
* the existing node-scoped read; no page-wide style columns are requested. */
|
||||
export async function readSnapshotOwnerSizes(
|
||||
send: Send,
|
||||
owners: ReadonlySet<number>,
|
||||
): Promise<Map<number, Size>> {
|
||||
const sizes = new Map<number, Size>();
|
||||
const objectGroup = `bsk-frame-sizes-${crypto.randomUUID()}`;
|
||||
try {
|
||||
const reply = await send<{ result?: { deepSerializedValue?: SerializedValue } }>(
|
||||
"Runtime.evaluate",
|
||||
{
|
||||
expression: `(() => {
|
||||
const result = [];
|
||||
const documents = [document];
|
||||
for (let i = 0; i < documents.length && result.length < ${owners.size}; i++) {
|
||||
for (const owner of documents[i].querySelectorAll('iframe,frame')) {
|
||||
if (result.length >= ${owners.size}) break;
|
||||
if (!owner.isConnected) continue;
|
||||
const style = getComputedStyle(owner);
|
||||
result.push([owner, JSON.stringify({
|
||||
width: owner.clientWidth - parseFloat(style.paddingLeft) - parseFloat(style.paddingRight),
|
||||
height: owner.clientHeight - parseFloat(style.paddingTop) - parseFloat(style.paddingBottom)
|
||||
})]);
|
||||
try { if (owner.contentDocument) documents.push(owner.contentDocument); } catch {}
|
||||
}
|
||||
}
|
||||
return result;
|
||||
})()`,
|
||||
objectGroup,
|
||||
serializationOptions: {
|
||||
serialization: "deep",
|
||||
maxDepth: 3,
|
||||
additionalParameters: { maxNodeDepth: 0, includeShadowTree: "none" },
|
||||
},
|
||||
},
|
||||
);
|
||||
const result = reply.result?.deepSerializedValue;
|
||||
if (result?.type !== "array" || !Array.isArray(result.value)) return sizes;
|
||||
for (const entry of result.value as SerializedValue[]) {
|
||||
if (entry.type !== "array" || !Array.isArray(entry.value)) continue;
|
||||
const [node, data] = entry.value as SerializedValue[];
|
||||
if (node?.type !== "node" || data?.type !== "string" || typeof data.value !== "string")
|
||||
continue;
|
||||
const id = (node.value as { backendNodeId?: number } | undefined)?.backendNodeId;
|
||||
if (id === undefined || !owners.has(id)) continue;
|
||||
try {
|
||||
const size = JSON.parse(data.value) as Size;
|
||||
if (
|
||||
size &&
|
||||
Number.isFinite(size.width) &&
|
||||
Number.isFinite(size.height) &&
|
||||
size.width > 0 &&
|
||||
size.height > 0
|
||||
)
|
||||
sizes.set(id, size);
|
||||
} catch {
|
||||
/* An invalid entry uses the existing individual read. */
|
||||
}
|
||||
}
|
||||
} finally {
|
||||
await send("Runtime.releaseObjectGroup", { objectGroup }, true).catch(() => {});
|
||||
}
|
||||
return sizes;
|
||||
}
|
||||
@@ -1,4 +1,5 @@
|
||||
// DOM interaction tools — click, hover, focus/blur, fill, press, and select.
|
||||
// DOM interaction tools — `tool.click`, `tool.fill`, `tool.press`, and
|
||||
// `tool.select`.
|
||||
//
|
||||
// All interaction tools:
|
||||
// 1. Resolve target tab (sandbox: must be inside Agent Window).
|
||||
@@ -13,14 +14,10 @@ import { ChromiumCdp } from "@/browser-driver/chromium-cdp";
|
||||
import type { CdpTarget } from "@/browser-driver/frame-graph";
|
||||
import type { SessionContext, SessionManager } from "@/session-manager/manager";
|
||||
import type {
|
||||
BlurParams,
|
||||
BlurResult,
|
||||
ClickParams,
|
||||
ClickResult,
|
||||
FillParams,
|
||||
FillResult,
|
||||
FocusParams,
|
||||
FocusResult,
|
||||
HoverParams,
|
||||
HoverResult,
|
||||
KeyModifier,
|
||||
@@ -172,7 +169,7 @@ export async function resolveBackendNode(
|
||||
};
|
||||
}
|
||||
if (hasRef) {
|
||||
const resolved = resolveSnapshotRef(ctx, params.ref as string, target.tabId);
|
||||
const resolved = resolveSnapshotRef(ctx, params.ref as string, target.tabId, "interact");
|
||||
if (isRpcError(resolved)) return resolved;
|
||||
return {
|
||||
backendNodeId: resolved.backendNodeId,
|
||||
@@ -186,8 +183,6 @@ export async function resolveBackendNode(
|
||||
}
|
||||
// selector path
|
||||
try {
|
||||
// Selector lookup itself attaches CDP, even when no element is found.
|
||||
cdp.trackSessionTab?.(ctx.sessionId, target.tabId);
|
||||
const doc = await cdp.send<{ root?: { nodeId?: number } }>(target.tabId, "DOM.getDocument", {
|
||||
depth: 0,
|
||||
});
|
||||
@@ -230,207 +225,6 @@ export async function resolveBackendNode(
|
||||
}
|
||||
}
|
||||
|
||||
// Check the target's own root, then its hosts: closed shadow roots are not
|
||||
// reachable via host.shadowRoot. DOM focus remains meaningful in background tabs.
|
||||
const FOCUS_CHECK = `function() {
|
||||
if (!this.isConnected) return false;
|
||||
let element = this;
|
||||
while (element) {
|
||||
const root = element.getRootNode();
|
||||
if (root.activeElement !== element) return false;
|
||||
element = root.host;
|
||||
}
|
||||
return true;
|
||||
}`;
|
||||
|
||||
const BLUR_TARGET = `function() {
|
||||
if (!this.isConnected) throw new Error('blur target is detached');
|
||||
const wasFocused = (${FOCUS_CHECK}).call(this);
|
||||
if (typeof this.blur !== 'function') return { ok: false, was_focused: wasFocused };
|
||||
this.blur();
|
||||
return { ok: true, was_focused: wasFocused };
|
||||
}`;
|
||||
|
||||
interface FocusScriptReply<T> {
|
||||
result?: { value?: T };
|
||||
exceptionDetails?: { text?: string; exception?: { description?: string } };
|
||||
}
|
||||
|
||||
function checkFocusAbort(signal: AbortSignal | undefined): void {
|
||||
if (signal?.aborted) throw new DOMException("interaction aborted", "AbortError");
|
||||
}
|
||||
|
||||
// Only focus/blur use this view. Guard every CDP boundary, including commands
|
||||
// inside selector resolution and frame scrolling, without changing other tools.
|
||||
function focusCdp(cdp: CdpRunner, signal: AbortSignal | undefined): CdpRunner {
|
||||
const send = <T = unknown>(target: CdpTarget, method: string, params?: object): Promise<T> => {
|
||||
checkFocusAbort(signal);
|
||||
return cdpRunnerForTarget(cdp, target).send<T>(target.tabId, method, params);
|
||||
};
|
||||
return {
|
||||
send: (tabId, method, params) => send({ tabId }, method, params),
|
||||
sendToTarget: send,
|
||||
trackSessionTab: cdp.trackSessionTab?.bind(cdp),
|
||||
getFrameGraph: cdp.getFrameGraph
|
||||
? (tabId) => {
|
||||
checkFocusAbort(signal);
|
||||
return cdp.getFrameGraph!(tabId);
|
||||
}
|
||||
: undefined,
|
||||
};
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// tool.focus / tool.blur
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
export function handleFocus(
|
||||
manager: SessionManager,
|
||||
params: FocusParams,
|
||||
deps: InteractionDeps = getDefaultDeps(),
|
||||
): Promise<FocusResult | RpcError> {
|
||||
return changeFocus(manager, params, deps, "focus");
|
||||
}
|
||||
|
||||
export function handleBlur(
|
||||
manager: SessionManager,
|
||||
params: BlurParams,
|
||||
deps: InteractionDeps = getDefaultDeps(),
|
||||
): Promise<BlurResult | RpcError> {
|
||||
return changeFocus(manager, params, deps, "blur");
|
||||
}
|
||||
|
||||
function changeFocus(
|
||||
manager: SessionManager,
|
||||
params: FocusParams,
|
||||
deps: InteractionDeps,
|
||||
action: "focus",
|
||||
): Promise<FocusResult | RpcError>;
|
||||
function changeFocus(
|
||||
manager: SessionManager,
|
||||
params: BlurParams,
|
||||
deps: InteractionDeps,
|
||||
action: "blur",
|
||||
): Promise<BlurResult | RpcError>;
|
||||
async function changeFocus(
|
||||
manager: SessionManager,
|
||||
params: FocusParams | BlurParams,
|
||||
deps: InteractionDeps,
|
||||
action: "focus" | "blur",
|
||||
): Promise<FocusResult | BlurResult | RpcError> {
|
||||
const ctx = lookupSession(manager, params, action);
|
||||
if (isRpcError(ctx)) return ctx;
|
||||
const cdp = focusCdp(deps.cdp, deps.signal);
|
||||
let objectId: string | undefined;
|
||||
let cleanupCdp: CdpRunner | undefined;
|
||||
let tabId: number | undefined;
|
||||
try {
|
||||
checkFocusAbort(deps.signal);
|
||||
const target = await resolveTargetTab(manager, ctx, params.tab_id, deps.tabsApi);
|
||||
checkFocusAbort(deps.signal);
|
||||
if (isRpcError(target)) return target;
|
||||
const denied = enforceAgentWindow(ctx, target, action);
|
||||
if (denied) return denied;
|
||||
tabId = target.tabId;
|
||||
const dialogCursor = markDialogCursor(deps.cdp, tabId);
|
||||
const node = await resolveBackendNode(cdp, ctx, target, params, action);
|
||||
checkFocusAbort(deps.signal);
|
||||
if (isRpcError(node)) return node;
|
||||
const nodeCdp = cdpRunnerForTarget(cdp, node.cdpTarget);
|
||||
cleanupCdp = cdpRunnerForTarget(deps.cdp, node.cdpTarget);
|
||||
deps.cdp.trackSessionTab?.(ctx.sessionId, tabId);
|
||||
|
||||
if (action === "focus") {
|
||||
const scrollErr = await scrollElementAndFramesIntoView(
|
||||
cdp,
|
||||
tabId,
|
||||
node.cdpTarget,
|
||||
node.backendNodeId,
|
||||
node.frameId,
|
||||
);
|
||||
checkFocusAbort(deps.signal);
|
||||
if (scrollErr) return scrollErr;
|
||||
}
|
||||
const resolved = await backendNodeToObject(nodeCdp, tabId, node.backendNodeId);
|
||||
// Keep the handle before checking cancellation so finally can release it.
|
||||
if (!isRpcError(resolved)) objectId = resolved;
|
||||
checkFocusAbort(deps.signal);
|
||||
if (isRpcError(resolved)) return resolved;
|
||||
|
||||
const runScript = async <T>(functionDeclaration: string): Promise<T | undefined> => {
|
||||
const reply = await nodeCdp.send<FocusScriptReply<T>>(
|
||||
target.tabId,
|
||||
"Runtime.callFunctionOn",
|
||||
{
|
||||
objectId,
|
||||
functionDeclaration,
|
||||
returnByValue: true,
|
||||
},
|
||||
);
|
||||
checkFocusAbort(deps.signal);
|
||||
if (reply.exceptionDetails) {
|
||||
const details = reply.exceptionDetails;
|
||||
throw new Error(
|
||||
`${action} script failed: ${details.exception?.description ?? details.text ?? "unknown exception"}`,
|
||||
);
|
||||
}
|
||||
return reply.result?.value;
|
||||
};
|
||||
|
||||
let wasFocused: boolean | undefined;
|
||||
if (action === "focus") {
|
||||
await nodeCdp.send(tabId, "DOM.focus", { backendNodeId: node.backendNodeId });
|
||||
checkFocusAbort(deps.signal);
|
||||
} else {
|
||||
const mutation = await runScript<{ ok: boolean; was_focused: boolean }>(BLUR_TARGET);
|
||||
if (typeof mutation?.ok !== "boolean" || typeof mutation.was_focused !== "boolean") {
|
||||
throw new Error("blur script returned an unexpected result");
|
||||
}
|
||||
if (!mutation.ok) {
|
||||
return { code: "invalid_params", message: "target element does not support blur()" };
|
||||
}
|
||||
wasFocused = mutation.was_focused;
|
||||
}
|
||||
// Use a separate call so microtasks from focus/blur handlers finish before
|
||||
// we report success. In particular, a blur handler can restore focus.
|
||||
const focused = await runScript<boolean>(FOCUS_CHECK);
|
||||
if (typeof focused !== "boolean") {
|
||||
throw new Error(`${action} verification returned an unexpected result`);
|
||||
}
|
||||
if (focused !== (action === "focus")) {
|
||||
throw new Error(
|
||||
action === "focus"
|
||||
? "target element did not become focused"
|
||||
: "target element remained focused after blur()",
|
||||
);
|
||||
}
|
||||
return attachDialogs(deps.cdp, tabId, dialogCursor, {
|
||||
tab_id: tabId,
|
||||
used_ref: node.usedRef,
|
||||
used_selector: node.usedSelector,
|
||||
focused,
|
||||
...(action === "blur" ? { was_focused: wasFocused! } : {}),
|
||||
});
|
||||
} catch (err) {
|
||||
return (
|
||||
throwIfAborted(deps.signal) ?? {
|
||||
code: "cdp_failed",
|
||||
message: err instanceof Error ? err.message : String(err),
|
||||
}
|
||||
);
|
||||
} finally {
|
||||
if (objectId !== undefined && cleanupCdp && tabId !== undefined) {
|
||||
// Cleanup must also run after cancellation. Navigation may have already
|
||||
// disposed the object, which must not replace the operation's result.
|
||||
try {
|
||||
await cleanupCdp.send(tabId, "Runtime.releaseObject", { objectId });
|
||||
} catch {
|
||||
// The target or execution context may no longer exist.
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
export async function resolveActionTarget(
|
||||
cdp: CdpRunner,
|
||||
ctx: SessionContext,
|
||||
@@ -813,53 +607,6 @@ type SelectMutationResult =
|
||||
// tool.fill
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
type FillFailureReason =
|
||||
| "target_not_fillable"
|
||||
| "fill_value_invalid"
|
||||
| "fill_target_changed"
|
||||
| "fill_focus_lost"
|
||||
| "fill_value_mismatch"
|
||||
| "fill_failed";
|
||||
|
||||
type FillPreparation =
|
||||
| { before: string; expected: string }
|
||||
| { reason: FillFailureReason; error: string };
|
||||
|
||||
type FillReadiness = "ready" | "background" | "fill_target_changed" | "fill_focus_lost";
|
||||
|
||||
function fillError(reason: FillFailureReason, message: string): RpcError {
|
||||
return rpcError(
|
||||
reason === "target_not_fillable" || reason === "fill_value_invalid"
|
||||
? "invalid_params"
|
||||
: "cdp_failed",
|
||||
reason,
|
||||
message,
|
||||
);
|
||||
}
|
||||
|
||||
interface FillScriptReply<T> {
|
||||
result?: { value?: T };
|
||||
exceptionDetails?: unknown;
|
||||
}
|
||||
|
||||
const FILL_EDITABLE_FUNCTION = `function() {
|
||||
const tag = this.tagName.toLowerCase();
|
||||
const supported = tag === 'input'
|
||||
? ['text', 'search', 'tel', 'url', 'email', 'password', 'number'].includes(this.type)
|
||||
: tag === 'textarea' || this.isContentEditable;
|
||||
return this.isConnected && supported && !this.readOnly && !this.matches(':disabled');
|
||||
}`;
|
||||
|
||||
// Chrome renders a trailing editable newline with an empty <div><br></div>.
|
||||
// innerText includes the padding break; it is not an extra typed character.
|
||||
const FILL_VALUE_FUNCTION = `function() {
|
||||
if (!this.isContentEditable) return this.value;
|
||||
const value = this.innerText;
|
||||
const tail = this.lastChild;
|
||||
const padding = tail && tail.nodeName === 'DIV' && tail.childNodes.length === 1 && tail.firstChild.nodeName === 'BR';
|
||||
return padding && value.endsWith('\\n\\n') ? value.slice(0, -1) : value;
|
||||
}`;
|
||||
|
||||
export async function handleFill(
|
||||
manager: SessionManager,
|
||||
params: FillParams,
|
||||
@@ -911,8 +658,12 @@ export async function handleFill(
|
||||
if (throwIfAborted(deps.signal)) {
|
||||
return { code: "cancelled", message: "fill aborted" };
|
||||
}
|
||||
await nodeCdp.send(target.tabId, "DOM.focus", { backendNodeId: node.backendNodeId });
|
||||
} catch (err) {
|
||||
return fillError("fill_failed", err instanceof Error ? err.message : String(err));
|
||||
return {
|
||||
code: "cdp_failed",
|
||||
message: err instanceof Error ? err.message : String(err),
|
||||
};
|
||||
}
|
||||
|
||||
if (throwIfAborted(deps.signal)) {
|
||||
@@ -925,252 +676,57 @@ export async function handleFill(
|
||||
const clearBefore = params.clear_before ?? true;
|
||||
|
||||
try {
|
||||
if (throwIfAborted(deps.signal)) {
|
||||
return { code: "cancelled", message: "fill aborted" };
|
||||
}
|
||||
try {
|
||||
await nodeCdp.send(target.tabId, "DOM.focus", { backendNodeId: node.backendNodeId });
|
||||
} catch (error) {
|
||||
// Chrome rejects DOM.focus for disabled controls, including inherited
|
||||
// fieldset state. Classify the live target before treating this as a
|
||||
// browser failure; the normal path needs no extra round trip.
|
||||
const editable = await nodeCdp.send<FillScriptReply<boolean>>(
|
||||
target.tabId,
|
||||
"Runtime.callFunctionOn",
|
||||
{ objectId, functionDeclaration: FILL_EDITABLE_FUNCTION, returnByValue: true },
|
||||
);
|
||||
if (throwIfAborted(deps.signal)) {
|
||||
return { code: "cancelled", message: "fill aborted" };
|
||||
}
|
||||
if (!editable.exceptionDetails && editable.result?.value === false) {
|
||||
return fillError(
|
||||
"target_not_fillable",
|
||||
"fill target is not editable or its input type is unsupported",
|
||||
);
|
||||
}
|
||||
throw error;
|
||||
}
|
||||
if (throwIfAborted(deps.signal)) {
|
||||
return { code: "cancelled", message: "fill aborted" };
|
||||
}
|
||||
// Check editability before clearing. Keep the expected result tied to
|
||||
// this object, including the existing value on the append path.
|
||||
const prepared = await nodeCdp.send<FillScriptReply<FillPreparation>>(
|
||||
target.tabId,
|
||||
"Runtime.callFunctionOn",
|
||||
{
|
||||
if (clearBefore) {
|
||||
// Clear input/textarea value or wipe contenteditable innerText,
|
||||
// then fire `input` so frameworks observe the empty state.
|
||||
await nodeCdp.send(target.tabId, "Runtime.callFunctionOn", {
|
||||
objectId,
|
||||
functionDeclaration: `function(value, clearBefore) {
|
||||
const tag = this.tagName.toLowerCase();
|
||||
const native = tag === 'input' || tag === 'textarea';
|
||||
if (!(${FILL_EDITABLE_FUNCTION}).call(this)) return { reason: 'target_not_fillable', error: 'fill target is not editable or its input type is unsupported' };
|
||||
if (this.getRootNode().activeElement !== this) return { reason: 'fill_focus_lost', error: 'fill target does not have focus' };
|
||||
const before = clearBefore ? '' : (${FILL_VALUE_FUNCTION}).call(this);
|
||||
let expected = before + value;
|
||||
if (native) {
|
||||
// Use the browser's own value sanitization (e.g. textarea
|
||||
// line endings) without changing the live control.
|
||||
const normalizer = this.ownerDocument.createElement(tag);
|
||||
if (tag === 'input') {
|
||||
normalizer.type = this.type;
|
||||
normalizer.multiple = this.multiple;
|
||||
}
|
||||
// insertText treats line breaks in a single-line input as spaces.
|
||||
if (tag === 'input') expected = expected.replace(/\\r\\n|\\r|\\n/g, ' ');
|
||||
normalizer.value = expected;
|
||||
if (expected !== '' && normalizer.value === '' && this.type === 'number') {
|
||||
return { reason: 'fill_value_invalid', error: 'fill value is not valid for a number input' };
|
||||
}
|
||||
expected = normalizer.value;
|
||||
if (this.type !== 'number' && this.maxLength >= 0 && expected.length > this.maxLength) {
|
||||
return { reason: 'fill_value_invalid', error: 'fill value exceeds the target maxlength' };
|
||||
}
|
||||
} else {
|
||||
expected = expected.replace(/\\r\\n?/g, '\\n');
|
||||
functionDeclaration: `function() {
|
||||
if (this.isContentEditable) { this.textContent = ''; }
|
||||
else {
|
||||
const proto = this instanceof HTMLTextAreaElement
|
||||
? HTMLTextAreaElement.prototype
|
||||
: HTMLInputElement.prototype;
|
||||
const descriptor = Object.getOwnPropertyDescriptor(proto, 'value');
|
||||
if (descriptor && descriptor.set) descriptor.set.call(this, '');
|
||||
else this.value = '';
|
||||
}
|
||||
if (clearBefore) {
|
||||
if (native) {
|
||||
const proto = tag === 'textarea' ? HTMLTextAreaElement.prototype : HTMLInputElement.prototype;
|
||||
Object.getOwnPropertyDescriptor(proto, 'value').set.call(this, '');
|
||||
} else {
|
||||
this.textContent = '';
|
||||
}
|
||||
this.dispatchEvent(new Event('input', { bubbles: true }));
|
||||
}
|
||||
return { before, expected };
|
||||
this.dispatchEvent(new Event('input', { bubbles: true }));
|
||||
}`,
|
||||
arguments: [{ value: params.value }, { value: clearBefore }],
|
||||
returnByValue: true,
|
||||
},
|
||||
);
|
||||
if (throwIfAborted(deps.signal)) {
|
||||
return { code: "cancelled", message: "fill aborted" };
|
||||
}
|
||||
if (prepared.exceptionDetails) {
|
||||
return fillError("fill_failed", "fill preparation script failed");
|
||||
}
|
||||
const preparation = prepared.result?.value;
|
||||
if (preparation && "error" in preparation) {
|
||||
return fillError(preparation.reason, preparation.error);
|
||||
}
|
||||
if (typeof preparation?.before !== "string" || typeof preparation?.expected !== "string") {
|
||||
return fillError("fill_failed", "fill preparation returned an unexpected result");
|
||||
}
|
||||
// A separate call runs after the clearing event's microtasks drain.
|
||||
// DOM focus works in background tabs. Use document.hasFocus() only to
|
||||
// detect deferred focus events, never to reject background input.
|
||||
const checkReady = async (): Promise<FillReadiness | RpcError> => {
|
||||
const reply = await nodeCdp.send<FillScriptReply<FillReadiness>>(
|
||||
target.tabId,
|
||||
"Runtime.callFunctionOn",
|
||||
{
|
||||
objectId,
|
||||
functionDeclaration: `function(before) {
|
||||
if (!(${FILL_EDITABLE_FUNCTION}).call(this) ||
|
||||
(${FILL_VALUE_FUNCTION}).call(this) !== before) return 'fill_target_changed';
|
||||
if (this.getRootNode().activeElement !== this) return 'fill_focus_lost';
|
||||
return this.ownerDocument.hasFocus() ? 'ready' : 'background';
|
||||
}`,
|
||||
arguments: [{ value: preparation.before }],
|
||||
returnByValue: true,
|
||||
},
|
||||
);
|
||||
const state = reply.result?.value;
|
||||
if (
|
||||
reply.exceptionDetails ||
|
||||
(state !== "ready" &&
|
||||
state !== "background" &&
|
||||
state !== "fill_target_changed" &&
|
||||
state !== "fill_focus_lost")
|
||||
) {
|
||||
return fillError(
|
||||
"fill_failed",
|
||||
"fill readiness script failed or returned an unexpected result",
|
||||
);
|
||||
}
|
||||
return state;
|
||||
};
|
||||
let ready = await checkReady();
|
||||
if (throwIfAborted(deps.signal)) {
|
||||
return { code: "cancelled", message: "fill aborted" };
|
||||
}
|
||||
// Restore focus once only if clearing left this same target editable
|
||||
// and unchanged. Recheck after focus handlers have run.
|
||||
if (clearBefore && ready === "fill_focus_lost") {
|
||||
await nodeCdp.send(target.tabId, "DOM.focus", { backendNodeId: node.backendNodeId });
|
||||
if (throwIfAborted(deps.signal)) {
|
||||
return { code: "cancelled", message: "fill aborted" };
|
||||
}
|
||||
ready = await checkReady();
|
||||
});
|
||||
}
|
||||
if (throwIfAborted(deps.signal)) {
|
||||
return { code: "cancelled", message: "fill aborted" };
|
||||
}
|
||||
if (typeof ready !== "string") return ready;
|
||||
if (ready !== "ready" && ready !== "background") {
|
||||
return fillError(ready, "fill target changed or lost focus before typing");
|
||||
}
|
||||
if (params.value !== "" && (!clearBefore || ready === "background")) {
|
||||
// Native editing commands also support number/email inputs, whose
|
||||
// selection APIs cannot set a caret, and multiline contenteditables.
|
||||
// Also do this for background replacement: CDP input focuses the
|
||||
// renderer, delivering deferred focus events before it inserts text.
|
||||
// Use a command-only event so this does not invoke an End shortcut.
|
||||
try {
|
||||
await deps.cdp.send(target.tabId, "Input.dispatchKeyEvent", {
|
||||
type: "rawKeyDown",
|
||||
commands: ["moveToEndOfDocument"],
|
||||
});
|
||||
} finally {
|
||||
await deps.cdp.send(target.tabId, "Input.dispatchKeyEvent", { type: "keyUp" });
|
||||
}
|
||||
if (throwIfAborted(deps.signal)) {
|
||||
return { code: "cancelled", message: "fill aborted" };
|
||||
}
|
||||
// Focus and key handlers can change the target or move focus too.
|
||||
ready = await checkReady();
|
||||
if (throwIfAborted(deps.signal)) {
|
||||
return { code: "cancelled", message: "fill aborted" };
|
||||
}
|
||||
if (typeof ready !== "string") return ready;
|
||||
if (ready !== "ready" && ready !== "background") {
|
||||
return fillError(ready, "fill target changed or lost focus while positioning the caret");
|
||||
}
|
||||
}
|
||||
// CDP `Input.insertText` handles IME / multi-byte input out of the
|
||||
// box, much more reliably than per-key `dispatchKeyEvent`.
|
||||
if (params.value !== "") {
|
||||
await deps.cdp.send(target.tabId, "Input.insertText", { text: params.value });
|
||||
}
|
||||
await deps.cdp.send(target.tabId, "Input.insertText", { text: params.value });
|
||||
if (throwIfAborted(deps.signal)) {
|
||||
return { code: "cancelled", message: "fill aborted" };
|
||||
}
|
||||
// Keep the existing notifications, then read in a separate call so
|
||||
// nested microtasks queued by the page cannot race the verification.
|
||||
const notified = await nodeCdp.send<FillScriptReply<unknown>>(
|
||||
target.tabId,
|
||||
"Runtime.callFunctionOn",
|
||||
{
|
||||
objectId,
|
||||
functionDeclaration: `function() {
|
||||
this.dispatchEvent(new Event('input', { bubbles: true }));
|
||||
this.dispatchEvent(new Event('change', { bubbles: true }));
|
||||
}`,
|
||||
returnByValue: true,
|
||||
},
|
||||
);
|
||||
if (throwIfAborted(deps.signal)) {
|
||||
return { code: "cancelled", message: "fill aborted" };
|
||||
}
|
||||
if (notified.exceptionDetails) {
|
||||
return fillError("fill_failed", "fill notification script failed");
|
||||
}
|
||||
const verified = await nodeCdp.send<
|
||||
FillScriptReply<{ connected: boolean; matches: boolean; valueLength: number }>
|
||||
>(target.tabId, "Runtime.callFunctionOn", {
|
||||
// Fire `input` + `change` so React / Vue controlled inputs commit.
|
||||
await nodeCdp.send(target.tabId, "Runtime.callFunctionOn", {
|
||||
objectId,
|
||||
functionDeclaration: `function(expected) {
|
||||
const value = (${FILL_VALUE_FUNCTION}).call(this);
|
||||
return { connected: this.isConnected, matches: value === expected, valueLength: value.length };
|
||||
}`,
|
||||
arguments: [{ value: preparation.expected }],
|
||||
functionDeclaration: `function() {
|
||||
this.dispatchEvent(new Event('input', { bubbles: true }));
|
||||
this.dispatchEvent(new Event('change', { bubbles: true }));
|
||||
}`,
|
||||
returnByValue: true,
|
||||
});
|
||||
if (throwIfAborted(deps.signal)) {
|
||||
return { code: "cancelled", message: "fill aborted" };
|
||||
}
|
||||
const verification = verified.result?.value;
|
||||
if (
|
||||
verified.exceptionDetails ||
|
||||
typeof verification?.connected !== "boolean" ||
|
||||
typeof verification?.matches !== "boolean" ||
|
||||
typeof verification?.valueLength !== "number"
|
||||
) {
|
||||
return fillError(
|
||||
"fill_failed",
|
||||
"fill verification script failed or returned an unexpected result",
|
||||
);
|
||||
}
|
||||
if (!verification.connected) {
|
||||
return fillError("fill_target_changed", "fill target was removed or replaced during input");
|
||||
}
|
||||
if (!verification.matches) {
|
||||
return fillError(
|
||||
"fill_value_mismatch",
|
||||
"fill could not verify the expected value; observe the page before deciding whether to retry",
|
||||
);
|
||||
}
|
||||
return attachDialogs(deps.cdp, target.tabId, dialogCursor, {
|
||||
tab_id: target.tabId,
|
||||
used_ref: node.usedRef,
|
||||
used_selector: node.usedSelector,
|
||||
value_length: verification.valueLength,
|
||||
});
|
||||
} catch (err) {
|
||||
return fillError("fill_failed", err instanceof Error ? err.message : String(err));
|
||||
} finally {
|
||||
await nodeCdp.send(target.tabId, "Runtime.releaseObject", { objectId }).catch(() => undefined);
|
||||
return {
|
||||
code: "cdp_failed",
|
||||
message: err instanceof Error ? err.message : String(err),
|
||||
};
|
||||
}
|
||||
|
||||
return attachDialogs(deps.cdp, target.tabId, dialogCursor, {
|
||||
tab_id: target.tabId,
|
||||
used_ref: node.usedRef,
|
||||
used_selector: node.usedSelector,
|
||||
value_length: params.value.length,
|
||||
});
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
@@ -28,13 +28,7 @@ import type {
|
||||
RpcError,
|
||||
WaitUntil,
|
||||
} from "@/transport/types";
|
||||
import {
|
||||
type BrowserNavigationApi,
|
||||
chromeBrowserNavigationApi,
|
||||
navigateWithBrowserApi,
|
||||
} from "./browser-navigation";
|
||||
import { attachDialogs, markDialogCursor } from "./dialogs";
|
||||
import { cdpError, isCdpExtensionAccessDenied } from "./errors";
|
||||
import {
|
||||
type CdpRunner,
|
||||
type ChromeTabsApi,
|
||||
@@ -48,7 +42,6 @@ import {
|
||||
export interface NavigationDeps {
|
||||
cdp: CdpRunner;
|
||||
tabsApi: ChromeTabsApi;
|
||||
browserNavigation?: BrowserNavigationApi;
|
||||
/** Optional AbortSignal — M7 abort hook (M10.2 will wire the full chain). */
|
||||
signal?: AbortSignal;
|
||||
/** Override default timeout when the caller omits `timeout_ms`. */
|
||||
@@ -486,81 +479,6 @@ async function readTabUrl(api: ChromeTabsApi, tabId: number): Promise<string | u
|
||||
}
|
||||
}
|
||||
|
||||
/** Recover only a failed preflight; never replay an already-dispatched navigation. */
|
||||
async function recoverBrowserNavigation(
|
||||
deps: NavigationDeps,
|
||||
tabId: number,
|
||||
action: (api: BrowserNavigationApi) => Promise<unknown>,
|
||||
waitUntil: WaitUntil,
|
||||
timeoutMs: number,
|
||||
): Promise<ReloadResult | RpcError> {
|
||||
const abort = linkedAbortSignal(deps.signal);
|
||||
const deadline = Date.now() + timeoutMs;
|
||||
const api = deps.browserNavigation ?? chromeBrowserNavigationApi;
|
||||
try {
|
||||
let outcome = await navigateWithBrowserApi(
|
||||
api,
|
||||
tabId,
|
||||
() => action(api),
|
||||
waitUntil === "networkidle" ? "commit" : waitUntil,
|
||||
timeoutMs,
|
||||
abort.signal,
|
||||
);
|
||||
if (outcome.reached === "failed") return outcome.error;
|
||||
if (outcome.reached === "cancelled" || abort.signal.aborted) {
|
||||
return { code: "cancelled", message: "navigation recovery aborted" };
|
||||
}
|
||||
if (outcome.reached === "match") {
|
||||
// A completed reload is not a recovery if the restricted frame remains.
|
||||
await deps.cdp.send(tabId, "Page.enable", {});
|
||||
if (abort.signal.aborted)
|
||||
return { code: "cancelled", message: "navigation recovery aborted" };
|
||||
if (waitUntil === "networkidle") {
|
||||
// webNavigation cannot prove network idle. Subscribe on the new
|
||||
// document before enabling CDP lifecycle events after its commit.
|
||||
const frame = await readMainFrameInfo(deps.cdp, tabId);
|
||||
if (!frame.frameId) return cdpError("no main frame after navigation");
|
||||
const remaining = deadline - Date.now();
|
||||
if (remaining <= 0) {
|
||||
outcome = { reached: "timeout", lastLifecycle: "commit" };
|
||||
} else {
|
||||
const wait = startLifecycleWait(
|
||||
deps.cdp,
|
||||
tabId,
|
||||
frame.frameId,
|
||||
"networkIdle",
|
||||
remaining,
|
||||
abort.signal,
|
||||
{ loaderId: frame.loaderId ?? undefined },
|
||||
);
|
||||
await deps.cdp.send(tabId, "Page.setLifecycleEventsEnabled", { enabled: true });
|
||||
outcome = await wait.promise;
|
||||
}
|
||||
}
|
||||
}
|
||||
if (outcome.reached === "cancelled" || abort.signal.aborted) {
|
||||
return { code: "cancelled", message: "navigation recovery aborted" };
|
||||
}
|
||||
return {
|
||||
tab_id: tabId,
|
||||
final_url: await readTabUrl(deps.tabsApi, tabId),
|
||||
reached: outcome.reached === "match" ? waitUntil : "timeout",
|
||||
...(outcome.reached === "timeout"
|
||||
? {
|
||||
error_text: `timed out waiting for ${waitUntil} during navigation recovery after ${timeoutMs}ms`,
|
||||
}
|
||||
: {}),
|
||||
};
|
||||
} catch (error) {
|
||||
return abort.signal.aborted
|
||||
? { code: "cancelled", message: "navigation recovery aborted" }
|
||||
: cdpError(error);
|
||||
} finally {
|
||||
abort.abort();
|
||||
abort.cleanup();
|
||||
}
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// tool.navigate
|
||||
// ---------------------------------------------------------------------------
|
||||
@@ -587,20 +505,7 @@ export async function handleNavigate(
|
||||
|
||||
try {
|
||||
deps.cdp.trackSessionTab?.(ctx.sessionId, target.tabId);
|
||||
try {
|
||||
await ensureCdpReady(deps.cdp, target.tabId);
|
||||
} catch (error) {
|
||||
if (!isCdpExtensionAccessDenied(error)) throw error;
|
||||
const recovered = await recoverBrowserNavigation(
|
||||
deps,
|
||||
target.tabId,
|
||||
(api) => api.update(target.tabId, { url: params.url }),
|
||||
waitUntil,
|
||||
timeoutMs,
|
||||
);
|
||||
if (isRpcError(recovered)) return recovered;
|
||||
return attachDialogs(deps.cdp, target.tabId, dialogCursor, { ...recovered, url: params.url });
|
||||
}
|
||||
await ensureCdpReady(deps.cdp, target.tabId);
|
||||
const expected = cdpLifecycleName(waitUntil);
|
||||
const beforeReadyState = await probeMainFrameReadyState(deps.cdp, target.tabId);
|
||||
const beforeFrame = await readMainFrameInfo(deps.cdp, target.tabId);
|
||||
@@ -669,7 +574,10 @@ export async function handleNavigate(
|
||||
}`,
|
||||
});
|
||||
} catch (err) {
|
||||
return cdpError(err);
|
||||
return {
|
||||
code: "cdp_failed",
|
||||
message: err instanceof Error ? err.message : String(err),
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
@@ -819,24 +727,7 @@ export async function handleReload(
|
||||
|
||||
try {
|
||||
deps.cdp.trackSessionTab?.(ctx.sessionId, target.tabId);
|
||||
try {
|
||||
await ensureCdpReady(deps.cdp, target.tabId);
|
||||
} catch (error) {
|
||||
if (!isCdpExtensionAccessDenied(error)) throw error;
|
||||
const previousUrl = await readTabUrl(deps.tabsApi, target.tabId);
|
||||
const recovered = await recoverBrowserNavigation(
|
||||
deps,
|
||||
target.tabId,
|
||||
(api) => api.reload(target.tabId, { bypassCache: ignoreCache }),
|
||||
waitUntil,
|
||||
timeoutMs,
|
||||
);
|
||||
if (isRpcError(recovered)) return recovered;
|
||||
return attachDialogs(deps.cdp, target.tabId, dialogCursor, {
|
||||
...recovered,
|
||||
previous_url: previousUrl,
|
||||
});
|
||||
}
|
||||
await ensureCdpReady(deps.cdp, target.tabId);
|
||||
const previousUrl = await readTabUrl(deps.tabsApi, target.tabId);
|
||||
const beforeFrame = await readMainFrameInfo(deps.cdp, target.tabId);
|
||||
const expected = cdpLifecycleName(waitUntil);
|
||||
@@ -885,7 +776,10 @@ export async function handleReload(
|
||||
}`,
|
||||
});
|
||||
} catch (err) {
|
||||
return cdpError(err);
|
||||
return {
|
||||
code: "cdp_failed",
|
||||
message: err instanceof Error ? err.message : String(err),
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
import type { CapturedSceneInput } from "./vom/facts";
|
||||
// Observation handlers — `tool.snapshot`, `tool.get_html`, `tool.screenshot`,
|
||||
// and semantic `tool.observe` (design §7). Each handler resolves the target
|
||||
// tab (defaulting to the Agent Window's active tab when omitted) and
|
||||
@@ -9,6 +8,7 @@ import {
|
||||
applyVomInteractionRecovery,
|
||||
type CondSurface,
|
||||
isVomReferenceNode,
|
||||
type Rect,
|
||||
renderVom,
|
||||
type VomNode,
|
||||
type VomOptions,
|
||||
@@ -18,7 +18,7 @@ import { ChromiumCdp } from "@/browser-driver/chromium-cdp";
|
||||
import type { CdpTarget } from "@/browser-driver/frame-graph";
|
||||
import {
|
||||
type CaptureSuppressSendToTab,
|
||||
withExtensionOverlayHidden,
|
||||
withOverlaysHiddenForCapture,
|
||||
} from "@/lib/capture-suppress-bridge";
|
||||
import type { SessionContext, SessionManager } from "@/session-manager/manager";
|
||||
import type {
|
||||
@@ -35,7 +35,6 @@ import type {
|
||||
import { attachDialogs, markDialogCursor } from "./dialogs";
|
||||
import { rpcError } from "./errors";
|
||||
import { resolveNodeGeometry } from "./frame-geometry";
|
||||
import { screenshotPageRect } from "./geometry/coordinate-types";
|
||||
import {
|
||||
type ChromeTabsApi,
|
||||
enforceToolTargetScope,
|
||||
@@ -48,16 +47,27 @@ import {
|
||||
normaliseRef as sharedNormaliseRef,
|
||||
type ToolEffect,
|
||||
} from "./shared";
|
||||
import { lookupRefTarget, resolveSnapshotRef } from "./snapshot-ref";
|
||||
import { type CapturedNode, type CapturedSurfaceProbe, probeHoverSurfaces } from "./vom/capture";
|
||||
import { captureObservationFacts, semanticCapture } from "./vom/capture-coordinator";
|
||||
import type { FrameDocument as CapturedFrameDocument } from "./vom/frame-document";
|
||||
import { resolveSnapshotRef } from "./snapshot-ref";
|
||||
import {
|
||||
type CapturedNode,
|
||||
type CapturedSurfaceProbe,
|
||||
type CapturedViewModel,
|
||||
captureViewModel,
|
||||
collectOverlayExcludedBackendIds,
|
||||
probeHoverSurfaces,
|
||||
} from "./vom/capture";
|
||||
import { type CapturedFrameDocument, captureFrameData } from "./vom/frame-capture";
|
||||
import { withOverlayBypass } from "./vom/hover-perception";
|
||||
import { probeTooltipNames } from "./vom/name-enrichment";
|
||||
import {
|
||||
type CaptureVomObservationResult,
|
||||
projectRecordSafeObservation,
|
||||
} from "./vom/record-safe-observation";
|
||||
import {
|
||||
clusterRenderedSurfaces,
|
||||
discoverRenderedSurfaces,
|
||||
projectRenderedSurfaces,
|
||||
} from "./vom/rendered-surfaces";
|
||||
import {
|
||||
buildSemanticGraph,
|
||||
buildSemanticVomScene,
|
||||
@@ -89,6 +99,9 @@ export const normaliseRef = sharedNormaliseRef;
|
||||
// screenshot — `tool.screenshot`
|
||||
// ---------------------------------------------------------------------------
|
||||
|
||||
const VISUAL_SURFACE_SCREENSHOT_MAX_EDGE = 2_048;
|
||||
const VISUAL_SURFACE_SCREENSHOT_MAX_PIXELS = 4_000_000;
|
||||
|
||||
/**
|
||||
* Strip the `data:image/...;base64,` prefix from a Chrome
|
||||
* `captureVisibleTab` dataURL and return the raw base64 payload.
|
||||
@@ -103,8 +116,8 @@ export function stripDataUrlPrefix(dataUrl: string): string {
|
||||
|
||||
/**
|
||||
* Parse a PNG's IHDR chunk and return `(width, height)`. Returns
|
||||
* `null` on any malformed input so callers fall back to `0/0` instead
|
||||
* of throwing.
|
||||
* `null` on malformed input so callers can reject dimensions that are
|
||||
* not authoritative instead of guessing from a CSS-space rectangle.
|
||||
*
|
||||
* PNG layout: 8-byte signature, then a 4-byte length, 4-byte type
|
||||
* ("IHDR"), then the chunk data — width is bytes 16-19 BE, height is
|
||||
@@ -116,9 +129,9 @@ export function parsePngDimensions(base64: string): { width: number; height: num
|
||||
const head = base64.length > 64 ? base64.slice(0, 64) : base64;
|
||||
const bin = atob(head);
|
||||
if (bin.length < 24) return null;
|
||||
if (bin.charCodeAt(0) !== 0x89 || bin.charCodeAt(1) !== 0x50 || bin.charCodeAt(2) !== 0x4e) {
|
||||
return null;
|
||||
}
|
||||
const expectedSignature = [0x89, 0x50, 0x4e, 0x47, 0x0d, 0x0a, 0x1a, 0x0a];
|
||||
if (expectedSignature.some((byte, index) => bin.charCodeAt(index) !== byte)) return null;
|
||||
if (bin.slice(12, 16) !== "IHDR") return null;
|
||||
const u32 = (off: number) =>
|
||||
(bin.charCodeAt(off) << 24) |
|
||||
(bin.charCodeAt(off + 1) << 16) |
|
||||
@@ -181,6 +194,8 @@ async function captureElementScreenshot(
|
||||
target: CdpTarget,
|
||||
backendNodeId: number,
|
||||
frameId?: string,
|
||||
visualSurface = false,
|
||||
observedVisibleRect?: Rect,
|
||||
signal?: AbortSignal,
|
||||
): Promise<{ image_base64: string; width: number; height: number } | RpcError> {
|
||||
if (signal?.aborted) return cancelled("screenshot");
|
||||
@@ -188,20 +203,46 @@ async function captureElementScreenshot(
|
||||
cdp,
|
||||
tabId,
|
||||
{ target, backendNodeId, ...(frameId ? { frameId } : {}) },
|
||||
{ scrollIntoView: true },
|
||||
{ scrollIntoView: !visualSurface },
|
||||
);
|
||||
if (isRpcError(geometry)) return geometry;
|
||||
if (signal?.aborted) return cancelled("screenshot");
|
||||
const rect = geometry.topBounds;
|
||||
const clip = screenshotPageRect(rect, geometry.topViewport);
|
||||
if (!clip) return { code: "cdp_failed", message: "invalid screenshot coordinate space" };
|
||||
const liveRect = geometry.topBounds;
|
||||
const rect =
|
||||
visualSurface && observedVisibleRect
|
||||
? (() => {
|
||||
const x = Math.max(liveRect.x, observedVisibleRect.x);
|
||||
const y = Math.max(liveRect.y, observedVisibleRect.y);
|
||||
const right = Math.min(
|
||||
liveRect.x + liveRect.width,
|
||||
observedVisibleRect.x + observedVisibleRect.w,
|
||||
);
|
||||
const bottom = Math.min(
|
||||
liveRect.y + liveRect.height,
|
||||
observedVisibleRect.y + observedVisibleRect.h,
|
||||
);
|
||||
return right > x && bottom > y ? { x, y, width: right - x, height: bottom - y } : null;
|
||||
})()
|
||||
: liveRect;
|
||||
if (!rect) return { code: "permission_denied", message: "surface is no longer visible" };
|
||||
const scale = visualSurface
|
||||
? Math.min(
|
||||
1,
|
||||
VISUAL_SURFACE_SCREENSHOT_MAX_EDGE / rect.width,
|
||||
VISUAL_SURFACE_SCREENSHOT_MAX_EDGE / rect.height,
|
||||
Math.sqrt(VISUAL_SURFACE_SCREENSHOT_MAX_PIXELS / (rect.width * rect.height)),
|
||||
)
|
||||
: 1;
|
||||
|
||||
try {
|
||||
const shot = await cdp.send<{ data?: string }>(tabId, "Page.captureScreenshot", {
|
||||
format: "png",
|
||||
clip: {
|
||||
...clip.rect,
|
||||
scale: 1,
|
||||
x: rect.x,
|
||||
y: rect.y,
|
||||
width: rect.width,
|
||||
height: rect.height,
|
||||
scale,
|
||||
},
|
||||
});
|
||||
if (signal?.aborted) return cancelled("screenshot");
|
||||
@@ -209,10 +250,10 @@ async function captureElementScreenshot(
|
||||
if (!image_base64) {
|
||||
return { code: "cdp_failed", message: "Page.captureScreenshot returned no data" };
|
||||
}
|
||||
const dims = parsePngDimensions(image_base64) ?? {
|
||||
width: Math.round(rect.width),
|
||||
height: Math.round(rect.height),
|
||||
};
|
||||
const dims = parsePngDimensions(image_base64);
|
||||
if (!dims) {
|
||||
return { code: "cdp_failed", message: "Page.captureScreenshot returned invalid PNG data" };
|
||||
}
|
||||
return { image_base64, width: dims.width, height: dims.height };
|
||||
} catch (err) {
|
||||
return {
|
||||
@@ -308,13 +349,7 @@ export async function handleScreenshot(
|
||||
if (!deps.cdp) {
|
||||
return { code: "cdp_failed", message: "screenshot ref capture requires CDP" };
|
||||
}
|
||||
if (lookupRefTarget(ctx, ref, target.tabId)?.kind === "visual-region")
|
||||
return rpcError(
|
||||
"unsupported",
|
||||
"ref_kind_unsupported",
|
||||
"visual-region screenshot execution is not available in this build",
|
||||
);
|
||||
const node = resolveSnapshotRef(ctx, ref, target.tabId);
|
||||
const node = resolveSnapshotRef(ctx, ref, target.tabId, "screenshot");
|
||||
if (isRpcError(node)) return node;
|
||||
if (signal?.aborted) return cancelled("screenshot");
|
||||
deps.cdp.trackSessionTab?.(ctx.sessionId, target.tabId);
|
||||
@@ -325,7 +360,7 @@ export async function handleScreenshot(
|
||||
tabId: target.tabId,
|
||||
...(node.cdpSessionId ? { sessionId: node.cdpSessionId } : {}),
|
||||
};
|
||||
const captured = await withExtensionOverlayHidden(
|
||||
const captured = await withOverlaysHiddenForCapture(
|
||||
target.tabId,
|
||||
() =>
|
||||
captureElementScreenshot(
|
||||
@@ -334,6 +369,8 @@ export async function handleScreenshot(
|
||||
nodeTarget,
|
||||
node.backendNodeId,
|
||||
node.frameId,
|
||||
node.kind === "surface",
|
||||
node.visibleRect,
|
||||
signal,
|
||||
),
|
||||
deps.sendToTab,
|
||||
@@ -357,7 +394,7 @@ export async function handleScreenshot(
|
||||
);
|
||||
}
|
||||
|
||||
const captured = await withExtensionOverlayHidden(
|
||||
const captured = await withOverlaysHiddenForCapture(
|
||||
target.tabId,
|
||||
() => captureFullTabPng(deps, ctx, target, signal),
|
||||
deps.sendToTab,
|
||||
@@ -365,7 +402,10 @@ export async function handleScreenshot(
|
||||
if (isRpcError(captured)) return captured;
|
||||
if (signal?.aborted) return cancelled("screenshot");
|
||||
const image_base64 = captured;
|
||||
const dims = parsePngDimensions(image_base64) ?? { width: 0, height: 0 };
|
||||
const dims = parsePngDimensions(image_base64);
|
||||
if (!dims) {
|
||||
return { code: "cdp_failed", message: "screenshot capture returned invalid PNG data" };
|
||||
}
|
||||
return withShotDialogs({
|
||||
image_base64,
|
||||
width: dims.width,
|
||||
@@ -531,7 +571,7 @@ function buildActiveScopeBlocks(nodes: VomNode[], signals: VomNodeDomSignals): A
|
||||
|
||||
function buildConditionalSurfaces(
|
||||
nodes: VomNode[],
|
||||
captured: CapturedSceneInput,
|
||||
captured: CapturedViewModel,
|
||||
probes: CapturedSurfaceProbe[],
|
||||
): CondSurface[] {
|
||||
if (probes.length === 0) return [];
|
||||
@@ -661,9 +701,161 @@ export interface BuildVomSceneOptions {
|
||||
|
||||
export type VomFrameDocument = CapturedFrameDocument<CdpAxNode>;
|
||||
|
||||
function legacyFrameDocuments(
|
||||
axNodes: CdpAxNode[],
|
||||
captured: CapturedViewModel,
|
||||
pageUrl?: string,
|
||||
rootTarget: VomFrameDocument["target"] = { tabId: 0 },
|
||||
): VomFrameDocument[] {
|
||||
const rootFrameId = captured.rootFrameId ?? "root";
|
||||
const documents: VomFrameDocument[] = [
|
||||
{
|
||||
frameId: rootFrameId,
|
||||
contextScopeId: rootFrameId,
|
||||
target: rootTarget,
|
||||
...(pageUrl ? { url: pageUrl } : {}),
|
||||
axNodes: [],
|
||||
domNodes: captured.nodes.map((node) => ({ ...node, frameId: node.frameId ?? rootFrameId })),
|
||||
},
|
||||
];
|
||||
const pending = [...captured.iframeNodes.entries()];
|
||||
let progress = true;
|
||||
let nextSyntheticFrame = 1;
|
||||
while (pending.length > 0 && progress) {
|
||||
progress = false;
|
||||
for (let index = pending.length - 1; index >= 0; index -= 1) {
|
||||
const [ownerBackendNodeId, domNodes] = pending[index];
|
||||
const parent = documents.find((document) =>
|
||||
document.domNodes.some((node) => node.backendNodeId === ownerBackendNodeId),
|
||||
);
|
||||
if (!parent) continue;
|
||||
const frameId =
|
||||
domNodes.find((node) => node.frameId)?.frameId ?? `legacy-frame-${nextSyntheticFrame++}`;
|
||||
documents.push({
|
||||
frameId,
|
||||
parentFrameId: parent.frameId,
|
||||
ownerBackendNodeId,
|
||||
contextScopeId: frameId,
|
||||
target: parent.target,
|
||||
axNodes: [],
|
||||
domNodes: domNodes.map((node) => ({ ...node, frameId: node.frameId ?? frameId })),
|
||||
});
|
||||
pending.splice(index, 1);
|
||||
progress = true;
|
||||
}
|
||||
}
|
||||
|
||||
const documentByFrameId = new Map(documents.map((document) => [document.frameId, document]));
|
||||
const backendFrame = new Map<number, string>();
|
||||
const childFrameByOwner = new Map<number, string>();
|
||||
for (const document of documents) {
|
||||
if (document.ownerBackendNodeId !== undefined) {
|
||||
childFrameByOwner.set(document.ownerBackendNodeId, document.frameId);
|
||||
}
|
||||
for (const node of document.domNodes) backendFrame.set(node.backendNodeId, document.frameId);
|
||||
}
|
||||
const axById = new Map(axNodes.map((node) => [node.nodeId, node]));
|
||||
const ownership = new Map<string, string>();
|
||||
const resolving = new Set<string>();
|
||||
const frameForAx = (node: CdpAxNode): string => {
|
||||
const cached = ownership.get(node.nodeId);
|
||||
if (cached) return cached;
|
||||
let frameId: string | undefined;
|
||||
if (node.frameId && documentByFrameId.has(node.frameId)) frameId = node.frameId;
|
||||
if (!frameId && typeof node.backendDOMNodeId === "number") {
|
||||
frameId = backendFrame.get(node.backendDOMNodeId);
|
||||
}
|
||||
if (!frameId && node.parentId && !resolving.has(node.nodeId)) {
|
||||
const parent = axById.get(node.parentId);
|
||||
if (parent) {
|
||||
frameId =
|
||||
typeof parent.backendDOMNodeId === "number"
|
||||
? childFrameByOwner.get(parent.backendDOMNodeId)
|
||||
: undefined;
|
||||
if (!frameId) {
|
||||
resolving.add(node.nodeId);
|
||||
frameId = frameForAx(parent);
|
||||
resolving.delete(node.nodeId);
|
||||
}
|
||||
}
|
||||
}
|
||||
frameId ??= rootFrameId;
|
||||
ownership.set(node.nodeId, frameId);
|
||||
return frameId;
|
||||
};
|
||||
for (const node of axNodes) frameForAx(node);
|
||||
for (const node of axNodes) {
|
||||
const frameId = ownership.get(node.nodeId) ?? rootFrameId;
|
||||
const document = documentByFrameId.get(frameId) ?? documents[0];
|
||||
document.axNodes.push({
|
||||
...node,
|
||||
frameId,
|
||||
...(node.parentId && ownership.get(node.parentId) === frameId
|
||||
? { parentId: node.parentId }
|
||||
: { parentId: undefined }),
|
||||
...(node.childIds
|
||||
? { childIds: node.childIds.filter((childId) => ownership.get(childId) === frameId) }
|
||||
: {}),
|
||||
});
|
||||
}
|
||||
return documents;
|
||||
}
|
||||
|
||||
function withLegacyBackendIds(scene: VomScene): VomScene {
|
||||
const used = new Set<number>();
|
||||
const idMap = new Map<number, number>();
|
||||
let nextVirtualId = -1;
|
||||
for (const node of scene.nodes) {
|
||||
const preferred = node.backendNodeId;
|
||||
const id = preferred !== undefined && !used.has(preferred) ? preferred : nextVirtualId--;
|
||||
used.add(id);
|
||||
idMap.set(node.id, id);
|
||||
}
|
||||
return {
|
||||
...scene,
|
||||
nodes: scene.nodes.map((node) => ({
|
||||
...node,
|
||||
id: idMap.get(node.id) as number,
|
||||
parentId: node.parentId === null ? null : (idMap.get(node.parentId) ?? null),
|
||||
...(node.domParentId !== undefined
|
||||
? { domParentId: node.domParentId === null ? null : (idMap.get(node.domParentId) ?? null) }
|
||||
: {}),
|
||||
...(node.domAncestorIds
|
||||
? { domAncestorIds: node.domAncestorIds.flatMap((id) => idMap.get(id) ?? []) }
|
||||
: {}),
|
||||
})),
|
||||
...(scene.surfaces
|
||||
? {
|
||||
surfaces: scene.surfaces.map((surface) => ({
|
||||
...surface,
|
||||
triggerId: idMap.get(surface.triggerId) ?? surface.triggerId,
|
||||
})),
|
||||
}
|
||||
: {}),
|
||||
...(scene.activeScopeBlocks
|
||||
? {
|
||||
activeScopeBlocks: scene.activeScopeBlocks.map((block) => ({
|
||||
...block,
|
||||
triggerId: idMap.get(block.triggerId) ?? block.triggerId,
|
||||
})),
|
||||
}
|
||||
: {}),
|
||||
};
|
||||
}
|
||||
|
||||
export function buildVomScene(
|
||||
axNodes: CdpAxNode[],
|
||||
captured: CapturedViewModel,
|
||||
options: BuildVomSceneOptions = {},
|
||||
): VomScene {
|
||||
return withLegacyBackendIds(
|
||||
buildFrameVomScene(legacyFrameDocuments(axNodes, captured, options.pageUrl), captured, options),
|
||||
);
|
||||
}
|
||||
|
||||
export function buildFrameVomScene(
|
||||
documents: VomFrameDocument[],
|
||||
captured: CapturedSceneInput,
|
||||
captured: CapturedViewModel,
|
||||
options: BuildVomSceneOptions = {},
|
||||
): VomScene {
|
||||
const scene = buildSemanticVomScene({
|
||||
@@ -679,7 +871,7 @@ export function buildFrameVomScene(
|
||||
function attachCapturedSceneAnnotations(
|
||||
scene: VomScene,
|
||||
documents: VomFrameDocument[],
|
||||
captured: CapturedSceneInput,
|
||||
captured: CapturedViewModel,
|
||||
surfaceProbes: CapturedSurfaceProbe[],
|
||||
): VomScene {
|
||||
const rootDocument = documents.find((document) => document.frameId === scene.rootFrameId);
|
||||
@@ -829,6 +1021,51 @@ export async function handleGetHtml(
|
||||
}
|
||||
}
|
||||
|
||||
function emptyCapturedViewModel(viewport = { width: 0, height: 0 }): CapturedViewModel {
|
||||
return { viewport, nodes: [], iframeNodes: new Map(), excludedBackendNodeIds: new Set() };
|
||||
}
|
||||
|
||||
interface LayoutMetricsViewportReply {
|
||||
cssLayoutViewport?: { clientWidth?: number; clientHeight?: number };
|
||||
layoutViewport?: { clientWidth?: number; clientHeight?: number };
|
||||
}
|
||||
|
||||
async function fallbackCapturedViewModel(
|
||||
cdp: CdpRunner,
|
||||
tabId: number,
|
||||
signal?: AbortSignal,
|
||||
): Promise<CapturedViewModel> {
|
||||
throwIfAborted(signal, "observation");
|
||||
let viewport = { width: 0, height: 0 };
|
||||
try {
|
||||
const metrics = await cdp.send<LayoutMetricsViewportReply>(tabId, "Page.getLayoutMetrics", {});
|
||||
throwIfAborted(signal, "observation");
|
||||
const source = metrics.cssLayoutViewport ?? metrics.layoutViewport ?? {};
|
||||
viewport = {
|
||||
width: source.clientWidth ?? 0,
|
||||
height: source.clientHeight ?? 0,
|
||||
};
|
||||
} catch (error) {
|
||||
if (isAbortError(error)) throw error;
|
||||
}
|
||||
const excludedBackendNodeIds = await collectOverlayExcludedBackendIds(cdp, tabId, signal);
|
||||
throwIfAborted(signal, "observation");
|
||||
return { ...emptyCapturedViewModel(viewport), excludedBackendNodeIds };
|
||||
}
|
||||
|
||||
async function captureForVom(
|
||||
cdp: CdpRunner,
|
||||
tabId: number,
|
||||
options: CaptureVomObservationOptions,
|
||||
): Promise<CapturedViewModel> {
|
||||
try {
|
||||
return await captureViewModel(cdp, tabId, { signal: options.signal });
|
||||
} catch (error) {
|
||||
if (isAbortError(error)) throw error;
|
||||
return fallbackCapturedViewModel(cdp, tabId, options.signal);
|
||||
}
|
||||
}
|
||||
|
||||
export interface HoverProbeOutcome {
|
||||
/** Whether any active hover was dispatched during this observation. */
|
||||
performed: boolean;
|
||||
@@ -861,7 +1098,7 @@ const NO_HOVER_PROBES: HoverProbeOutcome = {
|
||||
async function runHoverProbes(
|
||||
cdp: CdpRunner,
|
||||
tabId: number,
|
||||
captured: CapturedSceneInput,
|
||||
captured: CapturedViewModel,
|
||||
documents: VomFrameDocument[],
|
||||
staticSemantics: ReturnType<typeof resolveSemanticGraph>,
|
||||
options: CaptureVomObservationOptions,
|
||||
@@ -887,6 +1124,7 @@ async function runHoverProbes(
|
||||
|
||||
export interface CaptureVomObservationOptions extends VomOptions {
|
||||
conditionalSurfaceProbe?: boolean;
|
||||
renderedSurfaceDiscovery?: boolean;
|
||||
hoverProbeBypassOverlay?: (tabId: number, enabled: boolean) => Promise<void>;
|
||||
signal?: AbortSignal;
|
||||
}
|
||||
@@ -900,9 +1138,14 @@ export async function captureVomObservation(
|
||||
throwIfAborted(options.signal, "observation");
|
||||
await cdp.ensureAttachedToUrl?.(tabId, url);
|
||||
throwIfAborted(options.signal, "observation");
|
||||
const facts = await captureObservationFacts<CdpAxNode>(cdp, tabId, options.signal, url);
|
||||
const { captured, documents: normalizedDocuments } = semanticCapture(facts);
|
||||
const captured = await captureForVom(cdp, tabId, options);
|
||||
throwIfAborted(options.signal, "observation");
|
||||
const documents = await captureFrameData<CdpAxNode>(cdp, tabId, captured, options.signal);
|
||||
throwIfAborted(options.signal, "observation");
|
||||
const normalizedDocuments =
|
||||
documents.length === 1 && captured.iframeNodes.size > 0
|
||||
? legacyFrameDocuments(documents[0].axNodes, captured, url, documents[0].target)
|
||||
: documents;
|
||||
const semanticGraph = buildSemanticGraph({
|
||||
documents: normalizedDocuments,
|
||||
viewport: captured.viewport,
|
||||
@@ -930,43 +1173,25 @@ export async function captureVomObservation(
|
||||
captured,
|
||||
hoverProbes.surfaceProbes,
|
||||
);
|
||||
// Reserve space using the renderer's character-based token estimate. Like VOM
|
||||
// headers, this integrity notice remains visible even under a tiny token budget.
|
||||
const notices: string[] = [];
|
||||
if (facts.issues.some((issue) => issue.stage === "geometry"))
|
||||
notices.push(
|
||||
"@warning geometry incomplete: some page or frame content has no top-level coordinates.",
|
||||
);
|
||||
const incompleteStages = ["dom", "ax", "forms", "ownership"].filter((stage) =>
|
||||
facts.issues.some((issue) => issue.stage === stage),
|
||||
);
|
||||
if (incompleteStages.length)
|
||||
notices.push(
|
||||
`@warning observation incomplete: some ${incompleteStages.join(", ")} data is unavailable or omitted.`,
|
||||
);
|
||||
if (
|
||||
facts.issues.some(
|
||||
(issue) => issue.stage === "identity" && issue.reason !== "identity-unverified",
|
||||
)
|
||||
)
|
||||
notices.push(
|
||||
"@warning observation incomplete: some documents were omitted because their identity changed or could not be revalidated.",
|
||||
);
|
||||
if (facts.issues.some((issue) => issue.reason === "identity-unverified"))
|
||||
notices.push(
|
||||
"@warning document identity unverified: some retained documents could not be checked for changes during capture.",
|
||||
);
|
||||
const captureNotice = notices.join("\n");
|
||||
const rendered = renderVom(decoratedScene, {
|
||||
const observedScene = options.renderedSurfaceDiscovery
|
||||
? projectRenderedSurfaces(
|
||||
decoratedScene,
|
||||
normalizedDocuments,
|
||||
clusterRenderedSurfaces(
|
||||
discoverRenderedSurfaces(
|
||||
normalizedDocuments,
|
||||
captured.viewport,
|
||||
captured.excludedBackendNodeIds,
|
||||
),
|
||||
),
|
||||
)
|
||||
: decoratedScene;
|
||||
const rendered = renderVom(observedScene, {
|
||||
maxDepth: options.maxDepth,
|
||||
maxTokens:
|
||||
!captureNotice || options.maxTokens === undefined
|
||||
? options.maxTokens
|
||||
: Math.max(0, options.maxTokens - Math.ceil((captureNotice.length + 1) / 4)),
|
||||
maxTokens: options.maxTokens,
|
||||
redactValues: options.redactValues,
|
||||
activeRegionPolicy: options.activeRegionPolicy,
|
||||
});
|
||||
if (captureNotice) rendered.text += `\n${captureNotice}`;
|
||||
throwIfAborted(options.signal, "observation");
|
||||
return projectRecordSafeObservation({
|
||||
rootFrameId: captured.rootFrameId ?? normalizedDocuments[0]?.frameId ?? "root",
|
||||
@@ -1016,6 +1241,7 @@ async function handleVomObservation(
|
||||
maxTokens: params.max_tokens,
|
||||
activeRegionPolicy: true,
|
||||
conditionalSurfaceProbe: effectiveConditionalSurfaceProbe,
|
||||
renderedSurfaceDiscovery: toolName === "observe",
|
||||
hoverProbeBypassOverlay: deps.hoverProbeBypassOverlay,
|
||||
signal,
|
||||
});
|
||||
@@ -1033,6 +1259,9 @@ async function handleVomObservation(
|
||||
tabId: target.tabId,
|
||||
...(ref.frameId ? { frameId: ref.frameId } : {}),
|
||||
...(refTarget?.sessionId ? { cdpSessionId: refTarget.sessionId } : {}),
|
||||
...(ref.visibleRect ? { visibleRect: ref.visibleRect } : {}),
|
||||
...(ref.kind ? { kind: ref.kind } : {}),
|
||||
...(ref.capabilities ? { capabilities: ref.capabilities } : {}),
|
||||
},
|
||||
] as const;
|
||||
}),
|
||||
|
||||
@@ -1,142 +0,0 @@
|
||||
import { cdpTargetKey } from "@/browser-driver/frame-graph";
|
||||
import type { NodeAddress } from "./frame-geometry";
|
||||
import {
|
||||
clipPolygon,
|
||||
projectRegionToViewport,
|
||||
type Region,
|
||||
rectPolygon,
|
||||
regionBounds,
|
||||
type ViewportRect,
|
||||
} from "./geometry";
|
||||
import { GeometryContext } from "./geometry/frame-context";
|
||||
import { type CdpRunner, sendToCdpTarget } from "./shared";
|
||||
|
||||
// Ask the renderer to apply containing-block clips (including shadow DOM),
|
||||
// instead of treating layout quads as visible pixels. Each document is measured
|
||||
// locally; the existing frame projections supply the top-viewport coordinates.
|
||||
// IntersectionObserver reports a bounding rectangle, not an occlusion/hit test.
|
||||
const VISIBLE_RECT = `function(timeoutMs) {
|
||||
const element = this;
|
||||
const visible = () => element.isConnected && element.checkVisibility({
|
||||
checkOpacity: true, checkVisibilityCSS: true, contentVisibilityAuto: true
|
||||
});
|
||||
if (typeof element.checkVisibility !== 'function' || !visible()) return null;
|
||||
return new Promise((resolve, reject) => {
|
||||
const observer = new IntersectionObserver(([entry]) => {
|
||||
clearTimeout(timer);
|
||||
observer.disconnect();
|
||||
const rect = entry.intersectionRect;
|
||||
resolve(visible() && entry.isIntersecting && rect.width > 0 && rect.height > 0
|
||||
? { x: rect.x, y: rect.y, width: rect.width, height: rect.height }
|
||||
: null);
|
||||
}, { root: element.ownerDocument });
|
||||
const timer = setTimeout(() => {
|
||||
observer.disconnect();
|
||||
reject(new Error('scroll-to visibility measurement timed out'));
|
||||
}, timeoutMs);
|
||||
observer.observe(element);
|
||||
});
|
||||
}`;
|
||||
|
||||
async function visibleRect(
|
||||
cdp: CdpRunner,
|
||||
address: NodeAddress,
|
||||
deadline: number,
|
||||
): Promise<ViewportRect | null> {
|
||||
const resolved = await sendToCdpTarget<{ object?: { objectId?: string } }>(
|
||||
cdp,
|
||||
address.target,
|
||||
"DOM.resolveNode",
|
||||
{ backendNodeId: address.backendNodeId },
|
||||
);
|
||||
if (!resolved.object?.objectId) throw new Error("scroll-to could not resolve the target element");
|
||||
const reply = await sendToCdpTarget<{
|
||||
result?: { value?: ViewportRect | null };
|
||||
exceptionDetails?: { text?: string; exception?: { description?: string } };
|
||||
}>(cdp, address.target, "Runtime.callFunctionOn", {
|
||||
objectId: resolved.object.objectId,
|
||||
functionDeclaration: VISIBLE_RECT,
|
||||
// Bound this read even if a background document stops rendering. Its
|
||||
// observer always disconnects; cancellation cannot leave a live observer.
|
||||
arguments: [{ value: Math.max(1, Math.min(1_000, deadline - Date.now())) }],
|
||||
awaitPromise: true,
|
||||
returnByValue: true,
|
||||
});
|
||||
if (reply.exceptionDetails) {
|
||||
const details = reply.exceptionDetails;
|
||||
throw new Error(details.exception?.description ?? details.text ?? "visibility script failed");
|
||||
}
|
||||
const rect = reply.result?.value;
|
||||
if (rect === null) return null;
|
||||
if (
|
||||
!rect ||
|
||||
![rect.x, rect.y, rect.width, rect.height].every(Number.isFinite) ||
|
||||
rect.width <= 0 ||
|
||||
rect.height <= 0
|
||||
) {
|
||||
throw new Error("scroll-to visibility measurement returned invalid bounds");
|
||||
}
|
||||
return rect;
|
||||
}
|
||||
|
||||
async function projectRect(
|
||||
context: GeometryContext,
|
||||
address: NodeAddress,
|
||||
rect: ViewportRect,
|
||||
): Promise<Region> {
|
||||
let region: Region = [rectPolygon({ x: rect.x, y: rect.y, w: rect.width, h: rect.height })];
|
||||
if (!address.frameId) return region;
|
||||
const frame = await context.frame(address.frameId);
|
||||
if (!frame || cdpTargetKey(frame.target) !== cdpTargetKey(address.target)) {
|
||||
throw new Error("scroll-to frame no longer belongs to its target");
|
||||
}
|
||||
const parent = frame.parentFrameId ? await context.frame(frame.parentFrameId) : undefined;
|
||||
if (parent && cdpTargetKey(parent.target) === cdpTargetKey(frame.target)) {
|
||||
// DOM rectangles are document-local. Same-target iframe quads are already
|
||||
// target-local, so cross this one boundary before the target projection.
|
||||
const viewport = await context.viewport(frame.target);
|
||||
if (frame.ownerBackendNodeId === undefined || !viewport) {
|
||||
throw new Error("scroll-to could not resolve the frame viewport");
|
||||
}
|
||||
const local = await context.snapshotProjection(address, frame.ownerBackendNodeId, [], viewport);
|
||||
if (local.status !== "available") throw new Error("scroll-to could not project the frame");
|
||||
region = projectRegionToViewport(region, local.projection.geometry);
|
||||
}
|
||||
const projection = await context.targetProjection(frame.frameId);
|
||||
if (!projection) throw new Error("scroll-to could not project the target viewport");
|
||||
return projectRegionToViewport(region, projection);
|
||||
}
|
||||
|
||||
/** Only scroll-to needs renderer-clipped bounds; other interaction geometry is unchanged. */
|
||||
export async function scrollVisibleBounds(
|
||||
cdp: CdpRunner,
|
||||
tabId: number,
|
||||
address: NodeAddress,
|
||||
deadline: number,
|
||||
): Promise<ViewportRect | null> {
|
||||
const context = new GeometryContext(cdp, tabId);
|
||||
const rect = await visibleRect(cdp, address, deadline);
|
||||
if (!rect) return null;
|
||||
let region = await projectRect(context, address, rect);
|
||||
if (address.frameId) {
|
||||
const ancestry = await context.ancestry(address.frameId);
|
||||
if (!ancestry) throw new Error("scroll-to could not resolve the frame ancestry");
|
||||
for (const child of ancestry) {
|
||||
const parent = child.parentFrameId ? await context.frame(child.parentFrameId) : undefined;
|
||||
if (!parent || child.ownerBackendNodeId === undefined) {
|
||||
throw new Error("scroll-to could not resolve the frame owner");
|
||||
}
|
||||
const owner = {
|
||||
target: parent.target,
|
||||
frameId: parent.frameId,
|
||||
backendNodeId: child.ownerBackendNodeId,
|
||||
};
|
||||
// A visible child document can still have a hidden or clipped iframe.
|
||||
const ownerRect = await visibleRect(cdp, owner, deadline);
|
||||
if (!ownerRect) return null;
|
||||
const clips = await projectRect(context, owner, ownerRect);
|
||||
region = region.flatMap((polygon) => clips.map((clip) => clipPolygon(polygon, clip)));
|
||||
}
|
||||
}
|
||||
return regionBounds(region);
|
||||
}
|
||||
@@ -1,137 +0,0 @@
|
||||
import { ChromiumCdp } from "@/browser-driver/chromium-cdp";
|
||||
import { type CdpTarget, cdpTargetKey } from "@/browser-driver/frame-graph";
|
||||
import type { SessionManager } from "@/session-manager/manager";
|
||||
import type { RpcError, ScrollToParams, ScrollToResult } from "@/transport/types";
|
||||
import { attachDialogs, markDialogCursor } from "./dialogs";
|
||||
import { cdpError, rpcError } from "./errors";
|
||||
import { scrollElementAndFramesIntoView } from "./frame-geometry";
|
||||
import { resolveBackendNode } from "./interaction";
|
||||
import { scrollVisibleBounds } from "./scroll-visibility";
|
||||
import {
|
||||
type CdpRunner,
|
||||
type ChromeTabsApi,
|
||||
chromeTabsApi,
|
||||
enforceAgentWindow,
|
||||
isRpcError,
|
||||
lookupSession,
|
||||
resolveTargetTab,
|
||||
sendToCdpTarget,
|
||||
} from "./shared";
|
||||
|
||||
export interface ScrollToDeps {
|
||||
cdp: CdpRunner;
|
||||
tabsApi: ChromeTabsApi;
|
||||
signal?: AbortSignal;
|
||||
}
|
||||
|
||||
let defaultDeps: { cdp: ChromiumCdp; tabsApi: ChromeTabsApi } | null = null;
|
||||
function getDefaultDeps(): { cdp: ChromiumCdp; tabsApi: ChromeTabsApi } {
|
||||
if (!defaultDeps) defaultDeps = { cdp: new ChromiumCdp(), tabsApi: chromeTabsApi };
|
||||
return defaultDeps;
|
||||
}
|
||||
|
||||
export async function handleScrollTo(
|
||||
manager: SessionManager,
|
||||
params: ScrollToParams,
|
||||
deps: ScrollToDeps = getDefaultDeps(),
|
||||
): Promise<ScrollToResult | RpcError> {
|
||||
const ctxOrErr = lookupSession(manager, params, "scroll-to");
|
||||
if (isRpcError(ctxOrErr)) return ctxOrErr;
|
||||
const ctx = ctxOrErr;
|
||||
const timeout = params.timeout_ms ?? 30_000;
|
||||
if (!Number.isInteger(timeout) || timeout <= 0) {
|
||||
return { code: "invalid_params", message: "timeout_ms must be a positive integer" };
|
||||
}
|
||||
const deadline = Date.now() + timeout;
|
||||
const checkActive = () => {
|
||||
if (deps.signal?.aborted) throw new DOMException("scroll-to aborted", "AbortError");
|
||||
if (Date.now() >= deadline) throw new DOMException("scroll-to timed out", "TimeoutError");
|
||||
};
|
||||
const objectGroup = `bsk-scroll-${crypto.randomUUID()}`;
|
||||
const objectTargets = new Map<string, CdpTarget>();
|
||||
const send = async <T>(target: CdpTarget, method: string, args?: object): Promise<T> => {
|
||||
checkActive();
|
||||
// Also own objects allocated by the shared scroll fallback. Record the
|
||||
// target before awaiting so cancellation cannot skip their cleanup.
|
||||
if (method === "DOM.resolveNode") objectTargets.set(cdpTargetKey(target), target);
|
||||
const result = await sendToCdpTarget<T>(
|
||||
deps.cdp,
|
||||
target,
|
||||
method,
|
||||
method === "DOM.resolveNode" ? { ...args, objectGroup } : args,
|
||||
);
|
||||
checkActive();
|
||||
return result;
|
||||
};
|
||||
let graph: ReturnType<NonNullable<CdpRunner["getFrameGraph"]>> | undefined;
|
||||
const cdp: CdpRunner = {
|
||||
send: (tabId, method, args) => send({ tabId }, method, args),
|
||||
sendToTarget: send,
|
||||
trackSessionTab: deps.cdp.trackSessionTab?.bind(deps.cdp),
|
||||
getFrameGraph: deps.cdp.getFrameGraph
|
||||
? async (tabId) => {
|
||||
checkActive();
|
||||
graph ??= deps.cdp.getFrameGraph!(tabId);
|
||||
const result = await graph;
|
||||
checkActive();
|
||||
return result;
|
||||
}
|
||||
: undefined,
|
||||
};
|
||||
try {
|
||||
checkActive();
|
||||
const target = await resolveTargetTab(manager, ctx, params.tab_id, deps.tabsApi);
|
||||
checkActive();
|
||||
if (isRpcError(target)) return target;
|
||||
const denied = enforceAgentWindow(ctx, target, "scroll-to");
|
||||
if (denied) return denied;
|
||||
const dialogCursor = markDialogCursor(deps.cdp, target.tabId);
|
||||
const node = await resolveBackendNode(cdp, ctx, target, params, "scroll-to");
|
||||
checkActive();
|
||||
if (isRpcError(node)) return node;
|
||||
deps.cdp.trackSessionTab?.(ctx.sessionId, target.tabId);
|
||||
const scrollError = await scrollElementAndFramesIntoView(
|
||||
cdp,
|
||||
target.tabId,
|
||||
node.cdpTarget,
|
||||
node.backendNodeId,
|
||||
node.frameId,
|
||||
);
|
||||
checkActive();
|
||||
if (scrollError) return scrollError;
|
||||
const bounds = await scrollVisibleBounds(
|
||||
cdp,
|
||||
target.tabId,
|
||||
{
|
||||
target: node.cdpTarget,
|
||||
backendNodeId: node.backendNodeId,
|
||||
frameId: node.frameId,
|
||||
},
|
||||
deadline,
|
||||
);
|
||||
checkActive();
|
||||
if (!bounds)
|
||||
return rpcError(
|
||||
"permission_denied",
|
||||
"element_not_visible",
|
||||
"scroll-to target has no visible area",
|
||||
);
|
||||
return attachDialogs(deps.cdp, target.tabId, dialogCursor, {
|
||||
tab_id: target.tabId,
|
||||
used_ref: node.usedRef,
|
||||
used_selector: node.usedSelector,
|
||||
...bounds,
|
||||
});
|
||||
} catch (error) {
|
||||
if (deps.signal?.aborted) return { code: "cancelled", message: "scroll-to aborted" };
|
||||
if (Date.now() >= deadline) return { code: "timeout", message: "scroll-to timed out" };
|
||||
return cdpError(error);
|
||||
} finally {
|
||||
// Cleanup bypasses the cancellation guard and cannot replace the result.
|
||||
for (const target of objectTargets.values()) {
|
||||
await sendToCdpTarget(deps.cdp, target, "Runtime.releaseObjectGroup", { objectGroup }).catch(
|
||||
() => {},
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -2,7 +2,6 @@ import { type SessionManager, SessionStartCleanupError } from "@/session-manager
|
||||
import type { RpcError } from "@/transport/types";
|
||||
import { rpcError } from "./errors";
|
||||
import { clearRecordingForSession } from "./record";
|
||||
import type { CdpRunner, ChromeTabsApi } from "./shared";
|
||||
import { isRpcError } from "./shared";
|
||||
import { returnBorrowedTab, type TabManagementDeps } from "./tabs";
|
||||
|
||||
@@ -74,17 +73,11 @@ export interface SessionStopResult {
|
||||
/** Tab ids whose return path failed; those entries remain borrowed so
|
||||
* shutdown can be retried without closing the Agent Window. */
|
||||
return_failures?: Array<{ tab_id: number; code: string; message: string }>;
|
||||
/**
|
||||
* True when the Agent Window was *released* to the user (instead of being
|
||||
* closed) because it still contained user-created tabs after the agent's own
|
||||
* tabs were closed. Single-session scope.
|
||||
*/
|
||||
window_released?: boolean;
|
||||
}
|
||||
|
||||
export interface SessionStopDeps {
|
||||
signal?: AbortSignal;
|
||||
cdp?: Pick<CdpRunner, "releaseSessionTab"> & {
|
||||
cdp?: {
|
||||
detachSession(sessionId: string): Promise<void>;
|
||||
};
|
||||
/**
|
||||
@@ -94,13 +87,6 @@ export interface SessionStopDeps {
|
||||
* without a real browser.
|
||||
*/
|
||||
tabManagement?: TabManagementDeps;
|
||||
/**
|
||||
* Read-only Chrome tabs API used to *query* remaining tabs before deciding
|
||||
* whether to release the window. Kept separate from `tabManagement.tabs`
|
||||
* (a `TabMutationApi` that has no `query`) so the mutation interface stays
|
||||
* pure. Tests can inject a fake `ChromeTabsApi` too.
|
||||
*/
|
||||
tabsQuery?: ChromeTabsApi;
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -166,10 +152,8 @@ export async function handleSessionStart(
|
||||
* cleanly (review parity with M6).
|
||||
* 3. Detach CDP sessions the extension still holds for this
|
||||
* session (no-op if M6/M7 didn't attach to any tab).
|
||||
* 4. Close the agent-created tabs and the home tab (design §3.2).
|
||||
* 5. If any tab remains — those are user-created tabs — release the
|
||||
* window to the user (dropOnly) instead of closing it, so user
|
||||
* tabs survive. Otherwise close the window as before.
|
||||
* 4. Close the Agent Window. SessionManager.stop() removes the
|
||||
* Chrome window and forgets the context.
|
||||
*
|
||||
* Failures in step 1 keep the Agent Window open: a failed borrowed tab
|
||||
* may still be there, so closing the window would risk losing user
|
||||
@@ -204,19 +188,15 @@ export async function handleSessionStop(
|
||||
const returnFailures: SessionStopResult["return_failures"] = [];
|
||||
const borrowedIds = Array.from(ctx.borrowedTabs.keys());
|
||||
for (const tabId of borrowedIds) {
|
||||
// A close event may have removed this borrow while another tab returned.
|
||||
if (!ctx.borrowedTabs.has(tabId)) continue;
|
||||
try {
|
||||
const tabManagement = {
|
||||
...(deps.tabManagement ?? {}),
|
||||
cdp: deps.cdp ?? deps.tabManagement?.cdp,
|
||||
signal: deps.signal,
|
||||
isAgentWindowId:
|
||||
deps.tabManagement?.isAgentWindowId ??
|
||||
((windowId: number) => manager.findByWindowId(windowId) !== null),
|
||||
};
|
||||
const outcome = await returnBorrowedTab(ctx, tabId, tabManagement);
|
||||
if (!ctx.borrowedTabs.has(tabId)) continue;
|
||||
if (typeof outcome === "object" && "code" in outcome) {
|
||||
console.warn(`[bsk session_stop] auto-return failed for tab ${tabId}`, outcome);
|
||||
returnFailures?.push({
|
||||
@@ -229,7 +209,6 @@ export async function handleSessionStop(
|
||||
ctx.borrowedTabs.delete(tabId);
|
||||
}
|
||||
} catch (err) {
|
||||
if (!ctx.borrowedTabs.has(tabId)) continue;
|
||||
const message = err instanceof Error ? err.message : String(err);
|
||||
console.warn(`[bsk session_stop] auto-return threw for tab ${tabId}: ${message}`);
|
||||
returnFailures?.push({
|
||||
@@ -240,15 +219,8 @@ export async function handleSessionStop(
|
||||
}
|
||||
}
|
||||
|
||||
// A previously failed tab may have closed during a later return. Only
|
||||
// confirmed close events remove borrows; ordinary move failures stay retryable.
|
||||
const pendingReturnFailures = returnFailures.filter((failure) =>
|
||||
ctx.borrowedTabs.has(failure.tab_id),
|
||||
);
|
||||
if (deps.signal?.aborted) {
|
||||
const nonCancelFailures = pendingReturnFailures.filter(
|
||||
(failure) => failure.code !== "cancelled",
|
||||
);
|
||||
const nonCancelFailures = returnFailures?.filter((failure) => failure.code !== "cancelled");
|
||||
if (nonCancelFailures && nonCancelFailures.length > 0) {
|
||||
return {
|
||||
...(returnedTabIds.length > 0 ? { returned_tab_ids: returnedTabIds } : {}),
|
||||
@@ -260,8 +232,8 @@ export async function handleSessionStop(
|
||||
|
||||
const result: SessionStopResult = {};
|
||||
if (returnedTabIds.length > 0) result.returned_tab_ids = returnedTabIds;
|
||||
if (pendingReturnFailures.length > 0) {
|
||||
result.return_failures = pendingReturnFailures;
|
||||
if (returnFailures && returnFailures.length > 0) {
|
||||
result.return_failures = returnFailures;
|
||||
// A failed return means at least one borrowed user tab may still be
|
||||
// inside the Agent Window. Keep the session/window alive so the user
|
||||
// can retry `bsk session stop` or explicitly `bsk tab return` after the
|
||||
@@ -281,66 +253,8 @@ export async function handleSessionStop(
|
||||
return { code: "cancelled", message: "session_stop aborted before window close" };
|
||||
}
|
||||
|
||||
// Step 4: close every tab explicitly created by the agent, including the
|
||||
// home tab. `tabsApi` is a
|
||||
// TabMutationApi (remove only); `queryApi` is a separate read-only
|
||||
// ChromeTabsApi. If neither is injected, we conservatively fall back to
|
||||
// closing the window (see Step 5).
|
||||
const tabsApi = deps.tabManagement?.tabs;
|
||||
const queryApi = deps.tabsQuery;
|
||||
|
||||
if (tabsApi) {
|
||||
// Close each agent-created tab that still exists.
|
||||
const agentCreatedTabIds = Array.from(ctx.agentCreatedTabs);
|
||||
for (const tabId of agentCreatedTabIds) {
|
||||
try {
|
||||
await tabsApi.remove(tabId);
|
||||
ctx.agentCreatedTabs.delete(tabId);
|
||||
} catch (err) {
|
||||
// Tab may already be gone (closed by the user). Non-fatal.
|
||||
console.warn(`[bsk session_stop] failed to close agent tab ${tabId}`, err);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Step 5: decide whether to release (keep) the window or close it.
|
||||
let shouldRelease = false;
|
||||
if (queryApi) {
|
||||
try {
|
||||
const liveWindowTabs = await queryApi.query({ windowId: ctx.agentWindowId });
|
||||
// Only genuine *user* tabs count toward keeping the window open.
|
||||
// An agent tab that failed to close in Step 4 may still be present
|
||||
// here; if we counted it as a reason to release (dropOnly), the
|
||||
// window would be kept and that agent tab would leak (issue #57
|
||||
// regression). Exclude any id still tracked in agentCreatedTabs.
|
||||
const userTabs = liveWindowTabs.filter((t) => {
|
||||
if (t.id === undefined) return false;
|
||||
return !ctx.agentCreatedTabs.has(t.id);
|
||||
});
|
||||
const leakedAgentTabs = liveWindowTabs.filter(
|
||||
(t) => t.id !== undefined && ctx.agentCreatedTabs.has(t.id),
|
||||
);
|
||||
if (leakedAgentTabs.length > 0) {
|
||||
console.warn(
|
||||
`[bsk session_stop] ${leakedAgentTabs.length} agent tab(s) failed to close; forcing window close instead of release`,
|
||||
leakedAgentTabs.map((t) => t.id),
|
||||
);
|
||||
}
|
||||
shouldRelease = userTabs.length > 0;
|
||||
} catch {
|
||||
// Query failed (e.g. window already gone) — conservatively close it.
|
||||
shouldRelease = false;
|
||||
}
|
||||
}
|
||||
|
||||
if (shouldRelease) {
|
||||
// Keep the window + its user tabs; only drop the session binding.
|
||||
await manager.stop(params.session_id, { dropOnly: true });
|
||||
result.window_released = true;
|
||||
} else {
|
||||
// Window is empty (or we couldn't verify state) — close it.
|
||||
await manager.stop(params.session_id);
|
||||
}
|
||||
// Step 4: close the Agent Window and drop the context.
|
||||
await manager.stop(params.session_id);
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
@@ -55,10 +55,8 @@ export interface CdpRunner {
|
||||
sendToTarget?<T = unknown>(target: CdpTarget, method: string, params?: object): Promise<T>;
|
||||
detach?(tabId: number): Promise<void>;
|
||||
getFrameGraph?(tabId: number): Promise<CdpFrameGraph>;
|
||||
getAttachmentId?(tabId: number): string | undefined;
|
||||
ensureAttachedToUrl?(tabId: number, expectedUrl: string | undefined): Promise<void>;
|
||||
trackSessionTab?(sessionId: string, tabId: number): void;
|
||||
releaseSessionTab?(sessionId: string, tabId: number): Promise<void>;
|
||||
onEvent?(handler: (source: CdpDebuggee, method: string, params: unknown) => void): {
|
||||
dispose(): void;
|
||||
};
|
||||
|
||||
@@ -2,8 +2,9 @@
|
||||
// compound CDP node identity via the session RefStore, and build stable
|
||||
// `ref_not_found` errors for hard-failure tool paths.
|
||||
|
||||
import type { Rect } from "@browser-skill/vom";
|
||||
import type { SessionContext } from "@/session-manager/manager";
|
||||
import { normaliseRef, type RefEntry } from "@/session-manager/ref-store";
|
||||
import { normaliseRef, type RefCapability, type RefTargetKind } from "@/session-manager/ref-store";
|
||||
import type { RpcError } from "@/transport/types";
|
||||
import { rpcError } from "./errors";
|
||||
|
||||
@@ -12,24 +13,19 @@ export interface SnapshotRefLookup {
|
||||
refKey: string;
|
||||
frameId?: string;
|
||||
cdpSessionId?: string;
|
||||
visibleRect?: Rect;
|
||||
kind: RefTargetKind;
|
||||
capabilities: RefCapability[];
|
||||
}
|
||||
|
||||
/** Typed lookup never turns a visual anchor into a DOM operation target. */
|
||||
export function lookupRefTarget(
|
||||
ctx: SessionContext,
|
||||
refKey: string,
|
||||
tabId: number,
|
||||
): RefEntry | null {
|
||||
function refEntryForTab(ctx: SessionContext, refKey: string, tabId: number) {
|
||||
const entry = ctx.refStore.resolveEntry(refKey);
|
||||
if (!entry) return null;
|
||||
const ownerTabId =
|
||||
entry.kind === "visual-region" ? entry.candidate.document.target.tabId : entry.tabId;
|
||||
return ownerTabId === tabId ? entry : null;
|
||||
return entry?.tabId === tabId ? entry : null;
|
||||
}
|
||||
|
||||
/**
|
||||
* Soft lookup: returns `null` when the ref is unknown or bound to a
|
||||
* different tab, or is a visual region. Used by paths that report `matched: false` instead of
|
||||
* different tab. Used by paths that report `matched: false` instead of
|
||||
* emitting an RPC error (e.g. `tool.request_help`).
|
||||
*/
|
||||
export function lookupSnapshotRef(
|
||||
@@ -38,13 +34,16 @@ export function lookupSnapshotRef(
|
||||
tabId: number,
|
||||
): SnapshotRefLookup | null {
|
||||
const refKey = normaliseRef(ref);
|
||||
const entry = lookupRefTarget(ctx, refKey, tabId);
|
||||
if (!entry || entry.kind !== "dom") return null;
|
||||
const entry = refEntryForTab(ctx, refKey, tabId);
|
||||
if (!entry) return null;
|
||||
return {
|
||||
backendNodeId: entry.backendNodeId,
|
||||
refKey,
|
||||
...(entry.frameId ? { frameId: entry.frameId } : {}),
|
||||
...(entry.cdpSessionId ? { cdpSessionId: entry.cdpSessionId } : {}),
|
||||
...(entry.visibleRect ? { visibleRect: entry.visibleRect } : {}),
|
||||
kind: entry.kind,
|
||||
capabilities: entry.capabilities,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -57,14 +56,8 @@ export function resolveSnapshotRef(
|
||||
ctx: SessionContext,
|
||||
ref: string,
|
||||
tabId: number,
|
||||
requiredCapability?: RefCapability,
|
||||
): SnapshotRefLookup | RpcError {
|
||||
const entry = lookupRefTarget(ctx, ref, tabId);
|
||||
if (entry?.kind === "visual-region")
|
||||
return rpcError(
|
||||
"unsupported",
|
||||
"ref_kind_unsupported",
|
||||
`ref ${ref} is a visual region, not a DOM operation target`,
|
||||
);
|
||||
const looked = lookupSnapshotRef(ctx, ref, tabId);
|
||||
if (looked === null) {
|
||||
return rpcError(
|
||||
@@ -73,5 +66,13 @@ export function resolveSnapshotRef(
|
||||
`ref ${ref} unknown for tab ${tabId} in session ${ctx.sessionId}`,
|
||||
);
|
||||
}
|
||||
if (requiredCapability && !looked.capabilities.includes(requiredCapability)) {
|
||||
return rpcError(
|
||||
"permission_denied",
|
||||
"ref_capability_denied",
|
||||
`ref ${ref} does not support ${requiredCapability}`,
|
||||
{ ref: looked.refKey, required_capability: requiredCapability, kind: looked.kind },
|
||||
);
|
||||
}
|
||||
return looked;
|
||||
}
|
||||
|
||||
@@ -10,7 +10,7 @@ import {
|
||||
import type { SessionContext, SessionManager } from "@/session-manager/manager";
|
||||
import type { RpcError } from "@/transport/types";
|
||||
import { rpcError } from "./errors";
|
||||
import { type CdpRunner, isRpcError, lookupSession } from "./shared";
|
||||
import { isRpcError, lookupSession } from "./shared";
|
||||
|
||||
export type TabScope = "user" | "agent" | "all";
|
||||
|
||||
@@ -287,10 +287,6 @@ export interface TabManagementDeps {
|
||||
approveBorrow?: BorrowConfirmationApprover;
|
||||
/** Clears Agent-scoped overlays after a borrowed tab is returned. */
|
||||
agentOverlayReset?: AgentOverlayResetApi;
|
||||
/** Releases this session's CDP claim after a borrowed tab is returned. */
|
||||
cdp?: Pick<CdpRunner, "releaseSessionTab">;
|
||||
/** Runs after tab_return validation, before moving the borrowed tab. */
|
||||
beforeReturn?: (sessionId: string, tabId: number) => Promise<void>;
|
||||
/**
|
||||
* Reports whether `windowId` is any live session's Agent Window.
|
||||
* `tab_return`'s fallback window picker uses this to avoid moving a
|
||||
@@ -373,7 +369,6 @@ function buildCreateProps(
|
||||
* Returns the created tab on success, or an `RpcError` on failure.
|
||||
*/
|
||||
async function createTabAndCleanup(
|
||||
ctx: SessionContext,
|
||||
deps: TabManagementDeps,
|
||||
createProps: chrome.tabs.CreateProperties,
|
||||
): Promise<CreatedChromeTab | RpcError> {
|
||||
@@ -386,28 +381,25 @@ async function createTabAndCleanup(
|
||||
message: err instanceof Error ? err.message : String(err),
|
||||
};
|
||||
}
|
||||
if (typeof tab.id !== "number") {
|
||||
return { code: "protocol_error", message: "chrome.tabs.create returned no tab id" };
|
||||
}
|
||||
// Claim the concrete id returned by Chrome. Ownership never depends on
|
||||
// matching this request to an asynchronous onCreated event.
|
||||
ctx.agentCreatedTabs.add(tab.id);
|
||||
if (aborted(deps.signal, "tab_create")) {
|
||||
try {
|
||||
await getTabsApi(deps).remove(tab.id);
|
||||
ctx.agentCreatedTabs.delete(tab.id);
|
||||
} catch (cleanupErr) {
|
||||
// Keep the claim when cleanup fails so session_stop can retry instead
|
||||
// of releasing an agent-owned tab to the user.
|
||||
return rpcError(
|
||||
"protocol_error",
|
||||
"cleanup_failed",
|
||||
`tab_create aborted but cleanup of tab ${tab.id} failed: ${describeError(cleanupErr)}`,
|
||||
{ resource_type: "tab", resource_id: tab.id },
|
||||
);
|
||||
// We already opened the tab; close it on abort so we don't leak.
|
||||
if (typeof tab.id === "number") {
|
||||
try {
|
||||
await getTabsApi(deps).remove(tab.id);
|
||||
} catch (cleanupErr) {
|
||||
return rpcError(
|
||||
"protocol_error",
|
||||
"cleanup_failed",
|
||||
`tab_create aborted but cleanup of tab ${tab.id} failed: ${describeError(cleanupErr)}`,
|
||||
{ resource_type: "tab", resource_id: tab.id },
|
||||
);
|
||||
}
|
||||
}
|
||||
return { code: "cancelled", message: "tab_create aborted" };
|
||||
}
|
||||
if (typeof tab.id !== "number") {
|
||||
return { code: "protocol_error", message: "chrome.tabs.create returned no tab id" };
|
||||
}
|
||||
return { ...tab, id: tab.id };
|
||||
}
|
||||
|
||||
@@ -434,7 +426,7 @@ export async function handleTabCreate(
|
||||
const paramErr = validateTabCreateParams(params);
|
||||
if (paramErr) return paramErr;
|
||||
|
||||
const tab = await createTabAndCleanup(ctx, deps, buildCreateProps(ctx, params));
|
||||
const tab = await createTabAndCleanup(deps, buildCreateProps(ctx, params));
|
||||
if (isRpcError(tab)) return tab;
|
||||
|
||||
return {
|
||||
@@ -534,9 +526,6 @@ export async function handleTabClose(
|
||||
}
|
||||
try {
|
||||
await getTabsApi(deps).remove(params.tab_id);
|
||||
// Keep the tracking set accurate so session_stop won't try to close a
|
||||
// tab that's already gone (design §3.1).
|
||||
ctx.agentCreatedTabs.delete(params.tab_id);
|
||||
} catch (err) {
|
||||
return {
|
||||
code: "protocol_error",
|
||||
@@ -764,6 +753,13 @@ async function executeBorrowCore(
|
||||
);
|
||||
if (moveErr) return moveErr;
|
||||
|
||||
// Best-effort activation — failure is non-fatal.
|
||||
try {
|
||||
await p.tabsApi.update(p.tabId, { active: true });
|
||||
} catch (err) {
|
||||
console.debug("[bsk tab_borrow] activate after move failed", err);
|
||||
}
|
||||
|
||||
return { originalWindowId, originalIndex };
|
||||
}
|
||||
|
||||
@@ -827,12 +823,6 @@ export async function handleTabBorrow(
|
||||
message: err instanceof Error ? err.message : String(err),
|
||||
};
|
||||
}
|
||||
// Activate after commit so overlay/event observers see the tab as claimed.
|
||||
try {
|
||||
await tabsApi.update(params.tab_id, { active: true });
|
||||
} catch (err) {
|
||||
console.debug("[bsk tab_borrow] activate after move failed", err);
|
||||
}
|
||||
return {
|
||||
tab_id: params.tab_id,
|
||||
original_window_id: coreResult.originalWindowId,
|
||||
@@ -949,22 +939,16 @@ async function cleanupUnusedFallbackWindow(
|
||||
}
|
||||
}
|
||||
|
||||
async function releaseReturnedTabState(
|
||||
function resetAgentOverlaysInReturnedTab(
|
||||
ctx: SessionContext,
|
||||
tabId: number,
|
||||
deps: TabManagementDeps,
|
||||
): Promise<void> {
|
||||
): void {
|
||||
void getAgentOverlayResetApi(deps)
|
||||
.resetAgentOverlays(tabId, ctx.sessionId)
|
||||
.catch((err) => {
|
||||
console.debug("[bsk tab_return] agent overlay reset failed", err);
|
||||
});
|
||||
try {
|
||||
await deps.cdp?.releaseSessionTab?.(ctx.sessionId, tabId);
|
||||
} catch (err) {
|
||||
// A successful move must not be retried because debugger cleanup failed.
|
||||
console.debug("[bsk tab_return] CDP release failed", err);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -1038,7 +1022,7 @@ export async function returnBorrowedTab(
|
||||
});
|
||||
const movedTab = Array.isArray(moved) ? moved[0] : moved;
|
||||
const finalIndex = typeof movedTab?.index === "number" ? movedTab.index : targetIndex;
|
||||
await releaseReturnedTabState(ctx, tabId, deps);
|
||||
resetAgentOverlaysInReturnedTab(ctx, tabId, deps);
|
||||
return {
|
||||
tabId,
|
||||
toWindowId: targetWindowId,
|
||||
@@ -1080,7 +1064,7 @@ export async function returnBorrowedTab(
|
||||
});
|
||||
const movedTab = Array.isArray(moved) ? moved[0] : moved;
|
||||
const finalIndex = typeof movedTab?.index === "number" ? movedTab.index : target.index;
|
||||
await releaseReturnedTabState(ctx, tabId, deps);
|
||||
resetAgentOverlaysInReturnedTab(ctx, tabId, deps);
|
||||
return {
|
||||
tabId,
|
||||
toWindowId: target.windowId,
|
||||
@@ -1126,7 +1110,6 @@ export async function handleTabReturn(
|
||||
message: `tab_return: tab ${params.tab_id} is not borrowed by this session`,
|
||||
};
|
||||
}
|
||||
await deps.beforeReturn?.(ctx.sessionId, params.tab_id);
|
||||
const outcome = await returnBorrowedTab(ctx, params.tab_id, {
|
||||
...deps,
|
||||
isAgentWindowId:
|
||||
|
||||
@@ -1,42 +0,0 @@
|
||||
// Shared time boundary for browser-side file-transfer transactions. Concrete
|
||||
// upload/download mechanisms own their state machines and effect semantics.
|
||||
|
||||
export class BoundedWaitError extends Error {
|
||||
constructor(
|
||||
readonly kind: "timeout" | "aborted",
|
||||
message: string,
|
||||
) {
|
||||
super(message);
|
||||
}
|
||||
}
|
||||
|
||||
export function remainingMs(deadline: number): number {
|
||||
return Math.max(0, deadline - Date.now());
|
||||
}
|
||||
|
||||
export async function waitBounded<T>(
|
||||
promise: Promise<T>,
|
||||
deadline: number,
|
||||
signal: AbortSignal | undefined,
|
||||
timeoutMessage: string,
|
||||
): Promise<T> {
|
||||
const remaining = remainingMs(deadline);
|
||||
if (signal?.aborted) throw new BoundedWaitError("aborted", "file transfer aborted");
|
||||
if (remaining === 0) throw new BoundedWaitError("timeout", timeoutMessage);
|
||||
|
||||
let timer: ReturnType<typeof setTimeout> | undefined;
|
||||
let onAbort: (() => void) | undefined;
|
||||
const boundary = new Promise<never>((_resolve, reject) => {
|
||||
timer = setTimeout(() => reject(new BoundedWaitError("timeout", timeoutMessage)), remaining);
|
||||
if (signal) {
|
||||
onAbort = () => reject(new BoundedWaitError("aborted", "file transfer aborted"));
|
||||
signal.addEventListener("abort", onAbort, { once: true });
|
||||
}
|
||||
});
|
||||
try {
|
||||
return await Promise.race([promise, boundary]);
|
||||
} finally {
|
||||
if (timer) clearTimeout(timer);
|
||||
if (signal && onAbort) signal.removeEventListener("abort", onAbort);
|
||||
}
|
||||
}
|
||||
@@ -2,13 +2,8 @@
|
||||
// target, then delegate the browser protocol transaction to the file-input
|
||||
// transaction module.
|
||||
|
||||
import {
|
||||
type CaptureSuppressSendToTab,
|
||||
withExtensionOverlayHidden,
|
||||
} from "@/lib/capture-suppress-bridge";
|
||||
import type { SessionManager } from "@/session-manager/manager";
|
||||
import type { RpcError, UploadParams, UploadResult } from "@/transport/types";
|
||||
import { uploadThroughFileDrop } from "./file-drop-transaction";
|
||||
import { uploadThroughActivatedFileInput } from "./file-input-transaction";
|
||||
import { clickResolvedTarget, type InteractionDeps, resolveActionTarget } from "./interaction";
|
||||
import {
|
||||
@@ -23,7 +18,6 @@ const DEFAULT_TIMEOUT_MS = 120_000;
|
||||
|
||||
export interface UploadDeps extends InteractionDeps {
|
||||
cdp: CdpRunner;
|
||||
sendToTab?: CaptureSuppressSendToTab;
|
||||
}
|
||||
|
||||
export async function handleUpload(
|
||||
@@ -47,39 +41,19 @@ export async function handleUpload(
|
||||
const address = await resolveActionTarget(deps.cdp, ctx, target, params, "upload");
|
||||
if (isRpcError(address)) return address;
|
||||
const timeoutMs = params.timeout_ms ?? DEFAULT_TIMEOUT_MS;
|
||||
const files = params.files.map((file) => file.staged_path as string);
|
||||
const mode = params.mode ?? "input";
|
||||
let usedRef = address.usedRef;
|
||||
let usedSelector = address.usedSelector;
|
||||
if (mode === "drop") {
|
||||
deps.cdp.trackSessionTab?.(ctx.sessionId, target.tabId);
|
||||
const transaction = await uploadThroughFileDrop({
|
||||
cdp: deps.cdp,
|
||||
actionTarget: address,
|
||||
files,
|
||||
timeoutMs,
|
||||
signal: deps.signal,
|
||||
withOverlayHidden: (operation) =>
|
||||
withExtensionOverlayHidden(target.tabId, operation, deps.sendToTab),
|
||||
});
|
||||
if (isRpcError(transaction)) return transaction;
|
||||
} else {
|
||||
const transaction = await uploadThroughActivatedFileInput({
|
||||
cdp: deps.cdp,
|
||||
actionTarget: address,
|
||||
files,
|
||||
timeoutMs,
|
||||
signal: deps.signal,
|
||||
trigger: () => clickResolvedTarget(ctx, address, {}, deps),
|
||||
});
|
||||
if (isRpcError(transaction)) return transaction;
|
||||
usedRef = transaction.click.used_ref;
|
||||
usedSelector = transaction.click.used_selector;
|
||||
}
|
||||
const transaction = await uploadThroughActivatedFileInput({
|
||||
cdp: deps.cdp,
|
||||
actionTarget: address,
|
||||
files: params.files.map((file) => file.staged_path as string),
|
||||
timeoutMs,
|
||||
signal: deps.signal,
|
||||
trigger: () => clickResolvedTarget(ctx, address, {}, deps),
|
||||
});
|
||||
if (isRpcError(transaction)) return transaction;
|
||||
return {
|
||||
tab_id: target.tabId,
|
||||
used_ref: usedRef,
|
||||
used_selector: usedSelector,
|
||||
used_ref: transaction.click.used_ref,
|
||||
used_selector: transaction.click.used_selector,
|
||||
file_names: params.files.map((file) => file.name),
|
||||
};
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,7 +1,7 @@
|
||||
import { describe, expect, it, vi } from "vitest";
|
||||
import { OVERLAY_HOST_MARKER_ATTR, OVERLAY_HOST_NAME } from "../../../lib/overlay-bridge";
|
||||
import { collectOverlayExcludedBackendIds, probeHoverSurfaces } from "../capture";
|
||||
import { captureObservationFacts, semanticCapture } from "../capture-coordinator";
|
||||
import { captureViewModel, collectOverlayExcludedBackendIds, probeHoverSurfaces } from "../capture";
|
||||
import { discoverRenderedSurfaces } from "../rendered-surfaces";
|
||||
|
||||
// Minimal but format-accurate captureSnapshot reply: a body with one
|
||||
// fixed full-screen overlay div carrying a password input.
|
||||
@@ -27,7 +27,6 @@ function fakeSnapshotReply() {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "root",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1, 2],
|
||||
nodeType: [1, 1, 1, 1],
|
||||
@@ -75,7 +74,6 @@ function hoverTriggerSnapshotReply() {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "root",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1],
|
||||
nodeType: [1, 1, 1],
|
||||
@@ -120,7 +118,6 @@ function twoHoverTriggerSnapshotReply() {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "root",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1, 1],
|
||||
nodeType: [1, 1, 1, 1],
|
||||
@@ -174,7 +171,6 @@ function nestedHoverTriggerSnapshotReply() {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "root",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1, 2, 3],
|
||||
nodeType: [1, 1, 1, 1, 1],
|
||||
@@ -215,48 +211,38 @@ function makeCdp(snapshot: unknown) {
|
||||
if (method === "DOMSnapshot.enable") return {};
|
||||
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return {
|
||||
visualViewport: { clientWidth: 1000 },
|
||||
cssVisualViewport: { clientWidth: 1000 },
|
||||
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
|
||||
};
|
||||
return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 } };
|
||||
}
|
||||
if (method === "Runtime.evaluate") {
|
||||
return {
|
||||
result: {
|
||||
deepSerializedValue: {
|
||||
type: "array",
|
||||
value: [
|
||||
value: {
|
||||
controls: [
|
||||
{
|
||||
type: "array",
|
||||
value: [
|
||||
{ type: "node", value: { backendNodeId: 13 } },
|
||||
{
|
||||
type: "string",
|
||||
value: JSON.stringify({
|
||||
state: "filled",
|
||||
sensitive: true,
|
||||
placeholder: "secret",
|
||||
}),
|
||||
},
|
||||
],
|
||||
state: "filled",
|
||||
sensitive: true,
|
||||
defaultValue: "hunter2",
|
||||
value: "hunter2",
|
||||
placeholder: "secret",
|
||||
},
|
||||
],
|
||||
childFrames: [],
|
||||
},
|
||||
},
|
||||
};
|
||||
}
|
||||
if (method === "Runtime.releaseObjectGroup") return {};
|
||||
throw new Error(`unexpected ${method}`);
|
||||
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
|
||||
};
|
||||
}
|
||||
|
||||
describe("snapshot capture and hover", () => {
|
||||
describe("captureViewModel", () => {
|
||||
it("parses nodes, attrs, rects, paint order and styles", async () => {
|
||||
const { nodes, viewport } = semanticCapture(
|
||||
await captureObservationFacts(makeCdp(fakeSnapshotReply()), 4),
|
||||
).captured;
|
||||
const { nodes, viewport, iframeNodes } = await captureViewModel(
|
||||
makeCdp(fakeSnapshotReply()),
|
||||
4,
|
||||
);
|
||||
expect(iframeNodes.size).toBe(0);
|
||||
expect(viewport).toEqual({ width: 1000, height: 800 });
|
||||
const div = nodes.find((n) => n.backendNodeId === 12);
|
||||
expect(div).toMatchObject({ tag: "div", position: "fixed", parentBackendNodeId: 11 });
|
||||
@@ -268,11 +254,32 @@ describe("snapshot capture and hover", () => {
|
||||
|
||||
it("never hovers the page while capturing", async () => {
|
||||
const cdp = makeCdp(fakeSnapshotReply());
|
||||
semanticCapture(await captureObservationFacts(cdp, 4)).captured;
|
||||
await captureViewModel(cdp, 4);
|
||||
|
||||
expect(cdp.send).not.toHaveBeenCalledWith(4, "Input.dispatchMouseEvent", expect.anything());
|
||||
});
|
||||
|
||||
it("batch-enriches form controls without per-node object resolution", async () => {
|
||||
const cdp = makeCdp(fakeSnapshotReply());
|
||||
const result = await captureViewModel(cdp, 4);
|
||||
const input = result.nodes.find((node) => node.backendNodeId === 13);
|
||||
|
||||
expect(input).toMatchObject({
|
||||
formState: "filled",
|
||||
formPlaceholder: "secret",
|
||||
attrs: { type: "password" },
|
||||
});
|
||||
expect(input?.formValue).toBeUndefined();
|
||||
expect(input?.formDefaultValue).toBeUndefined();
|
||||
expect(cdp.send).toHaveBeenCalledWith(
|
||||
4,
|
||||
"Runtime.evaluate",
|
||||
expect.objectContaining({ returnByValue: true }),
|
||||
);
|
||||
expect(cdp.send).not.toHaveBeenCalledWith(4, "DOM.resolveNode", expect.anything());
|
||||
expect(cdp.send).not.toHaveBeenCalledWith(4, "Runtime.callFunctionOn", expect.anything());
|
||||
});
|
||||
|
||||
it("runs hover surface probes when explicitly enabled", async () => {
|
||||
let hoverStateCalls = 0;
|
||||
const cdp = {
|
||||
@@ -281,8 +288,6 @@ describe("snapshot capture and hover", () => {
|
||||
if (method === "DOMSnapshot.captureSnapshot") return hoverTriggerSnapshotReply();
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return {
|
||||
visualViewport: { clientWidth: 1000 },
|
||||
cssVisualViewport: { clientWidth: 1000 },
|
||||
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
|
||||
};
|
||||
}
|
||||
@@ -314,7 +319,7 @@ describe("snapshot capture and hover", () => {
|
||||
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
|
||||
};
|
||||
|
||||
const captured = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
|
||||
const captured = await captureViewModel(cdp, 4);
|
||||
const surfaceProbes = await probeHoverSurfaces(cdp, 4, captured.nodes);
|
||||
|
||||
expect(surfaceProbes).toEqual([
|
||||
@@ -346,8 +351,6 @@ describe("snapshot capture and hover", () => {
|
||||
if (method === "DOMSnapshot.captureSnapshot") return twoHoverTriggerSnapshotReply();
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return {
|
||||
visualViewport: { clientWidth: 1000 },
|
||||
cssVisualViewport: { clientWidth: 1000 },
|
||||
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
|
||||
};
|
||||
}
|
||||
@@ -376,7 +379,7 @@ describe("snapshot capture and hover", () => {
|
||||
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
|
||||
};
|
||||
|
||||
const captured = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
|
||||
const captured = await captureViewModel(cdp, 4);
|
||||
const surfaceProbes = await probeHoverSurfaces(cdp, 4, captured.nodes);
|
||||
|
||||
expect(surfaceProbes).toEqual([
|
||||
@@ -396,8 +399,6 @@ describe("snapshot capture and hover", () => {
|
||||
if (method === "DOMSnapshot.captureSnapshot") return nestedHoverTriggerSnapshotReply();
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return {
|
||||
visualViewport: { clientWidth: 1000 },
|
||||
cssVisualViewport: { clientWidth: 1000 },
|
||||
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
|
||||
};
|
||||
}
|
||||
@@ -423,7 +424,7 @@ describe("snapshot capture and hover", () => {
|
||||
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
|
||||
};
|
||||
|
||||
const captured = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
|
||||
const captured = await captureViewModel(cdp, 4);
|
||||
await probeHoverSurfaces(cdp, 4, captured.nodes);
|
||||
|
||||
expect(hoverMoves).toBe(1);
|
||||
@@ -455,7 +456,6 @@ describe("snapshot capture and hover", () => {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "root",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1, 0, 3, 4],
|
||||
nodeName: [i("html"), i("body"), i("div"), i(OVERLAY_HOST_NAME), i("div"), i("button")],
|
||||
@@ -486,7 +486,7 @@ describe("snapshot capture and hover", () => {
|
||||
],
|
||||
};
|
||||
|
||||
const { nodes } = semanticCapture(await captureObservationFacts(makeCdp(snapshot), 4)).captured;
|
||||
const { nodes } = await captureViewModel(makeCdp(snapshot), 4);
|
||||
const ids = nodes.map((n) => n.backendNodeId);
|
||||
// Real page nodes survive.
|
||||
expect(ids).toContain(12);
|
||||
@@ -517,7 +517,6 @@ describe("snapshot capture and hover", () => {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "root",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1, 0, 3, 4],
|
||||
nodeName: [i("html"), i("body"), i("div"), i(OVERLAY_HOST_NAME), i("div"), i("button")],
|
||||
@@ -548,9 +547,7 @@ describe("snapshot capture and hover", () => {
|
||||
],
|
||||
};
|
||||
|
||||
const { excludedBackendNodeIds } = semanticCapture(
|
||||
await captureObservationFacts(makeCdp(snapshot), 4),
|
||||
).captured;
|
||||
const { excludedBackendNodeIds } = await captureViewModel(makeCdp(snapshot), 4);
|
||||
expect(excludedBackendNodeIds).toEqual(new Set([13, 14, 15]));
|
||||
});
|
||||
|
||||
@@ -571,7 +568,6 @@ describe("snapshot capture and hover", () => {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "root",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1],
|
||||
nodeName: [i("html"), i("body"), i(OVERLAY_HOST_NAME)],
|
||||
@@ -594,9 +590,7 @@ describe("snapshot capture and hover", () => {
|
||||
],
|
||||
};
|
||||
|
||||
const { nodes, excludedBackendNodeIds } = semanticCapture(
|
||||
await captureObservationFacts(makeCdp(snapshot), 4),
|
||||
).captured;
|
||||
const { nodes, excludedBackendNodeIds } = await captureViewModel(makeCdp(snapshot), 4);
|
||||
expect(nodes.map((n) => n.backendNodeId)).not.toContain(13);
|
||||
expect(excludedBackendNodeIds).toEqual(new Set([13]));
|
||||
});
|
||||
@@ -619,7 +613,6 @@ describe("snapshot capture and hover", () => {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "root",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1],
|
||||
nodeName: [i("html"), i("body"), i("div")],
|
||||
@@ -642,9 +635,7 @@ describe("snapshot capture and hover", () => {
|
||||
],
|
||||
};
|
||||
|
||||
const { nodes, excludedBackendNodeIds } = semanticCapture(
|
||||
await captureObservationFacts(makeCdp(snapshot), 4),
|
||||
).captured;
|
||||
const { nodes, excludedBackendNodeIds } = await captureViewModel(makeCdp(snapshot), 4);
|
||||
expect(nodes.map((n) => n.backendNodeId)).not.toContain(13);
|
||||
expect(excludedBackendNodeIds).toEqual(new Set([13]));
|
||||
});
|
||||
@@ -667,7 +658,6 @@ describe("snapshot capture and hover", () => {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "root",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1],
|
||||
nodeName: [i("html"), i("body"), i("div")],
|
||||
@@ -690,7 +680,7 @@ describe("snapshot capture and hover", () => {
|
||||
},
|
||||
],
|
||||
};
|
||||
const { nodes } = semanticCapture(await captureObservationFacts(makeCdp(snapshot), 4)).captured;
|
||||
const { nodes } = await captureViewModel(makeCdp(snapshot), 4);
|
||||
expect(nodes.find((n) => n.backendNodeId === 12)?.cursor).toBe("pointer");
|
||||
expect(nodes.find((n) => n.backendNodeId === 11)?.cursor).toBe("auto");
|
||||
});
|
||||
@@ -702,7 +692,6 @@ describe("snapshot capture and hover", () => {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "root",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1, 1, 1],
|
||||
nodeName: [i("html"), i("body"), i("button"), i("button"), i("button")],
|
||||
@@ -729,13 +718,51 @@ describe("snapshot capture and hover", () => {
|
||||
],
|
||||
};
|
||||
|
||||
const { nodes } = semanticCapture(await captureObservationFacts(makeCdp(snapshot), 4)).captured;
|
||||
const { nodes } = await captureViewModel(makeCdp(snapshot), 4);
|
||||
|
||||
expect(nodes.find((node) => node.backendNodeId === 12)?.rendered).toBe(true);
|
||||
expect(nodes.find((node) => node.backendNodeId === 13)?.rendered).toBe(false);
|
||||
expect(nodes.find((node) => node.backendNodeId === 14)?.rendered).toBe(false);
|
||||
});
|
||||
|
||||
it("propagates fully transparent ancestor suppression to painted descendants", async () => {
|
||||
const S = ["html", "body", "div", "canvas", "static", "auto", "visible", "1", "0"];
|
||||
const i = (value: string) => S.indexOf(value);
|
||||
const snapshot = {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1, 2],
|
||||
nodeName: [i("html"), i("body"), i("div"), i("canvas")],
|
||||
backendNodeId: [10, 11, 12, 13],
|
||||
attributes: [[], [], [], []],
|
||||
},
|
||||
layout: {
|
||||
nodeIndex: [1, 2, 3],
|
||||
styles: [
|
||||
[i("static"), i("auto"), i("auto"), i("visible"), i("1")],
|
||||
[i("static"), i("auto"), i("auto"), i("visible"), i("0")],
|
||||
[i("static"), i("auto"), i("auto"), i("visible"), i("1")],
|
||||
],
|
||||
bounds: [
|
||||
[0, 0, 1000, 800],
|
||||
[10, 10, 200, 100],
|
||||
[10, 10, 200, 100],
|
||||
],
|
||||
paintOrders: [0, 1, 2],
|
||||
},
|
||||
},
|
||||
],
|
||||
};
|
||||
|
||||
const { nodes } = await captureViewModel(makeCdp(snapshot), 4);
|
||||
const canvas = nodes.find((node) => node.backendNodeId === 13);
|
||||
|
||||
expect(canvas?.rendered).toBe(true);
|
||||
expect(canvas?.visuallySuppressed).toBe(true);
|
||||
});
|
||||
|
||||
it("subtracts scroll offset to make rects viewport-relative", async () => {
|
||||
const cdp = {
|
||||
send: vi.fn(async (_t: number, method: string) => {
|
||||
@@ -743,28 +770,25 @@ describe("snapshot capture and hover", () => {
|
||||
if (method === "DOMSnapshot.captureSnapshot") return fakeSnapshotReply();
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return {
|
||||
visualViewport: { clientWidth: 1000 },
|
||||
cssVisualViewport: { clientWidth: 1000 },
|
||||
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 200 },
|
||||
};
|
||||
}
|
||||
throw new Error(method);
|
||||
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
|
||||
};
|
||||
const { nodes } = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
|
||||
const { nodes } = await captureViewModel(cdp, 4);
|
||||
const div = nodes.find((n) => n.backendNodeId === 12);
|
||||
expect(div?.localRect?.y).toBe(-200);
|
||||
expect(div?.rect).toMatchObject({ y: 0, h: 600 });
|
||||
});
|
||||
|
||||
it("normalizes raw snapshot bounds before viewport clipping", async () => {
|
||||
it("normalizes device-pixel bounds by devicePixelRatio", async () => {
|
||||
const S = ["html", "body", "div", "position", "fixed", "static", "pointer-events", "auto"];
|
||||
const i = (s: string) => S.indexOf(s);
|
||||
const snapshot = {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "root",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1],
|
||||
nodeName: [i("html"), i("body"), i("div")],
|
||||
@@ -792,8 +816,6 @@ describe("snapshot capture and hover", () => {
|
||||
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return {
|
||||
visualViewport: { clientWidth: 2000 },
|
||||
cssVisualViewport: { clientWidth: 1000 },
|
||||
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
|
||||
layoutViewport: { clientWidth: 2000, clientHeight: 1600 },
|
||||
};
|
||||
@@ -801,19 +823,13 @@ describe("snapshot capture and hover", () => {
|
||||
throw new Error(method);
|
||||
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
|
||||
};
|
||||
const { nodes } = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
|
||||
const { nodes } = await captureViewModel(cdp, 4);
|
||||
expect(nodes.find((n) => n.backendNodeId === 12)?.rect).toEqual({
|
||||
x: 0,
|
||||
y: 0,
|
||||
w: 1000,
|
||||
h: 800,
|
||||
});
|
||||
expect(nodes.find((n) => n.backendNodeId === 12)?.localRect).toEqual({
|
||||
x: 0,
|
||||
y: 0,
|
||||
w: 1000,
|
||||
h: 800,
|
||||
});
|
||||
});
|
||||
|
||||
it("extracts textContent from #text child nodes via nodeValue", async () => {
|
||||
@@ -837,7 +853,6 @@ describe("snapshot capture and hover", () => {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "root",
|
||||
scrollOffsetX: 0,
|
||||
scrollOffsetY: 0,
|
||||
nodes: {
|
||||
@@ -870,15 +885,13 @@ describe("snapshot capture and hover", () => {
|
||||
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return {
|
||||
visualViewport: { clientWidth: 1000 },
|
||||
cssVisualViewport: { clientWidth: 1000 },
|
||||
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
|
||||
};
|
||||
}
|
||||
throw new Error(method);
|
||||
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
|
||||
};
|
||||
const { nodes } = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
|
||||
const { nodes } = await captureViewModel(cdp, 4);
|
||||
const btn = nodes.find((n) => n.backendNodeId === 12);
|
||||
expect(btn?.textContent).toBe("登录");
|
||||
const link = nodes.find((n) => n.backendNodeId === 14);
|
||||
@@ -888,7 +901,7 @@ describe("snapshot capture and hover", () => {
|
||||
expect(body?.textContent).toBeUndefined();
|
||||
});
|
||||
|
||||
it("retains explicit iframe document ownership and projected nodes", async () => {
|
||||
it("parses iframe sub-documents and returns iframeNodes keyed by iframe backendNodeId", async () => {
|
||||
const S = [
|
||||
"html",
|
||||
"body",
|
||||
@@ -962,38 +975,39 @@ describe("snapshot capture and hover", () => {
|
||||
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return {
|
||||
visualViewport: { clientWidth: 1000 },
|
||||
cssVisualViewport: { clientWidth: 1000 },
|
||||
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
|
||||
};
|
||||
}
|
||||
if (method === "DOM.getBoxModel")
|
||||
return { model: { content: [100, 300, 900, 300, 900, 700, 100, 700] } };
|
||||
if (method === "DOM.resolveNode") return { object: { objectId: "owner" } };
|
||||
if (method === "Runtime.callFunctionOn")
|
||||
return { result: { value: { width: 800, height: 400 } } };
|
||||
if (method === "Runtime.releaseObject") return {};
|
||||
throw new Error(method);
|
||||
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
|
||||
};
|
||||
const facts = await captureObservationFacts(cdp, 4);
|
||||
const root = facts.documents.find((doc) => doc.frame.frameId === "main-frame")!;
|
||||
const child = facts.documents.find((doc) => doc.frame.frameId === "child-frame")!;
|
||||
expect(facts.documents).toHaveLength(2);
|
||||
expect(root.domNodes.find((n) => n.backendNodeId === 13)?.tag).toBe("iframe");
|
||||
const subNodes = child.domNodes;
|
||||
const {
|
||||
nodes,
|
||||
iframeNodes,
|
||||
frameNodes,
|
||||
frameOwnerBackendNodeIds,
|
||||
frameParentIds,
|
||||
rootFrameId,
|
||||
} = await captureViewModel(cdp, 4);
|
||||
// Main frame has 4 nodes; iframe is included
|
||||
expect(nodes.find((n) => n.backendNodeId === 13)?.tag).toBe("iframe");
|
||||
// iframeNodes keyed by the <iframe> element's backendNodeId=13
|
||||
expect(iframeNodes.size).toBe(1);
|
||||
expect(iframeNodes.has(13)).toBe(true);
|
||||
const subNodes = iframeNodes.get(13)!;
|
||||
const input = subNodes.find((n) => n.backendNodeId === 101);
|
||||
expect(input?.tag).toBe("input");
|
||||
expect(input?.attrs.type).toBe("text");
|
||||
expect(input?.ownerFrameBackendNodeId).toBe(13);
|
||||
expect(input?.localRect).toEqual({ x: 0, y: 0, w: 200, h: 40 });
|
||||
expect(input?.rect).toEqual({ x: 100, y: 300, w: 200, h: 40 });
|
||||
expect(facts.rootFrameId).toBe("main-frame");
|
||||
expect(child.frame.ownerBackendNodeId).toBe(13);
|
||||
expect(child.frame.parentFrameId).toBe("main-frame");
|
||||
expect(rootFrameId).toBe("main-frame");
|
||||
expect(frameNodes?.get("child-frame")).toBe(subNodes);
|
||||
expect(frameOwnerBackendNodeIds?.get("child-frame")).toBe(13);
|
||||
expect(frameParentIds?.get("child-frame")).toBe("main-frame");
|
||||
});
|
||||
|
||||
it("projects iframe documents independently of owner snapshot geometry", async () => {
|
||||
it("captures iframe documents without requiring owner-frame geometry", async () => {
|
||||
const S = [
|
||||
"html",
|
||||
"body",
|
||||
@@ -1011,7 +1025,6 @@ describe("snapshot capture and hover", () => {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "root",
|
||||
scrollOffsetX: 0,
|
||||
scrollOffsetY: 0,
|
||||
nodes: {
|
||||
@@ -1029,7 +1042,6 @@ describe("snapshot capture and hover", () => {
|
||||
},
|
||||
},
|
||||
{
|
||||
frameId: "child",
|
||||
scrollOffsetX: 0,
|
||||
scrollOffsetY: 0,
|
||||
nodes: {
|
||||
@@ -1053,28 +1065,18 @@ describe("snapshot capture and hover", () => {
|
||||
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return {
|
||||
visualViewport: { clientWidth: 1000 },
|
||||
cssVisualViewport: { clientWidth: 1000 },
|
||||
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
|
||||
};
|
||||
}
|
||||
if (method === "DOM.getBoxModel")
|
||||
return { model: { content: [100, 300, 900, 300, 900, 700, 100, 700] } };
|
||||
if (method === "DOM.resolveNode") return { object: { objectId: "owner" } };
|
||||
if (method === "Runtime.callFunctionOn")
|
||||
return { result: { value: { width: 800, height: 400 } } };
|
||||
if (method === "Runtime.releaseObject") return {};
|
||||
throw new Error(method);
|
||||
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
|
||||
};
|
||||
|
||||
const { documents } = await captureObservationFacts(cdp, 4);
|
||||
const input = documents
|
||||
.find((doc) => doc.frame.frameId === "child")
|
||||
?.domNodes?.find((n) => n.backendNodeId === 101);
|
||||
const { iframeNodes } = await captureViewModel(cdp, 4);
|
||||
const input = iframeNodes.get(13)?.find((n) => n.backendNodeId === 101);
|
||||
|
||||
expect(input?.localRect).toEqual({ x: 20, y: 20, w: 120, h: 60 });
|
||||
expect(input?.rect).toEqual({ x: 120, y: 320, w: 120, h: 60 });
|
||||
expect(input?.rect).toBeNull();
|
||||
});
|
||||
|
||||
it("recursively normalizes nested iframe sub-documents", async () => {
|
||||
@@ -1095,7 +1097,6 @@ describe("snapshot capture and hover", () => {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "root",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1],
|
||||
nodeName: [i("html"), i("body"), i("iframe")],
|
||||
@@ -1117,9 +1118,6 @@ describe("snapshot capture and hover", () => {
|
||||
},
|
||||
},
|
||||
{
|
||||
scrollOffsetX: 0,
|
||||
scrollOffsetY: 0,
|
||||
frameId: "child",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1],
|
||||
nodeName: [i("html"), i("body"), i("iframe")],
|
||||
@@ -1141,9 +1139,6 @@ describe("snapshot capture and hover", () => {
|
||||
},
|
||||
},
|
||||
{
|
||||
scrollOffsetX: 0,
|
||||
scrollOffsetY: 0,
|
||||
frameId: "nested",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0],
|
||||
nodeName: [i("body"), i("input")],
|
||||
@@ -1160,54 +1155,21 @@ describe("snapshot capture and hover", () => {
|
||||
],
|
||||
};
|
||||
const cdp = {
|
||||
send: vi.fn(
|
||||
async (
|
||||
_t: number,
|
||||
method: string,
|
||||
params?: { backendNodeId?: number; objectId?: string },
|
||||
) => {
|
||||
if (method === "DOMSnapshot.enable") return {};
|
||||
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return {
|
||||
visualViewport: { clientWidth: 1000 },
|
||||
cssVisualViewport: { clientWidth: 1000 },
|
||||
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
|
||||
};
|
||||
}
|
||||
if (method === "DOM.getBoxModel")
|
||||
return {
|
||||
model: {
|
||||
content:
|
||||
params?.backendNodeId === 13
|
||||
? [10, 20, 310, 20, 310, 220, 10, 220]
|
||||
: [15, 26, 115, 26, 115, 106, 15, 106],
|
||||
},
|
||||
};
|
||||
if (method === "DOM.resolveNode")
|
||||
return { object: { objectId: String(params?.backendNodeId) } };
|
||||
if (method === "Runtime.callFunctionOn")
|
||||
return {
|
||||
result: {
|
||||
value:
|
||||
params?.objectId === "13"
|
||||
? { width: 300, height: 200 }
|
||||
: { width: 100, height: 80 },
|
||||
},
|
||||
};
|
||||
if (method === "Runtime.releaseObject") return {};
|
||||
throw new Error(method);
|
||||
},
|
||||
) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
|
||||
send: vi.fn(async (_t: number, method: string) => {
|
||||
if (method === "DOMSnapshot.enable") return {};
|
||||
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return {
|
||||
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
|
||||
};
|
||||
}
|
||||
throw new Error(method);
|
||||
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
|
||||
};
|
||||
|
||||
const { documents } = await captureObservationFacts(cdp, 4);
|
||||
const nestedIframe = documents
|
||||
.find((doc) => doc.frame.frameId === "child")
|
||||
?.domNodes?.find((n) => n.backendNodeId === 23);
|
||||
const input = documents
|
||||
.find((doc) => doc.frame.frameId === "nested")
|
||||
?.domNodes?.find((n) => n.backendNodeId === 31);
|
||||
const { iframeNodes } = await captureViewModel(cdp, 4);
|
||||
const nestedIframe = iframeNodes.get(13)?.find((n) => n.backendNodeId === 23);
|
||||
const input = iframeNodes.get(23)?.find((n) => n.backendNodeId === 31);
|
||||
|
||||
expect(nestedIframe?.localRect).toEqual({ x: 5, y: 6, w: 100, h: 80 });
|
||||
expect(nestedIframe?.rect).toEqual({ x: 15, y: 26, w: 100, h: 80 });
|
||||
@@ -1216,14 +1178,104 @@ describe("snapshot capture and hover", () => {
|
||||
expect(input?.rect).toEqual({ x: 16, y: 28, w: 40, h: 20 });
|
||||
});
|
||||
|
||||
it("subtracts CSS scroll once without dividing snapshot bounds by a metrics ratio", async () => {
|
||||
it("keeps same-origin iframe canvas discovery in top-level CSS coordinates at dpr 1 and 2", async () => {
|
||||
const captureAtDpr = async (dpr: number) => {
|
||||
const S = ["html", "body", "iframe", "canvas", "static", "auto"];
|
||||
const i = (s: string) => S.indexOf(s);
|
||||
const scale = (values: number[]) => values.map((value) => value * dpr);
|
||||
const snapshot = {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "main",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1],
|
||||
nodeName: [i("html"), i("body"), i("iframe")],
|
||||
backendNodeId: [10, 11, 13],
|
||||
attributes: [[], [], []],
|
||||
contentDocumentIndex: { index: [2], value: [1] },
|
||||
},
|
||||
layout: {
|
||||
nodeIndex: [1, 2],
|
||||
styles: [
|
||||
[i("static"), i("auto")],
|
||||
[i("static"), i("auto")],
|
||||
],
|
||||
bounds: [scale([0, 0, 1000, 800]), scale([100, 150, 300, 200])],
|
||||
paintOrders: [0, 1],
|
||||
},
|
||||
},
|
||||
{
|
||||
frameId: "child",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0],
|
||||
nodeName: [i("body"), i("canvas")],
|
||||
backendNodeId: [20, 21],
|
||||
attributes: [[], []],
|
||||
},
|
||||
layout: {
|
||||
nodeIndex: [0, 1],
|
||||
styles: [
|
||||
[i("static"), i("auto")],
|
||||
[i("static"), i("auto")],
|
||||
],
|
||||
bounds: [scale([0, 0, 300, 200]), scale([20, 30, 120, 60])],
|
||||
paintOrders: [0, 1],
|
||||
},
|
||||
},
|
||||
],
|
||||
};
|
||||
const cdp = {
|
||||
send: vi.fn(async (_tabId: number, method: string) => {
|
||||
if (method === "DOMSnapshot.enable") return {};
|
||||
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return {
|
||||
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
|
||||
layoutViewport: { clientWidth: 1000 * dpr, clientHeight: 800 * dpr },
|
||||
};
|
||||
}
|
||||
throw new Error(method);
|
||||
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
|
||||
};
|
||||
const captured = await captureViewModel(cdp, 4);
|
||||
const childNodes = captured.frameNodes?.get("child") ?? [];
|
||||
return discoverRenderedSurfaces(
|
||||
[
|
||||
{
|
||||
frameId: "child",
|
||||
contextScopeId: "child",
|
||||
parentFrameId: "main",
|
||||
ownerBackendNodeId: 13,
|
||||
target: { tabId: 4 },
|
||||
domNodes: childNodes,
|
||||
axNodes: [],
|
||||
},
|
||||
],
|
||||
captured.viewport,
|
||||
);
|
||||
};
|
||||
|
||||
const atDpr1 = await captureAtDpr(1);
|
||||
const atDpr2 = await captureAtDpr(2);
|
||||
|
||||
expect(atDpr1).toEqual([
|
||||
expect.objectContaining({
|
||||
backendNodeId: 21,
|
||||
frameId: "child",
|
||||
visibleRect: { x: 120, y: 180, w: 120, h: 60 },
|
||||
}),
|
||||
]);
|
||||
expect(atDpr2).toEqual(atDpr1);
|
||||
});
|
||||
|
||||
it("normalizes bounds then subtracts CSS scroll at dpr>1", async () => {
|
||||
const S = ["html", "body", "div", "position", "fixed", "static", "pointer-events", "auto"];
|
||||
const i = (s: string) => S.indexOf(s);
|
||||
const snapshot = {
|
||||
strings: S,
|
||||
documents: [
|
||||
{
|
||||
frameId: "root",
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, 1],
|
||||
nodeName: [i("html"), i("body"), i("div")],
|
||||
@@ -1251,8 +1303,6 @@ describe("snapshot capture and hover", () => {
|
||||
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return {
|
||||
visualViewport: { clientWidth: 2000 },
|
||||
cssVisualViewport: { clientWidth: 1000 },
|
||||
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 100 },
|
||||
layoutViewport: { clientWidth: 2000, clientHeight: 1600 },
|
||||
};
|
||||
@@ -1260,7 +1310,7 @@ describe("snapshot capture and hover", () => {
|
||||
throw new Error(method);
|
||||
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
|
||||
};
|
||||
const { nodes } = semanticCapture(await captureObservationFacts(cdp, 4)).captured;
|
||||
const { nodes } = await captureViewModel(cdp, 4);
|
||||
expect(nodes.find((n) => n.backendNodeId === 12)?.rect?.y).toBe(400 / 2 - 100);
|
||||
});
|
||||
|
||||
|
||||
@@ -1,151 +0,0 @@
|
||||
import { describe, expect, it, vi } from "vitest";
|
||||
import type { CdpRunner } from "../../shared";
|
||||
import { verifyDocumentIdentity, verifyVisualTargetIdentity } from "../document-identity";
|
||||
import type { VisualCandidate } from "../visual-discovery";
|
||||
|
||||
const candidate: VisualCandidate = {
|
||||
document: {
|
||||
attachmentId: "attached",
|
||||
target: { tabId: 4, sessionId: "child-session" },
|
||||
frameId: "child-frame",
|
||||
documentElementBackendNodeId: 10,
|
||||
},
|
||||
backendNodeId: 20,
|
||||
parentBackendNodeId: 10,
|
||||
region: {
|
||||
status: "available",
|
||||
borderBox: { x: 0, y: 0, width: 10, height: 10 },
|
||||
crop: { x: 0, y: 0, width: 10, height: 10 },
|
||||
},
|
||||
};
|
||||
|
||||
function fixture(
|
||||
options: {
|
||||
connected?: boolean;
|
||||
sameDocument?: boolean;
|
||||
root?: number;
|
||||
missing?: boolean;
|
||||
fail?: string;
|
||||
abortAt?: string;
|
||||
detachAt?: string;
|
||||
} = {},
|
||||
) {
|
||||
const controller = new AbortController();
|
||||
let attachment = "attached";
|
||||
const send = vi.fn(
|
||||
async (_tab: number, _session: string, method: string, params: Record<string, unknown>) => {
|
||||
if (options.abortAt === method) controller.abort();
|
||||
if (options.detachAt === method) attachment = "new-attachment";
|
||||
if (options.fail === method) throw new Error("CDP failed");
|
||||
if (method === "Page.createIsolatedWorld") return { executionContextId: 7 };
|
||||
if (method === "DOM.resolveNode")
|
||||
return options.missing ? {} : { object: { objectId: "anchor" } };
|
||||
if (method === "Runtime.evaluate" || method === "Runtime.callFunctionOn") {
|
||||
let root: unknown = {};
|
||||
if (method === "Runtime.callFunctionOn") {
|
||||
const document = { documentElement: {} };
|
||||
// Exercise the actual predicate, including connection and owner checks.
|
||||
root = new Function("document", `return (${params.functionDeclaration}).call(this)`).call(
|
||||
{
|
||||
isConnected: options.connected ?? true,
|
||||
ownerDocument: options.sameDocument === false ? {} : document,
|
||||
},
|
||||
document,
|
||||
);
|
||||
}
|
||||
return {
|
||||
result: {
|
||||
deepSerializedValue:
|
||||
root === null
|
||||
? { type: "null" }
|
||||
: { type: "node", value: { backendNodeId: options.root ?? 10 } },
|
||||
},
|
||||
};
|
||||
}
|
||||
if (method === "Runtime.releaseObjectGroup") return {};
|
||||
throw new Error(`unexpected ${method}`);
|
||||
},
|
||||
);
|
||||
const cdp = {
|
||||
send: vi.fn(),
|
||||
sendToTarget: (
|
||||
target: { tabId: number; sessionId?: string },
|
||||
method: string,
|
||||
params: Record<string, unknown>,
|
||||
) => send(target.tabId, target.sessionId!, method, params),
|
||||
getAttachmentId: () => attachment,
|
||||
} as unknown as CdpRunner;
|
||||
return { cdp, send, controller };
|
||||
}
|
||||
|
||||
describe("visual target identity", () => {
|
||||
it("uses the exact frame and target with bounded local reads and releases objects", async () => {
|
||||
const { cdp, send } = fixture();
|
||||
expect(await verifyVisualTargetIdentity(cdp, candidate)).toBe("current");
|
||||
expect(send.mock.calls.map((c) => c[2])).toEqual([
|
||||
"Page.createIsolatedWorld",
|
||||
"DOM.resolveNode",
|
||||
"Runtime.callFunctionOn",
|
||||
"Runtime.releaseObjectGroup",
|
||||
]);
|
||||
expect(
|
||||
send.mock.calls.every(([tab, session]) => tab === 4 && session === "child-session"),
|
||||
).toBe(true);
|
||||
expect(send.mock.calls[0][3]).toMatchObject({ frameId: "child-frame" });
|
||||
expect(send.mock.calls[1][3]).toMatchObject({ backendNodeId: 20, executionContextId: 7 });
|
||||
expect(send.mock.calls[2][3]).toMatchObject({ objectId: "anchor" });
|
||||
expect(send.mock.calls[3][3].objectGroup).toBe(send.mock.calls[1][3].objectGroup);
|
||||
});
|
||||
|
||||
it.each([
|
||||
{ connected: false },
|
||||
{ sameDocument: false },
|
||||
{ root: 11 },
|
||||
])("rejects detached/adopted/replaced DOM: %j", async (options) => {
|
||||
const { cdp } = fixture(options);
|
||||
expect(await verifyVisualTargetIdentity(cdp, candidate)).toBe("changed");
|
||||
});
|
||||
|
||||
it("does not add anchor reads to existing capture identity verification", async () => {
|
||||
const { cdp, send } = fixture();
|
||||
expect(await verifyDocumentIdentity(cdp, candidate.document)).toBe("current");
|
||||
expect(send.mock.calls.map((c) => c[2])).toEqual([
|
||||
"Page.createIsolatedWorld",
|
||||
"Runtime.evaluate",
|
||||
"Runtime.releaseObjectGroup",
|
||||
]);
|
||||
});
|
||||
|
||||
it.each([
|
||||
"Page.createIsolatedWorld",
|
||||
"DOM.resolveNode",
|
||||
"Runtime.callFunctionOn",
|
||||
])("fails closed and cleans up when %s fails", async (fail) => {
|
||||
const { cdp, send } = fixture({ fail });
|
||||
expect(await verifyVisualTargetIdentity(cdp, candidate)).toBe("unavailable");
|
||||
expect(send.mock.calls.at(-1)?.[2]).toBe("Runtime.releaseObjectGroup");
|
||||
});
|
||||
|
||||
it("rejects attachment changes before and during verification", async () => {
|
||||
const first = fixture();
|
||||
expect(
|
||||
await verifyVisualTargetIdentity({ ...first.cdp, getAttachmentId: () => "other" }, candidate),
|
||||
).toBe("changed");
|
||||
expect(first.send).not.toHaveBeenCalled();
|
||||
const second = fixture({ detachAt: "Runtime.callFunctionOn" });
|
||||
expect(await verifyVisualTargetIdentity(second.cdp, candidate)).toBe("changed");
|
||||
const missing = fixture({ missing: true });
|
||||
expect(await verifyVisualTargetIdentity(missing.cdp, candidate)).toBe("unavailable");
|
||||
});
|
||||
|
||||
it.each([
|
||||
"DOM.resolveNode",
|
||||
"Runtime.callFunctionOn",
|
||||
])("propagates cancellation at %s after releasing the object group", async (abortAt) => {
|
||||
const { cdp, send, controller } = fixture({ abortAt });
|
||||
await expect(
|
||||
verifyVisualTargetIdentity(cdp, candidate, controller.signal),
|
||||
).rejects.toMatchObject({ name: "AbortError" });
|
||||
expect(send.mock.calls.at(-1)?.[2]).toBe("Runtime.releaseObjectGroup");
|
||||
});
|
||||
});
|
||||
@@ -1,168 +0,0 @@
|
||||
import { describe, expect, it, vi } from "vitest";
|
||||
import { OVERLAY_HOST_MARKER_ATTR } from "@/lib/overlay-bridge";
|
||||
import { createCaptureCheckpoint } from "../capture-abort";
|
||||
import { buildDocumentIndex, type DecodedNode } from "../facts";
|
||||
import { decodeDocument, REQUESTED_STYLES, VISUAL_SNAPSHOT } from "../snapshot";
|
||||
|
||||
function node(id: number, parent: number | null): DecodedNode {
|
||||
return {
|
||||
backendNodeId: id,
|
||||
parentBackendNodeId: parent,
|
||||
tag: "div",
|
||||
attrs: {},
|
||||
paintOrder: 0,
|
||||
position: "static",
|
||||
pointerEvents: "auto",
|
||||
};
|
||||
}
|
||||
|
||||
describe("document facts", () => {
|
||||
it.each([
|
||||
1_000, 10_000, 100_000,
|
||||
])("indexes deep and wide inputs of %i without copying ancestors", async (count) => {
|
||||
for (const wide of [false, true]) {
|
||||
let reads = 0;
|
||||
const input = Array.from({ length: count }, (_, i) => {
|
||||
const item = node(i, i ? (wide ? 0 : i - 1) : null);
|
||||
if (i === 0) item.attrs[OVERLAY_HOST_MARKER_ATTR] = "";
|
||||
Object.defineProperty(item, "parentBackendNodeId", {
|
||||
get: () => {
|
||||
reads++;
|
||||
return i ? (wide ? 0 : i - 1) : null;
|
||||
},
|
||||
});
|
||||
return item;
|
||||
}).reverse(); // parent need not precede child
|
||||
const index = await buildDocumentIndex(input);
|
||||
expect(index.nodes.size).toBe(count);
|
||||
expect(index.excludedBackendNodeIds.size).toBe(count);
|
||||
expect(reads).toBeLessThanOrEqual(count * 8);
|
||||
expect(index.nodes.get(count - 1)).toBe(input[0]);
|
||||
}
|
||||
});
|
||||
|
||||
it("handles cycles and orphans and propagates overlay through shadow roots", async () => {
|
||||
const host = { ...node(1, null), attrs: { [OVERLAY_HOST_MARKER_ATTR]: "" } };
|
||||
const input = [
|
||||
node(3, 2),
|
||||
{ ...node(2, 1), tag: "#document-fragment" },
|
||||
host,
|
||||
node(4, 99),
|
||||
node(5, 6),
|
||||
node(6, 5),
|
||||
node(7, 6),
|
||||
];
|
||||
const index = await buildDocumentIndex(input);
|
||||
expect([...index.excludedBackendNodeIds].sort()).toEqual([1, 2, 3]);
|
||||
expect(index.nodes.size).toBe(input.length);
|
||||
});
|
||||
|
||||
it("does not propagate a descendant overlay backwards into a cycle", async () => {
|
||||
const overlay = { ...node(3, 1), attrs: { [OVERLAY_HOST_MARKER_ATTR]: "" } };
|
||||
const index = await buildDocumentIndex([overlay, node(1, 2), node(2, 1)]);
|
||||
expect([...index.excludedBackendNodeIds]).toEqual([3]);
|
||||
});
|
||||
|
||||
it("decodes current observation bounds, styles and attributes without projecting coordinates", async () => {
|
||||
const strings = ["div", "aria-hidden", "true", "inert", "", "visible", "0", "static", "auto"];
|
||||
const styles = REQUESTED_STYLES.map((style) =>
|
||||
style === "visibility" ? 5 : style === "opacity" ? 6 : style === "position" ? 7 : 8,
|
||||
);
|
||||
const { nodes } = await decodeDocument(
|
||||
{
|
||||
nodes: { backendNodeId: [1], parentIndex: [-1], nodeName: [0], attributes: [[1, 2, 3, 4]] },
|
||||
layout: { nodeIndex: [0], bounds: [[10, 20, 120, 40]], styles: [styles] },
|
||||
},
|
||||
strings,
|
||||
);
|
||||
expect(nodes[0].attrs).toEqual({ "aria-hidden": "true", inert: "" });
|
||||
expect(nodes[0].layout).toEqual({
|
||||
boundsSpace: "snapshot-document-layout",
|
||||
bounds: [10, 20, 120, 40],
|
||||
styles: {
|
||||
position: "static",
|
||||
"pointer-events": "auto",
|
||||
cursor: "auto",
|
||||
visibility: "visible",
|
||||
opacity: "0",
|
||||
},
|
||||
});
|
||||
expect(nodes[0]).not.toHaveProperty("rect");
|
||||
expect(nodes[0]).not.toHaveProperty("excluded");
|
||||
});
|
||||
|
||||
it("keeps short blocks synchronous and checks cancellation after yielding", async () => {
|
||||
const clock = vi.spyOn(performance, "now").mockReturnValue(0);
|
||||
try {
|
||||
const controller = new AbortController();
|
||||
const checkpoint = createCaptureCheckpoint(controller.signal);
|
||||
for (let i = 0; i < 20; i++) expect(checkpoint()).toBeUndefined();
|
||||
clock.mockReturnValue(9);
|
||||
const pending = checkpoint();
|
||||
expect(pending).toBeInstanceOf(Promise);
|
||||
controller.abort();
|
||||
await expect(pending).rejects.toMatchObject({ name: "AbortError" });
|
||||
} finally {
|
||||
clock.mockRestore();
|
||||
}
|
||||
});
|
||||
|
||||
it("checks cancellation at bounded indexing blocks", async () => {
|
||||
const controller = new AbortController();
|
||||
const input = Array.from({ length: 100_000 }, (_, i) => node(i, i ? i - 1 : null));
|
||||
let reads = 0;
|
||||
for (const item of input)
|
||||
Object.defineProperty(item, "attrs", {
|
||||
get: () => {
|
||||
reads++;
|
||||
if (reads === 100) controller.abort();
|
||||
return {};
|
||||
},
|
||||
});
|
||||
await expect(buildDocumentIndex(input, controller.signal)).rejects.toMatchObject({
|
||||
name: "AbortError",
|
||||
});
|
||||
expect(reads).toBeLessThanOrEqual(356);
|
||||
});
|
||||
});
|
||||
|
||||
describe("visual ancestry facts", () => {
|
||||
it("distinguishes document roots, malformed roots, missing parents and cycles", async () => {
|
||||
const input = [
|
||||
{ ...node(0, null), nodeType: 9 },
|
||||
{ ...node(1, 0), nodeType: 1 },
|
||||
{ ...node(2, 1), nodeType: 11 },
|
||||
node(3, 2),
|
||||
node(4, 99),
|
||||
node(5, 6),
|
||||
node(6, 5),
|
||||
node(7, 5),
|
||||
{ ...node(8, null), nodeType: 1 },
|
||||
{ ...node(9, null), nodeType: 9, parentMissing: true },
|
||||
];
|
||||
const index = await buildDocumentIndex(input.reverse(), undefined, true);
|
||||
for (const id of [0, 1, 2, 3]) expect(index.ancestryComplete!.get(id)).toBe(true);
|
||||
for (const id of [4, 5, 6, 7, 8, 9]) expect(index.ancestryComplete!.get(id)).toBe(false);
|
||||
});
|
||||
|
||||
it("retains client offsets in their source units and does not disguise missing parent indices", async () => {
|
||||
const decoded = await decodeDocument(
|
||||
{
|
||||
nodes: { backendNodeId: [1, 2], nodeType: [1, 1], nodeName: [0, 0], parentIndex: [99] },
|
||||
layout: {
|
||||
nodeIndex: [0],
|
||||
bounds: [[745, 455.625, 97, 59.5]],
|
||||
clientRects: [[5, 5, 68, 38]],
|
||||
},
|
||||
},
|
||||
["div"],
|
||||
undefined,
|
||||
VISUAL_SNAPSHOT,
|
||||
);
|
||||
expect(decoded.nodes[0].layout?.clientRect).toEqual([5, 5, 68, 38]);
|
||||
expect(decoded.nodes[0].layout?.bounds).toEqual([745, 455.625, 97, 59.5]);
|
||||
expect(decoded.nodes.every((node) => node.parentMissing)).toBe(true);
|
||||
const index = await buildDocumentIndex(decoded.nodes, undefined, true);
|
||||
expect([...index.ancestryComplete!.values()]).toEqual([false, false]);
|
||||
});
|
||||
});
|
||||
@@ -1,298 +0,0 @@
|
||||
import { describe, expect, it, vi } from "vitest";
|
||||
import { type CdpRunner, cdpRunnerForTarget } from "../../shared";
|
||||
import { enrichFormControlStates } from "../form-capture";
|
||||
import { decodeDocument } from "../snapshot";
|
||||
|
||||
interface Control {
|
||||
id: number;
|
||||
value: string;
|
||||
type?: string;
|
||||
}
|
||||
|
||||
function snapshot(groups: Control[][]) {
|
||||
const strings: string[] = [];
|
||||
const str = (value: string) => {
|
||||
let index = strings.indexOf(value);
|
||||
if (index < 0) index = strings.push(value) - 1;
|
||||
return index;
|
||||
};
|
||||
const documents = groups.map((controls, groupIndex) => ({
|
||||
frameId: `frame-${groupIndex}`,
|
||||
nodes: {
|
||||
parentIndex: [-1, 0, ...controls.map(() => 1)],
|
||||
nodeName: [str("html"), str("body"), ...controls.map(() => str("input"))],
|
||||
backendNodeId: [8000 + groupIndex * 2, 8001 + groupIndex * 2, ...controls.map((c) => c.id)],
|
||||
attributes: [
|
||||
[],
|
||||
[],
|
||||
...controls.map((c) => [
|
||||
str("type"),
|
||||
str(c.type ?? "text"),
|
||||
str("placeholder"),
|
||||
str("snapshot placeholder"),
|
||||
]),
|
||||
],
|
||||
inputValue: {
|
||||
index: controls.map((_, i) => i + 2),
|
||||
value: controls.map((c) => str(c.value)),
|
||||
},
|
||||
contentDocumentIndex: { index: [] as number[], value: [] as number[] },
|
||||
},
|
||||
}));
|
||||
const root = documents[0].nodes;
|
||||
for (let i = 1; i < documents.length; i++) {
|
||||
root.contentDocumentIndex.index.push(root.backendNodeId.length);
|
||||
root.contentDocumentIndex.value.push(i);
|
||||
root.parentIndex.push(1);
|
||||
root.nodeName.push(str("iframe"));
|
||||
root.backendNodeId.push(9000 + i);
|
||||
root.attributes.push([]);
|
||||
}
|
||||
return { strings, documents };
|
||||
}
|
||||
|
||||
function state(value: string) {
|
||||
return {
|
||||
value,
|
||||
defaultValue: "",
|
||||
placeholder: "live placeholder",
|
||||
state: value ? "filled" : "empty",
|
||||
sensitive: false,
|
||||
};
|
||||
}
|
||||
|
||||
function reply(entries: Array<[number, unknown]>) {
|
||||
return {
|
||||
result: {
|
||||
deepSerializedValue: {
|
||||
type: "array",
|
||||
value: entries.map(([backendNodeId, fields]) => ({
|
||||
type: "array",
|
||||
value: [
|
||||
{ type: "node", value: { backendNodeId } },
|
||||
{ type: "string", value: JSON.stringify(fields) },
|
||||
],
|
||||
})),
|
||||
},
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
async function fakeCdp(
|
||||
groups: Control[][],
|
||||
evaluate: (params: Record<string, unknown>) => unknown,
|
||||
) {
|
||||
const snap = snapshot(groups);
|
||||
const send = vi.fn(async (_tabId: number, method: string, params?: object) => {
|
||||
if (method === "Runtime.evaluate") return evaluate(params as Record<string, unknown>);
|
||||
return {};
|
||||
});
|
||||
const nodes = await decodeControls(snap);
|
||||
return { send, cdp: { send: send as CdpRunner["send"] }, nodes };
|
||||
}
|
||||
|
||||
async function decodeControls(snap: ReturnType<typeof snapshot>) {
|
||||
return Promise.all(
|
||||
snap.documents.map(async (doc) =>
|
||||
(await decodeDocument(doc, snap.strings)).nodes.map((node) => ({ ...node, rect: null })),
|
||||
),
|
||||
);
|
||||
}
|
||||
|
||||
describe("form state identity", () => {
|
||||
it("matches reordered controls by identity and preserves controls missing from the batch", async () => {
|
||||
// The snapshot includes a shadow input. The runtime query skips it,
|
||||
// encounters a new input, and sees the remaining inputs in a new order.
|
||||
const { cdp, nodes } = await fakeCdp(
|
||||
[
|
||||
[
|
||||
{ id: 10, value: "" },
|
||||
{ id: 11, value: "old email" },
|
||||
{ id: 12, value: "old city" },
|
||||
],
|
||||
],
|
||||
() =>
|
||||
reply([
|
||||
[99, state("new control")],
|
||||
[12, state("上海")],
|
||||
[11, state("alice@example.com")],
|
||||
]),
|
||||
);
|
||||
await enrichFormControlStates(cdp, 7, nodes);
|
||||
expect(nodes[0].find((n) => n.backendNodeId === 10)).toMatchObject({
|
||||
formValue: "",
|
||||
formState: "empty",
|
||||
formPlaceholder: "snapshot placeholder",
|
||||
});
|
||||
expect(nodes[0].find((n) => n.backendNodeId === 11)).toMatchObject({
|
||||
formValue: "alice@example.com",
|
||||
});
|
||||
expect(nodes[0].find((n) => n.backendNodeId === 12)).toMatchObject({ formValue: "上海" });
|
||||
expect(nodes[0].some((n) => n.backendNodeId === 99)).toBe(false);
|
||||
});
|
||||
|
||||
it("does not shift state between frames when one frame is absent from the runtime batch", async () => {
|
||||
const { cdp, nodes } = await fakeCdp(
|
||||
[
|
||||
[],
|
||||
[{ id: 11, value: "inaccessible frame" }],
|
||||
[{ id: 21, value: "old second" }],
|
||||
[{ id: 31, value: "old third" }],
|
||||
],
|
||||
() =>
|
||||
reply([
|
||||
[31, state("third frame")],
|
||||
[21, state("second frame")],
|
||||
]),
|
||||
);
|
||||
await enrichFormControlStates(cdp, 7, nodes);
|
||||
const controls = nodes.slice(1).flat();
|
||||
expect(controls.find((n) => n.backendNodeId === 11)?.formValue).toBe("inaccessible frame");
|
||||
expect(controls.find((n) => n.backendNodeId === 21)?.formValue).toBe("second frame");
|
||||
expect(controls.find((n) => n.backendNodeId === 31)?.formValue).toBe("third frame");
|
||||
});
|
||||
|
||||
it("keeps identical backend ids in different OOPIF targets separate", async () => {
|
||||
const sendToTarget = vi.fn(async (target, method) => {
|
||||
if (method === "Runtime.evaluate") return reply([[11, state(target.sessionId)]]);
|
||||
return {};
|
||||
});
|
||||
const send = vi.fn(async () => {
|
||||
throw new Error("unexpected top-level target");
|
||||
});
|
||||
const cdp = { send, sendToTarget } as unknown as CdpRunner;
|
||||
for (const sessionId of ["left-frame", "right-frame"]) {
|
||||
const nodes = await decodeControls(snapshot([[{ id: 11, value: "old" }]]));
|
||||
await enrichFormControlStates(cdpRunnerForTarget(cdp, { tabId: 7, sessionId }), 7, nodes);
|
||||
expect(nodes[0].find((n) => n.backendNodeId === 11)?.formValue).toBe(sessionId);
|
||||
expect(sendToTarget).toHaveBeenCalledWith(
|
||||
{ tabId: 7, sessionId },
|
||||
"Runtime.releaseObjectGroup",
|
||||
expect.anything(),
|
||||
);
|
||||
}
|
||||
expect(send).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it.each([
|
||||
"unsupported",
|
||||
"legacy",
|
||||
"malformed",
|
||||
"invalid-state",
|
||||
])("preserves snapshot data when enrichment is %s", async (mode) => {
|
||||
const { cdp, send, nodes } = await fakeCdp([[{ id: 11, value: "snapshot value" }]], () => {
|
||||
if (mode === "unsupported") throw new Error("serialization unsupported");
|
||||
if (mode === "legacy") return { result: { value: { controls: [state("wrong value")] } } };
|
||||
const result = reply([
|
||||
[11, mode === "invalid-state" ? { value: "wrong value" } : state("wrong value")],
|
||||
]);
|
||||
if (mode === "malformed")
|
||||
result.result.deepSerializedValue.value[0].value[1].value = "not json";
|
||||
return result;
|
||||
});
|
||||
expect(await enrichFormControlStates(cdp, 7, nodes)).toBe(mode !== "unsupported");
|
||||
expect(nodes[0].find((n) => n.backendNodeId === 11)).toMatchObject({
|
||||
formValue: "snapshot value",
|
||||
formPlaceholder: "snapshot placeholder",
|
||||
});
|
||||
expect(send).toHaveBeenCalledWith(7, "Runtime.releaseObjectGroup", expect.anything());
|
||||
});
|
||||
|
||||
it("releases the batch's remote objects when capture is cancelled", async () => {
|
||||
const controller = new AbortController();
|
||||
const { cdp, send, nodes } = await fakeCdp([[{ id: 11, value: "old" }]], () => {
|
||||
controller.abort();
|
||||
return reply([[11, state("new")]]);
|
||||
});
|
||||
await expect(enrichFormControlStates(cdp, 7, nodes, controller.signal)).rejects.toMatchObject({
|
||||
name: "AbortError",
|
||||
});
|
||||
expect(send).toHaveBeenCalledWith(7, "Runtime.releaseObjectGroup", expect.anything());
|
||||
});
|
||||
|
||||
it("does not report success when cancelled during object cleanup", async () => {
|
||||
const controller = new AbortController();
|
||||
const nodes = await decodeControls(snapshot([[{ id: 11, value: "old" }]]));
|
||||
const cdp: CdpRunner = {
|
||||
send: vi.fn(async (_tabId, method) => {
|
||||
if (method === "Runtime.evaluate") return reply([[11, state("new")]]);
|
||||
if (method === "Runtime.releaseObjectGroup") controller.abort();
|
||||
return {};
|
||||
}) as CdpRunner["send"],
|
||||
};
|
||||
await expect(enrichFormControlStates(cdp, 7, nodes, controller.signal)).rejects.toMatchObject({
|
||||
name: "AbortError",
|
||||
});
|
||||
expect(cdp.send).toHaveBeenCalledWith(7, "Runtime.releaseObjectGroup", expect.anything());
|
||||
});
|
||||
|
||||
it("skips entries without node identity while still applying valid entries", async () => {
|
||||
const { cdp, nodes } = await fakeCdp(
|
||||
[
|
||||
[
|
||||
{ id: 11, value: "snapshot value" },
|
||||
{ id: 12, value: "old value" },
|
||||
],
|
||||
],
|
||||
() => {
|
||||
const result = reply([
|
||||
[11, state("wrong value")],
|
||||
[12, state("live value")],
|
||||
]);
|
||||
const element = result.result.deepSerializedValue.value[0].value[0];
|
||||
delete (element.value as { backendNodeId?: number }).backendNodeId;
|
||||
return result;
|
||||
},
|
||||
);
|
||||
await enrichFormControlStates(cdp, 7, nodes);
|
||||
expect(nodes[0].find((n) => n.backendNodeId === 11)?.formValue).toBe("snapshot value");
|
||||
expect(nodes[0].find((n) => n.backendNodeId === 12)?.formValue).toBe("live value");
|
||||
});
|
||||
|
||||
it.each([
|
||||
"password",
|
||||
"text",
|
||||
])("redacts a sensitive %s control after identity matching", async (type) => {
|
||||
const { cdp, nodes } = await fakeCdp([[{ id: 11, value: "secret", type }]], () =>
|
||||
reply([[11, { ...state("secret"), sensitive: true }]]),
|
||||
);
|
||||
await enrichFormControlStates(cdp, 7, nodes);
|
||||
const control = nodes[0].find((n) => n.backendNodeId === 11);
|
||||
expect(control?.formState).toBe("filled");
|
||||
expect(control?.formValue).toBeUndefined();
|
||||
expect(control?.formDefaultValue).toBeUndefined();
|
||||
expect(control?.attrs.value).toBeUndefined();
|
||||
});
|
||||
|
||||
it("keeps one bounded batch without per-control CDP queries", async () => {
|
||||
const controls = Array.from({ length: 251 }, (_, i) => ({ id: i + 1, value: "old" }));
|
||||
const elements = controls.map((c) => ({
|
||||
backendNodeId: c.id,
|
||||
tagName: "INPUT",
|
||||
type: "text",
|
||||
value: `live ${c.id}`,
|
||||
defaultValue: "",
|
||||
placeholder: "",
|
||||
}));
|
||||
const { cdp, send, nodes } = await fakeCdp([controls], (params) => {
|
||||
const doc = {
|
||||
querySelectorAll: (selector: string) =>
|
||||
selector === "input,textarea,select" ? elements : [],
|
||||
};
|
||||
const entries = new Function("document", `return ${params.expression}`)(doc) as Array<
|
||||
[{ backendNodeId: number }, string]
|
||||
>;
|
||||
expect(entries).toHaveLength(250);
|
||||
return reply(entries.map(([element, json]) => [element.backendNodeId, JSON.parse(json)]));
|
||||
});
|
||||
await enrichFormControlStates(cdp, 7, nodes);
|
||||
expect(nodes[0].find((n) => n.backendNodeId === 250)?.formValue).toBe("live 250");
|
||||
expect(nodes[0].find((n) => n.backendNodeId === 251)?.formValue).toBe("old");
|
||||
expect(send.mock.calls.filter(([, method]) => method === "Runtime.evaluate")).toHaveLength(1);
|
||||
expect(
|
||||
send.mock.calls.filter(([, method]) => method === "Runtime.releaseObjectGroup"),
|
||||
).toHaveLength(1);
|
||||
expect(send).not.toHaveBeenCalledWith(7, "DOM.resolveNode", expect.anything());
|
||||
expect(send).not.toHaveBeenCalledWith(7, "Runtime.callFunctionOn", expect.anything());
|
||||
});
|
||||
});
|
||||
@@ -0,0 +1,198 @@
|
||||
import { describe, expect, it, vi } from "vitest";
|
||||
import type { CdpRunner } from "../../shared";
|
||||
import type { CapturedNode, CapturedViewModel } from "../capture";
|
||||
import { captureFrameData } from "../frame-capture";
|
||||
|
||||
function ownerNode(backendNodeId: number, x: number): CapturedNode {
|
||||
return {
|
||||
backendNodeId,
|
||||
parentBackendNodeId: 1,
|
||||
frameId: "main",
|
||||
ownerFrameBackendNodeId: null,
|
||||
tag: "iframe",
|
||||
attrs: {},
|
||||
rect: { x, y: 100, w: 300, h: 200 },
|
||||
localRect: { x, y: 100, w: 300, h: 200 },
|
||||
paintOrder: 1,
|
||||
position: "static",
|
||||
pointerEvents: "auto",
|
||||
};
|
||||
}
|
||||
|
||||
function childSnapshot(frameId: string, backendNodeId: number) {
|
||||
const strings = [frameId, "body", "button", "static", "auto", "pointer"];
|
||||
return {
|
||||
strings,
|
||||
documents: [
|
||||
{
|
||||
frameId,
|
||||
nodes: {
|
||||
parentIndex: [-1, 0],
|
||||
nodeName: [1, 2],
|
||||
backendNodeId: [backendNodeId - 1, backendNodeId],
|
||||
attributes: [[], []],
|
||||
},
|
||||
layout: {
|
||||
nodeIndex: [0, 1],
|
||||
styles: [
|
||||
[3, 4, 4],
|
||||
[3, 4, 5],
|
||||
],
|
||||
bounds: [
|
||||
[0, 0, 300, 200],
|
||||
[10, 20, 100, 40],
|
||||
],
|
||||
paintOrders: [0, 1],
|
||||
},
|
||||
},
|
||||
],
|
||||
};
|
||||
}
|
||||
|
||||
describe("captureFrameData", () => {
|
||||
it("captures and positions multiple OOPIF documents missing from the root snapshot", async () => {
|
||||
const leftOwner = ownerNode(10, 50);
|
||||
const rightOwner = ownerNode(20, 500);
|
||||
const captured: CapturedViewModel = {
|
||||
nodes: [leftOwner, rightOwner],
|
||||
viewport: { width: 1000, height: 800 },
|
||||
iframeNodes: new Map(),
|
||||
frameNodes: new Map([["main", [leftOwner, rightOwner]]]),
|
||||
frameOwnerBackendNodeIds: new Map(),
|
||||
rootFrameId: "main",
|
||||
excludedBackendNodeIds: new Set(),
|
||||
};
|
||||
const sendToTarget = vi.fn(async (target, method) => {
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return { cssLayoutViewport: { clientWidth: 300, clientHeight: 200, pageX: 0, pageY: 0 } };
|
||||
}
|
||||
if (method === "DOMSnapshot.enable" || method === "Accessibility.enable") return {};
|
||||
if (method === "DOMSnapshot.captureSnapshot") {
|
||||
return target.sessionId === "left-session"
|
||||
? childSnapshot("left", 101)
|
||||
: childSnapshot("right", 201);
|
||||
}
|
||||
if (method === "Accessibility.getFullAXTree") return { nodes: [] };
|
||||
throw new Error(`unexpected ${method}`);
|
||||
});
|
||||
const cdp: CdpRunner = {
|
||||
send: vi.fn(async (_tabId, method, params) => {
|
||||
if (method === "Accessibility.enable") return {};
|
||||
if (method === "Accessibility.getFullAXTree") return { nodes: [] };
|
||||
if (method === "DOM.getBoxModel") {
|
||||
const backendNodeId = (params as { backendNodeId?: number })?.backendNodeId;
|
||||
const x = backendNodeId === 10 ? 50 : 500;
|
||||
return { model: { content: [x, 100, x + 300, 100, x + 300, 300, x, 300] } };
|
||||
}
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
|
||||
}
|
||||
throw new Error(`unexpected root ${method}`);
|
||||
}) as CdpRunner["send"],
|
||||
sendToTarget: sendToTarget as unknown as NonNullable<CdpRunner["sendToTarget"]>,
|
||||
getFrameGraph: vi.fn(async () => ({
|
||||
rootFrameId: "main",
|
||||
frames: [
|
||||
{ frameId: "main", target: { tabId: 4 } },
|
||||
{
|
||||
frameId: "left",
|
||||
parentFrameId: "main",
|
||||
ownerBackendNodeId: 10,
|
||||
target: { tabId: 4, sessionId: "left-session" },
|
||||
},
|
||||
{
|
||||
frameId: "right",
|
||||
parentFrameId: "main",
|
||||
ownerBackendNodeId: 20,
|
||||
target: { tabId: 4, sessionId: "right-session" },
|
||||
},
|
||||
],
|
||||
})),
|
||||
};
|
||||
|
||||
const trees = await captureFrameData(cdp, 4, captured);
|
||||
|
||||
expect(trees.map((tree) => tree.frameId)).toEqual(["main", "left", "right"]);
|
||||
expect(
|
||||
captured.frameNodes?.get("left")?.find((node) => node.backendNodeId === 101)?.rect,
|
||||
).toEqual({ x: 60, y: 120, w: 100, h: 40 });
|
||||
expect(
|
||||
captured.frameNodes?.get("right")?.find((node) => node.backendNodeId === 201)?.rect,
|
||||
).toEqual({ x: 510, y: 120, w: 100, h: 40 });
|
||||
expect(captured.frameOwnerBackendNodeIds).toEqual(
|
||||
new Map([
|
||||
["left", 10],
|
||||
["right", 20],
|
||||
]),
|
||||
);
|
||||
expect(captured.frameParentIds).toEqual(
|
||||
new Map([
|
||||
["left", "main"],
|
||||
["right", "main"],
|
||||
]),
|
||||
);
|
||||
});
|
||||
|
||||
it("keeps OOPIF semantics when viewport projection is unavailable", async () => {
|
||||
const owner = { ...ownerNode(10, 50), rect: null, localRect: null };
|
||||
const captured: CapturedViewModel = {
|
||||
nodes: [owner],
|
||||
viewport: { width: 1000, height: 800 },
|
||||
iframeNodes: new Map(),
|
||||
frameNodes: new Map([["main", [owner]]]),
|
||||
rootFrameId: "main",
|
||||
excludedBackendNodeIds: new Set(),
|
||||
};
|
||||
const cdp: CdpRunner = {
|
||||
send: vi.fn(async (_tabId, method) => {
|
||||
if (method === "Accessibility.enable") return {};
|
||||
if (method === "Accessibility.getFullAXTree") return { nodes: [] };
|
||||
if (method === "DOM.getBoxModel") throw new Error("owner geometry unavailable");
|
||||
if (method === "Page.getLayoutMetrics") {
|
||||
return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
|
||||
}
|
||||
throw new Error(`unexpected root ${method}`);
|
||||
}) as CdpRunner["send"],
|
||||
sendToTarget: vi.fn(async (_target, method) => {
|
||||
if (method === "Page.getLayoutMetrics") throw new Error("viewport unavailable");
|
||||
if (method === "DOMSnapshot.enable" || method === "Accessibility.enable") return {};
|
||||
if (method === "DOMSnapshot.captureSnapshot") return childSnapshot("child", 101);
|
||||
if (method === "Accessibility.getFullAXTree") {
|
||||
return {
|
||||
nodes: [
|
||||
{
|
||||
nodeId: "button",
|
||||
backendDOMNodeId: 101,
|
||||
role: { type: "role", value: "button" },
|
||||
name: { type: "computedString", value: "Continue" },
|
||||
},
|
||||
],
|
||||
};
|
||||
}
|
||||
throw new Error(`unexpected ${method}`);
|
||||
}) as unknown as NonNullable<CdpRunner["sendToTarget"]>,
|
||||
getFrameGraph: vi.fn(async () => ({
|
||||
rootFrameId: "main",
|
||||
frames: [
|
||||
{ frameId: "main", target: { tabId: 4 } },
|
||||
{
|
||||
frameId: "child",
|
||||
parentFrameId: "main",
|
||||
ownerBackendNodeId: 10,
|
||||
target: { tabId: 4, sessionId: "child-session" },
|
||||
},
|
||||
],
|
||||
})),
|
||||
};
|
||||
|
||||
const documents = await captureFrameData(cdp, 4, captured);
|
||||
const childDocument = documents.find((document) => document.frameId === "child");
|
||||
|
||||
expect(childDocument?.axNodes).toEqual([
|
||||
expect.objectContaining({ backendDOMNodeId: 101, frameId: "child" }),
|
||||
]);
|
||||
expect(childDocument?.domNodes.find((node) => node.backendNodeId === 101)).toEqual(
|
||||
expect.objectContaining({ rect: null, localRect: { x: 10, y: 20, w: 100, h: 40 } }),
|
||||
);
|
||||
});
|
||||
});
|
||||
@@ -1,12 +1,7 @@
|
||||
import { describe, expect, it, vi } from "vitest";
|
||||
import { describe, expect, it } from "vitest";
|
||||
import type { CdpFrameGraph } from "@/browser-driver/frame-graph";
|
||||
import type { CapturedNode } from "../capture";
|
||||
import {
|
||||
buildFrameDocuments,
|
||||
type FrameAxBatch,
|
||||
type FrameDomInput,
|
||||
type FrameOwnedAxNode,
|
||||
} from "../frame-document";
|
||||
import type { CapturedNode, CapturedViewModel } from "../capture";
|
||||
import { buildFrameDocuments, type FrameAxBatch, type FrameOwnedAxNode } from "../frame-document";
|
||||
|
||||
function domNode(frameId: string, backendNodeId: number): CapturedNode {
|
||||
return {
|
||||
@@ -22,16 +17,19 @@ function domNode(frameId: string, backendNodeId: number): CapturedNode {
|
||||
};
|
||||
}
|
||||
|
||||
function captured(frameNodes: Map<string, CapturedNode[]>): FrameDomInput {
|
||||
function captured(frameNodes: Map<string, CapturedNode[]>): CapturedViewModel {
|
||||
return {
|
||||
nodes: frameNodes.get("main") ?? [],
|
||||
viewport: { width: 800, height: 600 },
|
||||
iframeNodes: new Map(),
|
||||
frameNodes,
|
||||
rootFrameId: "main",
|
||||
excludedBackendNodeIds: new Set(),
|
||||
};
|
||||
}
|
||||
|
||||
describe("buildFrameDocuments", () => {
|
||||
it("partitions mixed AX results by node ownership and cuts cross-frame parent edges", async () => {
|
||||
it("partitions mixed AX results by node ownership and cuts cross-frame parent edges", () => {
|
||||
const graph: CdpFrameGraph = {
|
||||
rootFrameId: "main",
|
||||
frames: [
|
||||
@@ -56,7 +54,7 @@ describe("buildFrameDocuments", () => {
|
||||
},
|
||||
];
|
||||
|
||||
const documents = await buildFrameDocuments(
|
||||
const documents = buildFrameDocuments(
|
||||
graph,
|
||||
batches,
|
||||
captured(
|
||||
@@ -74,7 +72,7 @@ describe("buildFrameDocuments", () => {
|
||||
expect(childNodes.find((node) => node.nodeId === "virtual")?.frameId).toBe("child");
|
||||
});
|
||||
|
||||
it("deduplicates overlapping same-target AX results using the strongest ownership", async () => {
|
||||
it("deduplicates overlapping same-target AX results using the strongest ownership", () => {
|
||||
const graph: CdpFrameGraph = {
|
||||
rootFrameId: "main",
|
||||
frames: [
|
||||
@@ -94,7 +92,7 @@ describe("buildFrameDocuments", () => {
|
||||
},
|
||||
];
|
||||
|
||||
const documents = await buildFrameDocuments(
|
||||
const documents = buildFrameDocuments(
|
||||
graph,
|
||||
batches,
|
||||
captured(
|
||||
@@ -109,7 +107,7 @@ describe("buildFrameDocuments", () => {
|
||||
expect(documents.find((document) => document.frameId === "child")?.axNodes).toHaveLength(1);
|
||||
});
|
||||
|
||||
it("uses target-scoped backend ownership when OOPIF backend ids collide", async () => {
|
||||
it("uses target-scoped backend ownership when OOPIF backend ids collide", () => {
|
||||
const graph: CdpFrameGraph = {
|
||||
rootFrameId: "main",
|
||||
frames: [
|
||||
@@ -131,7 +129,7 @@ describe("buildFrameDocuments", () => {
|
||||
nodes: [{ nodeId: `${frame.frameId}-node`, backendDOMNodeId: 7 }],
|
||||
}));
|
||||
|
||||
const documents = await buildFrameDocuments(
|
||||
const documents = buildFrameDocuments(
|
||||
graph,
|
||||
batches,
|
||||
captured(
|
||||
@@ -151,7 +149,7 @@ describe("buildFrameDocuments", () => {
|
||||
);
|
||||
});
|
||||
|
||||
it("uses captured frame parent identity instead of guessing from backend ids", async () => {
|
||||
it("uses captured frame parent identity instead of guessing from backend ids", () => {
|
||||
const frameNodes = new Map([
|
||||
["main", [domNode("main", 1)]],
|
||||
["left", [domNode("left", 7)]],
|
||||
@@ -159,51 +157,18 @@ describe("buildFrameDocuments", () => {
|
||||
["child", [domNode("child", 9)]],
|
||||
]);
|
||||
const capture = captured(frameNodes);
|
||||
capture.frameOwnerBackendNodeIds = new Map([["child", 7]]);
|
||||
capture.frameParentIds = new Map([["child", "left"]]);
|
||||
const frames = ["main", "left", "right", "child"].map((frameId) => ({
|
||||
frame: {
|
||||
frameId,
|
||||
target: { tabId: 4 },
|
||||
...(frameId === "child" ? { parentFrameId: "left", ownerBackendNodeId: 7 } : {}),
|
||||
},
|
||||
frame: { frameId, target: { tabId: 4 } },
|
||||
nodes: [],
|
||||
}));
|
||||
|
||||
const documents = await buildFrameDocuments(null, frames, capture);
|
||||
const documents = buildFrameDocuments(null, frames, capture);
|
||||
|
||||
expect(documents.find((document) => document.frameId === "child")).toMatchObject({
|
||||
parentFrameId: "left",
|
||||
ownerBackendNodeId: 7,
|
||||
});
|
||||
});
|
||||
it("rejects explicit AX frame ownership in a different target", async () => {
|
||||
const frames = [
|
||||
{ frameId: "main", target: { tabId: 4 } },
|
||||
{ frameId: "remote", target: { tabId: 4, sessionId: "remote" } },
|
||||
];
|
||||
const unresolved = vi.fn();
|
||||
const documents = await buildFrameDocuments(
|
||||
{ rootFrameId: "main", frames },
|
||||
[{ frame: frames[0], nodes: [{ nodeId: "wrong", frameId: "remote" }] }],
|
||||
captured(new Map()),
|
||||
undefined,
|
||||
unresolved,
|
||||
);
|
||||
expect(documents.every((doc) => doc.axNodes.length === 0)).toBe(true);
|
||||
expect(unresolved).toHaveBeenCalledOnce();
|
||||
});
|
||||
|
||||
it("resolves a reverse-ordered deep AX parent chain without recursion", async () => {
|
||||
const frame = { frameId: "main", target: { tabId: 4 } };
|
||||
const nodes: FrameOwnedAxNode[] = Array.from({ length: 10000 }, (_, i) => ({
|
||||
nodeId: String(i),
|
||||
...(i ? { parentId: String(i - 1) } : { frameId: "main" }),
|
||||
})).reverse();
|
||||
const documents = await buildFrameDocuments(
|
||||
{ rootFrameId: "main", frames: [frame] },
|
||||
[{ frame, nodes }],
|
||||
captured(new Map()),
|
||||
);
|
||||
expect(documents[0].axNodes).toHaveLength(10000);
|
||||
expect(documents[0].axNodes[0].frameId).toBe("main");
|
||||
});
|
||||
});
|
||||
|
||||
@@ -0,0 +1,256 @@
|
||||
import type { VomScene } from "@browser-skill/vom";
|
||||
import { describe, expect, it } from "vitest";
|
||||
import type { CapturedNode } from "../capture";
|
||||
import type { CapturedFrameDocument } from "../frame-capture";
|
||||
import {
|
||||
clusterRenderedSurfaces,
|
||||
discoverRenderedSurfaces,
|
||||
projectRenderedSurfaces,
|
||||
} from "../rendered-surfaces";
|
||||
import type { SemanticAxNode } from "../semantic-graph";
|
||||
|
||||
function domNode(backendNodeId: number, overrides: Partial<CapturedNode> = {}): CapturedNode {
|
||||
return {
|
||||
backendNodeId,
|
||||
parentBackendNodeId: null,
|
||||
frameId: "main",
|
||||
ownerFrameBackendNodeId: null,
|
||||
tag: "canvas",
|
||||
attrs: {},
|
||||
rect: { x: 10, y: 20, w: 800, h: 500 },
|
||||
localRect: { x: 10, y: 20, w: 800, h: 500 },
|
||||
paintOrder: 1,
|
||||
position: "static",
|
||||
pointerEvents: "auto",
|
||||
rendered: true,
|
||||
...overrides,
|
||||
};
|
||||
}
|
||||
|
||||
function document(
|
||||
domNodes: CapturedNode[],
|
||||
axNodes: SemanticAxNode[] = [],
|
||||
): CapturedFrameDocument<SemanticAxNode> {
|
||||
return {
|
||||
frameId: domNodes[0]?.frameId ?? "main",
|
||||
contextScopeId: domNodes[0]?.frameId ?? "main",
|
||||
target: { tabId: 4 },
|
||||
domNodes,
|
||||
axNodes,
|
||||
};
|
||||
}
|
||||
|
||||
describe("rendered surface discovery", () => {
|
||||
it("finds prominent rendered canvases and excludes hidden descendants", () => {
|
||||
const visible = domNode(2, { parentBackendNodeId: 1 });
|
||||
const hidden = domNode(3, { parentBackendNodeId: 4 });
|
||||
const surfaces = discoverRenderedSurfaces(
|
||||
[
|
||||
document([
|
||||
domNode(1, { tag: "main", rect: null, localRect: null }),
|
||||
visible,
|
||||
domNode(4, { tag: "section", attrs: { "aria-hidden": "true" }, rect: null }),
|
||||
hidden,
|
||||
]),
|
||||
],
|
||||
{ width: 1280, height: 720 },
|
||||
);
|
||||
|
||||
expect(surfaces).toHaveLength(1);
|
||||
expect(surfaces[0]).toMatchObject({ backendNodeId: 2 });
|
||||
});
|
||||
|
||||
it("keeps tiny canvases as individually addressable exact discoveries", () => {
|
||||
const surfaces = discoverRenderedSurfaces(
|
||||
[document([domNode(2, { rect: { x: 1, y: 1, w: 8, h: 8 } })])],
|
||||
{ width: 1280, height: 720 },
|
||||
);
|
||||
expect(surfaces).toEqual([expect.objectContaining({ backendNodeId: 2 })]);
|
||||
});
|
||||
|
||||
it("keeps a surface when the canvas only has partial native accessibility content", () => {
|
||||
const axNodes = [
|
||||
{
|
||||
nodeId: "canvas",
|
||||
backendDOMNodeId: 2,
|
||||
role: { type: "role", value: "presentation" },
|
||||
childIds: ["button"],
|
||||
frameId: "main",
|
||||
},
|
||||
{
|
||||
nodeId: "button",
|
||||
backendDOMNodeId: 3,
|
||||
role: { type: "role", value: "button" },
|
||||
frameId: "main",
|
||||
},
|
||||
] as SemanticAxNode[];
|
||||
expect(
|
||||
discoverRenderedSurfaces([document([domNode(2)], axNodes)], { width: 1280, height: 720 }),
|
||||
).toEqual([expect.objectContaining({ backendNodeId: 2 })]);
|
||||
});
|
||||
|
||||
it("discovers unnamed canvases without guessing labels from engineering attributes", () => {
|
||||
const canvas = domNode(2, {
|
||||
attrs: {
|
||||
id: "must-not-be-a-label",
|
||||
class: "must-not-be-a-label",
|
||||
"data-testid": "must-not-be-a-label",
|
||||
},
|
||||
});
|
||||
|
||||
expect(discoverRenderedSurfaces([document([canvas])], { width: 1280, height: 720 })).toEqual([
|
||||
expect.not.objectContaining({
|
||||
label: expect.anything(),
|
||||
}),
|
||||
]);
|
||||
});
|
||||
|
||||
it("treats blank explicit Canvas names as unnamed", () => {
|
||||
expect(
|
||||
discoverRenderedSurfaces(
|
||||
[document([domNode(2, { attrs: { "aria-label": " ", title: "\n\t" } })])],
|
||||
{ width: 1280, height: 720 },
|
||||
),
|
||||
).toEqual([expect.not.objectContaining({ label: expect.anything() })]);
|
||||
});
|
||||
|
||||
it("excludes canvases inside BrowserSkill-owned DOM subtrees", () => {
|
||||
const owner = domNode(1, { tag: "div", rect: null, localRect: null });
|
||||
const canvas = domNode(2, { parentBackendNodeId: 1 });
|
||||
|
||||
expect(
|
||||
discoverRenderedSurfaces(
|
||||
[document([owner, canvas])],
|
||||
{ width: 1280, height: 720 },
|
||||
new Set([1]),
|
||||
),
|
||||
).toEqual([]);
|
||||
});
|
||||
|
||||
it("excludes canvases suppressed by a fully transparent ancestor", () => {
|
||||
const owner = domNode(1, {
|
||||
tag: "div",
|
||||
rect: { x: 0, y: 0, w: 900, h: 600 },
|
||||
visuallySuppressed: true,
|
||||
});
|
||||
const canvas = domNode(2, { parentBackendNodeId: 1 });
|
||||
|
||||
expect(
|
||||
discoverRenderedSurfaces([document([owner, canvas])], { width: 1280, height: 720 }),
|
||||
).toEqual([]);
|
||||
});
|
||||
|
||||
it("clips canvases to overflow ancestors and drops fully clipped canvases", () => {
|
||||
const owner = domNode(1, {
|
||||
tag: "div",
|
||||
rect: { x: 10, y: 20, w: 100, h: 70 },
|
||||
overflowX: "hidden",
|
||||
overflowY: "hidden",
|
||||
});
|
||||
const partial = domNode(2, {
|
||||
parentBackendNodeId: 1,
|
||||
rect: { x: 55, y: 30, w: 140, h: 60 },
|
||||
});
|
||||
const fullyClipped = domNode(3, {
|
||||
parentBackendNodeId: 1,
|
||||
rect: { x: 140, y: 30, w: 80, h: 50 },
|
||||
});
|
||||
|
||||
expect(
|
||||
discoverRenderedSurfaces([document([owner, partial, fullyClipped])], {
|
||||
width: 1280,
|
||||
height: 720,
|
||||
}),
|
||||
).toEqual([
|
||||
expect.objectContaining({
|
||||
backendNodeId: 2,
|
||||
visibleRect: { x: 55, y: 30, w: 55, h: 60 },
|
||||
}),
|
||||
]);
|
||||
});
|
||||
});
|
||||
|
||||
describe("rendered surface clustering and projection", () => {
|
||||
it("collapses overlapping canvas layers and attaches them to the nearest retained parent", () => {
|
||||
const body = domNode(1, { tag: "body", rect: null, localRect: null });
|
||||
const surfaces = discoverRenderedSurfaces(
|
||||
[
|
||||
document([
|
||||
body,
|
||||
domNode(2, { parentBackendNodeId: 1, paintOrder: 1 }),
|
||||
domNode(3, { parentBackendNodeId: 1, paintOrder: 2 }),
|
||||
]),
|
||||
],
|
||||
{ width: 1280, height: 720 },
|
||||
);
|
||||
const groups = clusterRenderedSurfaces(surfaces);
|
||||
const scene: VomScene = {
|
||||
viewport: { width: 1280, height: 720 },
|
||||
nodes: [
|
||||
{
|
||||
id: 10,
|
||||
parentId: null,
|
||||
backendNodeId: 1,
|
||||
frameId: "main",
|
||||
tag: "body",
|
||||
role: "RootWebArea",
|
||||
rect: null,
|
||||
paintOrder: 0,
|
||||
position: "static",
|
||||
pointerEvents: "auto",
|
||||
},
|
||||
],
|
||||
};
|
||||
|
||||
expect(groups).toHaveLength(1);
|
||||
expect(groups[0]?.members).toHaveLength(2);
|
||||
expect(groups[0]?.label).toBeUndefined();
|
||||
expect(
|
||||
projectRenderedSurfaces(
|
||||
scene,
|
||||
[document([body, ...surfaces.map((s) => domNode(s.backendNodeId))])],
|
||||
groups,
|
||||
),
|
||||
).toMatchObject({
|
||||
visualSurfaces: [expect.objectContaining({ parentId: 10, backendNodeId: 3, memberCount: 2 })],
|
||||
});
|
||||
});
|
||||
|
||||
it("does not merge a contained canvas with a larger independent canvas", () => {
|
||||
const groups = clusterRenderedSurfaces([
|
||||
...discoverRenderedSurfaces(
|
||||
[
|
||||
document([
|
||||
domNode(1, { tag: "main", rect: null, localRect: null }),
|
||||
domNode(2, { parentBackendNodeId: 1 }),
|
||||
domNode(3, {
|
||||
parentBackendNodeId: 1,
|
||||
rect: { x: 30, y: 40, w: 200, h: 100 },
|
||||
}),
|
||||
]),
|
||||
],
|
||||
{ width: 1280, height: 720 },
|
||||
),
|
||||
]);
|
||||
|
||||
expect(groups).toHaveLength(2);
|
||||
});
|
||||
|
||||
it("does not merge coincident canvases owned by different containers", () => {
|
||||
const groups = clusterRenderedSurfaces(
|
||||
discoverRenderedSurfaces(
|
||||
[
|
||||
document([
|
||||
domNode(1, { tag: "section", rect: null, localRect: null }),
|
||||
domNode(2, { tag: "section", rect: null, localRect: null }),
|
||||
domNode(3, { parentBackendNodeId: 1 }),
|
||||
domNode(4, { parentBackendNodeId: 2 }),
|
||||
]),
|
||||
],
|
||||
{ width: 1280, height: 720 },
|
||||
),
|
||||
);
|
||||
|
||||
expect(groups).toHaveLength(2);
|
||||
});
|
||||
});
|
||||
@@ -1,147 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import { deduplicateVisualCandidates, MAX_VISUAL_DEDUP_KEYS } from "../visual-dedup";
|
||||
import type { VisualCandidate, VisualDiscoveryResult } from "../visual-discovery";
|
||||
|
||||
function candidate(id: number, width = 100, parent = 1): VisualCandidate {
|
||||
const crop = { x: 0, y: 0, width, height: 100 };
|
||||
return {
|
||||
document: {
|
||||
attachmentId: "a",
|
||||
target: { tabId: 1 },
|
||||
frameId: "main",
|
||||
documentElementBackendNodeId: 1,
|
||||
},
|
||||
backendNodeId: id,
|
||||
parentBackendNodeId: parent,
|
||||
region: { status: "available", borderBox: crop, crop },
|
||||
};
|
||||
}
|
||||
function discovery(candidates: VisualCandidate[]): VisualDiscoveryResult {
|
||||
return { candidates, complete: true, issues: [], captureIssues: [] };
|
||||
}
|
||||
|
||||
describe("visual candidate deduplication", () => {
|
||||
it("preserves small, unnamed and labelled candidates and their original evidence", async () => {
|
||||
const small = { ...candidate(3, 1), label: ' A "label"\n😀' };
|
||||
const large = candidate(2, 1000);
|
||||
const input = discovery([small, large]);
|
||||
Object.freeze(input.candidates);
|
||||
Object.freeze(small);
|
||||
Object.freeze(large);
|
||||
for (let i = 0; i < 2; i++) {
|
||||
const result = await deduplicateVisualCandidates(input);
|
||||
expect(result.candidates).toEqual([small, large]);
|
||||
expect(result.candidates[0]).toBe(small);
|
||||
expect(result.candidates[1]).toBe(large);
|
||||
expect(result).toMatchObject({
|
||||
candidateCount: 2,
|
||||
deduplicatedCount: 0,
|
||||
dedupDegraded: false,
|
||||
});
|
||||
}
|
||||
});
|
||||
|
||||
it("only deduplicates exact crops within the same full DOM identity and direct parent", async () => {
|
||||
const base = candidate(20);
|
||||
const variants = [
|
||||
candidate(30, 100, 2),
|
||||
{ ...candidate(40), parentBackendNodeId: null },
|
||||
...["x", "y", "width", "height"].map((axis) => ({
|
||||
...base,
|
||||
region: {
|
||||
...base.region,
|
||||
crop: {
|
||||
...base.region.crop,
|
||||
[axis]: base.region.crop[axis as keyof typeof base.region.crop] + 0.001,
|
||||
},
|
||||
},
|
||||
})),
|
||||
...[
|
||||
{ frameId: "child" },
|
||||
{ target: { tabId: 2 } },
|
||||
{ target: { tabId: 1, sessionId: "remote" } },
|
||||
{ documentElementBackendNodeId: 9 },
|
||||
{ attachmentId: "b" },
|
||||
].map((identity) => ({ ...base, document: { ...base.document, ...identity } })),
|
||||
];
|
||||
const duplicate = { ...candidate(10), label: "Not a new target" };
|
||||
const result = await deduplicateVisualCandidates(discovery([base, ...variants, duplicate]));
|
||||
expect(result.candidates).toEqual([base, ...variants]);
|
||||
expect(result.candidates[0]).toBe(base);
|
||||
expect(result.deduplicatedCount).toBe(1);
|
||||
});
|
||||
|
||||
it.each([
|
||||
50_001, 100_000,
|
||||
])("keeps all %s distinct candidates including the last tiny Canvas", async (count) => {
|
||||
const input = Array.from({ length: count }, (_, i) => candidate(i + 1, 100, i + 1));
|
||||
input[count - 1] = candidate(count, 1, count);
|
||||
// A remembered key still deduplicates; an unremembered key passes through.
|
||||
input.push({ ...input[0] }, { ...input[count - 1] });
|
||||
const result = await deduplicateVisualCandidates(discovery(input));
|
||||
expect(result.candidates).toEqual([...input.slice(0, count), input[count + 1]]);
|
||||
expect(result.candidates[count - 1]).toBe(input[count - 1]);
|
||||
expect(result).toMatchObject({
|
||||
candidateCount: count + 2,
|
||||
deduplicatedCount: 1,
|
||||
dedupDegraded: true,
|
||||
});
|
||||
});
|
||||
|
||||
it("does not report degradation when every key fits", async () => {
|
||||
const input = Array.from({ length: MAX_VISUAL_DEDUP_KEYS }, (_, i) => candidate(i, 1, i));
|
||||
input.push({ ...input[0] });
|
||||
const result = await deduplicateVisualCandidates(discovery(input));
|
||||
expect(result.candidates).toHaveLength(MAX_VISUAL_DEDUP_KEYS);
|
||||
expect(result.dedupDegraded).toBe(false);
|
||||
expect(result.deduplicatedCount).toBe(1);
|
||||
});
|
||||
|
||||
it("preserves upstream unknowns without counting issues as Canvas nodes", async () => {
|
||||
const input: VisualDiscoveryResult = {
|
||||
...discovery([candidate(2)]),
|
||||
complete: false,
|
||||
issues: [{ reason: "geometry-unavailable", target: { tabId: 1 }, frameId: "missing" }],
|
||||
captureIssues: [{ stage: "ax", reason: "capture-unavailable", target: { tabId: 1 } }],
|
||||
};
|
||||
const result = await deduplicateVisualCandidates(input);
|
||||
expect(result.complete).toBe(false);
|
||||
expect(result.candidateCount).toBe(1);
|
||||
expect(result.issues).toBe(input.issues);
|
||||
expect(result.captureIssues).toBe(input.captureIssues);
|
||||
const absent = await deduplicateVisualCandidates({
|
||||
...input,
|
||||
candidates: [],
|
||||
issues: [{ reason: "visual-facts-not-collected" }],
|
||||
});
|
||||
expect(absent).toMatchObject({
|
||||
complete: false,
|
||||
candidateCount: 0,
|
||||
issues: [{ reason: "visual-facts-not-collected" }],
|
||||
});
|
||||
expect(await deduplicateVisualCandidates(discovery([]))).toMatchObject({
|
||||
complete: true,
|
||||
candidates: [],
|
||||
candidateCount: 0,
|
||||
dedupDegraded: false,
|
||||
});
|
||||
});
|
||||
|
||||
it("drains cancellation through the shared checkpoint", async () => {
|
||||
const controller = new AbortController();
|
||||
controller.abort();
|
||||
await expect(
|
||||
deduplicateVisualCandidates(discovery([]), controller.signal),
|
||||
).rejects.toMatchObject({ name: "AbortError" });
|
||||
const during = new AbortController();
|
||||
const input = discovery(Array.from({ length: 100_000 }, (_, i) => candidate(i, 100, i)));
|
||||
const timer = setTimeout(() => during.abort(), 0);
|
||||
try {
|
||||
await expect(deduplicateVisualCandidates(input, during.signal)).rejects.toMatchObject({
|
||||
name: "AbortError",
|
||||
});
|
||||
} finally {
|
||||
clearTimeout(timer);
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -1,502 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import type { CdpFrame } from "@/browser-driver/frame-graph";
|
||||
import { OVERLAY_HOST_MARKER_ATTR } from "@/lib/overlay-bridge";
|
||||
import type { GeometryProjection } from "../../geometry";
|
||||
import { buildDocumentIndex, type DocumentFacts, type ObservationFacts } from "../facts";
|
||||
import type { FrameOwnedAxNode } from "../frame-document";
|
||||
import { normalizeDocument } from "../normalize";
|
||||
import { VISUAL_SNAPSHOT, VISUAL_STYLES } from "../snapshot";
|
||||
import { discoverVisualCandidates } from "../visual-discovery";
|
||||
|
||||
const defaults: Record<string, string> = {
|
||||
position: "static",
|
||||
"pointer-events": "auto",
|
||||
cursor: "auto",
|
||||
visibility: "visible",
|
||||
opacity: "1",
|
||||
display: "block",
|
||||
"overflow-x": "visible",
|
||||
"overflow-y": "visible",
|
||||
transform: "none",
|
||||
zoom: "1",
|
||||
"clip-path": "none",
|
||||
"mask-image": "none",
|
||||
rotate: "none",
|
||||
scale: "none",
|
||||
perspective: "none",
|
||||
clip: "auto",
|
||||
contain: "none",
|
||||
"overflow-clip-margin": "0px",
|
||||
};
|
||||
const projection: GeometryProjection = {
|
||||
sourceClips: [],
|
||||
edges: [],
|
||||
topViewport: { width: 1000, height: 800 },
|
||||
};
|
||||
interface Spec {
|
||||
id: number;
|
||||
parent?: number;
|
||||
tag?: string;
|
||||
styles?: Record<string, string>;
|
||||
bounds?: number[] | null;
|
||||
client?: number[];
|
||||
attrs?: Record<string, string>;
|
||||
}
|
||||
async function document(
|
||||
nodes: Spec[],
|
||||
options: {
|
||||
frame?: CdpFrame;
|
||||
projection?: GeometryProjection;
|
||||
pageScale?: number;
|
||||
scrollY?: number;
|
||||
layoutScale?: number;
|
||||
} = {},
|
||||
): Promise<DocumentFacts<FrameOwnedAxNode>> {
|
||||
const frame = options.frame ?? { frameId: "main", target: { tabId: 1 } };
|
||||
const strings: string[] = [];
|
||||
const str = (value: string) => {
|
||||
const index = strings.indexOf(value);
|
||||
if (index >= 0) return index;
|
||||
strings.push(value);
|
||||
return strings.length - 1;
|
||||
};
|
||||
const input: Spec[] = [
|
||||
{ id: 0, tag: "#document", bounds: null },
|
||||
{ id: 1, parent: 0, tag: "html", bounds: [0, 0, 1000, 800] },
|
||||
...nodes,
|
||||
];
|
||||
const layouts = input.filter((node) => node.bounds !== null);
|
||||
const normalized = await normalizeDocument(
|
||||
{
|
||||
nodes: {
|
||||
backendNodeId: input.map((n) => n.id),
|
||||
nodeType: input.map((n) =>
|
||||
n.tag === "#document" ? 9 : n.tag === "#document-fragment" ? 11 : 1,
|
||||
),
|
||||
parentIndex: input.map((n) =>
|
||||
n.parent === undefined ? -1 : input.findIndex((p) => p.id === n.parent),
|
||||
),
|
||||
nodeName: input.map((n) => str(n.tag ?? "canvas")),
|
||||
attributes: input.map((n) =>
|
||||
Object.entries(n.attrs ?? {}).flatMap(([k, v]) => [str(k), str(v)]),
|
||||
),
|
||||
},
|
||||
layout: {
|
||||
nodeIndex: layouts.map((n) => input.indexOf(n)),
|
||||
bounds: layouts.map((n) => n.bounds ?? [10, 20, 120, 40]),
|
||||
clientRects: layouts.map((n) => n.client ?? [0, 0, 1000, 800]),
|
||||
styles: layouts.map((n) =>
|
||||
VISUAL_STYLES.map((key) => str({ ...defaults, ...n.styles }[key])),
|
||||
),
|
||||
},
|
||||
},
|
||||
strings,
|
||||
{
|
||||
frameId: frame.frameId,
|
||||
ownerFrameBackendNodeId: frame.ownerBackendNodeId ?? null,
|
||||
target: frame.target,
|
||||
projection: {
|
||||
status: "available",
|
||||
projection: {
|
||||
source: { target: frame.target, frameId: frame.frameId },
|
||||
geometry: options.projection ?? projection,
|
||||
},
|
||||
},
|
||||
coordinates: {
|
||||
layoutUnitsPerCssPixel: options.layoutScale ?? 1,
|
||||
scrollCss: { x: 0, y: options.scrollY ?? 0 },
|
||||
},
|
||||
pageScale: options.pageScale ?? 1,
|
||||
},
|
||||
undefined,
|
||||
VISUAL_SNAPSHOT,
|
||||
);
|
||||
return {
|
||||
frame,
|
||||
identity: {
|
||||
attachmentId: "attached",
|
||||
target: frame.target,
|
||||
frameId: frame.frameId,
|
||||
documentElementBackendNodeId: 1,
|
||||
},
|
||||
index: normalized.index,
|
||||
geometry: normalized.geometry,
|
||||
domNodes: normalized.nodes,
|
||||
axNodes: [],
|
||||
};
|
||||
}
|
||||
function facts(
|
||||
documents: DocumentFacts<FrameOwnedAxNode>[],
|
||||
issues: ObservationFacts<FrameOwnedAxNode>["issues"] = [],
|
||||
): ObservationFacts<FrameOwnedAxNode> {
|
||||
return {
|
||||
visualFactsCollected: true,
|
||||
rootFrameId: "main",
|
||||
documents,
|
||||
viewport: { width: 1000, height: 800 },
|
||||
issues,
|
||||
startedAt: 1,
|
||||
finishedAt: 2,
|
||||
};
|
||||
}
|
||||
|
||||
describe("Canvas discovery", () => {
|
||||
it("distinguishes visual facts not collected from complete empty discovery and honors cancellation", async () => {
|
||||
const empty = facts([]);
|
||||
expect(await discoverVisualCandidates(empty)).toMatchObject({
|
||||
complete: true,
|
||||
candidates: [],
|
||||
issues: [],
|
||||
});
|
||||
expect(await discoverVisualCandidates({ ...empty, visualFactsCollected: false })).toMatchObject(
|
||||
{ complete: false, candidates: [], issues: [{ reason: "visual-facts-not-collected" }] },
|
||||
);
|
||||
const controller = new AbortController();
|
||||
controller.abort();
|
||||
await expect(
|
||||
discoverVisualCandidates({ ...empty, visualFactsCollected: false }, controller.signal),
|
||||
).rejects.toMatchObject({ name: "AbortError" });
|
||||
});
|
||||
|
||||
it("discovers Canvas and frame contents without corner radius facts", async () => {
|
||||
const own = await document([{ id: 2, parent: 1, styles: {} }]);
|
||||
expect(await discoverVisualCandidates(facts([own]))).toMatchObject({
|
||||
candidates: [{ backendNodeId: 2 }],
|
||||
complete: true,
|
||||
issues: [],
|
||||
});
|
||||
const parent = await document([{ id: 2, parent: 1, tag: "iframe", styles: {} }]);
|
||||
const child = await document([{ id: 3, parent: 1 }], {
|
||||
frame: {
|
||||
frameId: "child",
|
||||
parentFrameId: "main",
|
||||
ownerBackendNodeId: 2,
|
||||
target: { tabId: 1 },
|
||||
},
|
||||
});
|
||||
expect(await discoverVisualCandidates(facts([parent, child]))).toMatchObject({
|
||||
candidates: [{ backendNodeId: 3 }],
|
||||
complete: true,
|
||||
issues: [],
|
||||
});
|
||||
});
|
||||
|
||||
it.each([
|
||||
0.8, 1, 1.25, 2,
|
||||
])("combines layout-unit bounds with CSS client clips at scale %s", async (scale) => {
|
||||
const doc = await document(
|
||||
[
|
||||
{
|
||||
id: 2,
|
||||
parent: 1,
|
||||
tag: "div",
|
||||
bounds: [100, 200, 64, 34].map((n) => n * scale),
|
||||
client: [2, 2, 60, 30],
|
||||
styles: { "overflow-x": "hidden", "overflow-y": "hidden" },
|
||||
},
|
||||
{ id: 3, parent: 2, bounds: [102, 202, 120, 40].map((n) => n * scale) },
|
||||
],
|
||||
{ layoutScale: scale, scrollY: 75 },
|
||||
);
|
||||
const result = await discoverVisualCandidates(facts([doc]));
|
||||
expect(result.issues).toEqual([]);
|
||||
const expected = {
|
||||
borderBox: { x: 102, y: 127, width: 120, height: 40 },
|
||||
crop: { x: 102, y: 127, width: 60, height: 30 },
|
||||
};
|
||||
for (const box of ["borderBox", "crop"] as const)
|
||||
for (const key of ["x", "y", "width", "height"] as const)
|
||||
expect(result.candidates[0].region[box][key]).toBeCloseTo(expected[box][key], 8);
|
||||
});
|
||||
|
||||
it("normalizes a zero-width ancestor origin before one-axis clipping", async () => {
|
||||
const doc = await document(
|
||||
[
|
||||
{
|
||||
id: 2,
|
||||
parent: 1,
|
||||
tag: "div",
|
||||
bounds: [200, 400, 0, 60],
|
||||
client: [0, 0, 0, 30],
|
||||
styles: { "overflow-y": "hidden" },
|
||||
},
|
||||
{ id: 3, parent: 2, bounds: [200, 400, 240, 80] },
|
||||
],
|
||||
{ layoutScale: 2, scrollY: 75 },
|
||||
);
|
||||
const result = await discoverVisualCandidates(facts([doc]));
|
||||
expect(result.issues).toEqual([]);
|
||||
expect(result.candidates[0].region.crop).toEqual({ x: 100, y: 125, width: 120, height: 30 });
|
||||
});
|
||||
|
||||
it("keeps unnamed, semantic, aria-hidden, inert, pointer-none and visibility override Canvas", async () => {
|
||||
const doc = await document([
|
||||
{ id: 2, parent: 1 },
|
||||
{ id: 3, parent: 1, attrs: { "aria-label": "Chart" } },
|
||||
{
|
||||
id: 4,
|
||||
parent: 1,
|
||||
attrs: { "aria-hidden": "true", inert: "" },
|
||||
styles: { "pointer-events": "none" },
|
||||
},
|
||||
{ id: 5, parent: 1, tag: "div", styles: { visibility: "hidden" } },
|
||||
{ id: 6, parent: 5, styles: { visibility: "visible" } },
|
||||
{ id: 7, parent: 1, attrs: { hidden: "" }, styles: { display: "block" } },
|
||||
]);
|
||||
doc.axNodes.push({ nodeId: "canvas", backendDOMNodeId: 2 } as FrameOwnedAxNode);
|
||||
const result = await discoverVisualCandidates(facts([doc]));
|
||||
expect(result.candidates.map((c) => c.backendNodeId)).toEqual([2, 3, 4, 6, 7]);
|
||||
expect(result.candidates[1].label).toBe("Chart");
|
||||
expect(result.complete).toBe(true);
|
||||
});
|
||||
|
||||
it("excludes CSS transparent subtrees, hidden/zero/no-layout/fully clipped nodes and overlays", async () => {
|
||||
const doc = await document([
|
||||
{ id: 2, parent: 1, tag: "div", styles: { opacity: "0" } },
|
||||
{ id: 3, parent: 2 },
|
||||
{ id: 4, parent: 1, styles: { visibility: "hidden" } },
|
||||
{ id: 5, parent: 1, bounds: [0, 0, 0, 40] },
|
||||
{ id: 6, parent: 1, bounds: null },
|
||||
{ id: 7, parent: 1, bounds: [1200, 0, 100, 50] },
|
||||
{ id: 8, parent: 1, tag: "div", attrs: { [OVERLAY_HOST_MARKER_ATTR]: "" } },
|
||||
{ id: 9, parent: 8, tag: "#document-fragment", bounds: null },
|
||||
{ id: 10, parent: 9 },
|
||||
]);
|
||||
expect(await discoverVisualCandidates(facts([doc]))).toMatchObject({
|
||||
candidates: [],
|
||||
issues: [],
|
||||
complete: true,
|
||||
});
|
||||
});
|
||||
|
||||
it.each([
|
||||
["both", "hidden", "hidden", [0, 0, 60, 30], [60, 30]],
|
||||
["x", "clip", "visible", [0, 0, 60, 20], [60, 40]],
|
||||
["border", "hidden", "hidden", [5, 5, 68, 38], [64, 34]],
|
||||
])("uses client box for %s clipping", async (_name, x, y, client, expected) => {
|
||||
const doc = await document([
|
||||
{
|
||||
id: 2,
|
||||
parent: 1,
|
||||
tag: "div",
|
||||
bounds: [0, 0, 78, 48],
|
||||
client: client as number[],
|
||||
styles: { "overflow-x": x as string, "overflow-y": y as string },
|
||||
},
|
||||
{
|
||||
id: 3,
|
||||
parent: 2,
|
||||
bounds: x === "clip" || _name === "both" ? [0, 0, 120, 40] : [9, 9, 120, 40],
|
||||
},
|
||||
]);
|
||||
const [candidate] = (await discoverVisualCandidates(facts([doc]))).candidates;
|
||||
expect([candidate.region.crop.width, candidate.region.crop.height]).toEqual(expected);
|
||||
expect(candidate.region.clips?.backendNodeId).toBe(2);
|
||||
});
|
||||
|
||||
it("keeps Canvas border-box and clips partial viewport intersections", async () => {
|
||||
const doc = await document([{ id: 2, parent: 1, bounds: [950, 20, 130, 50] }]);
|
||||
const [candidate] = (await discoverVisualCandidates(facts([doc]))).candidates;
|
||||
expect(candidate.region.borderBox.width).toBe(130);
|
||||
expect(candidate.region.crop).toEqual({ x: 950, y: 20, width: 50, height: 50 });
|
||||
});
|
||||
|
||||
it("propagates owner ancestry across targets, without depending on semantic parents", async () => {
|
||||
const parent = await document([
|
||||
{
|
||||
id: 2,
|
||||
parent: 1,
|
||||
tag: "div",
|
||||
bounds: [0, 0, 200, 100],
|
||||
client: [0, 0, 200, 100],
|
||||
styles: { "overflow-x": "hidden", "overflow-y": "hidden" },
|
||||
},
|
||||
{ id: 3, parent: 2, tag: "iframe", bounds: [100, 0, 200, 200] },
|
||||
]);
|
||||
parent.domNodes.splice(0); // Visual discovery never reads the semantic subset.
|
||||
const child = await document([{ id: 2, parent: 1, bounds: [0, 0, 200, 200] }], {
|
||||
frame: {
|
||||
frameId: "child",
|
||||
parentFrameId: "main",
|
||||
ownerBackendNodeId: 3,
|
||||
target: { tabId: 1, sessionId: "remote" },
|
||||
},
|
||||
projection: {
|
||||
...projection,
|
||||
edges: [
|
||||
{
|
||||
sourceViewport: { width: 200, height: 200 },
|
||||
destinationQuad: [
|
||||
{ x: 100, y: 0 },
|
||||
{ x: 300, y: 0 },
|
||||
{ x: 300, y: 200 },
|
||||
{ x: 100, y: 200 },
|
||||
],
|
||||
},
|
||||
],
|
||||
},
|
||||
});
|
||||
const result = await discoverVisualCandidates(facts([child, parent]));
|
||||
expect(result.complete).toBe(true);
|
||||
expect(result.candidates[0]).toMatchObject({
|
||||
document: { frameId: "child", target: { sessionId: "remote" } },
|
||||
region: { crop: { x: 100, y: 0, width: 100, height: 100 } },
|
||||
});
|
||||
const owner = parent.index.nodes.get(3)!;
|
||||
owner.layout!.styles = { ...owner.layout!.styles, visibility: "hidden" };
|
||||
expect((await discoverVisualCandidates(facts([parent, child]))).candidates).toHaveLength(0);
|
||||
});
|
||||
|
||||
it.each<Record<string, string>>([
|
||||
{ transform: "matrix(0,1,-1,0,0,0)" },
|
||||
{ "clip-path": "circle(50%)" },
|
||||
{ "mask-image": "url(mask)" },
|
||||
{ zoom: "1.25", "overflow-x": "hidden" },
|
||||
])("reports unsupported ancestor geometry: %o", async (styles) => {
|
||||
const doc = await document([
|
||||
{ id: 2, parent: 1, tag: "div", styles },
|
||||
{ id: 3, parent: 2 },
|
||||
]);
|
||||
const result = await discoverVisualCandidates(facts([doc]));
|
||||
expect(result.candidates).toHaveLength(0);
|
||||
expect(result.issues[0].reason).toBe("geometry-unsupported");
|
||||
});
|
||||
|
||||
it("supports positive scale without overflow, rejects pinch and non-rectangular frame projection", async () => {
|
||||
const nodes = [
|
||||
{
|
||||
id: 2,
|
||||
parent: 1,
|
||||
styles: { transform: "matrix(1.25,0,0,1.25,0,0)" },
|
||||
bounds: [10, 20, 150, 50],
|
||||
},
|
||||
];
|
||||
expect(
|
||||
(await discoverVisualCandidates(facts([await document(nodes)]))).candidates,
|
||||
).toHaveLength(1);
|
||||
expect(
|
||||
(await discoverVisualCandidates(facts([await document(nodes, { pageScale: 1.5 })]))).issues[0]
|
||||
.reason,
|
||||
).toBe("geometry-unsupported");
|
||||
const rotated = {
|
||||
...projection,
|
||||
edges: [
|
||||
{
|
||||
sourceViewport: { width: 200, height: 200 },
|
||||
destinationQuad: [
|
||||
{ x: 10, y: 0 },
|
||||
{ x: 200, y: 10 },
|
||||
{ x: 190, y: 200 },
|
||||
{ x: 0, y: 190 },
|
||||
] as [
|
||||
{ x: number; y: number },
|
||||
{ x: number; y: number },
|
||||
{ x: number; y: number },
|
||||
{ x: number; y: number },
|
||||
],
|
||||
},
|
||||
],
|
||||
};
|
||||
expect(
|
||||
(await discoverVisualCandidates(facts([await document(nodes, { projection: rotated })])))
|
||||
.issues[0].reason,
|
||||
).toBe("geometry-unsupported");
|
||||
});
|
||||
|
||||
it("keeps partial capture separate from valid geometry, rejects unverified identities", async () => {
|
||||
const doc = await document([{ id: 2, parent: 1 }]);
|
||||
const partial = facts(
|
||||
[doc],
|
||||
[{ target: doc.frame.target, frameId: "main", stage: "ax", reason: "capture-unavailable" }],
|
||||
);
|
||||
const result = await discoverVisualCandidates(partial);
|
||||
expect(result.candidates).toHaveLength(1);
|
||||
expect(result.captureIssues).toBe(partial.issues);
|
||||
expect(result.complete).toBe(false);
|
||||
const unverified = { ...doc, identity: undefined };
|
||||
const failed = await discoverVisualCandidates(facts([unverified]));
|
||||
expect(failed.candidates).toHaveLength(0);
|
||||
expect(failed.issues[0].reason).toBe("identity-unverified");
|
||||
});
|
||||
|
||||
it("does not trust orphan, cyclic, boxless or missing frame-owner ancestry", async () => {
|
||||
const doc = await document([
|
||||
{ id: 2, parent: 1, tag: "div" },
|
||||
{ id: 3, parent: 2 },
|
||||
]);
|
||||
for (const parent of [99, 3]) {
|
||||
doc.index.nodes.get(2)!.parentBackendNodeId = parent;
|
||||
const index = await buildDocumentIndex([...doc.index.nodes.values()], undefined, true);
|
||||
const result = await discoverVisualCandidates(facts([{ ...doc, index }]));
|
||||
expect(result.candidates).toHaveLength(0);
|
||||
expect(result.issues[0].reason).toBe("ancestry-incomplete");
|
||||
}
|
||||
const boxless = await document([
|
||||
{ id: 2, parent: 1, tag: "div", bounds: null },
|
||||
{ id: 3, parent: 2 },
|
||||
]);
|
||||
expect((await discoverVisualCandidates(facts([boxless]))).issues[0].reason).toBe(
|
||||
"facts-unavailable",
|
||||
);
|
||||
const child = {
|
||||
...doc,
|
||||
frame: { ...doc.frame, frameId: "child", parentFrameId: "absent", ownerBackendNodeId: 2 },
|
||||
};
|
||||
expect((await discoverVisualCandidates(facts([child]))).issues[0].reason).toBe(
|
||||
"ownership-unresolved",
|
||||
);
|
||||
});
|
||||
|
||||
it("is deterministic, does not deduplicate or mutate inputs", async () => {
|
||||
const input = facts([
|
||||
await document([
|
||||
{ id: 2, parent: 1 },
|
||||
{ id: 3, parent: 1 },
|
||||
]),
|
||||
]);
|
||||
const freeze = (value: unknown): void => {
|
||||
if (!value || typeof value !== "object" || Object.isFrozen(value)) return;
|
||||
if (value instanceof Map) for (const item of value.values()) freeze(item);
|
||||
for (const item of Object.values(value)) freeze(item);
|
||||
Object.freeze(value);
|
||||
};
|
||||
freeze(input);
|
||||
const first = await discoverVisualCandidates(input);
|
||||
expect(await discoverVisualCandidates(input)).toEqual(first);
|
||||
expect(first.candidates).toHaveLength(2);
|
||||
});
|
||||
|
||||
it.each([
|
||||
1000, 10000, 100000,
|
||||
])("memoizes deep ancestry across %i nodes and checks cancellation", async (count) => {
|
||||
const doc = await document([{ id: 2, parent: 1 }]);
|
||||
const template = doc.index.nodes.get(2)!;
|
||||
let reads = 0;
|
||||
const input = [doc.index.nodes.get(0)!, doc.index.nodes.get(1)!];
|
||||
for (let id = 2; id < count + 2; id++) {
|
||||
const node = {
|
||||
...template,
|
||||
backendNodeId: id,
|
||||
tag: id < count / 2 ? "div" : "canvas",
|
||||
parentBackendNodeId: id < count / 2 ? id - 1 : count / 2 - 1,
|
||||
};
|
||||
Object.defineProperty(node, "parentBackendNodeId", {
|
||||
get: () => {
|
||||
reads++;
|
||||
return id < count / 2 ? id - 1 : count / 2 - 1;
|
||||
},
|
||||
});
|
||||
input.push(node);
|
||||
}
|
||||
const index = await buildDocumentIndex(input, undefined, true);
|
||||
reads = 0;
|
||||
const result = await discoverVisualCandidates(facts([{ ...doc, index }]));
|
||||
expect(result.candidates).toHaveLength(count / 2 + 2);
|
||||
expect(reads).toBeLessThan(count * 5);
|
||||
const controller = new AbortController();
|
||||
controller.abort();
|
||||
await expect(discoverVisualCandidates(facts([doc]), controller.signal)).rejects.toMatchObject({
|
||||
name: "AbortError",
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -1,250 +0,0 @@
|
||||
import { describe, expect, it } from "vitest";
|
||||
import {
|
||||
EMPTY_VISUAL_CONTEXT,
|
||||
extendVisualContext,
|
||||
projectVisualBox,
|
||||
resolveVisualRegion,
|
||||
type VisualAncestor,
|
||||
} from "../visual-region";
|
||||
|
||||
const styles = {
|
||||
position: "static",
|
||||
visibility: "visible",
|
||||
opacity: "1",
|
||||
display: "block",
|
||||
transform: "none",
|
||||
zoom: "1",
|
||||
"overflow-x": "visible",
|
||||
"overflow-y": "visible",
|
||||
"clip-path": "none",
|
||||
"mask-image": "none",
|
||||
rotate: "none",
|
||||
scale: "none",
|
||||
perspective: "none",
|
||||
clip: "auto",
|
||||
contain: "none",
|
||||
"overflow-clip-margin": "0px",
|
||||
};
|
||||
const ancestor: VisualAncestor = {
|
||||
document: {
|
||||
attachmentId: "a",
|
||||
target: { tabId: 1 },
|
||||
frameId: "main",
|
||||
documentElementBackendNodeId: 1,
|
||||
},
|
||||
backendNodeId: 2,
|
||||
styles,
|
||||
clientBox: { x: 5, y: 5, width: 60, height: 30 },
|
||||
};
|
||||
const box = { x: 0, y: 0, width: 120, height: 40 };
|
||||
|
||||
describe("shared visual region rules", () => {
|
||||
it.each([
|
||||
"visible",
|
||||
"hidden",
|
||||
"auto",
|
||||
"scroll",
|
||||
"clip",
|
||||
])("keeps %s screenshot bounds independent of rounded styling", (overflow) => {
|
||||
for (const clipContents of [true, false]) {
|
||||
const node = {
|
||||
...ancestor,
|
||||
styles: { ...styles, "overflow-x": overflow, "overflow-y": overflow },
|
||||
};
|
||||
const baseline = extendVisualContext(EMPTY_VISUAL_CONTEXT, node, clipContents);
|
||||
for (const radius of ["0px", "8px", "50%", "4px 8px"]) {
|
||||
const rounded = extendVisualContext(
|
||||
EMPTY_VISUAL_CONTEXT,
|
||||
{
|
||||
...node,
|
||||
styles: {
|
||||
...node.styles,
|
||||
"border-top-left-radius": radius,
|
||||
"border-top-right-radius": radius,
|
||||
"border-bottom-left-radius": radius,
|
||||
"border-bottom-right-radius": radius,
|
||||
},
|
||||
},
|
||||
clipContents,
|
||||
);
|
||||
expect(rounded).toEqual(baseline);
|
||||
expect(
|
||||
resolveVisualRegion({
|
||||
borderBox: box,
|
||||
frameVisibleBox: box,
|
||||
visibility: "visible",
|
||||
context: rounded,
|
||||
}),
|
||||
).toMatchObject({ status: "available" });
|
||||
expect(
|
||||
resolveVisualRegion({
|
||||
borderBox: box,
|
||||
frameVisibleBox: box,
|
||||
visibility: "hidden",
|
||||
context: rounded,
|
||||
}),
|
||||
).toEqual({ status: "empty" });
|
||||
if (clipContents && overflow !== "visible")
|
||||
expect(
|
||||
resolveVisualRegion({
|
||||
borderBox: box,
|
||||
frameVisibleBox: { x: 80, y: 0, width: 20, height: 20 },
|
||||
visibility: "visible",
|
||||
context: rounded,
|
||||
}),
|
||||
).toEqual({ status: "empty" });
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
it("accepts independently supplied normalized facts and preserves clipping policy", () => {
|
||||
const context = extendVisualContext(EMPTY_VISUAL_CONTEXT, {
|
||||
...ancestor,
|
||||
styles: { ...styles, "overflow-x": "hidden" },
|
||||
});
|
||||
expect(
|
||||
resolveVisualRegion({ borderBox: box, frameVisibleBox: box, visibility: "visible", context }),
|
||||
).toMatchObject({
|
||||
status: "available",
|
||||
crop: { x: 5, y: 0, width: 60, height: 40 },
|
||||
clips: { overflowX: "hidden", overflowY: "visible" },
|
||||
});
|
||||
const differentPolicy = extendVisualContext(EMPTY_VISUAL_CONTEXT, {
|
||||
...ancestor,
|
||||
styles: { ...styles, "overflow-x": "scroll" },
|
||||
});
|
||||
expect(differentPolicy.clip).toEqual(context.clip);
|
||||
expect(differentPolicy.clips).not.toEqual(context.clips);
|
||||
});
|
||||
|
||||
it("distinguishes fully clipped, missing client geometry and invalid rectangles", () => {
|
||||
const clipping = { ...ancestor, styles: { ...styles, "overflow-x": "hidden" } };
|
||||
const context = extendVisualContext(EMPTY_VISUAL_CONTEXT, {
|
||||
...clipping,
|
||||
clientBox: { x: 0, y: 0, width: 0, height: 20 },
|
||||
});
|
||||
expect(
|
||||
resolveVisualRegion({ borderBox: box, frameVisibleBox: box, visibility: "visible", context })
|
||||
.status,
|
||||
).toBe("empty");
|
||||
const unavailable = extendVisualContext(EMPTY_VISUAL_CONTEXT, { ...clipping, clientBox: null });
|
||||
expect(
|
||||
resolveVisualRegion({
|
||||
borderBox: box,
|
||||
frameVisibleBox: box,
|
||||
visibility: "visible",
|
||||
context: unavailable,
|
||||
}),
|
||||
).toEqual({ status: "unavailable", reason: "geometry-unavailable" });
|
||||
expect(
|
||||
resolveVisualRegion({
|
||||
borderBox: { ...box, x: NaN },
|
||||
frameVisibleBox: box,
|
||||
visibility: "visible",
|
||||
context: EMPTY_VISUAL_CONTEXT,
|
||||
}).status,
|
||||
).toBe("unavailable");
|
||||
expect(projectVisualBox({ x: 5, y: 5, width: 0, height: 20 }, [])).toEqual({
|
||||
x: 5,
|
||||
y: 5,
|
||||
width: 0,
|
||||
height: 20,
|
||||
});
|
||||
});
|
||||
|
||||
it.each<Record<string, string>>([
|
||||
{ rotate: "45deg" },
|
||||
{ scale: "-1 1" },
|
||||
{ perspective: "100px" },
|
||||
{ clip: "rect(0px, 20px, 20px, 0px)" },
|
||||
{ contain: "paint" },
|
||||
{ "overflow-x": "clip", "overflow-clip-margin": "10px" },
|
||||
{ transform: "matrix3d(1,0,0,0,0,1,0,0,0,0,1,0.01,0,0,0,1)" },
|
||||
])("refuses unsupported CSS evidence without changing DOM geometry: %o", (change) => {
|
||||
const context = extendVisualContext(EMPTY_VISUAL_CONTEXT, {
|
||||
...ancestor,
|
||||
styles: { ...styles, ...change },
|
||||
});
|
||||
expect(context.issue).toBe("geometry-unsupported");
|
||||
});
|
||||
|
||||
it("accepts axis-preserving matrix3d translation and independent positive scale", () => {
|
||||
for (const change of [
|
||||
{ transform: "matrix3d(1,0,0,0,0,1,0,0,0,0,1,0,10,20,0,1)" },
|
||||
{ scale: "1.25" },
|
||||
])
|
||||
expect(
|
||||
extendVisualContext(EMPTY_VISUAL_CONTEXT, { ...ancestor, styles: { ...styles, ...change } })
|
||||
.issue,
|
||||
).toBeUndefined();
|
||||
});
|
||||
|
||||
it.each([
|
||||
"matrix(1,0,0,1,0,0)",
|
||||
"matrix(1,0,0,1,10,20)",
|
||||
])("accepts unscaled overflow transform %s", (transform) => {
|
||||
const context = extendVisualContext(EMPTY_VISUAL_CONTEXT, {
|
||||
...ancestor,
|
||||
styles: {
|
||||
...styles,
|
||||
transform,
|
||||
position: "relative",
|
||||
"overflow-x": "hidden",
|
||||
"overflow-y": "hidden",
|
||||
},
|
||||
});
|
||||
expect(context.issue).toBeUndefined();
|
||||
const child = extendVisualContext(
|
||||
context,
|
||||
{
|
||||
...ancestor,
|
||||
styles: {
|
||||
...styles,
|
||||
position: "absolute",
|
||||
"overflow-x": "clip",
|
||||
"overflow-y": "clip",
|
||||
"overflow-clip-margin": "content-box",
|
||||
},
|
||||
},
|
||||
false,
|
||||
);
|
||||
expect(
|
||||
resolveVisualRegion({
|
||||
borderBox: box,
|
||||
frameVisibleBox: box,
|
||||
visibility: "visible",
|
||||
context: child,
|
||||
}),
|
||||
).toMatchObject({ status: "available", crop: { x: 5, y: 5, width: 60, height: 30 } });
|
||||
});
|
||||
|
||||
it("supports positioned overflow containers but refuses uncertain out-of-flow clipping", () => {
|
||||
const overflow = { ...ancestor, styles: { ...styles, "overflow-x": "hidden" } };
|
||||
const staticParent = extendVisualContext(EMPTY_VISUAL_CONTEXT, overflow);
|
||||
expect(
|
||||
extendVisualContext(
|
||||
staticParent,
|
||||
{ ...ancestor, styles: { ...styles, position: "absolute" } },
|
||||
false,
|
||||
).issue,
|
||||
).toBe("geometry-unsupported");
|
||||
const positionedParent = extendVisualContext(EMPTY_VISUAL_CONTEXT, {
|
||||
...overflow,
|
||||
styles: { ...overflow.styles, position: "relative" },
|
||||
});
|
||||
const child = extendVisualContext(
|
||||
positionedParent,
|
||||
{ ...ancestor, styles: { ...styles, position: "absolute" } },
|
||||
false,
|
||||
);
|
||||
expect(child.issue).toBeUndefined();
|
||||
expect(child.clip).toEqual(positionedParent.clip);
|
||||
expect(
|
||||
extendVisualContext(
|
||||
positionedParent,
|
||||
{ ...ancestor, styles: { ...styles, position: "fixed" } },
|
||||
false,
|
||||
).issue,
|
||||
).toBe("geometry-unsupported");
|
||||
});
|
||||
});
|
||||
@@ -1,40 +0,0 @@
|
||||
function captureAbortError(): Error {
|
||||
const error = new Error("observation aborted");
|
||||
error.name = "AbortError";
|
||||
return error;
|
||||
}
|
||||
|
||||
export function isAbortError(error: unknown): boolean {
|
||||
return (
|
||||
typeof error === "object" &&
|
||||
error !== null &&
|
||||
(error as { name?: string }).name === "AbortError"
|
||||
);
|
||||
}
|
||||
|
||||
export function throwIfAborted(signal: AbortSignal | undefined): void {
|
||||
if (signal?.aborted) throw captureAbortError();
|
||||
}
|
||||
|
||||
/** Check at bounded work blocks; yield only after a processing slice is spent.
|
||||
* Each caller owns its deadline, so unrelated captures do not share state. */
|
||||
export function createCaptureCheckpoint(signal?: AbortSignal): () => Promise<void> | undefined {
|
||||
throwIfAborted(signal);
|
||||
let deadline = performance.now() + 8;
|
||||
return () => {
|
||||
throwIfAborted(signal);
|
||||
if (performance.now() < deadline) return;
|
||||
return new Promise<void>((resolve) => {
|
||||
const channel = new MessageChannel();
|
||||
channel.port1.onmessage = () => {
|
||||
channel.port1.close();
|
||||
channel.port2.close();
|
||||
resolve();
|
||||
};
|
||||
channel.port2.postMessage(null);
|
||||
}).then(() => {
|
||||
throwIfAborted(signal);
|
||||
deadline = performance.now() + 8;
|
||||
});
|
||||
};
|
||||
}
|
||||
@@ -1,430 +0,0 @@
|
||||
import {
|
||||
type CdpFrame,
|
||||
type CdpFrameGraph,
|
||||
type CdpTarget,
|
||||
cdpTargetKey,
|
||||
} from "@/browser-driver/frame-graph";
|
||||
import { cssViewport, GeometryContext } from "../geometry/frame-context";
|
||||
import { type CdpRunner, cdpRunnerForTarget } from "../shared";
|
||||
import { collectOverlayExcludedBackendIds } from "./capture";
|
||||
import {
|
||||
isAbortError as isCaptureAbort,
|
||||
throwIfAborted as throwCaptureAborted,
|
||||
} from "./capture-abort";
|
||||
import { verifyDocumentIdentity } from "./document-identity";
|
||||
import type { CapturedSceneInput, DocumentIdentity } from "./facts";
|
||||
import { buildDocumentIndex, type CaptureIssue, type ObservationFacts } from "./facts";
|
||||
import { enrichFormControlStates } from "./form-capture";
|
||||
import {
|
||||
buildFrameDocuments,
|
||||
type FrameAxBatch,
|
||||
type FrameDocument,
|
||||
type FrameOwnedAxNode,
|
||||
} from "./frame-document";
|
||||
import { type NormalizedFrameDocument, normalizeSnapshot } from "./normalize";
|
||||
import {
|
||||
BASIC_SNAPSHOT,
|
||||
describeSnapshotFrames,
|
||||
type SnapshotReply,
|
||||
VISUAL_SNAPSHOT,
|
||||
} from "./snapshot";
|
||||
|
||||
interface TargetBatch<T extends FrameOwnedAxNode> {
|
||||
target: CdpTarget;
|
||||
frames: CdpFrame[];
|
||||
snapshotAttachmentId?: string;
|
||||
documents: NormalizedFrameDocument[];
|
||||
ax: FrameAxBatch<T>[];
|
||||
fallbackExcluded: Set<number>;
|
||||
snapshotFrameIds?: Set<string>;
|
||||
rootFrameId?: string;
|
||||
}
|
||||
|
||||
/** A fixed worker pool scoped to one capture; each worker issues at most one
|
||||
* collection request at a time. Geometry has its own measurement-phase bound. */
|
||||
async function collectTasks<T>(
|
||||
items: readonly T[],
|
||||
collect: (item: T) => Promise<void>,
|
||||
signal?: AbortSignal,
|
||||
): Promise<void> {
|
||||
let cursor = 0;
|
||||
let failed = false;
|
||||
let failure: unknown;
|
||||
await Promise.all(
|
||||
Array.from({ length: Math.min(4, items.length) }, async () => {
|
||||
try {
|
||||
while (cursor < items.length && !failed && !signal?.aborted) {
|
||||
const item = items[cursor++];
|
||||
await collect(item);
|
||||
}
|
||||
} catch (error) {
|
||||
if (!failed) failure = error;
|
||||
failed = true;
|
||||
}
|
||||
}),
|
||||
);
|
||||
// A worker's rejection must not let the capture outlive its own task scope.
|
||||
// In-flight reads and their finally blocks settle before cancellation/failure.
|
||||
throwCaptureAborted(signal);
|
||||
if (failed) throw failure;
|
||||
}
|
||||
|
||||
export async function captureObservationFacts<T extends FrameOwnedAxNode>(
|
||||
cdp: CdpRunner,
|
||||
tabId: number,
|
||||
signal?: AbortSignal,
|
||||
pageUrl?: string,
|
||||
options: { includeVisualFacts?: boolean } = {},
|
||||
): Promise<ObservationFacts<T>> {
|
||||
const profile = options.includeVisualFacts ? VISUAL_SNAPSHOT : BASIC_SNAPSHOT;
|
||||
const startedAt = Date.now();
|
||||
throwCaptureAborted(signal);
|
||||
let graph: CdpFrameGraph | undefined;
|
||||
try {
|
||||
graph = await cdp.getFrameGraph?.(tabId);
|
||||
} catch (error) {
|
||||
if (isCaptureAbort(error)) throw error;
|
||||
}
|
||||
throwCaptureAborted(signal);
|
||||
const geometry = new GeometryContext(cdp, tabId, graph, signal);
|
||||
const issues: CaptureIssue[] = [];
|
||||
const graphFrames = new Map(graph?.frames.map((frame) => [frame.frameId, frame]) ?? []);
|
||||
const groups = new Map<string, TargetBatch<T>>();
|
||||
for (const frame of graph?.frames ?? []) {
|
||||
const key = cdpTargetKey(frame.target);
|
||||
let group = groups.get(key);
|
||||
if (!group) {
|
||||
group = {
|
||||
target: frame.target,
|
||||
frames: [],
|
||||
documents: [],
|
||||
ax: [],
|
||||
fallbackExcluded: new Set(),
|
||||
};
|
||||
groups.set(key, group);
|
||||
}
|
||||
group.frames.push(
|
||||
!frame.target.sessionId && frame.frameId === graph?.rootFrameId && !frame.url && pageUrl
|
||||
? { ...frame, url: pageUrl }
|
||||
: frame,
|
||||
);
|
||||
}
|
||||
if (!groups.has(cdpTargetKey({ tabId })))
|
||||
groups.set(cdpTargetKey({ tabId }), {
|
||||
target: { tabId },
|
||||
frames: [],
|
||||
documents: [],
|
||||
ax: [],
|
||||
fallbackExcluded: new Set(),
|
||||
});
|
||||
const batches = [...groups.values()];
|
||||
const unavailable = (batch: TargetBatch<T>, stage: CaptureIssue["stage"], frameId?: string) =>
|
||||
issues.push({ target: batch.target, frameId, stage, reason: "capture-unavailable" });
|
||||
let firstFailure: unknown;
|
||||
const axReady = new Set<TargetBatch<T>>();
|
||||
await collectTasks(
|
||||
batches,
|
||||
async (batch) => {
|
||||
const scoped = cdpRunnerForTarget(cdp, batch.target);
|
||||
try {
|
||||
throwCaptureAborted(signal);
|
||||
await scoped.send(tabId, "DOMSnapshot.enable", {});
|
||||
throwCaptureAborted(signal);
|
||||
batch.snapshotAttachmentId = cdp.getAttachmentId?.(tabId);
|
||||
const snapshot = await scoped.send<SnapshotReply>(tabId, "DOMSnapshot.captureSnapshot", {
|
||||
computedStyles: profile.computedStyles,
|
||||
includePaintOrder: true,
|
||||
includeDOMRects: true,
|
||||
});
|
||||
throwCaptureAborted(signal);
|
||||
const observed = describeSnapshotFrames(snapshot, batch.target, graphFrames, pageUrl);
|
||||
batch.snapshotFrameIds = observed.ids;
|
||||
batch.rootFrameId = observed.rootFrameId;
|
||||
// Keep graph-only frames for AX fallback, never in preference to observed membership.
|
||||
batch.frames = [
|
||||
...observed.frames,
|
||||
...batch.frames.filter((frame) => !observed.ids.has(frame.frameId)),
|
||||
];
|
||||
batch.documents = await normalizeSnapshot(
|
||||
snapshot,
|
||||
batch.target,
|
||||
batch.frames.filter((frame) => observed.ids.has(frame.frameId)),
|
||||
geometry,
|
||||
issues,
|
||||
signal,
|
||||
observed.rootFrameId,
|
||||
profile,
|
||||
);
|
||||
const formsAvailable = await enrichFormControlStates(
|
||||
scoped,
|
||||
tabId,
|
||||
batch.documents.map((doc) => doc.nodes),
|
||||
signal,
|
||||
);
|
||||
throwCaptureAborted(signal);
|
||||
if (!formsAvailable) unavailable(batch, "forms");
|
||||
const present = new Set(batch.documents.map((doc) => doc.frame.frameId));
|
||||
for (const frame of batch.frames)
|
||||
if (!present.has(frame.frameId)) unavailable(batch, "dom", frame.frameId);
|
||||
} catch (error) {
|
||||
throwCaptureAborted(signal);
|
||||
if (isCaptureAbort(error)) throw error;
|
||||
firstFailure ??= error;
|
||||
unavailable(batch, "dom");
|
||||
batch.fallbackExcluded = await collectOverlayExcludedBackendIds(scoped, tabId, signal);
|
||||
}
|
||||
if (!batch.frames.length && !graph)
|
||||
batch.frames = [
|
||||
{
|
||||
frameId: "root",
|
||||
target: batch.target,
|
||||
...(!batch.target.sessionId && pageUrl ? { url: pageUrl } : {}),
|
||||
},
|
||||
];
|
||||
try {
|
||||
throwCaptureAborted(signal);
|
||||
await scoped.send(tabId, "Accessibility.enable", {});
|
||||
} catch (error) {
|
||||
throwCaptureAborted(signal);
|
||||
if (isCaptureAbort(error)) throw error;
|
||||
firstFailure ??= error;
|
||||
unavailable(batch, "ax");
|
||||
return;
|
||||
}
|
||||
axReady.add(batch);
|
||||
},
|
||||
signal,
|
||||
);
|
||||
|
||||
// Schedule AX by frame across all ready targets, rather than nesting pools.
|
||||
// Keep result slots in source order even when CDP replies arrive out of order.
|
||||
const axTasks: { batch: TargetBatch<T>; frame: CdpFrame; result?: FrameAxBatch<T> }[] =
|
||||
batches.flatMap((batch) =>
|
||||
axReady.has(batch) ? batch.frames.map((frame) => ({ batch, frame })) : [],
|
||||
);
|
||||
await collectTasks(
|
||||
axTasks,
|
||||
async (task) => {
|
||||
const { batch, frame } = task;
|
||||
try {
|
||||
throwCaptureAborted(signal);
|
||||
const result = await cdpRunnerForTarget(cdp, batch.target).send<{ nodes?: T[] }>(
|
||||
tabId,
|
||||
"Accessibility.getFullAXTree",
|
||||
frame.frameId === "root" ? {} : { frameId: frame.frameId },
|
||||
);
|
||||
throwCaptureAborted(signal);
|
||||
task.result = { frame, nodes: result.nodes ?? [] };
|
||||
} catch (error) {
|
||||
throwCaptureAborted(signal);
|
||||
if (isCaptureAbort(error)) throw error;
|
||||
firstFailure ??= error;
|
||||
unavailable(batch, "ax", frame.frameId);
|
||||
}
|
||||
},
|
||||
signal,
|
||||
);
|
||||
for (const task of axTasks) if (task.result) task.batch.ax.push(task.result);
|
||||
|
||||
let viewport = { width: 0, height: 0 };
|
||||
try {
|
||||
const measured = cssViewport(await geometry.layoutMetrics({ tabId }));
|
||||
viewport = { width: measured.width, height: measured.height };
|
||||
} catch (error) {
|
||||
if (isCaptureAbort(error)) throw error;
|
||||
}
|
||||
|
||||
// A snapshot claim outranks an old graph hint. Conflicting actual claims
|
||||
// cannot be resolved by completion order or by overwriting a frameId map.
|
||||
const claims = new Map<string, string>();
|
||||
const invalid = new Set<string>();
|
||||
for (const batch of batches) {
|
||||
const targetKey = cdpTargetKey(batch.target);
|
||||
for (const id of batch.snapshotFrameIds ?? []) {
|
||||
const previous = claims.get(id);
|
||||
if (previous !== undefined && previous !== targetKey) invalid.add(id);
|
||||
claims.set(id, targetKey);
|
||||
}
|
||||
const accepted = new Set(batch.frames.map((frame) => frame.frameId));
|
||||
for (const id of batch.snapshotFrameIds ?? []) if (!accepted.has(id)) invalid.add(id);
|
||||
}
|
||||
const currentFrames = batches.flatMap((batch) =>
|
||||
batch.frames.filter(
|
||||
(frame) =>
|
||||
!claims.has(frame.frameId) || claims.get(frame.frameId) === cdpTargetKey(batch.target),
|
||||
),
|
||||
);
|
||||
const rootBatch = batches.find((batch) => !batch.target.sessionId);
|
||||
const rootFrameId =
|
||||
rootBatch?.rootFrameId ?? graph?.rootFrameId ?? rootBatch?.frames[0]?.frameId ?? "root";
|
||||
const ownershipInvalid = new Set(invalid);
|
||||
const identities = new Map<string, DocumentIdentity>();
|
||||
const selected = new Map(currentFrames.map((frame) => [frame.frameId, frame]));
|
||||
const checks = batches.flatMap((batch) => {
|
||||
const docs = new Map(batch.documents.map((doc) => [doc.frame.frameId, doc]));
|
||||
return batch.frames
|
||||
.filter(
|
||||
(frame) =>
|
||||
!invalid.has(frame.frameId) &&
|
||||
cdpTargetKey(selected.get(frame.frameId)!.target) === cdpTargetKey(batch.target),
|
||||
)
|
||||
.map((frame) => ({ batch, frame, doc: docs.get(frame.frameId) }));
|
||||
});
|
||||
await collectTasks(
|
||||
checks,
|
||||
async ({ batch, frame, doc }) => {
|
||||
throwCaptureAborted(signal);
|
||||
if (!batch.snapshotAttachmentId || doc?.documentElementBackendNodeId === undefined) {
|
||||
issues.push({
|
||||
target: frame.target,
|
||||
frameId: frame.frameId,
|
||||
stage: "identity",
|
||||
reason: "identity-unverified",
|
||||
});
|
||||
return;
|
||||
}
|
||||
const identity: DocumentIdentity = {
|
||||
attachmentId: batch.snapshotAttachmentId,
|
||||
target: frame.target,
|
||||
frameId: frame.frameId,
|
||||
documentElementBackendNodeId: doc.documentElementBackendNodeId,
|
||||
};
|
||||
const verified = await verifyDocumentIdentity(cdp, identity, signal);
|
||||
const status = cdp.getAttachmentId?.(tabId) === identity.attachmentId ? verified : "changed";
|
||||
if (status === "current") identities.set(frame.frameId, identity);
|
||||
else {
|
||||
invalid.add(frame.frameId);
|
||||
issues.push({
|
||||
target: frame.target,
|
||||
frameId: frame.frameId,
|
||||
stage: "identity",
|
||||
reason: status === "changed" ? "document-changed" : "identity-unavailable",
|
||||
});
|
||||
}
|
||||
},
|
||||
signal,
|
||||
);
|
||||
const children = new Map<string, string[]>();
|
||||
for (const frame of currentFrames) {
|
||||
if (!frame.parentFrameId) continue;
|
||||
const siblings = children.get(frame.parentFrameId);
|
||||
if (siblings) siblings.push(frame.frameId);
|
||||
else children.set(frame.parentFrameId, [frame.frameId]);
|
||||
}
|
||||
const blocked = [...invalid];
|
||||
for (let i = 0; i < blocked.length; i++) {
|
||||
for (const child of children.get(blocked[i]) ?? []) {
|
||||
if (!invalid.has(child)) {
|
||||
invalid.add(child);
|
||||
blocked.push(child);
|
||||
}
|
||||
}
|
||||
}
|
||||
for (const frame of currentFrames) {
|
||||
if (ownershipInvalid.has(frame.frameId))
|
||||
issues.push({
|
||||
target: frame.target,
|
||||
frameId: frame.frameId,
|
||||
stage: "ownership",
|
||||
reason: "frame-ownership-unresolved",
|
||||
});
|
||||
}
|
||||
if (invalid.has(rootFrameId))
|
||||
throw new Error(
|
||||
ownershipInvalid.has(rootFrameId)
|
||||
? "observation root document ownership is ambiguous"
|
||||
: "observation document identity changed or could not be verified; observe again",
|
||||
);
|
||||
const frames = currentFrames.filter((frame) => !invalid.has(frame.frameId));
|
||||
const frameById = new Map(frames.map((frame) => [frame.frameId, frame]));
|
||||
const belongs = (frame: CdpFrame) => {
|
||||
const current = frameById.get(frame.frameId);
|
||||
return current && cdpTargetKey(current.target) === cdpTargetKey(frame.target);
|
||||
};
|
||||
const decoded = new Map(
|
||||
batches
|
||||
.flatMap((batch) => batch.documents)
|
||||
.filter((doc) => belongs(doc.frame))
|
||||
.map((doc) => [doc.frame.frameId, doc]),
|
||||
);
|
||||
const ax = batches.flatMap((batch) => batch.ax).filter((batch) => belongs(batch.frame));
|
||||
const documents = await buildFrameDocuments(
|
||||
{ rootFrameId, frames },
|
||||
ax,
|
||||
{
|
||||
nodes: [],
|
||||
rootFrameId,
|
||||
frameNodes: new Map([...decoded].map(([id, doc]) => [id, doc.nodes])),
|
||||
frameExcludedBackendNodeIds: new Map(
|
||||
[...decoded].map(([id, doc]) => [id, doc.index.excludedBackendNodeIds]),
|
||||
),
|
||||
},
|
||||
signal,
|
||||
(frame) =>
|
||||
issues.push({
|
||||
target: frame.target,
|
||||
frameId: frame.frameId,
|
||||
stage: "ownership",
|
||||
reason: "frame-ownership-unresolved",
|
||||
}),
|
||||
);
|
||||
const facts: ObservationFacts<T>["documents"][number][] = [];
|
||||
for (const document of documents) {
|
||||
const doc = decoded.get(document.frameId);
|
||||
const index = doc?.index ?? (await buildDocumentIndex([], signal));
|
||||
const fallback = groups.get(cdpTargetKey(document.target))?.fallbackExcluded;
|
||||
const {
|
||||
domNodes,
|
||||
axNodes,
|
||||
contextScopeId: _scope,
|
||||
excludedBackendNodeIds: _excluded,
|
||||
...frame
|
||||
} = document;
|
||||
facts.push({
|
||||
frame,
|
||||
identity: identities.get(document.frameId),
|
||||
...(doc?.geometry ? { geometry: doc.geometry } : {}),
|
||||
index: fallback?.size ? { ...index, excludedBackendNodeIds: fallback } : index,
|
||||
domNodes,
|
||||
axNodes,
|
||||
});
|
||||
}
|
||||
throwCaptureAborted(signal);
|
||||
if (firstFailure && facts.every((doc) => !doc.domNodes.length && !doc.axNodes.length))
|
||||
throw firstFailure;
|
||||
return {
|
||||
visualFactsCollected: profile.includeVisualFacts,
|
||||
rootFrameId,
|
||||
viewport,
|
||||
documents: facts,
|
||||
issues,
|
||||
startedAt,
|
||||
finishedAt: Date.now(),
|
||||
};
|
||||
}
|
||||
|
||||
/** Existing semantic consumers get a narrow view; no raw snapshot
|
||||
* data can leak through recording's allowlisted output DTO. */
|
||||
export function semanticCapture<T extends FrameOwnedAxNode>(
|
||||
facts: ObservationFacts<T>,
|
||||
): { captured: CapturedSceneInput; documents: FrameDocument<T>[] } {
|
||||
const documents = facts.documents.map((doc) => ({
|
||||
...doc.frame,
|
||||
contextScopeId: doc.frame.frameId,
|
||||
domNodes: doc.domNodes.filter(
|
||||
(node) => !doc.index.excludedBackendNodeIds.has(node.backendNodeId),
|
||||
),
|
||||
axNodes: doc.axNodes,
|
||||
excludedBackendNodeIds: doc.index.excludedBackendNodeIds,
|
||||
}));
|
||||
const root = documents.find((doc) => doc.frameId === facts.rootFrameId);
|
||||
return {
|
||||
documents,
|
||||
captured: {
|
||||
nodes: root?.domNodes ?? [],
|
||||
viewport: facts.viewport,
|
||||
rootFrameId: facts.rootFrameId,
|
||||
excludedBackendNodeIds: root?.excludedBackendNodeIds ?? new Set(),
|
||||
},
|
||||
};
|
||||
}
|
||||
@@ -1,37 +0,0 @@
|
||||
import type { Rect } from "@browser-skill/vom";
|
||||
|
||||
export interface CapturedNode {
|
||||
backendNodeId: number;
|
||||
parentBackendNodeId: number | null;
|
||||
frameId?: string;
|
||||
/** Owning iframe backend node id; `null` for the top-level document. */
|
||||
ownerFrameBackendNodeId?: number | null;
|
||||
tag: string;
|
||||
attrs: Record<string, string>;
|
||||
/** Top-level viewport-relative CSS px, clipped to the owning frame viewport. */
|
||||
rect: Rect | null;
|
||||
/** Frame-local viewport-relative CSS px before top-level projection. */
|
||||
localRect?: Rect | null;
|
||||
paintOrder: number;
|
||||
position: string;
|
||||
pointerEvents: string;
|
||||
/**
|
||||
* computed `cursor`. `cursor: pointer` is the strongest CDP-free signal
|
||||
* that a non-semantic element (a `<div>`/`<span>` with a click handler)
|
||||
* is actually an interactive control — used by the adapter to surface
|
||||
* custom buttons/checkboxes the AX tree drops as `generic`. Optional like
|
||||
* `textContent`: the live parser always sets it, hand-built fixtures may not.
|
||||
*/
|
||||
cursor?: string;
|
||||
/**
|
||||
* Whether the live DOM snapshot provides a painted, non-hidden box for this
|
||||
* node. Semantic resolution uses this only for DOM fallback nodes; AX-backed
|
||||
* nodes remain authoritative even when they are outside the viewport.
|
||||
*/
|
||||
rendered?: boolean;
|
||||
textContent?: string;
|
||||
formState?: "empty" | "filled" | "default";
|
||||
formValue?: string;
|
||||
formDefaultValue?: string;
|
||||
formPlaceholder?: string;
|
||||
}
|
||||
@@ -1,19 +1,310 @@
|
||||
// Browser-side hover probes and overlay exclusion fallback. Static collection
|
||||
// lives in capture-coordinator; snapshot decoding has no browser dependency.
|
||||
// CDP capture adapter: DOMSnapshot.captureSnapshot + Page.getLayoutMetrics
|
||||
// → CapturedNode[] + Viewport. This is the ONLY VOM module that touches
|
||||
// raw CDP. The captureSnapshot reply is columnar (parallel arrays + a
|
||||
// shared string table); requested computed styles are decoded through
|
||||
// STYLE_COL so capture and visibility policy share one explicit contract.
|
||||
|
||||
import type { Rect, Viewport } from "@browser-skill/vom";
|
||||
import { evaluateHoverTrigger } from "@/lib/hover-trigger-policy";
|
||||
import { OVERLAY_HOST_SELECTOR } from "../../lib/overlay-bridge";
|
||||
import { isOverlayHostNode, OVERLAY_HOST_SELECTOR } from "../../lib/overlay-bridge";
|
||||
import { childFrameProjection, type GeometryProjection, projectRectToViewport } from "../geometry";
|
||||
import type { CdpRunner } from "../shared";
|
||||
import type { CapturedNode } from "./capture-types";
|
||||
import type { CapturedSurfaceProbe } from "./facts";
|
||||
|
||||
export type {
|
||||
CapturedNode,
|
||||
CapturedSurfaceProbe,
|
||||
} from "./facts";
|
||||
|
||||
import { isAbortError, throwIfAborted } from "./capture-abort";
|
||||
import { clearHover, ProbeBudget, waitForHover } from "./hover-perception";
|
||||
|
||||
const REQUESTED_STYLES = [
|
||||
"position",
|
||||
"pointer-events",
|
||||
"cursor",
|
||||
"visibility",
|
||||
"opacity",
|
||||
"overflow-x",
|
||||
"overflow-y",
|
||||
] as const;
|
||||
const STYLE_COL = Object.fromEntries(
|
||||
REQUESTED_STYLES.map((name, index) => [name, index]),
|
||||
) as Record<(typeof REQUESTED_STYLES)[number], number>;
|
||||
|
||||
export interface CapturedNode {
|
||||
backendNodeId: number;
|
||||
parentBackendNodeId: number | null;
|
||||
frameId?: string;
|
||||
/** Owning iframe backend node id; `null` for the top-level document. */
|
||||
ownerFrameBackendNodeId?: number | null;
|
||||
tag: string;
|
||||
attrs: Record<string, string>;
|
||||
/** Top-level viewport-relative CSS px, clipped to the owning frame viewport. */
|
||||
rect: Rect | null;
|
||||
/** Frame-local viewport-relative CSS px before top-level projection. */
|
||||
localRect?: Rect | null;
|
||||
paintOrder: number;
|
||||
position: string;
|
||||
pointerEvents: string;
|
||||
/**
|
||||
* computed `cursor`. `cursor: pointer` is the strongest CDP-free signal
|
||||
* that a non-semantic element (a `<div>`/`<span>` with a click handler)
|
||||
* is actually an interactive control — used by the adapter to surface
|
||||
* custom buttons/checkboxes the AX tree drops as `generic`. Optional like
|
||||
* `textContent`: the live parser always sets it, hand-built fixtures may not.
|
||||
*/
|
||||
cursor?: string;
|
||||
overflowX?: string;
|
||||
overflowY?: string;
|
||||
/** True when this node or one of its DOM ancestors makes the subtree fully transparent/hidden. */
|
||||
visuallySuppressed?: boolean;
|
||||
/**
|
||||
* Whether the live DOM snapshot provides a painted, non-hidden box for this
|
||||
* node. Semantic resolution uses this only for DOM fallback nodes; AX-backed
|
||||
* nodes remain authoritative even when they are outside the viewport.
|
||||
*/
|
||||
rendered?: boolean;
|
||||
textContent?: string;
|
||||
formState?: "empty" | "filled" | "default";
|
||||
formValue?: string;
|
||||
formDefaultValue?: string;
|
||||
formPlaceholder?: string;
|
||||
}
|
||||
|
||||
export type CapturedIframeNodes = Map<number, CapturedNode[]>;
|
||||
|
||||
export interface CapturedSurfaceProbe {
|
||||
triggerBackendNodeId: number;
|
||||
triggerPoint?: { x: number; y: number };
|
||||
triggerAction: "hover" | "focus" | string;
|
||||
subItems: string[];
|
||||
confidence?: "high" | "medium" | "low";
|
||||
}
|
||||
|
||||
export interface CapturedViewModel {
|
||||
nodes: CapturedNode[];
|
||||
viewport: Viewport;
|
||||
iframeNodes: CapturedIframeNodes;
|
||||
frameNodes?: Map<string, CapturedNode[]>;
|
||||
frameOwnerBackendNodeIds?: Map<string, number>;
|
||||
/** Explicit DOMSnapshot frame ancestry; never inferred from backend node ids. */
|
||||
frameParentIds?: Map<string, string>;
|
||||
rootFrameId?: string;
|
||||
/** Backend node ids belonging to the agent overlay host + its shadow subtree. */
|
||||
excludedBackendNodeIds: Set<number>;
|
||||
}
|
||||
|
||||
export interface CaptureViewModelOptions {
|
||||
signal?: AbortSignal;
|
||||
}
|
||||
|
||||
function captureAbortError(): Error {
|
||||
const error = new Error("observation aborted");
|
||||
error.name = "AbortError";
|
||||
return error;
|
||||
}
|
||||
|
||||
function isAbortError(error: unknown): boolean {
|
||||
return (
|
||||
typeof error === "object" &&
|
||||
error !== null &&
|
||||
(error as { name?: string }).name === "AbortError"
|
||||
);
|
||||
}
|
||||
|
||||
function throwIfAborted(signal: AbortSignal | undefined): void {
|
||||
if (signal?.aborted) throw captureAbortError();
|
||||
}
|
||||
|
||||
/** Sparse array format Chrome uses for infrequently-set per-node fields. */
|
||||
interface SparseArray {
|
||||
index: number[];
|
||||
value: number[];
|
||||
}
|
||||
|
||||
interface RareBooleanData {
|
||||
index: number[];
|
||||
}
|
||||
|
||||
interface SnapshotDocument {
|
||||
frameId?: string | number;
|
||||
scrollOffsetX?: number;
|
||||
scrollOffsetY?: number;
|
||||
nodes?: {
|
||||
parentIndex?: number[];
|
||||
nodeName?: number[];
|
||||
backendNodeId?: number[];
|
||||
attributes?: number[][];
|
||||
/**
|
||||
* Per-node text value (index into strings), set for `#text` / CDATA nodes.
|
||||
* Element nodes carry -1. Same length as `backendNodeId`.
|
||||
*/
|
||||
nodeValue?: number[];
|
||||
/** Maps node array index → index into `documents[]` for frame content. */
|
||||
contentDocumentIndex?: SparseArray;
|
||||
inputValue?: SparseArray;
|
||||
textValue?: SparseArray;
|
||||
inputChecked?: RareBooleanData;
|
||||
optionSelected?: RareBooleanData;
|
||||
};
|
||||
layout?: {
|
||||
nodeIndex?: number[];
|
||||
styles?: number[][];
|
||||
bounds?: number[][];
|
||||
paintOrders?: number[];
|
||||
};
|
||||
}
|
||||
|
||||
function snapshotFrameId(document: SnapshotDocument, strings: string[]): string | undefined {
|
||||
if (typeof document.frameId === "string") return document.frameId || undefined;
|
||||
if (typeof document.frameId === "number") return str(strings, document.frameId) || undefined;
|
||||
return undefined;
|
||||
}
|
||||
|
||||
interface SnapshotReply {
|
||||
strings?: string[];
|
||||
documents?: SnapshotDocument[];
|
||||
}
|
||||
|
||||
interface LayoutMetricsReply {
|
||||
cssLayoutViewport?: {
|
||||
clientWidth?: number;
|
||||
clientHeight?: number;
|
||||
pageX?: number;
|
||||
pageY?: number;
|
||||
};
|
||||
layoutViewport?: { clientWidth?: number; clientHeight?: number; pageX?: number; pageY?: number };
|
||||
}
|
||||
|
||||
function isFormControlTag(tag: string): boolean {
|
||||
return tag === "input" || tag === "textarea" || tag === "select";
|
||||
}
|
||||
|
||||
function isSensitiveFormControl(node: Pick<CapturedNode, "tag" | "attrs">): boolean {
|
||||
return node.tag === "input" && (node.attrs.type ?? "").toLowerCase() === "password";
|
||||
}
|
||||
|
||||
function snapshotFormState(
|
||||
value: string | undefined,
|
||||
defaultValue: string,
|
||||
hasDefaultValue: boolean,
|
||||
sensitive: boolean,
|
||||
): CapturedNode["formState"] {
|
||||
if (sensitive) {
|
||||
if (value === undefined && !hasDefaultValue) return undefined;
|
||||
return (value ?? defaultValue) === "" ? "empty" : "filled";
|
||||
}
|
||||
if (value === undefined) return undefined;
|
||||
if (value === "") return "empty";
|
||||
return value === defaultValue ? "default" : "filled";
|
||||
}
|
||||
|
||||
const MAX_FORM_ENRICH_CONTROLS = 250;
|
||||
|
||||
interface CapturedFormState {
|
||||
value?: string;
|
||||
defaultValue?: string;
|
||||
placeholder?: string;
|
||||
state?: "empty" | "filled" | "default";
|
||||
sensitive?: boolean;
|
||||
}
|
||||
|
||||
interface CapturedFrameFormState {
|
||||
controls: CapturedFormState[];
|
||||
childFrames: CapturedFrameFormState[];
|
||||
}
|
||||
|
||||
function formStateBatchExpression(maxControls: number): string {
|
||||
return `(() => {
|
||||
const maxControls = ${JSON.stringify(maxControls)};
|
||||
let remaining = maxControls;
|
||||
const controlSelector = "input,textarea,select";
|
||||
const controlState = (el) => {
|
||||
const tag = el.tagName.toLowerCase();
|
||||
const type = tag === "input" ? String(el.type || "text").toLowerCase() : tag;
|
||||
const sensitive = type === "password" || type === "credit-card";
|
||||
const rawValue = typeof el.value === "string" ? el.value : "";
|
||||
const defaultValue = typeof el.defaultValue === "string" ? el.defaultValue : "";
|
||||
const placeholder = typeof el.placeholder === "string" ? el.placeholder : "";
|
||||
const state = rawValue === "" ? "empty" : rawValue === defaultValue ? "default" : "filled";
|
||||
return {
|
||||
state,
|
||||
sensitive,
|
||||
placeholder,
|
||||
...(sensitive ? {} : { value: rawValue, defaultValue }),
|
||||
};
|
||||
};
|
||||
const collect = (doc) => {
|
||||
const controls = [];
|
||||
for (const el of Array.from(doc.querySelectorAll(controlSelector))) {
|
||||
if (remaining <= 0) break;
|
||||
controls.push(controlState(el));
|
||||
remaining -= 1;
|
||||
}
|
||||
const childFrames = [];
|
||||
for (const frame of Array.from(doc.querySelectorAll("iframe"))) {
|
||||
let childDoc = null;
|
||||
try { childDoc = frame.contentDocument; } catch { childDoc = null; }
|
||||
childFrames.push(childDoc && remaining > 0 ? collect(childDoc) : { controls: [], childFrames: [] });
|
||||
}
|
||||
return { controls, childFrames };
|
||||
};
|
||||
return collect(document);
|
||||
})()`;
|
||||
}
|
||||
|
||||
function flattenFrameFormStates(
|
||||
frame: CapturedFrameFormState | undefined,
|
||||
out: CapturedFormState[][] = [],
|
||||
): CapturedFormState[][] {
|
||||
if (!frame) return out;
|
||||
out.push(Array.isArray(frame.controls) ? frame.controls : []);
|
||||
for (const child of Array.isArray(frame.childFrames) ? frame.childFrames : []) {
|
||||
flattenFrameFormStates(child, out);
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
function applyFormStates(nodes: CapturedNode[], states: CapturedFormState[]): void {
|
||||
let index = 0;
|
||||
for (const node of nodes) {
|
||||
if (!isFormControlTag(node.tag)) continue;
|
||||
const state = states[index];
|
||||
index += 1;
|
||||
if (!state) continue;
|
||||
node.formState = state.state;
|
||||
node.formPlaceholder = state.placeholder ?? "";
|
||||
if (state.sensitive || isSensitiveFormControl(node)) {
|
||||
delete node.formValue;
|
||||
delete node.formDefaultValue;
|
||||
delete node.attrs.value;
|
||||
} else {
|
||||
node.formDefaultValue = state.defaultValue ?? "";
|
||||
if (state.value !== undefined) node.formValue = state.value;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async function enrichFormControlStates(
|
||||
cdp: CdpRunner,
|
||||
tabId: number,
|
||||
frameNodeGroups: CapturedNode[][],
|
||||
signal?: AbortSignal,
|
||||
): Promise<void> {
|
||||
const hasControls = frameNodeGroups.some((nodes) =>
|
||||
nodes.some((node) => isFormControlTag(node.tag)),
|
||||
);
|
||||
if (!hasControls) return;
|
||||
try {
|
||||
throwIfAborted(signal);
|
||||
const result = await cdp.send<RuntimeEvaluateReply>(tabId, "Runtime.evaluate", {
|
||||
expression: formStateBatchExpression(MAX_FORM_ENRICH_CONTROLS),
|
||||
returnByValue: true,
|
||||
});
|
||||
throwIfAborted(signal);
|
||||
const frameStates = flattenFrameFormStates(runtimeValue<CapturedFrameFormState>(result));
|
||||
for (let i = 0; i < frameNodeGroups.length; i += 1) {
|
||||
applyFormStates(frameNodeGroups[i], frameStates[i] ?? []);
|
||||
}
|
||||
} catch (error) {
|
||||
if (isAbortError(error)) throw error;
|
||||
// Best-effort enrichment. DOMSnapshot/AX data still carries the nodes.
|
||||
}
|
||||
}
|
||||
|
||||
interface RuntimeEvaluateReply {
|
||||
result?: {
|
||||
value?: unknown;
|
||||
@@ -35,6 +326,44 @@ interface CdpDomNode {
|
||||
shadowRoots?: CdpDomNode[];
|
||||
}
|
||||
|
||||
interface ParseDocumentResult {
|
||||
nodes: CapturedNode[];
|
||||
excludedBackendNodeIds: Set<number>;
|
||||
}
|
||||
|
||||
interface FrameContext {
|
||||
frameId?: string;
|
||||
ownerFrameBackendNodeId: number | null;
|
||||
projection: GeometryProjection | null;
|
||||
scrollX: number;
|
||||
scrollY: number;
|
||||
}
|
||||
|
||||
function str(strings: string[], idx: number | undefined): string {
|
||||
if (idx === undefined || idx < 0) return "";
|
||||
return strings[idx] ?? "";
|
||||
}
|
||||
|
||||
function devicePixelRatio(metrics: LayoutMetricsReply): number {
|
||||
const layoutW = metrics.layoutViewport?.clientWidth ?? 0;
|
||||
const cssW = metrics.cssLayoutViewport?.clientWidth ?? 0;
|
||||
if (!layoutW || !cssW) return 1;
|
||||
const dpr = layoutW / cssW;
|
||||
if (!Number.isFinite(dpr) || dpr <= 0) return 1;
|
||||
return dpr >= 1 ? dpr : 1;
|
||||
}
|
||||
|
||||
function sparseIndexMap(sparse: SparseArray | undefined): Map<number, number> {
|
||||
const out = new Map<number, number>();
|
||||
if (!sparse?.index || !sparse.value) return out;
|
||||
for (let i = 0; i < sparse.index.length; i++) {
|
||||
const nodeIndex = sparse.index[i];
|
||||
const docIndex = sparse.value[i];
|
||||
if (nodeIndex !== undefined && docIndex !== undefined) out.set(nodeIndex, docIndex);
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
function collectBackendIdsFromDomNode(node: CdpDomNode | undefined, out: Set<number>): void {
|
||||
if (!node) return;
|
||||
if (typeof node.backendNodeId === "number") {
|
||||
@@ -443,3 +772,375 @@ export async function collectOverlayExcludedBackendIds(
|
||||
}
|
||||
return excluded;
|
||||
}
|
||||
|
||||
/**
|
||||
* Parse one DOMSnapshot document into CapturedNode[].
|
||||
*
|
||||
* @param doc - the raw DOMSnapshot document object
|
||||
* @param strings - the shared string table for the whole snapshot
|
||||
* @param dpr - device-pixel-ratio from Page.getLayoutMetrics
|
||||
* @param context - frame coordinate context; output rects are top viewport-relative
|
||||
*/
|
||||
function parseDocumentNodes(
|
||||
doc: SnapshotDocument,
|
||||
strings: string[],
|
||||
dpr: number,
|
||||
context: FrameContext,
|
||||
): ParseDocumentResult {
|
||||
const dn = doc.nodes;
|
||||
const dl = doc.layout;
|
||||
if (!dn?.backendNodeId) {
|
||||
return { nodes: [], excludedBackendNodeIds: new Set() };
|
||||
}
|
||||
|
||||
const count = dn.backendNodeId.length;
|
||||
const layoutByNode = new Map<number, number>();
|
||||
(dl?.nodeIndex ?? []).forEach((nodeIdx, layoutIdx) => layoutByNode.set(nodeIdx, layoutIdx));
|
||||
|
||||
// The agent's own overlay (WXT shadow host, marked with OVERLAY_HOST_MARKER_ATTR)
|
||||
// is injected into the page and its open shadow root
|
||||
// is inlined by DOMSnapshot as descendants of the host. Its fixed
|
||||
// full-viewport click-blocker would otherwise dominate occlusion detection
|
||||
// and hide the real page, so mark the host + its whole subtree excluded.
|
||||
// parentIndex always references an earlier node, so one forward pass suffices.
|
||||
const excluded = new Array<boolean>(count).fill(false);
|
||||
const excludedBackendNodeIds = new Set<number>();
|
||||
for (let n = 0; n < count; n++) {
|
||||
const parentIdx = dn.parentIndex?.[n] ?? -1;
|
||||
const inherited = parentIdx >= 0 && excluded[parentIdx];
|
||||
let isOverlayHost = inherited;
|
||||
if (!isOverlayHost) {
|
||||
const pairs = dn.attributes?.[n] ?? [];
|
||||
const attrNames: string[] = [];
|
||||
for (let a = 0; a + 1 < pairs.length; a += 2) {
|
||||
attrNames.push(str(strings, pairs[a]));
|
||||
}
|
||||
isOverlayHost = isOverlayHostNode(str(strings, dn.nodeName?.[n]), attrNames);
|
||||
}
|
||||
if (!isOverlayHost) continue;
|
||||
excluded[n] = true;
|
||||
const backendNodeId = dn.backendNodeId[n];
|
||||
if (backendNodeId !== undefined) {
|
||||
excludedBackendNodeIds.add(backendNodeId);
|
||||
}
|
||||
}
|
||||
|
||||
const posCol = STYLE_COL.position;
|
||||
const peCol = STYLE_COL["pointer-events"];
|
||||
const cursorCol = STYLE_COL.cursor;
|
||||
const visibilityCol = STYLE_COL.visibility;
|
||||
const opacityCol = STYLE_COL.opacity;
|
||||
const overflowXCol = STYLE_COL["overflow-x"];
|
||||
const overflowYCol = STYLE_COL["overflow-y"];
|
||||
const inputValues = sparseIndexMap(dn.inputValue);
|
||||
const textValues = sparseIndexMap(dn.textValue);
|
||||
const checkedInputs = new Set(dn.inputChecked?.index ?? []);
|
||||
const selectedOptions = new Set(dn.optionSelected?.index ?? []);
|
||||
|
||||
// Collect visible text from #text child nodes so element CapturedNodes
|
||||
// carry a textContent value usable as a button/link label fallback.
|
||||
// nodeValue is a parallel array: string index for text nodes, -1 otherwise.
|
||||
const nodeTextContent = new Map<number, string>();
|
||||
if (dn.nodeValue) {
|
||||
for (let n = 0; n < count; n++) {
|
||||
const nvIdx = dn.nodeValue[n] ?? -1;
|
||||
if (nvIdx < 0) continue;
|
||||
const text = str(strings, nvIdx).trim();
|
||||
if (!text) continue;
|
||||
const parentIdx = dn.parentIndex?.[n] ?? -1;
|
||||
if (parentIdx >= 0) {
|
||||
const existing = nodeTextContent.get(parentIdx);
|
||||
nodeTextContent.set(parentIdx, existing ? `${existing} ${text}` : text);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Build CapturedNodes.
|
||||
const nodes: CapturedNode[] = [];
|
||||
const visuallySuppressedByNodeIndex = new Array<boolean>(count).fill(false);
|
||||
for (let n = 0; n < count; n++) {
|
||||
if (excluded[n]) continue;
|
||||
const backendNodeId = dn.backendNodeId[n];
|
||||
const parentIdx = dn.parentIndex?.[n] ?? -1;
|
||||
const parentBackendNodeId = parentIdx >= 0 ? (dn.backendNodeId[parentIdx] ?? null) : null;
|
||||
const tag = str(strings, dn.nodeName?.[n]).toLowerCase();
|
||||
|
||||
const attrs: Record<string, string> = {};
|
||||
const pairs = dn.attributes?.[n] ?? [];
|
||||
for (let a = 0; a + 1 < pairs.length; a += 2) {
|
||||
attrs[str(strings, pairs[a]).toLowerCase()] = str(strings, pairs[a + 1]);
|
||||
}
|
||||
|
||||
let rect: Rect | null = null;
|
||||
let localRect: Rect | null = null;
|
||||
let paintOrder = 0;
|
||||
let position = "static";
|
||||
let pointerEvents = "auto";
|
||||
let cursor = "auto";
|
||||
let overflowX = "visible";
|
||||
let overflowY = "visible";
|
||||
let rendered = false;
|
||||
let visuallySuppressed =
|
||||
parentIdx >= 0 ? visuallySuppressedByNodeIndex[parentIdx] === true : false;
|
||||
const li = layoutByNode.get(n);
|
||||
if (li !== undefined) {
|
||||
const b = dl?.bounds?.[li];
|
||||
if (b && b.length >= 4 && b[2] > 0 && b[3] > 0) {
|
||||
localRect = {
|
||||
x: b[0] / dpr - context.scrollX,
|
||||
y: b[1] / dpr - context.scrollY,
|
||||
w: b[2] / dpr,
|
||||
h: b[3] / dpr,
|
||||
};
|
||||
const bounds = context.projection
|
||||
? projectRectToViewport(localRect, context.projection)
|
||||
: null;
|
||||
rect = bounds ? { x: bounds.x, y: bounds.y, w: bounds.width, h: bounds.height } : null;
|
||||
}
|
||||
paintOrder = dl?.paintOrders?.[li] ?? 0;
|
||||
const styleRow = dl?.styles?.[li] ?? [];
|
||||
position = str(strings, styleRow[posCol]) || "static";
|
||||
pointerEvents = str(strings, styleRow[peCol]) || "auto";
|
||||
cursor = str(strings, styleRow[cursorCol]) || "auto";
|
||||
const visibility = str(strings, styleRow[visibilityCol]) || "visible";
|
||||
const opacity = str(strings, styleRow[opacityCol]) || "1";
|
||||
overflowX = str(strings, styleRow[overflowXCol]) || "visible";
|
||||
overflowY = str(strings, styleRow[overflowYCol]) || "visible";
|
||||
visuallySuppressed ||=
|
||||
visibility === "hidden" ||
|
||||
visibility === "collapse" ||
|
||||
(Number.parseFloat(opacity) || 0) <= 0;
|
||||
rendered =
|
||||
localRect !== null &&
|
||||
visibility !== "hidden" &&
|
||||
visibility !== "collapse" &&
|
||||
(Number.parseFloat(opacity) || 0) > 0;
|
||||
}
|
||||
visuallySuppressedByNodeIndex[n] = visuallySuppressed;
|
||||
|
||||
// Skip non-element nodes (#text, #cdata-section, etc.) — they carry no
|
||||
// geometry and are never queried by callers.
|
||||
if (tag.startsWith("#")) continue;
|
||||
|
||||
const textContent = nodeTextContent.get(n);
|
||||
|
||||
const rawFormValueIndex = tag === "textarea" ? textValues.get(n) : inputValues.get(n);
|
||||
const rawFormValue =
|
||||
rawFormValueIndex !== undefined ? str(strings, rawFormValueIndex) : undefined;
|
||||
const sensitive = isSensitiveFormControl({ tag, attrs });
|
||||
const formDefaultValue = attrs.value ?? "";
|
||||
const formValue = sensitive ? undefined : rawFormValue;
|
||||
const formState = snapshotFormState(
|
||||
rawFormValue,
|
||||
formDefaultValue,
|
||||
Object.prototype.hasOwnProperty.call(attrs, "value"),
|
||||
sensitive,
|
||||
);
|
||||
if (sensitive) delete attrs.value;
|
||||
|
||||
nodes.push({
|
||||
backendNodeId,
|
||||
parentBackendNodeId,
|
||||
...(context.frameId ? { frameId: context.frameId } : {}),
|
||||
ownerFrameBackendNodeId: context.ownerFrameBackendNodeId,
|
||||
tag,
|
||||
attrs,
|
||||
rect,
|
||||
localRect,
|
||||
paintOrder,
|
||||
position,
|
||||
pointerEvents,
|
||||
cursor,
|
||||
overflowX,
|
||||
overflowY,
|
||||
visuallySuppressed,
|
||||
rendered,
|
||||
textContent,
|
||||
...(formValue !== undefined ? { formValue } : {}),
|
||||
...(tag === "input" || tag === "textarea"
|
||||
? {
|
||||
formPlaceholder: attrs.placeholder ?? "",
|
||||
...(!sensitive ? { formDefaultValue } : {}),
|
||||
...(formState ? { formState } : {}),
|
||||
}
|
||||
: {}),
|
||||
...(checkedInputs.has(n) ? { formValue: "true", formState: "filled" } : {}),
|
||||
...(selectedOptions.has(n) ? { formValue: attrs.value ?? textContent ?? "" } : {}),
|
||||
});
|
||||
}
|
||||
return { nodes, excludedBackendNodeIds };
|
||||
}
|
||||
|
||||
interface ParseFrameDocumentsResult {
|
||||
iframeNodes: CapturedIframeNodes;
|
||||
frameOwnerBackendNodeIds: Map<string, number>;
|
||||
frameParentIds: Map<string, string>;
|
||||
excludedBackendNodeIds: Set<number>;
|
||||
}
|
||||
|
||||
function parseChildFrameDocuments(
|
||||
documents: SnapshotDocument[],
|
||||
strings: string[],
|
||||
dpr: number,
|
||||
parentDocIndex: number,
|
||||
parentNodes: CapturedNode[],
|
||||
parentContext: FrameContext,
|
||||
visited = new Set<number>(),
|
||||
): ParseFrameDocumentsResult {
|
||||
const iframeNodes: CapturedIframeNodes = new Map();
|
||||
const frameOwnerBackendNodeIds = new Map<string, number>();
|
||||
const frameParentIds = new Map<string, string>();
|
||||
const excludedBackendNodeIds = new Set<number>();
|
||||
const parentDoc = documents[parentDocIndex];
|
||||
const cdi = sparseIndexMap(parentDoc?.nodes?.contentDocumentIndex);
|
||||
if (cdi.size === 0) {
|
||||
return { iframeNodes, frameOwnerBackendNodeIds, frameParentIds, excludedBackendNodeIds };
|
||||
}
|
||||
|
||||
const parentBackendIds = parentDoc?.nodes?.backendNodeId ?? [];
|
||||
const parentNodeByBackendId = new Map(parentNodes.map((node) => [node.backendNodeId, node]));
|
||||
|
||||
for (const [nodeArrayIdx, childDocIndex] of cdi) {
|
||||
if (visited.has(childDocIndex)) continue;
|
||||
const childDoc = documents[childDocIndex];
|
||||
if (!childDoc) continue;
|
||||
const iframeBackendId = parentBackendIds[nodeArrayIdx];
|
||||
if (iframeBackendId === undefined) continue;
|
||||
const iframeNode = parentNodeByBackendId.get(iframeBackendId);
|
||||
const projection =
|
||||
parentContext.projection && iframeNode?.localRect
|
||||
? childFrameProjection(parentContext.projection, iframeNode.localRect)
|
||||
: null;
|
||||
|
||||
const childContext: FrameContext = {
|
||||
frameId: snapshotFrameId(childDoc, strings),
|
||||
ownerFrameBackendNodeId: iframeBackendId,
|
||||
projection,
|
||||
scrollX: childDoc.scrollOffsetX ?? 0,
|
||||
scrollY: childDoc.scrollOffsetY ?? 0,
|
||||
};
|
||||
const nextVisited = new Set(visited);
|
||||
nextVisited.add(childDocIndex);
|
||||
const parsed = parseDocumentNodes(childDoc, strings, dpr, childContext);
|
||||
iframeNodes.set(iframeBackendId, parsed.nodes);
|
||||
if (childContext.frameId) {
|
||||
frameOwnerBackendNodeIds.set(childContext.frameId, iframeBackendId);
|
||||
if (parentContext.frameId) frameParentIds.set(childContext.frameId, parentContext.frameId);
|
||||
}
|
||||
for (const id of parsed.excludedBackendNodeIds) excludedBackendNodeIds.add(id);
|
||||
|
||||
const nested = parseChildFrameDocuments(
|
||||
documents,
|
||||
strings,
|
||||
dpr,
|
||||
childDocIndex,
|
||||
parsed.nodes,
|
||||
childContext,
|
||||
nextVisited,
|
||||
);
|
||||
for (const [nestedFrameId, nestedNodes] of nested.iframeNodes) {
|
||||
iframeNodes.set(nestedFrameId, nestedNodes);
|
||||
}
|
||||
for (const [frameId, ownerBackendNodeId] of nested.frameOwnerBackendNodeIds) {
|
||||
frameOwnerBackendNodeIds.set(frameId, ownerBackendNodeId);
|
||||
}
|
||||
for (const [frameId, parentFrameId] of nested.frameParentIds) {
|
||||
frameParentIds.set(frameId, parentFrameId);
|
||||
}
|
||||
for (const id of nested.excludedBackendNodeIds) excludedBackendNodeIds.add(id);
|
||||
}
|
||||
|
||||
return { iframeNodes, frameOwnerBackendNodeIds, frameParentIds, excludedBackendNodeIds };
|
||||
}
|
||||
|
||||
export async function captureViewModel(
|
||||
cdp: CdpRunner,
|
||||
tabId: number,
|
||||
options: CaptureViewModelOptions = {},
|
||||
): Promise<CapturedViewModel> {
|
||||
throwIfAborted(options.signal);
|
||||
let metrics: LayoutMetricsReply = {};
|
||||
try {
|
||||
metrics = await cdp.send<LayoutMetricsReply>(tabId, "Page.getLayoutMetrics", {});
|
||||
} catch (error) {
|
||||
if (isAbortError(error)) throw error;
|
||||
console.debug("[bsk capture] layout metrics unavailable", error);
|
||||
}
|
||||
throwIfAborted(options.signal);
|
||||
const dpr = devicePixelRatio(metrics);
|
||||
const vpSrc = metrics.cssLayoutViewport ?? metrics.layoutViewport ?? {};
|
||||
const viewport: Viewport = {
|
||||
width: vpSrc.clientWidth ?? 0,
|
||||
height: vpSrc.clientHeight ?? 0,
|
||||
};
|
||||
const scrollX = vpSrc.pageX ?? 0;
|
||||
const scrollY = vpSrc.pageY ?? 0;
|
||||
|
||||
await cdp.send(tabId, "DOMSnapshot.enable", {});
|
||||
throwIfAborted(options.signal);
|
||||
const snap = await cdp.send<SnapshotReply>(tabId, "DOMSnapshot.captureSnapshot", {
|
||||
computedStyles: REQUESTED_STYLES,
|
||||
includePaintOrder: true,
|
||||
includeDOMRects: true,
|
||||
});
|
||||
throwIfAborted(options.signal);
|
||||
|
||||
const strings = snap.strings ?? [];
|
||||
const documents = snap.documents ?? [];
|
||||
const doc0 = documents[0];
|
||||
if (!doc0?.nodes?.backendNodeId) {
|
||||
return {
|
||||
nodes: [],
|
||||
viewport,
|
||||
iframeNodes: new Map(),
|
||||
excludedBackendNodeIds: new Set(),
|
||||
};
|
||||
}
|
||||
|
||||
const topContext: FrameContext = {
|
||||
frameId: snapshotFrameId(doc0, strings),
|
||||
ownerFrameBackendNodeId: null,
|
||||
projection: {
|
||||
sourceClips: [],
|
||||
edges: [],
|
||||
topViewport: viewport,
|
||||
},
|
||||
scrollX,
|
||||
scrollY,
|
||||
};
|
||||
const mainParsed = parseDocumentNodes(doc0, strings, dpr, topContext);
|
||||
const nodes = mainParsed.nodes;
|
||||
const excludedBackendNodeIds = new Set(mainParsed.excludedBackendNodeIds);
|
||||
|
||||
const frameParsed = parseChildFrameDocuments(documents, strings, dpr, 0, nodes, topContext);
|
||||
const iframeNodes = frameParsed.iframeNodes;
|
||||
for (const id of frameParsed.excludedBackendNodeIds) {
|
||||
excludedBackendNodeIds.add(id);
|
||||
}
|
||||
|
||||
await enrichFormControlStates(cdp, tabId, [nodes, ...iframeNodes.values()], options.signal);
|
||||
throwIfAborted(options.signal);
|
||||
|
||||
const frameNodes = new Map<string, CapturedNode[]>();
|
||||
if (topContext.frameId) frameNodes.set(topContext.frameId, nodes);
|
||||
for (const iframeFrameNodes of iframeNodes.values()) {
|
||||
const frameId = iframeFrameNodes.find((node) => node.frameId)?.frameId;
|
||||
if (frameId) frameNodes.set(frameId, iframeFrameNodes);
|
||||
}
|
||||
for (const [frameId, ownerBackendNodeId] of frameParsed.frameOwnerBackendNodeIds) {
|
||||
if (!frameNodes.has(frameId)) {
|
||||
frameNodes.set(frameId, iframeNodes.get(ownerBackendNodeId) ?? []);
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
nodes,
|
||||
viewport,
|
||||
iframeNodes,
|
||||
frameNodes,
|
||||
frameOwnerBackendNodeIds: frameParsed.frameOwnerBackendNodeIds,
|
||||
frameParentIds: frameParsed.frameParentIds,
|
||||
...(topContext.frameId ? { rootFrameId: topContext.frameId } : {}),
|
||||
excludedBackendNodeIds,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -1,91 +0,0 @@
|
||||
import type { CdpRunner } from "../shared";
|
||||
import { sendToCdpTarget } from "../shared";
|
||||
import { isAbortError, throwIfAborted } from "./capture-abort";
|
||||
import type { DocumentIdentity } from "./facts";
|
||||
import type { VisualCandidate } from "./visual-discovery";
|
||||
|
||||
/** Compare the snapshot root with the current root in that exact frame.
|
||||
* Deep serialization supplies the backend ID without a separate describeNode. */
|
||||
export async function verifyDocumentIdentity(
|
||||
cdp: CdpRunner,
|
||||
identity: DocumentIdentity,
|
||||
signal?: AbortSignal,
|
||||
): Promise<"current" | "changed" | "unavailable"> {
|
||||
return verifyIdentity(cdp, identity, signal);
|
||||
}
|
||||
|
||||
/** Verify the visual anchor in its original frame; geometry is checked by screenshot execution. */
|
||||
export async function verifyVisualTargetIdentity(
|
||||
cdp: CdpRunner,
|
||||
candidate: VisualCandidate,
|
||||
signal?: AbortSignal,
|
||||
): Promise<"current" | "changed" | "unavailable"> {
|
||||
return verifyIdentity(cdp, candidate.document, signal, candidate.backendNodeId);
|
||||
}
|
||||
|
||||
async function verifyIdentity(
|
||||
cdp: CdpRunner,
|
||||
identity: DocumentIdentity,
|
||||
signal?: AbortSignal,
|
||||
anchorBackendNodeId?: number,
|
||||
): Promise<"current" | "changed" | "unavailable"> {
|
||||
const attached = () => cdp.getAttachmentId?.(identity.target.tabId) === identity.attachmentId;
|
||||
throwIfAborted(signal);
|
||||
if (!attached()) return "changed";
|
||||
const objectGroup = `bsk-document-identity-${crypto.randomUUID()}`;
|
||||
const send = <T>(method: string, params: object) => {
|
||||
throwIfAborted(signal);
|
||||
return sendToCdpTarget<T>(cdp, identity.target, method, params);
|
||||
};
|
||||
try {
|
||||
const world = await send<{ executionContextId: number }>("Page.createIsolatedWorld", {
|
||||
frameId: identity.frameId,
|
||||
worldName: "bsk-document-identity",
|
||||
});
|
||||
const serializationOptions = {
|
||||
serialization: "deep",
|
||||
additionalParameters: { maxNodeDepth: 0, includeShadowTree: "none" },
|
||||
};
|
||||
type RootReply = {
|
||||
result?: { deepSerializedValue?: { type: string; value?: { backendNodeId?: number } } };
|
||||
};
|
||||
let reply: RootReply;
|
||||
if (anchorBackendNodeId === undefined) {
|
||||
reply = await send<RootReply>("Runtime.evaluate", {
|
||||
expression: "document.documentElement",
|
||||
contextId: world.executionContextId,
|
||||
objectGroup,
|
||||
serializationOptions,
|
||||
});
|
||||
} else {
|
||||
const anchor = await send<{ object?: { objectId?: string } }>("DOM.resolveNode", {
|
||||
backendNodeId: anchorBackendNodeId,
|
||||
executionContextId: world.executionContextId,
|
||||
objectGroup,
|
||||
});
|
||||
if (!anchor.object?.objectId) return "unavailable";
|
||||
reply = await send<RootReply>("Runtime.callFunctionOn", {
|
||||
objectId: anchor.object.objectId,
|
||||
functionDeclaration:
|
||||
"function() { return this.isConnected && this.ownerDocument === document ? document.documentElement : null; }",
|
||||
objectGroup,
|
||||
serializationOptions,
|
||||
});
|
||||
}
|
||||
if (!attached()) return "changed";
|
||||
const root = reply.result?.deepSerializedValue;
|
||||
if (root?.type === "null") return "changed";
|
||||
const id = root?.type === "node" ? root.value?.backendNodeId : undefined;
|
||||
if (id === undefined) return "unavailable";
|
||||
return id === identity.documentElementBackendNodeId ? "current" : "changed";
|
||||
} catch (error) {
|
||||
throwIfAborted(signal);
|
||||
if (isAbortError(error)) throw error;
|
||||
return attached() ? "unavailable" : "changed";
|
||||
} finally {
|
||||
await sendToCdpTarget(cdp, identity.target, "Runtime.releaseObjectGroup", {
|
||||
objectGroup,
|
||||
}).catch(() => {});
|
||||
throwIfAborted(signal);
|
||||
}
|
||||
}
|
||||
@@ -1,182 +0,0 @@
|
||||
import type { Viewport } from "@browser-skill/vom";
|
||||
import type { CdpFrame, CdpTarget } from "@/browser-driver/frame-graph";
|
||||
import { isOverlayHostNode } from "@/lib/overlay-bridge";
|
||||
import type { GeometryProjection } from "../geometry";
|
||||
import type { FrameProjectionIssue, SnapshotCoordinates } from "../geometry/coordinate-types";
|
||||
import { createCaptureCheckpoint } from "./capture-abort";
|
||||
import type { CapturedNode } from "./capture-types";
|
||||
import type { FrameOwnedAxNode } from "./frame-document";
|
||||
|
||||
/** Bounds retain their raw snapshot document layout units until normalization. */
|
||||
export interface SnapshotLayout {
|
||||
readonly boundsSpace: "snapshot-document-layout";
|
||||
bounds?: number[];
|
||||
/** [clientLeft, clientTop, clientWidth, clientHeight], untransformed local CSS units. */
|
||||
clientRect?: number[];
|
||||
styles: Readonly<Record<string, string>>;
|
||||
}
|
||||
|
||||
export interface DecodedNode extends Omit<CapturedNode, "rect" | "localRect" | "rendered"> {
|
||||
nodeType?: number;
|
||||
parentMissing?: boolean;
|
||||
layout?: SnapshotLayout;
|
||||
}
|
||||
|
||||
export interface NodeFacts extends CapturedNode {
|
||||
nodeType?: number;
|
||||
parentMissing?: boolean;
|
||||
layout?: SnapshotLayout;
|
||||
}
|
||||
|
||||
export interface DocumentIndex<T extends DecodedNode = NodeFacts> {
|
||||
readonly nodes: ReadonlyMap<number, T>;
|
||||
readonly ancestryComplete?: ReadonlyMap<number, boolean>;
|
||||
readonly excludedBackendNodeIds: ReadonlySet<number>;
|
||||
}
|
||||
|
||||
export interface DecodedDocument {
|
||||
nodes: DecodedNode[];
|
||||
}
|
||||
|
||||
/** All snapshot nodes participate, including document and shadow roots. This
|
||||
* preserves overlay propagation when the semantic adapter omits those nodes. */
|
||||
export async function buildDocumentIndex<T extends DecodedNode>(
|
||||
input: readonly T[],
|
||||
signal?: AbortSignal,
|
||||
includeVisualFacts = false,
|
||||
): Promise<DocumentIndex<T>> {
|
||||
const checkpoint = createCaptureCheckpoint(signal);
|
||||
const nodes = new Map<number, T>();
|
||||
const overlayByNode = new Map<number, boolean>();
|
||||
const ancestryComplete = includeVisualFacts ? new Map<number, boolean>() : undefined;
|
||||
const excludedBackendNodeIds = new Set<number>();
|
||||
for (let i = 0; i < input.length; i++) {
|
||||
if (i % 256 === 0) {
|
||||
const pending = checkpoint();
|
||||
if (pending) await pending;
|
||||
}
|
||||
const node = input[i];
|
||||
nodes.set(node.backendNodeId, node);
|
||||
}
|
||||
let work = 0;
|
||||
for (const node of input) {
|
||||
if (work++ % 256 === 0) {
|
||||
const pending = checkpoint();
|
||||
if (pending) await pending;
|
||||
}
|
||||
if (overlayByNode.has(node.backendNodeId)) continue;
|
||||
const path: DecodedNode[] = [];
|
||||
const visiting = new Set<number>();
|
||||
let current: DecodedNode | undefined = node;
|
||||
let overlay = false;
|
||||
let complete = false;
|
||||
while (current && !overlayByNode.has(current.backendNodeId)) {
|
||||
if (work++ % 256 === 0) {
|
||||
const pending = checkpoint();
|
||||
if (pending) await pending;
|
||||
}
|
||||
if (visiting.has(current.backendNodeId)) {
|
||||
// Only an overlay inside the cycle may mark the cycle and its descendants.
|
||||
overlay = path
|
||||
.slice(path.findIndex((item) => item.backendNodeId === current!.backendNodeId))
|
||||
.some((item) => isOverlayHostNode(item.tag, Object.keys(item.attrs)));
|
||||
break;
|
||||
}
|
||||
visiting.add(current.backendNodeId);
|
||||
path.push(current);
|
||||
if (current.parentBackendNodeId === null) {
|
||||
if (ancestryComplete) complete = !current.parentMissing && current.nodeType === 9;
|
||||
current = undefined;
|
||||
break;
|
||||
}
|
||||
current = nodes.get(current.parentBackendNodeId);
|
||||
}
|
||||
if (current && overlayByNode.has(current.backendNodeId)) {
|
||||
overlay = overlayByNode.get(current.backendNodeId)!;
|
||||
if (ancestryComplete) complete = ancestryComplete.get(current.backendNodeId) === true;
|
||||
}
|
||||
for (let i = path.length - 1; i >= 0; i--) {
|
||||
if (work++ % 256 === 0) {
|
||||
const pending = checkpoint();
|
||||
if (pending) await pending;
|
||||
}
|
||||
const item = path[i];
|
||||
overlay = overlay || isOverlayHostNode(item.tag, Object.keys(item.attrs));
|
||||
overlayByNode.set(item.backendNodeId, overlay);
|
||||
if (ancestryComplete) {
|
||||
complete = complete && !item.parentMissing;
|
||||
ancestryComplete.set(item.backendNodeId, complete);
|
||||
}
|
||||
if (overlay) excludedBackendNodeIds.add(item.backendNodeId);
|
||||
}
|
||||
}
|
||||
return { nodes, ...(ancestryComplete ? { ancestryComplete } : {}), excludedBackendNodeIds };
|
||||
}
|
||||
|
||||
export interface DocumentIdentity {
|
||||
attachmentId: string;
|
||||
target: CdpTarget;
|
||||
frameId: string;
|
||||
documentElementBackendNodeId: number;
|
||||
}
|
||||
|
||||
/** Narrow input shared by the existing semantic scene/hover consumers. */
|
||||
export interface CapturedSceneInput {
|
||||
nodes: CapturedNode[];
|
||||
viewport: Viewport;
|
||||
rootFrameId?: string;
|
||||
excludedBackendNodeIds: ReadonlySet<number>;
|
||||
}
|
||||
|
||||
export interface CaptureIssue {
|
||||
/** Owner failure or inherited blockage; absent for other geometry failures. */
|
||||
projectionIssue?: FrameProjectionIssue;
|
||||
target: CdpTarget;
|
||||
frameId?: string;
|
||||
stage: "dom" | "ax" | "identity" | "ownership" | "geometry" | "forms";
|
||||
reason:
|
||||
| "document-changed"
|
||||
| "identity-unavailable"
|
||||
| "identity-unverified"
|
||||
| "capture-unavailable"
|
||||
| "frame-ownership-unresolved"
|
||||
| "geometry-unavailable";
|
||||
}
|
||||
|
||||
/** Shared per document; never retain the live GeometryContext in published facts. */
|
||||
export interface DocumentGeometry {
|
||||
readonly projections: readonly GeometryProjection[];
|
||||
readonly coordinates: SnapshotCoordinates;
|
||||
/** Visual viewport scale (pinch), distinct from browser UI zoom. */
|
||||
readonly pageScale?: number;
|
||||
}
|
||||
|
||||
export interface DocumentFacts<T extends FrameOwnedAxNode> {
|
||||
readonly geometry?: DocumentGeometry;
|
||||
readonly frame: CdpFrame;
|
||||
readonly identity?: DocumentIdentity;
|
||||
readonly index: DocumentIndex;
|
||||
readonly domNodes: CapturedNode[];
|
||||
readonly axNodes: T[];
|
||||
}
|
||||
|
||||
export interface ObservationFacts<T extends FrameOwnedAxNode> {
|
||||
/** Whether visual collection was enabled; partial capture failures remain in issues. */
|
||||
readonly visualFactsCollected: boolean;
|
||||
readonly rootFrameId: string;
|
||||
readonly viewport: Viewport;
|
||||
readonly documents: readonly DocumentFacts<T>[];
|
||||
readonly issues: readonly CaptureIssue[];
|
||||
readonly startedAt: number;
|
||||
readonly finishedAt: number;
|
||||
}
|
||||
|
||||
export interface CapturedSurfaceProbe {
|
||||
triggerBackendNodeId: number;
|
||||
triggerPoint?: { x: number; y: number };
|
||||
triggerAction: "hover" | "focus" | string;
|
||||
subItems: string[];
|
||||
confidence?: "high" | "medium" | "low";
|
||||
}
|
||||
|
||||
export type { CapturedNode } from "./capture-types";
|
||||
@@ -1,155 +0,0 @@
|
||||
import type { CdpRunner } from "../shared";
|
||||
import { isAbortError, throwIfAborted } from "./capture-abort";
|
||||
import type { CapturedNode } from "./capture-types";
|
||||
|
||||
interface RuntimeEvaluateReply {
|
||||
result?: { deepSerializedValue?: DeepSerializedValue };
|
||||
}
|
||||
const MAX_FORM_ENRICH_CONTROLS = 250;
|
||||
|
||||
interface CapturedFormState {
|
||||
value?: string;
|
||||
defaultValue?: string;
|
||||
placeholder?: string;
|
||||
state?: "empty" | "filled" | "default";
|
||||
sensitive?: boolean;
|
||||
}
|
||||
|
||||
interface DeepSerializedValue {
|
||||
type: string;
|
||||
value?: unknown;
|
||||
}
|
||||
|
||||
function formStateBatchExpression(maxControls: number): string {
|
||||
return `(() => {
|
||||
const maxControls = ${JSON.stringify(maxControls)};
|
||||
let remaining = maxControls;
|
||||
const controlSelector = "input,textarea,select";
|
||||
const controlState = (el) => {
|
||||
const tag = el.tagName.toLowerCase();
|
||||
const type = tag === "input" ? String(el.type || "text").toLowerCase() : tag;
|
||||
const sensitive = type === "password" || type === "credit-card";
|
||||
const rawValue = typeof el.value === "string" ? el.value : "";
|
||||
const defaultValue = typeof el.defaultValue === "string" ? el.defaultValue : "";
|
||||
const placeholder = typeof el.placeholder === "string" ? el.placeholder : "";
|
||||
const state = rawValue === "" ? "empty" : rawValue === defaultValue ? "default" : "filled";
|
||||
return {
|
||||
state,
|
||||
sensitive,
|
||||
placeholder,
|
||||
...(sensitive ? {} : { value: rawValue, defaultValue }),
|
||||
};
|
||||
};
|
||||
const controls = [];
|
||||
const collect = (doc) => {
|
||||
for (const el of Array.from(doc.querySelectorAll(controlSelector))) {
|
||||
if (remaining <= 0) break;
|
||||
// Deep serialization supplies the node's backend id. Keep the
|
||||
// state as JSON so decoding needs no general-purpose V8 deserializer.
|
||||
controls.push([el, JSON.stringify(controlState(el))]);
|
||||
remaining -= 1;
|
||||
}
|
||||
for (const frame of Array.from(doc.querySelectorAll("iframe"))) {
|
||||
if (remaining <= 0) break;
|
||||
let childDoc = null;
|
||||
try { childDoc = frame.contentDocument; } catch { childDoc = null; }
|
||||
if (childDoc) collect(childDoc);
|
||||
}
|
||||
};
|
||||
collect(document);
|
||||
return controls;
|
||||
})()`;
|
||||
}
|
||||
|
||||
function formStatesByBackendId(result: RuntimeEvaluateReply): Map<number, CapturedFormState> {
|
||||
const states = new Map<number, CapturedFormState>();
|
||||
const serialized = result.result?.deepSerializedValue;
|
||||
if (serialized?.type !== "array" || !Array.isArray(serialized.value)) return states;
|
||||
for (const entry of serialized.value as DeepSerializedValue[]) {
|
||||
if (entry?.type !== "array" || !Array.isArray(entry.value)) continue;
|
||||
const [element, json] = entry.value as DeepSerializedValue[];
|
||||
if (element?.type !== "node" || json?.type !== "string" || typeof json.value !== "string") {
|
||||
continue;
|
||||
}
|
||||
const backendNodeId = (element.value as { backendNodeId?: number } | undefined)?.backendNodeId;
|
||||
if (typeof backendNodeId !== "number" || !Number.isSafeInteger(backendNodeId)) continue;
|
||||
try {
|
||||
const state = JSON.parse(json.value) as CapturedFormState | null;
|
||||
if (
|
||||
!state ||
|
||||
!["empty", "filled", "default"].includes(state.state ?? "") ||
|
||||
typeof state.sensitive !== "boolean" ||
|
||||
typeof state.placeholder !== "string" ||
|
||||
(!state.sensitive &&
|
||||
(typeof state.value !== "string" || typeof state.defaultValue !== "string"))
|
||||
) {
|
||||
continue;
|
||||
}
|
||||
states.set(backendNodeId, state);
|
||||
} catch {
|
||||
// A malformed entry must not overwrite the snapshot's own state.
|
||||
}
|
||||
}
|
||||
return states;
|
||||
}
|
||||
|
||||
function applyFormStates(nodes: CapturedNode[], states: Map<number, CapturedFormState>): void {
|
||||
for (const node of nodes) {
|
||||
if (!["input", "textarea", "select"].includes(node.tag)) continue;
|
||||
const state = states.get(node.backendNodeId);
|
||||
if (!state) continue;
|
||||
node.formState = state.state;
|
||||
node.formPlaceholder = state.placeholder ?? "";
|
||||
if (
|
||||
state.sensitive ||
|
||||
(node.tag === "input" && (node.attrs.type ?? "").toLowerCase() === "password")
|
||||
) {
|
||||
delete node.formValue;
|
||||
delete node.formDefaultValue;
|
||||
delete node.attrs.value;
|
||||
} else {
|
||||
node.formDefaultValue = state.defaultValue ?? "";
|
||||
if (state.value !== undefined) node.formValue = state.value;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
export async function enrichFormControlStates(
|
||||
cdp: CdpRunner,
|
||||
tabId: number,
|
||||
frameNodeGroups: CapturedNode[][],
|
||||
signal?: AbortSignal,
|
||||
): Promise<boolean> {
|
||||
const hasControls = frameNodeGroups.some((nodes) =>
|
||||
nodes.some((node) => ["input", "textarea", "select"].includes(node.tag)),
|
||||
);
|
||||
if (!hasControls) return true;
|
||||
const objectGroup = `bsk-vom-forms-${crypto.randomUUID()}`;
|
||||
try {
|
||||
throwIfAborted(signal);
|
||||
const result = await cdp.send<RuntimeEvaluateReply>(tabId, "Runtime.evaluate", {
|
||||
expression: formStateBatchExpression(MAX_FORM_ENRICH_CONTROLS),
|
||||
objectGroup,
|
||||
serializationOptions: {
|
||||
serialization: "deep",
|
||||
maxDepth: 3,
|
||||
additionalParameters: { maxNodeDepth: 0, includeShadowTree: "none" },
|
||||
},
|
||||
});
|
||||
throwIfAborted(signal);
|
||||
// Backend ids are scoped to this capture's CDP target. OOPIF targets
|
||||
// have separate enrichment calls and never share this lookup.
|
||||
const states = formStatesByBackendId(result);
|
||||
for (const nodes of frameNodeGroups) {
|
||||
applyFormStates(nodes, states);
|
||||
}
|
||||
return true;
|
||||
} catch (error) {
|
||||
if (isAbortError(error)) throw error;
|
||||
// Best-effort enrichment. DOMSnapshot/AX data still carries the nodes.
|
||||
return false;
|
||||
} finally {
|
||||
await cdp.send(tabId, "Runtime.releaseObjectGroup", { objectGroup }).catch(() => undefined);
|
||||
throwIfAborted(signal);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,181 @@
|
||||
import type { CdpFrame, CdpFrameGraph } from "@/browser-driver/frame-graph";
|
||||
import { resolveFrameProjection } from "../frame-geometry";
|
||||
import { type GeometryProjection, projectRectToViewport } from "../geometry";
|
||||
import { type CdpRunner, cdpRunnerForTarget, sendToCdpTarget } from "../shared";
|
||||
import { type CapturedNode, type CapturedViewModel, captureViewModel } from "./capture";
|
||||
import {
|
||||
buildFrameDocuments,
|
||||
type FrameAxBatch,
|
||||
type FrameDocument,
|
||||
type FrameOwnedAxNode,
|
||||
} from "./frame-document";
|
||||
|
||||
export type FrameAxNode = FrameOwnedAxNode;
|
||||
export type CapturedFrameDocument<T extends FrameAxNode> = FrameDocument<T>;
|
||||
|
||||
function throwIfAborted(signal?: AbortSignal): void {
|
||||
if (signal?.aborted) throw new DOMException("observation aborted", "AbortError");
|
||||
}
|
||||
|
||||
function isAbortError(err: unknown): boolean {
|
||||
return err instanceof Error && err.name === "AbortError";
|
||||
}
|
||||
|
||||
async function discoverFrameGraph(cdp: CdpRunner, tabId: number): Promise<CdpFrameGraph | null> {
|
||||
if (!cdp.getFrameGraph) return null;
|
||||
try {
|
||||
return await cdp.getFrameGraph(tabId);
|
||||
} catch (err) {
|
||||
console.debug("[bsk observation] frame graph capture failed", err);
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
function transformFrameNodes(
|
||||
nodes: CapturedNode[],
|
||||
projection: GeometryProjection | null,
|
||||
): CapturedNode[] {
|
||||
return nodes.map((node) => ({
|
||||
...node,
|
||||
rect: projection
|
||||
? (() => {
|
||||
const bounds = projectRectToViewport(node.rect, projection);
|
||||
return bounds ? { x: bounds.x, y: bounds.y, w: bounds.width, h: bounds.height } : null;
|
||||
})()
|
||||
: null,
|
||||
}));
|
||||
}
|
||||
|
||||
async function captureMissingFrameDocuments(
|
||||
cdp: CdpRunner,
|
||||
tabId: number,
|
||||
graph: CdpFrameGraph,
|
||||
captured: CapturedViewModel,
|
||||
signal?: AbortSignal,
|
||||
): Promise<void> {
|
||||
if (!captured.frameNodes) captured.frameNodes = new Map();
|
||||
if (!captured.frameOwnerBackendNodeIds) captured.frameOwnerBackendNodeIds = new Map();
|
||||
if (!captured.frameParentIds) captured.frameParentIds = new Map();
|
||||
|
||||
for (const frame of graph.frames) {
|
||||
if (!frame.target.sessionId || captured.frameNodes.has(frame.frameId)) continue;
|
||||
try {
|
||||
const child = await captureViewModel(cdpRunnerForTarget(cdp, frame.target), tabId, {
|
||||
signal,
|
||||
});
|
||||
let projection: GeometryProjection | null = null;
|
||||
try {
|
||||
projection = await resolveFrameProjection(cdp, graph, frame.frameId);
|
||||
} catch (err) {
|
||||
if (isAbortError(err)) throw err;
|
||||
console.debug("[bsk observation] child frame geometry projection failed", {
|
||||
frameId: frame.frameId,
|
||||
err,
|
||||
});
|
||||
}
|
||||
const rootFrameId = child.rootFrameId ?? frame.frameId;
|
||||
const childFrames = child.frameNodes ?? new Map<string, CapturedNode[]>();
|
||||
if (!childFrames.has(rootFrameId)) childFrames.set(rootFrameId, child.nodes);
|
||||
if (rootFrameId !== frame.frameId && !childFrames.has(frame.frameId)) {
|
||||
childFrames.set(
|
||||
frame.frameId,
|
||||
child.nodes.map((node) => ({ ...node, frameId: frame.frameId })),
|
||||
);
|
||||
}
|
||||
for (const [childFrameId, nodes] of childFrames) {
|
||||
captured.frameNodes.set(childFrameId, transformFrameNodes(nodes, projection));
|
||||
}
|
||||
if (frame.ownerBackendNodeId !== undefined) {
|
||||
captured.iframeNodes.set(
|
||||
frame.ownerBackendNodeId,
|
||||
captured.frameNodes.get(frame.frameId) ?? [],
|
||||
);
|
||||
captured.frameOwnerBackendNodeIds.set(frame.frameId, frame.ownerBackendNodeId);
|
||||
}
|
||||
if (frame.parentFrameId) captured.frameParentIds.set(frame.frameId, frame.parentFrameId);
|
||||
for (const [childFrameId, ownerBackendNodeId] of child.frameOwnerBackendNodeIds ?? []) {
|
||||
captured.frameOwnerBackendNodeIds.set(childFrameId, ownerBackendNodeId);
|
||||
}
|
||||
for (const [childFrameId, parentFrameId] of child.frameParentIds ?? []) {
|
||||
captured.frameParentIds.set(childFrameId, parentFrameId);
|
||||
}
|
||||
} catch (err) {
|
||||
if (isAbortError(err)) throw err;
|
||||
console.debug("[bsk observation] child frame DOM capture failed", {
|
||||
frameId: frame.frameId,
|
||||
err,
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async function captureAxTrees<T extends FrameAxNode>(
|
||||
cdp: CdpRunner,
|
||||
tabId: number,
|
||||
discoveredFrames: CdpFrame[],
|
||||
captured: CapturedViewModel,
|
||||
signal?: AbortSignal,
|
||||
): Promise<FrameAxBatch<T>[]> {
|
||||
let frames = [...discoveredFrames];
|
||||
const capturedFrameIds = [...(captured.frameNodes?.keys() ?? [])];
|
||||
if (frames.length === 0) {
|
||||
const rootFrameId = captured.rootFrameId ?? capturedFrameIds[0] ?? "root";
|
||||
frames = [{ frameId: rootFrameId, target: { tabId } }];
|
||||
}
|
||||
for (const frameId of capturedFrameIds) {
|
||||
if (!frames.some((frame) => frame.frameId === frameId)) {
|
||||
frames.push({ frameId, target: { tabId } });
|
||||
}
|
||||
}
|
||||
|
||||
let firstFailure: unknown;
|
||||
const trees = await Promise.all(
|
||||
frames.map(async (frame): Promise<FrameAxBatch<T>> => {
|
||||
try {
|
||||
throwIfAborted(signal);
|
||||
await sendToCdpTarget(cdp, frame.target, "Accessibility.enable", {});
|
||||
const result = await sendToCdpTarget<{ nodes?: T[] }>(
|
||||
cdp,
|
||||
frame.target,
|
||||
"Accessibility.getFullAXTree",
|
||||
frame.frameId === "root" ? {} : { frameId: frame.frameId },
|
||||
);
|
||||
throwIfAborted(signal);
|
||||
return {
|
||||
frame,
|
||||
nodes: result.nodes ?? [],
|
||||
};
|
||||
} catch (err) {
|
||||
if (isAbortError(err)) throw err;
|
||||
firstFailure ??= err;
|
||||
console.debug("[bsk observation] frame AX capture failed", {
|
||||
frameId: frame.frameId,
|
||||
err,
|
||||
});
|
||||
return { frame, nodes: [] };
|
||||
}
|
||||
}),
|
||||
);
|
||||
const capturedNodeCount = [...captured.iframeNodes.values()].reduce(
|
||||
(count, nodes) => count + nodes.length,
|
||||
captured.nodes.length,
|
||||
);
|
||||
if (firstFailure && capturedNodeCount === 0 && trees.every((tree) => tree.nodes.length === 0)) {
|
||||
throw firstFailure;
|
||||
}
|
||||
return trees;
|
||||
}
|
||||
|
||||
export async function captureFrameData<T extends FrameAxNode>(
|
||||
cdp: CdpRunner,
|
||||
tabId: number,
|
||||
captured: CapturedViewModel,
|
||||
signal?: AbortSignal,
|
||||
): Promise<CapturedFrameDocument<T>[]> {
|
||||
const graph = await discoverFrameGraph(cdp, tabId);
|
||||
const frames = graph?.frames ?? [];
|
||||
if (graph) await captureMissingFrameDocuments(cdp, tabId, graph, captured, signal);
|
||||
throwIfAborted(signal);
|
||||
const batches = await captureAxTrees<T>(cdp, tabId, frames, captured, signal);
|
||||
return buildFrameDocuments(graph, batches, captured);
|
||||
}
|
||||
@@ -4,8 +4,7 @@ import {
|
||||
type CdpTarget,
|
||||
cdpTargetKey,
|
||||
} from "@/browser-driver/frame-graph";
|
||||
import { createCaptureCheckpoint } from "./capture-abort";
|
||||
import type { CapturedNode } from "./capture-types";
|
||||
import type { CapturedNode, CapturedViewModel } from "./capture";
|
||||
|
||||
export interface FrameOwnedAxNode {
|
||||
nodeId: string;
|
||||
@@ -24,15 +23,6 @@ export interface FrameDocument<T extends FrameOwnedAxNode> extends CdpFrame {
|
||||
contextScopeId: string;
|
||||
axNodes: T[];
|
||||
domNodes: CapturedNode[];
|
||||
excludedBackendNodeIds?: ReadonlySet<number>;
|
||||
}
|
||||
|
||||
/** Explicit snapshot document data used to join DOM and AX ownership. */
|
||||
export interface FrameDomInput {
|
||||
nodes: CapturedNode[];
|
||||
rootFrameId?: string;
|
||||
frameNodes?: ReadonlyMap<string, CapturedNode[]>;
|
||||
frameExcludedBackendNodeIds?: ReadonlyMap<string, ReadonlySet<number>>;
|
||||
}
|
||||
|
||||
interface Ownership {
|
||||
@@ -57,25 +47,35 @@ function targetBackendKey(target: CdpTarget, backendNodeId: number): string {
|
||||
function frameList<T extends FrameOwnedAxNode>(
|
||||
graph: CdpFrameGraph | null,
|
||||
batches: FrameAxBatch<T>[],
|
||||
captured: CapturedViewModel,
|
||||
): CdpFrame[] {
|
||||
const frames = new Map<string, CdpFrame>();
|
||||
for (const frame of graph?.frames ?? []) frames.set(frame.frameId, frame);
|
||||
for (const batch of batches) {
|
||||
if (!frames.has(batch.frame.frameId)) frames.set(batch.frame.frameId, batch.frame);
|
||||
}
|
||||
return [...frames.values()];
|
||||
for (const frameId of captured.frameNodes?.keys() ?? []) {
|
||||
if (!frames.has(frameId))
|
||||
frames.set(frameId, { frameId, target: { tabId: batches[0]?.frame.target.tabId ?? 0 } });
|
||||
}
|
||||
return [...frames.values()].map((frame) => {
|
||||
const ownerBackendNodeId =
|
||||
frame.ownerBackendNodeId ?? captured.frameOwnerBackendNodeIds?.get(frame.frameId);
|
||||
const parentFrameId = frame.parentFrameId ?? captured.frameParentIds?.get(frame.frameId);
|
||||
return {
|
||||
...frame,
|
||||
...(ownerBackendNodeId !== undefined ? { ownerBackendNodeId } : {}),
|
||||
...(parentFrameId ? { parentFrameId } : {}),
|
||||
};
|
||||
});
|
||||
}
|
||||
|
||||
export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
|
||||
export function buildFrameDocuments<T extends FrameOwnedAxNode>(
|
||||
graph: CdpFrameGraph | null,
|
||||
batches: FrameAxBatch<T>[],
|
||||
captured: FrameDomInput,
|
||||
signal?: AbortSignal,
|
||||
unresolved?: (frame: CdpFrame) => void,
|
||||
): Promise<FrameDocument<T>[]> {
|
||||
const checkpoint = createCaptureCheckpoint(signal);
|
||||
let work = 0;
|
||||
const frames = frameList(graph, batches);
|
||||
captured: CapturedViewModel,
|
||||
): FrameDocument<T>[] {
|
||||
const frames = frameList(graph, batches, captured);
|
||||
const frameById = new Map(frames.map((frame) => [frame.frameId, frame]));
|
||||
const rootFrameId = graph?.rootFrameId ?? captured.rootFrameId ?? frames[0]?.frameId;
|
||||
const domNodesForFrame = (frameId: string): CapturedNode[] =>
|
||||
@@ -83,80 +83,54 @@ export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
|
||||
const backendOwner = new Map<string, string>();
|
||||
for (const frame of frames) {
|
||||
for (const node of domNodesForFrame(frame.frameId)) {
|
||||
if (work++ % 256 === 0) {
|
||||
const pending = checkpoint();
|
||||
if (pending) await pending;
|
||||
}
|
||||
backendOwner.set(targetBackendKey(frame.target, node.backendNodeId), frame.frameId);
|
||||
}
|
||||
}
|
||||
|
||||
const candidates = new Map<string, OwnedCandidate<T>>();
|
||||
for (const batch of batches) {
|
||||
const nodeById = new Map<string, T>();
|
||||
for (const node of batch.nodes) {
|
||||
if (work++ % 256 === 0) {
|
||||
const pending = checkpoint();
|
||||
if (pending) await pending;
|
||||
}
|
||||
nodeById.set(node.nodeId, node);
|
||||
}
|
||||
let reported = false;
|
||||
const nodeById = new Map(batch.nodes.map((node) => [node.nodeId, node]));
|
||||
const ownershipByNodeId = new Map<string, Ownership>();
|
||||
for (const node of batch.nodes) {
|
||||
const path: T[] = [];
|
||||
const visiting = new Set<string>();
|
||||
let current: T | undefined = node;
|
||||
let ownership: Ownership = { frameId: batch.frame.frameId, strength: 1 };
|
||||
while (current) {
|
||||
if (work++ % 256 === 0) {
|
||||
const pending = checkpoint();
|
||||
if (pending) await pending;
|
||||
}
|
||||
const cached = ownershipByNodeId.get(current.nodeId);
|
||||
if (cached) {
|
||||
ownership = cached;
|
||||
break;
|
||||
}
|
||||
if (visiting.has(current.nodeId)) break;
|
||||
visiting.add(current.nodeId);
|
||||
if (current.frameId) {
|
||||
const frame = frameById.get(current.frameId);
|
||||
// An explicit contradiction must not fall through to a guessed owner.
|
||||
if (!frame || cdpTargetKey(frame.target) !== cdpTargetKey(batch.frame.target)) {
|
||||
if (!reported) {
|
||||
unresolved?.(batch.frame);
|
||||
reported = true;
|
||||
}
|
||||
ownership = { frameId: "", strength: 0 };
|
||||
break;
|
||||
}
|
||||
ownership = { frameId: frame.frameId, strength: 4 };
|
||||
ownershipByNodeId.set(current.nodeId, ownership);
|
||||
break;
|
||||
}
|
||||
const frameId =
|
||||
typeof current.backendDOMNodeId === "number"
|
||||
? backendOwner.get(targetBackendKey(batch.frame.target, current.backendDOMNodeId))
|
||||
: undefined;
|
||||
const resolving = new Set<string>();
|
||||
const resolveOwnership = (node: T): Ownership => {
|
||||
const cached = ownershipByNodeId.get(node.nodeId);
|
||||
if (cached) return cached;
|
||||
if (node.frameId && frameById.has(node.frameId)) {
|
||||
const ownership = { frameId: node.frameId, strength: 4 };
|
||||
ownershipByNodeId.set(node.nodeId, ownership);
|
||||
return ownership;
|
||||
}
|
||||
if (typeof node.backendDOMNodeId === "number") {
|
||||
const frameId = backendOwner.get(
|
||||
targetBackendKey(batch.frame.target, node.backendDOMNodeId),
|
||||
);
|
||||
if (frameId) {
|
||||
ownership = { frameId, strength: 3 };
|
||||
ownershipByNodeId.set(current.nodeId, ownership);
|
||||
break;
|
||||
const ownership = { frameId, strength: 3 };
|
||||
ownershipByNodeId.set(node.nodeId, ownership);
|
||||
return ownership;
|
||||
}
|
||||
path.push(current);
|
||||
current = current.parentId ? nodeById.get(current.parentId) : undefined;
|
||||
}
|
||||
for (let i = path.length - 1; i >= 0; i--) {
|
||||
if (work++ % 256 === 0) {
|
||||
const pending = checkpoint();
|
||||
if (pending) await pending;
|
||||
if (node.parentId && !resolving.has(node.nodeId)) {
|
||||
const parent = nodeById.get(node.parentId);
|
||||
if (parent) {
|
||||
resolving.add(node.nodeId);
|
||||
const inherited = resolveOwnership(parent);
|
||||
resolving.delete(node.nodeId);
|
||||
const ownership = {
|
||||
frameId: inherited.frameId,
|
||||
strength: Math.min(2, inherited.strength),
|
||||
};
|
||||
ownershipByNodeId.set(node.nodeId, ownership);
|
||||
return ownership;
|
||||
}
|
||||
ownership = { frameId: ownership.frameId, strength: Math.min(2, ownership.strength) };
|
||||
ownershipByNodeId.set(path[i].nodeId, ownership);
|
||||
}
|
||||
if (!ownershipByNodeId.has(node.nodeId)) ownershipByNodeId.set(node.nodeId, ownership);
|
||||
if (!ownership.frameId) continue;
|
||||
const ownership = { frameId: batch.frame.frameId, strength: 1 };
|
||||
ownershipByNodeId.set(node.nodeId, ownership);
|
||||
return ownership;
|
||||
};
|
||||
|
||||
for (const node of batch.nodes) {
|
||||
const ownership = resolveOwnership(node);
|
||||
const key = targetNodeKey(batch.frame.target, node.nodeId);
|
||||
const existing = candidates.get(key);
|
||||
if (!existing || ownership.strength > existing.ownership.strength) {
|
||||
@@ -170,10 +144,6 @@ export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
|
||||
);
|
||||
const axNodesByFrame = new Map<string, T[]>();
|
||||
for (const candidate of candidates.values()) {
|
||||
if (work++ % 256 === 0) {
|
||||
const pending = checkpoint();
|
||||
if (pending) await pending;
|
||||
}
|
||||
const { node, target, ownership } = candidate;
|
||||
const parentFrameId = node.parentId
|
||||
? ownershipByTargetNode.get(targetNodeKey(target, node.parentId))
|
||||
@@ -199,6 +169,5 @@ export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
|
||||
contextScopeId: frame.frameId,
|
||||
axNodes: axNodesByFrame.get(frame.frameId) ?? [],
|
||||
domNodes: domNodesForFrame(frame.frameId),
|
||||
excludedBackendNodeIds: captured.frameExcludedBackendNodeIds?.get(frame.frameId),
|
||||
}));
|
||||
}
|
||||
|
||||
@@ -1,356 +0,0 @@
|
||||
import type { Viewport } from "@browser-skill/vom";
|
||||
import { type CdpFrame, type CdpTarget, cdpTargetKey } from "@/browser-driver/frame-graph";
|
||||
import { type GeometryProjection, projectRectToViewport } from "../geometry";
|
||||
import {
|
||||
type FrameProjectionState,
|
||||
projectSnapshotRect,
|
||||
type SnapshotCoordinates,
|
||||
snapshotCoordinates,
|
||||
snapshotViewportRect,
|
||||
} from "../geometry/coordinate-types";
|
||||
import {
|
||||
GeometryContext,
|
||||
type LayoutMetrics,
|
||||
snapshotLayoutScale,
|
||||
} from "../geometry/frame-context";
|
||||
import {
|
||||
createCaptureCheckpoint,
|
||||
isAbortError as isCaptureAbort,
|
||||
throwIfAborted as throwCaptureAborted,
|
||||
} from "./capture-abort";
|
||||
import {
|
||||
buildDocumentIndex,
|
||||
type CaptureIssue,
|
||||
type DocumentGeometry,
|
||||
type DocumentIndex,
|
||||
type NodeFacts,
|
||||
} from "./facts";
|
||||
import {
|
||||
BASIC_SNAPSHOT,
|
||||
decodeDocument,
|
||||
type SnapshotDocument,
|
||||
type SnapshotProfile,
|
||||
type SnapshotReply,
|
||||
snapshotFrameId,
|
||||
} from "./snapshot";
|
||||
|
||||
export interface FrameContext {
|
||||
frameId?: string;
|
||||
ownerFrameBackendNodeId: number | null;
|
||||
projection: FrameProjectionState | null;
|
||||
targetProjection?: GeometryProjection | null;
|
||||
target: CdpTarget;
|
||||
coordinates: SnapshotCoordinates | null;
|
||||
pageScale?: number;
|
||||
}
|
||||
|
||||
export interface NormalizedDocument {
|
||||
geometry?: DocumentGeometry;
|
||||
nodes: NodeFacts[];
|
||||
index: DocumentIndex;
|
||||
documentElementBackendNodeId?: number;
|
||||
}
|
||||
|
||||
/** Interpret one document using a supplied projection. No live reads or frame scheduling. */
|
||||
export async function normalizeDocument(
|
||||
doc: SnapshotDocument,
|
||||
strings: string[],
|
||||
context: FrameContext,
|
||||
signal?: AbortSignal,
|
||||
profile: SnapshotProfile = BASIC_SNAPSHOT,
|
||||
): Promise<NormalizedDocument> {
|
||||
const decoded = await decodeDocument(doc, strings, signal, profile);
|
||||
const checkpoint = createCaptureCheckpoint(signal);
|
||||
const nodes: NodeFacts[] = [];
|
||||
for (let i = 0; i < decoded.nodes.length; i++) {
|
||||
if (i % 256 === 0) {
|
||||
const pending = checkpoint();
|
||||
if (pending) await pending;
|
||||
}
|
||||
const node = decoded.nodes[i];
|
||||
const bounds = node.layout?.bounds ?? [];
|
||||
const input = snapshotViewportRect(
|
||||
bounds,
|
||||
{ target: context.target, frameId: context.frameId },
|
||||
context.coordinates,
|
||||
);
|
||||
const local = input?.rect;
|
||||
let rect =
|
||||
input && context.projection?.status === "available"
|
||||
? projectSnapshotRect(input, context.projection.projection)
|
||||
: null;
|
||||
if (rect && context.targetProjection !== undefined)
|
||||
rect = context.targetProjection
|
||||
? projectRectToViewport(
|
||||
{ x: rect.x, y: rect.y, w: rect.width, h: rect.height },
|
||||
context.targetProjection,
|
||||
)
|
||||
: null;
|
||||
const visibility = node.layout?.styles.visibility || "visible";
|
||||
const opacity = node.layout?.styles.opacity || "1";
|
||||
nodes.push({
|
||||
...node,
|
||||
...(context.frameId ? { frameId: context.frameId } : {}),
|
||||
ownerFrameBackendNodeId: context.ownerFrameBackendNodeId,
|
||||
localRect: local ? { x: local.x, y: local.y, w: local.width, h: local.height } : null,
|
||||
rect: rect ? { x: rect.x, y: rect.y, w: rect.width, h: rect.height } : null,
|
||||
rendered:
|
||||
bounds.length >= 4 &&
|
||||
bounds.slice(0, 4).every(Number.isFinite) &&
|
||||
bounds[2] > 0 &&
|
||||
bounds[3] > 0 &&
|
||||
visibility !== "hidden" &&
|
||||
visibility !== "collapse" &&
|
||||
(Number.parseFloat(opacity) || 0) > 0,
|
||||
});
|
||||
}
|
||||
const index = await buildDocumentIndex(nodes, signal, profile.includeVisualFacts);
|
||||
return {
|
||||
nodes: nodes.filter(
|
||||
(node) => !node.tag.startsWith("#") && !index.excludedBackendNodeIds.has(node.backendNodeId),
|
||||
),
|
||||
index,
|
||||
...(profile.includeVisualFacts &&
|
||||
context.coordinates &&
|
||||
context.projection?.status === "available" &&
|
||||
context.targetProjection !== null
|
||||
? {
|
||||
geometry: {
|
||||
projections: [
|
||||
context.projection.projection.geometry,
|
||||
...(context.targetProjection ? [context.targetProjection] : []),
|
||||
],
|
||||
coordinates: context.coordinates,
|
||||
pageScale: context.pageScale,
|
||||
},
|
||||
}
|
||||
: {}),
|
||||
documentElementBackendNodeId: nodes.find(
|
||||
(node) =>
|
||||
node.nodeType === 1 &&
|
||||
node.parentBackendNodeId !== null &&
|
||||
index.nodes.get(node.parentBackendNodeId)?.nodeType === 9,
|
||||
)?.backendNodeId,
|
||||
};
|
||||
}
|
||||
|
||||
export interface NormalizedFrameDocument extends NormalizedDocument {
|
||||
frame: CdpFrame;
|
||||
}
|
||||
|
||||
/** One target's snapshot. Source ownership is checked before interpreting any
|
||||
* coordinates. Snapshot and live quad coordinates are deliberately not conflated. */
|
||||
export async function normalizeSnapshot(
|
||||
snapshot: SnapshotReply,
|
||||
target: CdpTarget,
|
||||
frames: readonly CdpFrame[],
|
||||
geometry: GeometryContext,
|
||||
issues: CaptureIssue[],
|
||||
signal?: AbortSignal,
|
||||
rootFrameId?: string,
|
||||
profile: SnapshotProfile = BASIC_SNAPSHOT,
|
||||
): Promise<NormalizedFrameDocument[]> {
|
||||
const strings = snapshot.strings ?? [];
|
||||
const raw = snapshot.documents ?? [];
|
||||
const ownerIds = new Set<number>();
|
||||
for (const document of raw) {
|
||||
for (const index of document.nodes?.contentDocumentIndex?.index ?? []) {
|
||||
const id = document.nodes?.backendNodeId?.[index];
|
||||
if (id !== undefined) ownerIds.add(id);
|
||||
}
|
||||
}
|
||||
geometry.registerSnapshotOwners(target, ownerIds);
|
||||
const frameById = new Map(frames.map((frame) => [frame.frameId, frame]));
|
||||
const sources = new Map<string, SnapshotDocument>();
|
||||
for (const doc of raw) {
|
||||
const id = snapshotFrameId(doc, strings);
|
||||
if (!id || !frameById.has(id) || sources.has(id)) {
|
||||
issues.push({
|
||||
target,
|
||||
frameId: id,
|
||||
stage: "ownership",
|
||||
reason: "frame-ownership-unresolved",
|
||||
});
|
||||
continue;
|
||||
}
|
||||
sources.set(id, doc);
|
||||
}
|
||||
let metrics: LayoutMetrics = {};
|
||||
try {
|
||||
metrics = await geometry.layoutMetrics(target);
|
||||
} catch (error) {
|
||||
if (isCaptureAbort(error)) throw error;
|
||||
}
|
||||
const viewport: Viewport = {
|
||||
width: metrics.cssLayoutViewport?.clientWidth ?? 0,
|
||||
height: metrics.cssLayoutViewport?.clientHeight ?? 0,
|
||||
};
|
||||
const layoutUnitsPerCssPixel = snapshotLayoutScale(metrics);
|
||||
const viewportAvailable = [viewport.width, viewport.height].every(
|
||||
(size) => Number.isFinite(size) && size > 0,
|
||||
);
|
||||
|
||||
const children = new Map<string, CdpFrame[]>();
|
||||
const pending: CdpFrame[] = [];
|
||||
for (const frame of frames) {
|
||||
if (!frame.parentFrameId || !frameById.has(frame.parentFrameId)) pending.push(frame);
|
||||
else {
|
||||
const siblings = children.get(frame.parentFrameId);
|
||||
if (siblings) siblings.push(frame);
|
||||
else children.set(frame.parentFrameId, [frame]);
|
||||
}
|
||||
}
|
||||
const projections = new Map<string, FrameProjectionState | null>();
|
||||
const result: NormalizedFrameDocument[] = [];
|
||||
let targetProjection: GeometryProjection | null = null;
|
||||
const targetRoot = rootFrameId ? frameById.get(rootFrameId) : undefined;
|
||||
if (target.sessionId && targetRoot) {
|
||||
try {
|
||||
const known = await geometry.frame(targetRoot.frameId);
|
||||
if (known && cdpTargetKey(known.target) === cdpTargetKey(target))
|
||||
targetProjection = await geometry.targetProjection(targetRoot.frameId);
|
||||
} catch (error) {
|
||||
if (isCaptureAbort(error)) throw error;
|
||||
}
|
||||
}
|
||||
const checkpoint = createCaptureCheckpoint(signal);
|
||||
const visited = new Set<string>();
|
||||
const remaining = frames[Symbol.iterator]();
|
||||
for (let cursor = 0; visited.size < frames.length; cursor++) {
|
||||
if (cursor >= pending.length) {
|
||||
let next = remaining.next();
|
||||
while (!next.done && visited.has(next.value.frameId)) next = remaining.next();
|
||||
if (next.done) break;
|
||||
pending.push(next.value);
|
||||
}
|
||||
if (cursor % 256 === 0) {
|
||||
const pending = checkpoint();
|
||||
if (pending) await pending;
|
||||
}
|
||||
const frame = pending[cursor];
|
||||
if (visited.has(frame.frameId)) continue;
|
||||
visited.add(frame.frameId);
|
||||
for (const child of children.get(frame.frameId) ?? []) pending.push(child);
|
||||
const doc = sources.get(frame.frameId);
|
||||
if (!doc) continue;
|
||||
const source = { target, frameId: frame.frameId };
|
||||
const coordinates = snapshotCoordinates(
|
||||
doc,
|
||||
layoutUnitsPerCssPixel,
|
||||
frame.frameId === rootFrameId
|
||||
? { x: metrics.cssLayoutViewport?.pageX, y: metrics.cssLayoutViewport?.pageY }
|
||||
: undefined,
|
||||
);
|
||||
let state: FrameProjectionState | null =
|
||||
frame.frameId === rootFrameId
|
||||
? viewportAvailable && coordinates
|
||||
? {
|
||||
status: "available",
|
||||
projection: {
|
||||
source,
|
||||
geometry: { sourceClips: [], edges: [], topViewport: viewport },
|
||||
},
|
||||
}
|
||||
: { status: "unavailable", source, reason: "snapshot-coordinates-unavailable" }
|
||||
: (projections.get(frame.frameId) ?? null);
|
||||
if (!state && frame.frameId !== rootFrameId)
|
||||
issues.push({
|
||||
target,
|
||||
frameId: frame.frameId,
|
||||
stage: "ownership",
|
||||
reason: "frame-ownership-unresolved",
|
||||
});
|
||||
if (!coordinates && (!state || state.status === "available"))
|
||||
state = { status: "unavailable", source, reason: "snapshot-coordinates-unavailable" };
|
||||
projections.set(frame.frameId, state);
|
||||
const projection = state?.status === "available" ? state.projection : null;
|
||||
if (!projection || (target.sessionId && !targetProjection))
|
||||
issues.push({
|
||||
target,
|
||||
frameId: frame.frameId,
|
||||
stage: "geometry",
|
||||
reason: "geometry-unavailable",
|
||||
...(state && state.status !== "available" ? { projectionIssue: state } : {}),
|
||||
});
|
||||
|
||||
// Only direct siblings share this pool. Keep normalization in its existing
|
||||
// breadth-first order, independent of owner read completion order.
|
||||
const siblings = (children.get(frame.frameId) ?? []).filter((child) =>
|
||||
sources.has(child.frameId),
|
||||
);
|
||||
const edge = projection?.geometry.edges[0];
|
||||
const clips = edge
|
||||
? [edge.destinationQuad, ...(edge.destinationClips ?? [])]
|
||||
: (projection?.geometry.sourceClips ?? []);
|
||||
let next = 0;
|
||||
let failure: unknown;
|
||||
await Promise.all(
|
||||
Array.from({ length: Math.min(4, siblings.length) }, async () => {
|
||||
while (next < siblings.length && !signal?.aborted && !failure) {
|
||||
const child = siblings[next++];
|
||||
const childSource = { target, frameId: child.frameId };
|
||||
if (!projection) {
|
||||
projections.set(
|
||||
child.frameId,
|
||||
state && state.status !== "available"
|
||||
? {
|
||||
status: "blocked",
|
||||
source: childSource,
|
||||
cause: state.status === "blocked" ? state.cause : state,
|
||||
}
|
||||
: null,
|
||||
);
|
||||
continue;
|
||||
}
|
||||
if (child.ownerBackendNodeId === undefined) {
|
||||
projections.set(child.frameId, null);
|
||||
continue;
|
||||
}
|
||||
if (!snapshotCoordinates(sources.get(child.frameId)!, layoutUnitsPerCssPixel)) {
|
||||
projections.set(child.frameId, {
|
||||
status: "unavailable",
|
||||
source: childSource,
|
||||
reason: "snapshot-coordinates-unavailable",
|
||||
});
|
||||
continue;
|
||||
}
|
||||
try {
|
||||
projections.set(
|
||||
child.frameId,
|
||||
await geometry.snapshotProjection(
|
||||
childSource,
|
||||
child.ownerBackendNodeId,
|
||||
clips,
|
||||
viewport,
|
||||
),
|
||||
);
|
||||
} catch (error) {
|
||||
failure ??= error;
|
||||
}
|
||||
}
|
||||
}),
|
||||
);
|
||||
// Join active reads and their cleanup before returning cancellation.
|
||||
if (failure) throw failure;
|
||||
throwCaptureAborted(signal);
|
||||
const normalized = await normalizeDocument(
|
||||
doc,
|
||||
strings,
|
||||
{
|
||||
frameId: frame.frameId,
|
||||
ownerFrameBackendNodeId: frame.ownerBackendNodeId ?? null,
|
||||
projection: state,
|
||||
...(profile.includeVisualFacts
|
||||
? { pageScale: metrics.cssVisualViewport?.scale ?? metrics.visualViewport?.scale }
|
||||
: {}),
|
||||
target,
|
||||
...(target.sessionId ? { targetProjection } : {}),
|
||||
coordinates,
|
||||
},
|
||||
signal,
|
||||
profile,
|
||||
);
|
||||
result.push({ ...normalized, frame });
|
||||
}
|
||||
return result;
|
||||
}
|
||||
@@ -2,10 +2,7 @@ import type { Rect, RenderedRef, VomResult } from "@browser-skill/vom";
|
||||
import type { CdpTarget } from "@/browser-driver/frame-graph";
|
||||
import { readRecordingDocumentIdentity } from "@/shared/recording-document-identity";
|
||||
import type { CapturedSurfaceProbe } from "./capture";
|
||||
import type {
|
||||
FrameDocument as CapturedFrameDocument,
|
||||
FrameOwnedAxNode as FrameAxNode,
|
||||
} from "./frame-document";
|
||||
import type { CapturedFrameDocument, FrameAxNode } from "./frame-capture";
|
||||
|
||||
/** Frame identity needed to resolve an `@eN` that lives in an iframe. */
|
||||
export interface CaptureVomFrame {
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user