Compare commits

..
Author SHA1 Message Date
drakezhang 388c1283bc fix: clarify invalid selectors and dedupe diagnostics 2026-09-01 21:03:22 +08:00
drakezhang b449be1544 chore: add session-loss diagnostics 2026-09-01 20:16:32 +08:00
183 changed files with 3568 additions and 16787 deletions
-29
View File
@@ -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
-4
View File
@@ -7,10 +7,6 @@ dist/
.output/
.wxt/
.web-extension-id
.pnpm-store/
# Git worktrees
.worktrees/
# Logs
*.log
-109
View File
@@ -1,109 +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.
## [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 -3
View File
@@ -134,10 +134,9 @@ dependencies = [
[[package]]
name = "bsk"
version = "0.2.1"
version = "0.1.11"
dependencies = [
"anyhow",
"base64",
"bsk-protocol",
"clap",
"console",
@@ -169,7 +168,7 @@ dependencies = [
[[package]]
name = "bsk-protocol"
version = "0.2.1"
version = "0.1.11"
dependencies = [
"schemars",
"semver",
+2 -3
View File
@@ -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"
@@ -36,14 +36,13 @@ flate2 = "1.1.9"
tar = "0.4.46"
zip = { version = "7.2.0", default-features = false, features = ["deflate"] }
sha2 = "0.11.0"
base64 = "0.22"
tempfile = "3"
nix = { version = "0.29", features = ["signal", "process"] }
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"
+7 -13
View File
@@ -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
+3 -9
View File
@@ -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
+3 -6
View File
@@ -1,6 +1,6 @@
# BrowserSkill — Privacy Policy
**Last updated:** August 20, 2026
**Last updated:** May 25, 2026
This Privacy Policy describes how the **BrowserSkill** browser extension (the "Extension") handles information when you install and use it. BrowserSkill is published as part of the open-source [BrowserSkill](https://github.com/Tencent/BrowserSkill) project. The source code is publicly auditable.
@@ -14,7 +14,7 @@ BrowserSkill is a local automation bridge that lets AI coding agents (such as Cu
## 2. Single Purpose
The Extension's single purpose is to expose browser automation primitives (navigation, DOM observation, screenshots, clicks, form filling, task-scoped file transfer, and tab management) to a locally running BrowserSkill daemon over a WebSocket connection on `127.0.0.1`, so that an AI agent invoked by the user can interact with web pages on the user's behalf.
The Extension's single purpose is to expose browser automation primitives (navigation, DOM observation, screenshots, clicks, form filling, tab management) to a locally running BrowserSkill daemon over a WebSocket connection on `127.0.0.1`, so that an AI agent invoked by the user can interact with web pages on the user's behalf.
## 3. Data the Extension Accesses
@@ -26,7 +26,6 @@ Depending on the commands the user (via their AI agent) sends to the local daemo
| **User input simulated by the agent** | Mouse clicks, keystrokes, and form values that the AI agent dispatches through the Chrome DevTools Protocol (CDP). | Required to perform automation actions the user has asked the agent to do. |
| **Tab and window metadata** | Tab IDs, URLs, titles, window IDs of the Agent Window and any tabs the user explicitly authorizes. | Required to target automation commands at the correct tab/window. |
| **Local extension storage** | A randomly generated 8-character instance ID and an optional user-supplied label. | Used so the local daemon can recognize this browser instance across reconnects. No personal data is stored. |
| **File transfers requested by the agent** | Local files explicitly supplied to `bsk upload`, and the file created by a single `bsk download` action. | Required to attach a task file to a web page or return a browser-generated download to the invoking local agent. |
| **OS notifications** | Permission to display a system notification when the agent requests to "borrow" one of the user's existing tabs. | Required to obtain explicit, per-tab user consent before the agent touches any pre-existing tab. |
## 4. Data the Extension Does **Not** Collect
@@ -35,7 +34,7 @@ BrowserSkill does **not**:
- Send any data to remote servers, the Extension's authors, or any third party.
- Call any LLM, AI, or cloud API. The Extension contains no API keys, model identifiers, or remote endpoints.
- Read or transmit cookies, browsing history, bookmarks, saved passwords, or autofill data. It observes only the download initiated by an active `bsk download` call, not download history generally.
- Read or transmit cookies, browsing history, bookmarks, downloads, saved passwords, or autofill data.
- Use webcam, microphone, geolocation, or any device sensor.
- Include analytics, telemetry, crash reporting, advertising SDKs, or fingerprinting code.
- Track users across websites or across sessions.
@@ -51,7 +50,6 @@ The Extension requests the following Chrome permissions. Each is used solely for
- **`alarms`** — Periodically wake the service worker to keep the local WebSocket connection alive.
- **`idle`** — Detect when the device returns from idle/locked so the Extension can promptly re-establish the local WebSocket connection after the machine wakes. No idle data is stored or transmitted.
- **`notifications`** — Show a system notification to obtain user approval before the agent borrows a user-owned tab.
- **`downloads`** — Correlate and route the one browser download initiated by an active `bsk download` command. If that claimed transaction fails, BrowserSkill cancels an in-progress file or removes its completed temporary browser file. It is not used to enumerate download history or alter unclaimed downloads.
- **`storage`** — Persist a random instance ID and optional label in `chrome.storage.local`.
- **Host permission `<all_urls>`** — Inject a small status overlay (showing "Agent Active") on pages controlled by the agent, and enable automation across whatever sites the user directs the agent to. The Extension does **not** read or transmit page content from sites the agent is not actively driving.
@@ -63,7 +61,6 @@ All Extension activity stays on the user's local device. The only network traffi
- The instance ID and optional label persist in `chrome.storage.local` until the user uninstalls the Extension or clears extension storage.
- Page content, screenshots, DOM snapshots, and other observed data are returned to the local daemon in response to commands and are **not retained by the Extension**. They live only as long as the agent's tool call.
- Upload and download bytes are staged by the local daemon in a private, session-scoped directory. Download staging is removed after it is copied to the requested destination. Upload staging is retained until the session ends so a later form submission can still read the attached file. Remaining staging is removed when the session ends or disconnects, or when the daemon next starts after a crash.
## 8. User Control
@@ -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 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@browser-skill/extension",
"version": "0.2.1",
"version": "0.1.7",
"private": true,
"type": "module",
"scripts": {
@@ -254,69 +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);
@@ -714,155 +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);
@@ -165,7 +165,6 @@ export class ChromiumCdp {
private readonly api: CdpDebuggerApi;
private readonly attachedTabs = new Set<number>();
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>();
@@ -183,13 +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();
@@ -200,10 +193,6 @@ export class ChromiumCdp {
/** 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) {
@@ -436,11 +425,6 @@ 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);
@@ -448,19 +432,13 @@ export class ChromiumCdp {
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. */
@@ -475,17 +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;
@@ -672,23 +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, {
@@ -878,9 +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)));
}
}
@@ -23,7 +23,7 @@ describe("BorrowConfirmationOverlay", () => {
id: "req-1",
isActiveTab: true,
tabTitle: "Example",
timeoutMs: 60_000,
timeoutMs: 5000,
onAllow,
onDeny,
},
@@ -32,7 +32,7 @@ describe("BorrowConfirmationOverlay", () => {
);
expect(screen.getByText("允许借用标签页?")).toBeTruthy();
for (let i = 0; i < 60; i++) {
for (let i = 0; i < 5; i++) {
await act(async () => {
await vi.advanceTimersByTimeAsync(1000);
});
@@ -66,7 +66,7 @@ describe("BorrowConfirmationOverlay", () => {
id: "req-fallback",
isActiveTab: true,
tabTitle: "Example",
timeoutMs: 60_000,
timeoutMs: 5000,
onAllow,
onDeny,
},
@@ -74,7 +74,7 @@ describe("BorrowConfirmationOverlay", () => {
/>,
);
for (let i = 0; i < 60; i++) {
for (let i = 0; i < 5; i++) {
await act(async () => {
await vi.advanceTimersByTimeAsync(1000);
});
@@ -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);
+68 -67
View File
@@ -1,6 +1,7 @@
import { i18n } from "@browser-skill/i18n";
import { ChromiumCdp } from "@/browser-driver/chromium-cdp";
import { ConnectionController } from "@/lib/connection-controller";
import { DiagnosticLogger } from "@/lib/diagnostics";
import { startHeartbeat } from "@/lib/heartbeat";
import {
getConnectionEnabled,
@@ -25,7 +26,7 @@ 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,
@@ -41,22 +42,26 @@ 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";
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 diagnostics = new DiagnosticLogger();
diagnostics.record("extension.worker.started", {
diagnostic_build: "lumi-session-loss-v2",
extension_version: __BSK_EXT_VERSION__,
extension_runtime_id: chrome.runtime.id,
daemon_ws_url: __BSK_DAEMON_WS_URL__,
});
const controller = new ConnectionController(diagnostics.sink);
const transport = new WSTransport({
url: __BSK_DAEMON_WS_URL__,
diagnostics: diagnostics.sink,
});
diagnostics.bindTransport((frame) => transport.send(frame));
const sessions = new SessionManager({ diagnostics: diagnostics.sink });
const cdp = new ChromiumCdp();
const sessionsLive = attachSessionsLiveFlag({ manager: sessions });
let overlayGeneration = 0;
const controlModes = new Map<string, OverlayMode>();
@@ -87,24 +92,6 @@ 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 +103,13 @@ 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(),
),
);
}
@@ -139,6 +121,9 @@ export default defineBackground(() => {
}
function onOverlaySessionStateChanged(): void {
diagnostics.record("background.sessions.changed", {
live_session_ids: sessions.list().map((ctx) => ctx.sessionId),
});
void sessionsLive.syncFromManager();
const liveSessionIds = new Set(sessions.list().map((ctx) => ctx.sessionId));
for (const sessionId of controlModes.keys()) {
@@ -166,33 +151,17 @@ 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();
},
diagnostics: diagnostics.sink,
});
const recordDeps = {
tabsApi: chrome.tabs,
@@ -223,9 +192,6 @@ 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 } : {}),
@@ -243,6 +209,7 @@ export default defineBackground(() => {
title: i18n.t("helpRequest.notificationTitle", { ns: "extension" }),
body: "",
}),
diagnostics: diagnostics.sink,
});
dispatcher.start();
if (typeof chrome.notifications?.onClicked?.addListener === "function") {
@@ -275,6 +242,7 @@ export default defineBackground(() => {
transport,
cdp,
onSessionsChanged: onOverlaySessionStateChanged,
diagnostics: diagnostics.sink,
});
// MV3 service worker keepalive + reconnect supervisor (review M4/M5
@@ -286,6 +254,7 @@ export default defineBackground(() => {
startKeepalive({
transport,
shouldConnect: () => controller.isConnectionEnabled,
diagnostics: diagnostics.sink,
});
// Application-level heartbeat (Chrome 116+): while the post-handshake
@@ -299,6 +268,19 @@ export default defineBackground(() => {
controller.subscribe((snap) =>
cb(snap.state === "connected" || snap.state === "version_skew"),
),
diagnostics: diagnostics.sink,
});
controller.subscribe((snapshot) => {
const ready = snapshot.state === "connected" || snapshot.state === "version_skew";
diagnostics.setTransportReady(ready);
diagnostics.record("background.controller.snapshot", {
state: snapshot.state,
connection_enabled: snapshot.connectionEnabled,
instance_id: snapshot.instanceId,
last_error: snapshot.lastError,
live_session_ids: sessions.list().map((ctx) => ctx.sessionId),
});
});
// Wake-driven reconnect (best effort). An MV3 service worker is killed
@@ -307,7 +289,12 @@ export default defineBackground(() => {
// the worker and let us reconnect immediately instead of waiting for
// the next 30s alarm tick. They only help when the daemon is actually
// running; a cold daemon is (re)spawned by the next `bsk` command.
const reconnectIfNeeded = () => {
const reconnectIfNeeded = (source: string) => {
diagnostics.record("background.wake_reconnect.requested", {
source,
controller_enabled: controller.isConnectionEnabled,
transport_state: transport.state,
});
if (!controller.isConnectionEnabled) return;
if (transport.state === "connected") return;
void transport.connect().catch((err) => {
@@ -315,13 +302,14 @@ export default defineBackground(() => {
});
};
if (typeof chrome.runtime?.onStartup?.addListener === "function") {
chrome.runtime.onStartup.addListener(reconnectIfNeeded);
chrome.runtime.onStartup.addListener(() => reconnectIfNeeded("runtime.onStartup"));
}
if (typeof chrome.idle?.onStateChanged?.addListener === "function") {
chrome.idle.onStateChanged.addListener((state) => {
diagnostics.record("chrome.idle.state_changed", { state });
// "active" fires when the user returns from idle/locked — the most
// reliable "machine just woke" signal we get.
if (state === "active") reconnectIfNeeded();
if (state === "active") reconnectIfNeeded("idle.active");
});
// Treat >60s of no input as idle so the active transition is timely.
chrome.idle.setDetectionInterval?.(60);
@@ -329,14 +317,21 @@ export default defineBackground(() => {
void (async () => {
const connectionEnabled = await getConnectionEnabled();
diagnostics.record("background.controller.attach_started", { connectionEnabled });
await controller.attach(transport, detectBrowserMeta(), connectionEnabled, {
beforeDisconnect: async () => {
diagnostics.record("background.before_disconnect_cleanup", {
live_session_ids: sessions.list().map((ctx) => ctx.sessionId),
});
const report = await cleanupAfterDisconnect();
if (report.failures.length > 0) {
console.warn("[browser-skill] session cleanup before disconnect was incomplete", report);
}
},
onDisconnected: async () => {
diagnostics.record("background.after_disconnect_cleanup", {
live_session_ids: sessions.list().map((ctx) => ctx.sessionId),
});
const report = await cleanupAfterDisconnect();
if (report.failures.length > 0) {
console.warn("[browser-skill] session cleanup after disconnect was incomplete", report);
@@ -344,6 +339,7 @@ export default defineBackground(() => {
},
});
})().catch((err) => {
diagnostics.record("background.controller.attach_failed", { error: err });
console.error("[browser-skill] controller failed to attach", err);
});
@@ -359,11 +355,7 @@ 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;
}
@@ -428,6 +420,15 @@ export default defineBackground(() => {
dbg.__bhDispatcher = dispatcher;
}
if (typeof chrome.runtime?.onSuspend?.addListener === "function") {
chrome.runtime.onSuspend.addListener(() => {
diagnostics.record("extension.worker.suspending", {
live_session_ids: sessions.list().map((ctx) => ctx.sessionId),
transport_state: transport.state,
});
});
}
console.info("[browser-skill] background worker initialised");
});
@@ -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" });
+2 -2
View File
@@ -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);
@@ -0,0 +1,85 @@
import { describe, expect, it, vi } from "vitest";
import { DiagnosticLogger } from "../diagnostics";
class MemoryStorage {
value: Record<string, unknown> = {};
async get(key: string): Promise<Record<string, unknown>> {
return { [key]: this.value[key] };
}
async set(items: Record<string, unknown>): Promise<void> {
this.value = { ...this.value, ...items };
}
}
describe("DiagnosticLogger", () => {
it("persists evidence before transport readiness and flushes it after reconnect", async () => {
const storage = new MemoryStorage();
const send = vi.fn();
const logger = new DiagnosticLogger(storage);
logger.bindTransport(send);
logger.record("transport.socket.closed", { code: 1006 });
await logger.flush();
expect(send).not.toHaveBeenCalled();
logger.setTransportReady(true);
await logger.flush();
expect(send).toHaveBeenCalledOnce();
expect(send.mock.calls[0]?.[0]).toMatchObject({
event: "browser.diagnostic",
payload: {
schema_version: 1,
entries: [
{
event: "transport.socket.closed",
fields: { code: 1006 },
},
],
},
});
expect(storage.value.bsk_diagnostic_events_v1).toEqual([]);
});
it("keeps persisted evidence when the transport rejects the flush", async () => {
const storage = new MemoryStorage();
const logger = new DiagnosticLogger(storage);
logger.bindTransport(() => {
throw new Error("socket closed");
});
logger.record("session.stop.requested", { session_id: "abcd" });
logger.setTransportReady(true);
await logger.flush();
expect(storage.value.bsk_diagnostic_events_v1).toMatchObject([
{ event: "session.stop.requested", fields: { session_id: "abcd" } },
]);
});
it("does not resend an acknowledged event when send records a new event", async () => {
const storage = new MemoryStorage();
const batches: Array<{ payload?: { entries?: Array<{ event: string }> } }> = [];
const logger = new DiagnosticLogger(storage);
logger.record("dispatcher.rpc.received", { rpc_id: "one" });
await logger.flush();
logger.bindTransport((frame) => {
batches.push(frame as { payload?: { entries?: Array<{ event: string }> } });
if (batches.length === 1) {
logger.record("dispatcher.rpc.response_sent", { rpc_id: "one" });
}
});
logger.setTransportReady(true);
await logger.flush();
await logger.flush();
expect(batches.map((batch) => batch.payload?.entries?.map((entry) => entry.event))).toEqual([
["dispatcher.rpc.received"],
["dispatcher.rpc.response_sent"],
]);
expect(storage.value.bsk_diagnostic_events_v1).toEqual([]);
});
});
@@ -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,
@@ -6,6 +6,7 @@ import {
} from "../transport/handshake";
import type { Transport } from "../transport/transport";
import type { ConnectionState, HandshakeResult } from "../transport/types";
import type { DiagnosticSink } from "./diagnostics";
import { getLabel, getOrCreateInstanceId } from "./instance-id";
import { compareProtocol, parseProtocolMajor } from "./semver";
@@ -51,6 +52,11 @@ export class ConnectionController {
private handshakeAbort: AbortController | null = null;
private handshakeRetryTimer: ReturnType<typeof setTimeout> | null = null;
private suppressDisconnectRecovery = false;
private readonly diagnostics?: DiagnosticSink;
constructor(diagnostics?: DiagnosticSink) {
this.diagnostics = diagnostics;
}
get isConnectionEnabled(): boolean {
return this.connectionEnabled;
@@ -89,8 +95,20 @@ export class ConnectionController {
this.lifecycleHooks = lifecycleHooks;
this.instanceId = await getOrCreateInstanceId();
this.label = await getLabel();
this.diagnostics?.("controller.attach", {
instance_id: this.instanceId,
connection_enabled: connectionEnabled,
transport_state: transport.state,
});
transport.onConnectionStateChange((s) => {
this.diagnostics?.("controller.transport_state", {
transport_state: s,
controller_state: this.currentState,
connection_generation: this.connectionGeneration,
suppress_disconnect_recovery: this.suppressDisconnectRecovery,
recovery_inflight: this.disconnectRecovery !== null,
});
if (s === "disconnected") {
// An in-flight handshake belongs to the dead connection — cancel it so
// a late resolution can never clobber the next attempt.
@@ -103,6 +121,9 @@ export class ConnectionController {
// handshake bounce); the caller owns the reconnect policy there.
this.suppressDisconnectRecovery = false;
} else {
this.diagnostics?.("controller.disconnect_recovery.requested", {
connection_generation: this.connectionGeneration,
});
void this.recoverFromDisconnect();
}
}
@@ -161,6 +182,12 @@ export class ConnectionController {
const generation = ++this.connectionGeneration;
const abort = new AbortController();
this.handshakeAbort = abort;
this.diagnostics?.("controller.handshake.started", {
connection_generation: generation,
browser_name: browser.name,
browser_version: browser.version,
instance_id: this.instanceId,
});
void this.runHandshake(browser, generation, abort.signal);
}
@@ -197,11 +224,21 @@ export class ConnectionController {
}
this.clearHandshakeRetry();
this.lastError = null;
this.diagnostics?.("controller.handshake.completed", {
connection_generation: generation,
verdict: verdict.kind,
daemon_version: outcome.result.version,
daemon_protocol: outcome.result.protocol_version,
});
this.setState(verdict.kind);
} catch (err) {
if (generation !== this.connectionGeneration || signal.aborted || isAbortError(err)) return;
this.handshake = null;
this.lastError = err instanceof Error ? err.message : String(err);
this.diagnostics?.("controller.handshake.failed", {
connection_generation: generation,
error: err,
});
// Bounce the half-open socket deliberately; the retry timer below owns
// the reconnect, so skip unexpected-loss recovery for this disconnect.
this.suppressDisconnectRecovery = true;
@@ -228,23 +265,57 @@ export class ConnectionController {
}
private recoverFromDisconnect(): Promise<void> {
if (this.disconnectRecovery) return this.disconnectRecovery;
if (this.disconnectRecovery) {
this.diagnostics?.("controller.disconnect_recovery.coalesced", {
connection_generation: this.connectionGeneration,
});
return this.disconnectRecovery;
}
const recovery = (async () => {
const recoveryGeneration = this.connectionGeneration;
this.diagnostics?.("controller.disconnect_recovery.started", {
recovery_generation: recoveryGeneration,
});
// WSTransport schedules its reconnect timer immediately after notifying
// state listeners. Yield once, then disconnect explicitly so that timer
// is cancelled before local session teardown begins.
await Promise.resolve();
if (!this.connectionEnabled || !this.transport) return;
if (!this.connectionEnabled || !this.transport) {
this.diagnostics?.("controller.disconnect_recovery.skipped", {
recovery_generation: recoveryGeneration,
reason: "disabled_or_missing_transport",
});
return;
}
// Another path already reconnected while we yielded — nothing to do.
if (this.currentState !== "disconnected") return;
if (this.currentState !== "disconnected") {
this.diagnostics?.("controller.disconnect_recovery.skipped", {
recovery_generation: recoveryGeneration,
reason: "state_already_changed",
current_state: this.currentState,
});
return;
}
await this.transport.disconnect().catch(() => {});
try {
this.diagnostics?.("controller.disconnect_cleanup.started", {
recovery_generation: recoveryGeneration,
current_generation: this.connectionGeneration,
});
await this.lifecycleHooks.onDisconnected?.();
this.diagnostics?.("controller.disconnect_cleanup.completed", {
recovery_generation: recoveryGeneration,
current_generation: this.connectionGeneration,
});
} catch (err) {
console.warn("[browser-skill] session cleanup after disconnect failed", err);
}
if (!this.connectionEnabled) return;
try {
this.diagnostics?.("controller.disconnect_reconnect.started", {
recovery_generation: recoveryGeneration,
current_generation: this.connectionGeneration,
});
await this.transport.connect();
} catch (err) {
this.lastError = err instanceof Error ? err.message : String(err);
@@ -252,22 +323,39 @@ export class ConnectionController {
}
})();
this.disconnectRecovery = recovery.finally(() => {
this.diagnostics?.("controller.disconnect_recovery.completed", {
connection_generation: this.connectionGeneration,
current_state: this.currentState,
});
this.disconnectRecovery = null;
});
return this.disconnectRecovery;
}
private cancelHandshake(): void {
const previousGeneration = this.connectionGeneration;
this.connectionGeneration += 1;
this.diagnostics?.("controller.handshake.cancelled", {
previous_generation: previousGeneration,
next_generation: this.connectionGeneration,
had_abort_controller: this.handshakeAbort !== null,
});
this.handshakeAbort?.abort();
this.handshakeAbort = null;
}
private scheduleHandshakeRetry(browser: { name: string; version: string }): void {
if (this.handshakeRetryTimer || !this.connectionEnabled) return;
this.diagnostics?.("controller.handshake_retry.scheduled", {
delay_ms: HANDSHAKE_RETRY_DELAY_MS,
connection_generation: this.connectionGeneration,
});
this.handshakeRetryTimer = setTimeout(() => {
this.handshakeRetryTimer = null;
if (!this.connectionEnabled || !this.transport) return;
this.diagnostics?.("controller.handshake_retry.timer_fired", {
connection_generation: this.connectionGeneration,
});
void this.transport.connect().catch((err) => {
this.lastError = err instanceof Error ? err.message : String(err);
this.setState("disconnected");
+178
View File
@@ -0,0 +1,178 @@
import type { ProtocolFrame } from "@/transport/types";
const STORAGE_KEY = "bsk_diagnostic_events_v1";
const MAX_ENTRIES = 500;
export type DiagnosticFields = Record<string, unknown>;
export type DiagnosticSink = (event: string, fields?: DiagnosticFields) => void;
export interface DiagnosticEntry {
id: string;
sequence: number;
timestamp: string;
monotonic_ms: number;
worker_boot_id: string;
event: string;
fields: DiagnosticFields;
}
interface DiagnosticStorage {
get(key: string): Promise<Record<string, unknown>>;
set(items: Record<string, unknown>): Promise<void>;
}
function defaultStorage(): DiagnosticStorage | null {
if (typeof chrome === "undefined" || !chrome.storage?.local) return null;
return {
get: (key) => chrome.storage.local.get(key),
set: (items) => chrome.storage.local.set(items),
};
}
function makeBootId(): string {
try {
return crypto.randomUUID();
} catch {
return `worker-${Date.now()}-${Math.random().toString(16).slice(2)}`;
}
}
function normalise(value: unknown): unknown {
if (value instanceof Error) {
return { name: value.name, message: value.message, stack: value.stack };
}
if (typeof value === "bigint") return value.toString();
if (Array.isArray(value)) return value.map(normalise);
if (value && typeof value === "object") {
return Object.fromEntries(
Object.entries(value as Record<string, unknown>).map(([key, child]) => [
key,
normalise(child),
]),
);
}
return value;
}
/**
* Persistent diagnostics for the MV3 background worker.
*
* Events are first written to chrome.storage.local so a worker termination or
* dead WebSocket does not erase the evidence. Once the post-handshake link is
* ready, pending entries are forwarded to the daemon as one
* `browser.diagnostic` event and removed from the local queue.
*/
export class DiagnosticLogger {
readonly workerBootId: string;
readonly sink: DiagnosticSink;
private sequence = 0;
private storageQueue: Promise<void> = Promise.resolve();
private flushPromise: Promise<void> | null = null;
private flushRequested = false;
private send: ((frame: ProtocolFrame) => void) | null = null;
private transportReady = false;
private readonly storage: DiagnosticStorage | null;
constructor(storage: DiagnosticStorage | null = defaultStorage()) {
this.workerBootId = makeBootId();
this.storage = storage;
this.sink = (event, fields = {}) => this.record(event, fields);
}
bindTransport(send: (frame: ProtocolFrame) => void): void {
this.send = send;
}
setTransportReady(ready: boolean): void {
this.transportReady = ready;
if (ready) void this.flush();
}
record(event: string, fields: DiagnosticFields = {}): void {
const sequence = ++this.sequence;
const entry: DiagnosticEntry = {
id: `${this.workerBootId}:${sequence}`,
sequence,
timestamp: new Date().toISOString(),
monotonic_ms: Math.round(performance.now()),
worker_boot_id: this.workerBootId,
event,
fields: normalise(fields) as DiagnosticFields,
};
console.info("[bsk diagnostic]", entry);
this.storageQueue = this.storageQueue
.then(async () => {
if (!this.storage) return;
const stored = await this.storage.get(STORAGE_KEY);
const previous = Array.isArray(stored[STORAGE_KEY])
? (stored[STORAGE_KEY] as DiagnosticEntry[])
: [];
await this.storage.set({
[STORAGE_KEY]: [...previous, entry].slice(-MAX_ENTRIES),
});
})
.catch((error) => {
console.warn("[bsk diagnostic] failed to persist event", error);
});
if (this.transportReady) void this.flush();
}
flush(): Promise<void> {
if (this.flushPromise) {
this.flushRequested = true;
return this.flushPromise;
}
const running = (async () => {
await this.storageQueue;
if (!this.transportReady || !this.send || !this.storage) return;
const stored = await this.storage.get(STORAGE_KEY);
const entries = Array.isArray(stored[STORAGE_KEY])
? (stored[STORAGE_KEY] as DiagnosticEntry[])
: [];
if (entries.length === 0) return;
try {
this.send({
event: "browser.diagnostic",
payload: {
schema_version: 1,
worker_boot_id: this.workerBootId,
entries,
},
});
} catch (error) {
console.warn("[bsk diagnostic] daemon flush failed", error);
return;
}
const sentIds = new Set(entries.map((entry) => entry.id));
// Serialize acknowledgement behind every record write that may have
// started while send() was in progress. Without this, a concurrent
// record can read the pre-ack queue and write an already-sent entry
// back into storage, causing the next batch to duplicate it.
this.storageQueue = this.storageQueue
.then(async () => {
const current = await this.storage?.get(STORAGE_KEY);
const currentEntries = Array.isArray(current?.[STORAGE_KEY])
? (current[STORAGE_KEY] as DiagnosticEntry[])
: [];
await this.storage?.set({
[STORAGE_KEY]: currentEntries.filter((entry) => !sentIds.has(entry.id)),
});
})
.catch((error) => {
console.warn("[bsk diagnostic] failed to acknowledge event batch", error);
});
await this.storageQueue;
})().catch((error) => {
console.warn("[bsk diagnostic] flush failed", error);
});
this.flushPromise = running.finally(() => {
this.flushPromise = null;
if (this.flushRequested && this.transportReady) {
this.flushRequested = false;
void this.flush();
}
});
return this.flushPromise;
}
}
+6
View File
@@ -21,6 +21,7 @@
* after the handshake has landed.
*/
import type { DiagnosticSink } from "@/lib/diagnostics";
import type { ProtocolFrame } from "@/transport/types";
export const HEARTBEAT_EVENT = "system.heartbeat";
@@ -46,6 +47,7 @@ export interface HeartbeatOptions {
intervalMs?: number;
/** Inject fake timers (tests). */
timers?: HeartbeatTimers;
diagnostics?: DiagnosticSink;
}
export interface HeartbeatHandle {
@@ -74,7 +76,9 @@ export function startHeartbeat(options: HeartbeatOptions): HeartbeatHandle {
const beat = () => {
try {
options.send({ event: HEARTBEAT_EVENT, payload: {} });
options.diagnostics?.("heartbeat.sent");
} catch (err) {
options.diagnostics?.("heartbeat.send_failed", { error: err });
// The socket raced a close between the state change and this
// tick. The transport's own reconnect path recovers; swallow so
// the interval keeps running (it is cleared on the disconnect
@@ -87,12 +91,14 @@ export function startHeartbeat(options: HeartbeatOptions): HeartbeatHandle {
if (timer !== null) {
timers.clearInterval(timer);
timer = null;
options.diagnostics?.("heartbeat.timer.stopped");
}
};
const start = () => {
if (timer !== null) return;
timer = timers.setInterval(beat, intervalMs);
options.diagnostics?.("heartbeat.timer.started", { interval_ms: intervalMs });
};
const unsubscribe = options.onActiveChange((active) => {
+17 -2
View File
@@ -20,6 +20,7 @@
* SW idle threshold.
*/
import type { DiagnosticSink } from "@/lib/diagnostics";
import type { Transport } from "@/transport/transport";
export const KEEPALIVE_ALARM_NAME = "bh-keepalive";
@@ -59,6 +60,7 @@ export interface KeepaliveOptions {
alarmName?: string;
/** Override the alarm period (tests). */
periodMin?: number;
diagnostics?: DiagnosticSink;
}
export interface KeepaliveHandle {
@@ -79,11 +81,24 @@ export function startKeepalive(options: KeepaliveOptions): KeepaliveHandle {
const period = options.periodMin ?? KEEPALIVE_PERIOD_MIN;
const tick = async () => {
if (options.shouldConnect && !options.shouldConnect()) return;
if (options.transport.state === "connected") return;
if (options.shouldConnect && !options.shouldConnect()) {
options.diagnostics?.("keepalive.tick.skipped", { reason: "connection_disabled" });
return;
}
if (options.transport.state === "connected") {
options.diagnostics?.("keepalive.tick.healthy", { transport_state: "connected" });
return;
}
options.diagnostics?.("keepalive.reconnect.started", {
transport_state: options.transport.state,
});
try {
await options.transport.connect();
options.diagnostics?.("keepalive.reconnect.completed", {
transport_state: options.transport.state,
});
} catch (err) {
options.diagnostics?.("keepalive.reconnect.failed", { error: err });
console.debug("[bsk keepalive] connect attempt failed", err);
}
};
+2 -4
View File
@@ -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
-26
View File
@@ -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() });
@@ -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 });
},
};
@@ -1,3 +1,4 @@
import type { DiagnosticSink } from "@/lib/diagnostics";
import { handleSessionStop, type SessionStopDeps } from "@/tools/session";
import type { SessionManager } from "./manager";
@@ -15,6 +16,7 @@ export interface DisconnectCleanupOptions {
manager: SessionManager;
sessionStopDeps?: SessionStopDeps;
onSessionsChanged?: () => void;
diagnostics?: DiagnosticSink;
}
/**
@@ -29,7 +31,15 @@ export function createDisconnectCleanup(options: DisconnectCleanupOptions) {
let inFlight: Promise<DisconnectCleanupReport> | null = null;
return (): Promise<DisconnectCleanupReport> => {
if (inFlight) return inFlight;
if (inFlight) {
options.diagnostics?.("disconnect_cleanup.coalesced", {
live_session_ids: options.manager.list().map((ctx) => ctx.sessionId),
});
return inFlight;
}
options.diagnostics?.("disconnect_cleanup.scheduled", {
live_session_ids: options.manager.list().map((ctx) => ctx.sessionId),
});
inFlight = cleanupSessions(options).finally(() => {
inFlight = null;
});
@@ -42,8 +52,17 @@ async function cleanupSessions(
): Promise<DisconnectCleanupReport> {
const stoppedSessionIds: string[] = [];
const failures: DisconnectCleanupFailure[] = [];
const capturedSessions = options.manager.list();
options.diagnostics?.("disconnect_cleanup.started", {
captured_session_ids: capturedSessions.map((ctx) => ctx.sessionId),
});
for (const ctx of options.manager.list()) {
for (const ctx of capturedSessions) {
options.diagnostics?.("disconnect_cleanup.session_stop.started", {
session_id: ctx.sessionId,
agent_window_id: ctx.agentWindowId,
still_registered: options.manager.has(ctx.sessionId),
});
try {
const result = await handleSessionStop(
options.manager,
@@ -62,14 +81,26 @@ async function cleanupSessions(
continue;
}
stoppedSessionIds.push(ctx.sessionId);
options.diagnostics?.("disconnect_cleanup.session_stop.completed", {
session_id: ctx.sessionId,
});
} catch (err) {
failures.push({
sessionId: ctx.sessionId,
message: err instanceof Error ? err.message : String(err),
});
options.diagnostics?.("disconnect_cleanup.session_stop.failed", {
session_id: ctx.sessionId,
error: err,
});
}
}
options.onSessionsChanged?.();
options.diagnostics?.("disconnect_cleanup.completed", {
stopped_session_ids: stoppedSessionIds,
failures,
remaining_session_ids: options.manager.list().map((ctx) => ctx.sessionId),
});
return { stoppedSessionIds, failures };
}
@@ -1,3 +1,4 @@
import type { DiagnosticSink } from "@/lib/diagnostics";
import type { Transport } from "@/transport/transport";
import type { EventFrame } from "@/transport/types";
import type { SessionManager } from "./manager";
@@ -24,6 +25,7 @@ export interface SessionEventHandlerOptions {
* `chrome.storage.session` "sessions live" flag (review M4/M5 I3).
*/
onSessionsChanged?: () => void;
diagnostics?: DiagnosticSink;
}
function chromeWindowEvents(): WindowRemovedListener {
@@ -50,6 +52,11 @@ export function attachSessionEventHandler(options: SessionEventHandlerOptions):
const onRemoved = (windowId: number): void => {
const ctx = manager.findByWindowId(windowId);
options.diagnostics?.("chrome.window.removed", {
window_id: windowId,
matched_session_id: ctx?.sessionId ?? null,
live_session_ids: manager.list().map((entry) => entry.sessionId),
});
if (!ctx) return;
const returnFailures = Array.from(ctx.borrowedTabs.keys()).map((tabId) => ({
tab_id: tabId,
@@ -81,7 +88,16 @@ export function attachSessionEventHandler(options: SessionEventHandlerOptions):
};
try {
transport.send(event);
options.diagnostics?.("session.window_closed.sent", {
session_id: ctx.sessionId,
window_id: windowId,
});
} catch (err) {
options.diagnostics?.("session.window_closed.send_failed", {
session_id: ctx.sessionId,
window_id: windowId,
error: err,
});
console.warn("[bh] could not push session.window_closed event", err);
}
})
+42 -29
View File
@@ -1,3 +1,4 @@
import type { DiagnosticSink } from "@/lib/diagnostics";
import { AGENT_WINDOW_HOME, type AgentWindowApi, chromeAgentWindowApi } from "./agent-window";
import { RefStore } from "./ref-store";
@@ -6,20 +7,9 @@ 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;
@@ -34,6 +24,7 @@ export interface BorrowReservation {
export interface SessionManagerOptions {
agentWindow?: AgentWindowApi;
now?: () => number;
diagnostics?: DiagnosticSink;
}
/** Options for starting a session's Agent Window. */
@@ -94,10 +85,12 @@ export class SessionManager {
private readonly borrowReservations = new Map<number, string>();
private readonly agentWindow: AgentWindowApi;
private readonly now: () => number;
private readonly diagnostics?: DiagnosticSink;
constructor(options: SessionManagerOptions = {}) {
this.agentWindow = options.agentWindow ?? chromeAgentWindowApi;
this.now = options.now ?? Date.now;
this.diagnostics = options.diagnostics;
}
has(sessionId: string): boolean {
@@ -117,19 +110,6 @@ 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
@@ -193,6 +173,13 @@ export class SessionManager {
* daemon in the `tool.session_start` reply.
*/
async start(sessionId: string, opts: SessionStartOptions = {}): Promise<SessionContext> {
this.diagnostics?.("session_manager.start.requested", {
session_id: sessionId,
existing_session_ids: this.list().map((ctx) => ctx.sessionId),
focused: opts.focused ?? null,
size: opts.size ?? null,
signal_aborted: opts.signal?.aborted ?? false,
});
if (this.sessions.has(sessionId)) {
throw new Error(`[bh] session ${sessionId} already exists`);
}
@@ -202,8 +189,12 @@ export class SessionManager {
try {
const { signal: _signal, ...createOptions } = opts;
windowId = await this.agentWindow.create(AGENT_WINDOW_HOME, createOptions);
this.diagnostics?.("session_manager.window.created", {
session_id: sessionId,
agent_window_id: windowId,
});
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 = {
@@ -211,16 +202,22 @@ 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);
this.windowIndex.set(windowId, sessionId);
this.diagnostics?.("session_manager.start.committed", {
session_id: sessionId,
agent_window_id: windowId,
live_session_ids: this.list().map((entry) => entry.sessionId),
});
return ctx;
} catch (startupError) {
this.diagnostics?.("session_manager.start.failed", {
session_id: sessionId,
agent_window_id: windowId,
error: startupError,
});
if (windowId !== null) {
try {
await this.agentWindow.remove(windowId);
@@ -244,12 +241,28 @@ export class SessionManager {
options: { dropOnly?: boolean } = {},
): Promise<SessionContext | null> {
const ctx = this.sessions.get(sessionId);
this.diagnostics?.("session_manager.stop.requested", {
session_id: sessionId,
drop_only: options.dropOnly ?? false,
existed: ctx !== undefined,
live_session_ids: this.list().map((entry) => entry.sessionId),
});
if (!ctx) return null;
if (!options.dropOnly) {
await this.agentWindow.remove(ctx.agentWindowId);
this.diagnostics?.("session_manager.window.removed", {
session_id: sessionId,
agent_window_id: ctx.agentWindowId,
});
}
this.sessions.delete(sessionId);
this.windowIndex.delete(ctx.agentWindowId);
this.diagnostics?.("session_manager.stop.committed", {
session_id: sessionId,
agent_window_id: ctx.agentWindowId,
drop_only: options.dropOnly ?? false,
live_session_ids: this.list().map((entry) => entry.sessionId),
});
return ctx;
}
@@ -127,38 +127,6 @@ describe("requestBorrowConfirmation", () => {
expect(message.requestId.length).toBeGreaterThan(0);
});
it("proactively focuses the user window before sending the overlay message", async () => {
tabs.get.mockResolvedValueOnce({ id: 42, title: "Tab" });
windows.getLastFocused.mockResolvedValueOnce(
userWindowWithActiveTab({ windowId: 77, tabId: 7, url: "https://app.example/" }),
);
tabs.sendMessage.mockResolvedValueOnce({ type: "borrow-response", allowed: true });
const pending = requestBorrowConfirmation(42, {
deps: { tabs, windows, notifications },
});
await vi.runAllTimersAsync();
await pending;
expect(windows.update).toHaveBeenCalledWith(77, { focused: true });
});
it("still proceeds when proactive window focus fails", async () => {
tabs.get.mockResolvedValueOnce({ id: 42, title: "Tab" });
windows.getLastFocused.mockResolvedValueOnce(
userWindowWithActiveTab({ windowId: 77, tabId: 7, url: "https://app.example/" }),
);
windows.update.mockRejectedValueOnce(new Error("window gone"));
tabs.sendMessage.mockResolvedValueOnce({ type: "borrow-response", allowed: true });
const pending = requestBorrowConfirmation(42, {
deps: { tabs, windows, notifications },
});
await vi.runAllTimersAsync();
expect(await pending).toBe(true);
});
it("sends confirmation to the borrow target when it is the active tab", async () => {
tabs.get.mockResolvedValueOnce({ id: 42, title: "Active Tab" });
windows.getLastFocused.mockResolvedValueOnce(
@@ -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");
@@ -314,114 +232,13 @@ describe("ToolDispatcher", () => {
});
});
it("bypasses and restores the control overlay for an upload trigger click", async () => {
const sendMessage = vi.fn(async () => undefined);
vi.stubGlobal("chrome", {
tabs: {
get: vi.fn(async () => ({ id: 7, windowId: 4242, active: true })),
query: vi.fn(async () => [{ id: 7, windowId: 4242, active: true }]),
sendMessage,
},
});
const { transport, sent, deliver } = fakeTransport();
const sessions = new SessionManager({
agentWindow: {
create: vi.fn(async () => 4242),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
},
});
const ctx = await sessions.start("aa11");
ctx.refStore.set("e1", 123, { tabId: 7 });
const send = vi.fn(async <T>(_tabId: number, method: string, params?: object) => {
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 1280, clientHeight: 720 } } as T;
}
if (method === "DOM.getContentQuads") {
return { quads: [[0, 0, 20, 0, 20, 20, 0, 20]] } as T;
}
if (method === "DOM.resolveNode") {
return { object: { objectId: "trigger-object" } } as T;
}
if (method === "DOM.describeNode") return { node: { backendNodeId: 456 } } as T;
if (method === "Runtime.callFunctionOn") {
const declaration = (params as { functionDeclaration?: string }).functionDeclaration ?? "";
if (declaration.includes("count: state.inputs.length")) {
return { result: { value: { count: 1, multiple: false } } } as T;
}
if (declaration.includes("inputs[0]")) {
return { result: { objectId: "input-object" } } as T;
}
return { result: { value: true } } as T;
}
if (method === "Runtime.evaluate") {
const expression = (params as { expression?: string }).expression ?? "";
if (expression.includes("overlayDetails")) {
return { result: { value: { hitIndex: 0 } } } as T;
}
if (expression.includes("overlayHostPresent")) {
return {
result: {
value: { overlayHostPresent: true, overlayHostConnected: true },
},
} as T;
}
if (expression.includes("count:")) {
return { result: { value: { count: 1, multiple: false } } } as T;
}
if (expression.includes("?.inputs[0]")) {
return { result: { objectId: "input-object" } } as T;
}
return { result: { value: true } } as T;
}
return {} as T;
});
const cdp = {
send,
detachSession: vi.fn(async () => {}),
ensureNetworkCapture: vi.fn(async () => {}),
networkEntriesSince: vi.fn(() => ({
tab_id: 7,
entries: [],
next_since: 0,
truncated: false,
})),
setDeviceMetricsOverride: vi.fn(async () => {}),
clearDeviceMetricsOverride: vi.fn(async () => {}),
setUserAgentOverride: vi.fn(async () => {}),
setTouchEmulationEnabled: vi.fn(async () => {}),
};
const dispatcher = new ToolDispatcher({ transport, sessions, cdp: cdp as TestDispatcherCdp });
dispatcher.start();
deliver(
makeRequest("tool.upload", {
session_id: "aa11",
ref: "@e1",
files: [{ transfer_id: "tr_1", name: "test.png", staged_path: "/stage/test.png" }],
}),
);
await flushMicrotasks();
await vi.waitFor(() => expect(sent).toHaveLength(1));
expect(sent[0]).toMatchObject({ result: { tab_id: 7, file_names: ["test.png"] } });
expect(sendMessage).toHaveBeenNthCalledWith(1, 7, {
type: "bh-automation-bypass",
enabled: true,
});
expect(sendMessage).toHaveBeenNthCalledWith(2, 7, {
type: "bh-automation-bypass",
enabled: false,
});
});
it("detaches CDP state before stopping a session", async () => {
const { transport, sent, deliver } = fakeTransport();
const sessions = new SessionManager({
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 +274,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 4242),
remove,
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
await sessions.start("aa11");
@@ -505,7 +322,7 @@ 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 +342,7 @@ 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 +366,7 @@ 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 +383,7 @@ 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 +400,7 @@ 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();
@@ -600,32 +417,16 @@ describe("ToolDispatcher", () => {
});
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" }));
@@ -642,7 +443,6 @@ 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 () => {
@@ -656,7 +456,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const order: string[] = [];
@@ -738,7 +538,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 1),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
const cdp = {
@@ -788,135 +588,6 @@ 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: {
@@ -928,7 +599,7 @@ 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 });
@@ -965,7 +636,7 @@ 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");
@@ -1017,7 +688,7 @@ 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 });
@@ -1051,7 +722,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 4242),
remove: vi.fn(),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
transport.send = () => {
@@ -1073,7 +744,7 @@ describe("ToolDispatcher", () => {
agentWindow: {
create: vi.fn(async () => 5555),
remove,
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
},
});
transport.send = () => {
@@ -1101,7 +772,7 @@ 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 });
@@ -1152,7 +823,7 @@ 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 });
@@ -1173,7 +844,7 @@ 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 () => {}),
};
}
@@ -1,988 +0,0 @@
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";
import { handleUpload } from "../upload";
function sessions() {
return new SessionManager({
agentWindow: {
create: vi.fn(async () => 100),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
},
});
}
function tabsApi() {
return {
get: vi.fn(
async (tabId: number) => ({ id: tabId, windowId: 100, active: true }) as chrome.tabs.Tab,
),
query: vi.fn(async () => [{ id: 4, windowId: 100, active: true } as chrome.tabs.Tab]),
};
}
function fakeEvent<T extends (...args: never[]) => unknown>() {
const listeners = new Set<T>();
return {
addListener: (listener: T) => listeners.add(listener),
removeListener: (listener: T) => listeners.delete(listener),
emit: (...args: Parameters<T>) => {
for (const listener of listeners) listener(...args);
},
};
}
function actionTarget(frameId?: string, sessionId?: string): ResolvedActionTarget {
return {
tab: { tabId: 4, windowId: 100, active: true },
backendNodeId: 123,
cdpTarget: { tabId: 4, ...(sessionId ? { sessionId } : {}) },
...(frameId ? { frameId } : {}),
usedRef: "e3",
};
}
function withoutOverlay<T>(operation: () => Promise<T>): Promise<T> {
return operation();
}
function uploadCdp(
options: {
inputCount?: number;
multiple?: boolean;
chooser?: { frameId?: string; backendNodeId?: number; mode?: string };
pendingResolve?: boolean;
} = {},
) {
const calls: Array<{ method: string; params?: object }> = [];
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 } };
if (method === "DOM.getContentQuads") return { quads: [[0, 0, 20, 0, 20, 20, 0, 20]] };
if (method === "DOM.resolveNode") {
if (options.pendingResolve) return new Promise<never>(() => {});
return { object: { objectId: "trigger-object" } };
}
if (method === "Runtime.callFunctionOn") {
const declaration = (params as { functionDeclaration?: string }).functionDeclaration ?? "";
if (declaration.includes("Object.defineProperty")) return { result: { value: true } };
if (declaration.includes("count: state.inputs.length")) {
return {
result: {
value: {
count: options.inputCount ?? 1,
multiple: options.multiple ?? true,
},
},
};
}
if (declaration.includes("inputs[0]")) {
return { result: { objectId: "input-object" } };
}
return { result: { value: true } };
}
if (method === "DOM.describeNode") return { node: { backendNodeId: 456 } };
if (
method === "Input.dispatchMouseEvent" &&
(params as { type?: string }).type === "mousePressed" &&
options.chooser
) {
cdpEvent?.({ tabId: 4 }, "Page.fileChooserOpened", options.chooser);
}
return {};
});
const cdp: CdpRunner = {
send: send as unknown as CdpRunner["send"],
onEvent: (handler) => {
cdpEvent = handler;
return { dispose: vi.fn() };
},
};
return {
calls,
emitChooser: (event: { frameId?: string; backendNodeId?: number; mode?: string }) =>
cdpEvent?.({ tabId: 4 }, "Page.fileChooserOpened", event),
cdp,
};
}
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();
const ctx = await manager.start("s1");
ctx.refStore.set("e3", 123, { tabId: 4 });
const { cdp, calls } = uploadCdp();
const result = await handleUpload(
manager,
{
session_id: "s1",
ref: "@e3",
files: [
{ transfer_id: "tr_1", name: "one.png", staged_path: "/private/stage/one" },
{ transfer_id: "tr_2", name: "two.png", staged_path: "/private/stage/two" },
],
},
{ cdp, tabsApi: tabsApi() },
);
expect(result).toMatchObject({ tab_id: 4, file_names: ["one.png", "two.png"] });
expect(calls[0]).toEqual({
method: "Page.setInterceptFileChooserDialog",
params: { enabled: true },
});
expect(calls).toContainEqual({
method: "Page.setInterceptFileChooserDialog",
params: { enabled: false, cancel: true },
});
expect(calls).toContainEqual({
method: "DOM.setFileInputFiles",
params: { files: ["/private/stage/one", "/private/stage/two"], backendNodeId: 456 },
});
});
it("fails immediately when the trigger does not activate a file input", async () => {
const { cdp } = uploadCdp({ inputCount: 0 });
const result = await uploadThroughActivatedFileInput({
cdp,
actionTarget: actionTarget(),
files: ["/private/stage/one"],
timeoutMs: 100,
trigger: async () => ({ tab_id: 4, x: 10, y: 10 }),
});
expect(result).toMatchObject({
code: "unsupported",
data: { reason: "file_input_not_activated", phase: "resolve_input" },
});
});
it("fails before clicking when chooser interception is unavailable", async () => {
const trigger = vi.fn(async () => ({ tab_id: 4, x: 10, y: 10 }));
const cdp: CdpRunner = {
send: vi.fn(async (_tabId: number, method: string) => {
if (method === "Page.setInterceptFileChooserDialog") {
throw new Error("method unavailable");
}
return {};
}) as CdpRunner["send"],
};
const result = await uploadThroughActivatedFileInput({
cdp,
actionTarget: actionTarget(),
files: ["/private/stage/one"],
timeoutMs: 100,
trigger,
});
expect(result).toMatchObject({
code: "cdp_failed",
data: { effect_state: "none", phase: "arm_interception" },
});
expect(trigger).not.toHaveBeenCalled();
});
it("uses an exact chooser event as an independent input-location signal", async () => {
const { cdp, calls, emitChooser } = uploadCdp({ inputCount: 0 });
const result = await uploadThroughActivatedFileInput({
cdp,
actionTarget: actionTarget("f1"),
files: ["/private/stage/one"],
timeoutMs: 100,
trigger: async () => {
emitChooser({ frameId: "f1", backendNodeId: 789, mode: "selectSingle" });
return { tab_id: 4, x: 10, y: 10 };
},
});
expect(result).toMatchObject({ multiple: false });
expect(calls).toContainEqual({
method: "DOM.setFileInputFiles",
params: { files: ["/private/stage/one"], backendNodeId: 789 },
});
});
it("reports a File System Access picker without waiting for a timeout", async () => {
const { cdp, emitChooser } = uploadCdp({
inputCount: 0,
});
const result = await uploadThroughActivatedFileInput({
cdp,
actionTarget: actionTarget("f1"),
files: ["/private/stage/one"],
timeoutMs: 100,
trigger: async () => {
emitChooser({ frameId: "f1", mode: "selectSingle" });
return { tab_id: 4, x: 10, y: 10 };
},
});
expect(result).toMatchObject({
code: "unsupported",
message: "upload trigger invoked a non-input file picker",
data: { reason: "file_input_not_activated", phase: "resolve_input" },
});
});
it("bounds a stuck file-input probe", async () => {
const { cdp } = uploadCdp({ pendingResolve: true });
const result = await uploadThroughActivatedFileInput({
cdp,
actionTarget: actionTarget(),
files: ["/private/stage/one"],
timeoutMs: 5,
trigger: vi.fn(),
});
expect(result).toMatchObject({
code: "timeout",
data: { reason: "file_input_probe_failed", phase: "arm_input_probe" },
});
});
it("marks a timed-out file assignment unknown and detaches browser state", async () => {
const fixture = uploadCdp();
const originalSend = fixture.cdp.send;
const detach = vi.fn(async () => {});
fixture.cdp.detach = detach;
fixture.cdp.send = vi.fn((tabId: number, method: string, params?: object) => {
if (method === "DOM.setFileInputFiles") return new Promise<never>(() => {});
return originalSend(tabId, method, params);
}) as CdpRunner["send"];
const result = await uploadThroughActivatedFileInput({
cdp: fixture.cdp,
actionTarget: actionTarget(),
files: ["/private/stage/one"],
timeoutMs: 10,
trigger: async () => ({ tab_id: 4, x: 10, y: 10 }),
});
expect(result).toMatchObject({
code: "timeout",
data: { effect_state: "unknown", phase: "set_files" },
});
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 === "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");
ctx.refStore.set("e3", 123, { tabId: 4 });
const onCreated = fakeEvent<(item: chrome.downloads.DownloadItem) => void>();
const onChanged = fakeEvent<(delta: chrome.downloads.DownloadDelta) => void>();
const onDeterminingFilename =
fakeEvent<
(
item: chrome.downloads.DownloadItem,
suggest: (suggestion?: chrome.downloads.DownloadFilenameSuggestion) => void,
) => void | true
>();
const initial = {
id: 9,
url: "https://example.test/result.zip",
finalUrl: "https://example.test/result.zip",
filename: "result.zip",
state: "in_progress",
fileSize: -1,
totalBytes: 12,
mime: "application/zip",
danger: "safe",
} as chrome.downloads.DownloadItem;
const completed = {
...initial,
filename: "/profile/Downloads/BrowserSkill/tr_1/result.zip",
state: "complete",
fileSize: 12,
} as chrome.downloads.DownloadItem;
const downloads: DownloadsApi = {
onCreated,
onChanged,
onDeterminingFilename,
search: vi.fn(async () => [completed]),
cancel: vi.fn(async () => {}),
removeFile: vi.fn(async () => {}),
};
let cdpEvent: Parameters<NonNullable<CdpRunner["onEvent"]>>[0] | undefined;
let suggested: chrome.downloads.DownloadFilenameSuggestion | undefined;
const send = vi.fn(async (_tabId: number, method: string, params?: object) => {
if (method === "Page.getLayoutMetrics")
return { cssLayoutViewport: { clientWidth: 1280, clientHeight: 720 } };
if (method === "DOM.getContentQuads") return { quads: [[0, 0, 20, 0, 20, 20, 0, 20]] };
if (
method === "Input.dispatchMouseEvent" &&
(params as { type?: string }).type === "mousePressed"
) {
cdpEvent?.({ tabId: 4 }, "Page.downloadWillBegin", {
url: initial.url,
suggestedFilename: "result.zip",
});
await new Promise<void>((resolve) => {
onDeterminingFilename.emit(initial, (value) => {
suggested = value;
resolve();
});
});
onCreated.emit(completed);
}
return {};
});
const cdp: CdpRunner = {
send: send as unknown as CdpRunner["send"],
onEvent: (handler) => {
cdpEvent = handler;
return { dispose: vi.fn() };
},
};
const result = await handleDownload(
manager,
{ session_id: "s1", ref: "@e3", browser_relative_dir: "BrowserSkill/tr_1" },
{ cdp, tabsApi: tabsApi(), downloads },
);
expect(suggested).toEqual({
filename: "BrowserSkill/tr_1/result.zip",
conflictAction: "overwrite",
});
expect(result).toMatchObject({
tab_id: 4,
suggested_filename: "result.zip",
byte_size: 12,
browser_path: completed.filename,
});
});
it("does not claim a download without an intent from the exact target", async () => {
const onCreated = fakeEvent<(item: chrome.downloads.DownloadItem) => void>();
const onChanged = fakeEvent<(delta: chrome.downloads.DownloadDelta) => void>();
const onDeterminingFilename =
fakeEvent<
(
item: chrome.downloads.DownloadItem,
suggest: (suggestion?: chrome.downloads.DownloadFilenameSuggestion) => void,
) => void | true
>();
const downloads: DownloadsApi = {
onCreated,
onChanged,
onDeterminingFilename,
search: vi.fn(async () => []),
cancel: vi.fn(async () => {}),
removeFile: vi.fn(async () => {}),
};
let cdpEvent: Parameters<NonNullable<CdpRunner["onEvent"]>>[0] | undefined;
const cdp: CdpRunner = {
send: vi.fn(async () => ({})) as unknown as CdpRunner["send"],
onEvent: (handler) => {
cdpEvent = handler;
return { dispose: vi.fn() };
},
};
const unrelated = {
id: 17,
url: "https://example.test/unrelated.zip",
finalUrl: "https://example.test/unrelated.zip",
filename: "unrelated.zip",
state: "in_progress",
} as chrome.downloads.DownloadItem;
let defaultSuggestionCalled = false;
const result = await captureBrowserDownload({
cdp,
target: { tabId: 4, sessionId: "expected-child" },
downloads,
browserRelativeDir: "BrowserSkill/tr_1",
timeoutMs: 5,
trigger: async () => {
cdpEvent?.({ tabId: 4, sessionId: "other-child" }, "Page.downloadWillBegin", {
url: unrelated.url,
suggestedFilename: unrelated.filename,
});
onDeterminingFilename.emit(unrelated, (suggestion) => {
defaultSuggestionCalled = suggestion === undefined;
});
return { tab_id: 4, x: 10, y: 10 };
},
});
expect(defaultSuggestionCalled).toBe(true);
expect(downloads.cancel).not.toHaveBeenCalled();
expect(result).toMatchObject({
code: "cdp_failed",
data: { reason: "download_capture_failed" },
});
});
it("correlates a filename candidate that arrives before the CDP intent", async () => {
const onCreated = fakeEvent<(item: chrome.downloads.DownloadItem) => void>();
const onChanged = fakeEvent<(delta: chrome.downloads.DownloadDelta) => void>();
const onDeterminingFilename =
fakeEvent<
(
item: chrome.downloads.DownloadItem,
suggest: (suggestion?: chrome.downloads.DownloadFilenameSuggestion) => void,
) => void | true
>();
const initial = {
id: 21,
url: "https://example.test/candidate-first.bin",
finalUrl: "https://example.test/candidate-first.bin",
filename: "candidate-first.bin",
state: "in_progress",
fileSize: -1,
totalBytes: 4,
bytesReceived: 0,
} as chrome.downloads.DownloadItem;
const complete = {
...initial,
state: "complete",
fileSize: 4,
} as chrome.downloads.DownloadItem;
const downloads: DownloadsApi = {
onCreated,
onChanged,
onDeterminingFilename,
search: vi.fn(async () => [complete]),
cancel: vi.fn(async () => {}),
removeFile: vi.fn(async () => {}),
};
let cdpEvent: Parameters<NonNullable<CdpRunner["onEvent"]>>[0] | undefined;
const cdp: CdpRunner = {
send: vi.fn(async () => ({})) as CdpRunner["send"],
onEvent: (handler) => {
cdpEvent = handler;
return { dispose: vi.fn() };
},
};
let suggestion: chrome.downloads.DownloadFilenameSuggestion | undefined;
const result = await captureBrowserDownload({
cdp,
target: { tabId: 4 },
downloads,
browserRelativeDir: "BrowserSkill/tr_21",
timeoutMs: 1_000,
trigger: async () => {
const suggested = new Promise<void>((resolve) => {
onDeterminingFilename.emit(initial, (value) => {
suggestion = value;
resolve();
});
});
cdpEvent?.({ tabId: 4 }, "Page.downloadWillBegin", {
url: initial.url,
suggestedFilename: initial.filename,
});
await suggested;
onCreated.emit(complete);
return { tab_id: 4, x: 10, y: 10 };
},
});
expect(suggestion).toEqual({
filename: "BrowserSkill/tr_21/candidate-first.bin",
conflictAction: "overwrite",
});
expect(result).toMatchObject({ item: { id: 21, state: "complete" } });
});
it("removes a completed download when the final size exceeds the limit", async () => {
const onCreated = fakeEvent<(item: chrome.downloads.DownloadItem) => void>();
const onChanged = fakeEvent<(delta: chrome.downloads.DownloadDelta) => void>();
const onDeterminingFilename =
fakeEvent<
(
item: chrome.downloads.DownloadItem,
suggest: (suggestion?: chrome.downloads.DownloadFilenameSuggestion) => void,
) => void | true
>();
const initial = {
id: 22,
url: "https://example.test/oversized.bin",
finalUrl: "https://example.test/oversized.bin",
filename: "oversized.bin",
state: "in_progress",
fileSize: -1,
totalBytes: -1,
bytesReceived: 0,
} as chrome.downloads.DownloadItem;
const complete = {
...initial,
filename: "/profile/Downloads/BrowserSkill/tr_22/oversized.bin",
state: "complete",
fileSize: 8,
totalBytes: 8,
bytesReceived: 8,
} as chrome.downloads.DownloadItem;
const downloads: DownloadsApi = {
onCreated,
onChanged,
onDeterminingFilename,
search: vi.fn(async () => [complete]),
cancel: vi.fn(async () => {}),
removeFile: vi.fn(async () => {}),
};
let cdpEvent: Parameters<NonNullable<CdpRunner["onEvent"]>>[0] | undefined;
const cdp: CdpRunner = {
send: vi.fn(async () => ({})) as CdpRunner["send"],
onEvent: (handler) => {
cdpEvent = handler;
return { dispose: vi.fn() };
},
};
const result = await captureBrowserDownload({
cdp,
target: { tabId: 4 },
downloads,
browserRelativeDir: "BrowserSkill/tr_22",
maxByteSize: 4,
timeoutMs: 1_000,
trigger: async () => {
cdpEvent?.({ tabId: 4 }, "Page.downloadWillBegin", {
url: initial.url,
suggestedFilename: initial.filename,
});
await new Promise<void>((resolve) => {
onDeterminingFilename.emit(initial, () => resolve());
});
onCreated.emit(initial);
onChanged.emit({ id: initial.id, state: { current: "complete" } });
return { tab_id: 4, x: 10, y: 10 };
},
});
expect(result).toMatchObject({
code: "cdp_failed",
data: { reason: "download_capture_failed", effect_state: "committed" },
});
expect(downloads.removeFile).toHaveBeenCalledWith(initial.id);
expect(downloads.cancel).not.toHaveBeenCalled();
});
it("reconciles a download that completes while cancellation is being requested", async () => {
const onCreated = fakeEvent<(item: chrome.downloads.DownloadItem) => void>();
const onChanged = fakeEvent<(delta: chrome.downloads.DownloadDelta) => void>();
const onDeterminingFilename =
fakeEvent<
(
item: chrome.downloads.DownloadItem,
suggest: (suggestion?: chrome.downloads.DownloadFilenameSuggestion) => void,
) => void | true
>();
const initial = {
id: 23,
url: "https://example.test/racing.bin",
finalUrl: "https://example.test/racing.bin",
filename: "racing.bin",
state: "in_progress",
fileSize: -1,
totalBytes: -1,
bytesReceived: 0,
} as chrome.downloads.DownloadItem;
const complete = {
...initial,
filename: "/profile/Downloads/BrowserSkill/tr_23/racing.bin",
state: "complete",
fileSize: 4,
totalBytes: 4,
bytesReceived: 4,
} as chrome.downloads.DownloadItem;
const downloads: DownloadsApi = {
onCreated,
onChanged,
onDeterminingFilename,
search: vi.fn().mockResolvedValueOnce([initial]).mockResolvedValueOnce([complete]),
cancel: vi.fn(async () => {
throw new Error("download already complete");
}),
removeFile: vi.fn(async () => {}),
};
let cdpEvent: Parameters<NonNullable<CdpRunner["onEvent"]>>[0] | undefined;
const cdp: CdpRunner = {
send: vi.fn(async () => ({})) as CdpRunner["send"],
onEvent: (handler) => {
cdpEvent = handler;
return { dispose: vi.fn() };
},
};
const result = await captureBrowserDownload({
cdp,
target: { tabId: 4 },
downloads,
browserRelativeDir: "BrowserSkill/tr_23",
timeoutMs: 80,
trigger: async () => {
cdpEvent?.({ tabId: 4 }, "Page.downloadWillBegin", {
url: initial.url,
suggestedFilename: initial.filename,
});
await new Promise<void>((resolve) => {
onDeterminingFilename.emit(initial, () => resolve());
});
onCreated.emit(initial);
return { tab_id: 4, x: 10, y: 10 };
},
});
expect(result).toMatchObject({
code: "cdp_failed",
data: { reason: "download_capture_failed", effect_state: "committed" },
});
expect(downloads.cancel).toHaveBeenCalledWith(initial.id);
expect(downloads.removeFile).toHaveBeenCalledWith(initial.id);
expect(result).not.toMatchObject({ data: { cleanup_state: "failed" } });
});
it("rejects ambiguous attribution without cancelling either unclaimed download", async () => {
const onCreated = fakeEvent<(item: chrome.downloads.DownloadItem) => void>();
const onChanged = fakeEvent<(delta: chrome.downloads.DownloadDelta) => void>();
const onDeterminingFilename =
fakeEvent<
(
item: chrome.downloads.DownloadItem,
suggest: (suggestion?: chrome.downloads.DownloadFilenameSuggestion) => void,
) => void | true
>();
const downloads: DownloadsApi = {
onCreated,
onChanged,
onDeterminingFilename,
search: vi.fn(async () => []),
cancel: vi.fn(async () => {}),
removeFile: vi.fn(async () => {}),
};
let cdpEvent: Parameters<NonNullable<CdpRunner["onEvent"]>>[0] | undefined;
const cdp: CdpRunner = {
send: vi.fn(async () => ({})) as CdpRunner["send"],
onEvent: (handler) => {
cdpEvent = handler;
return { dispose: vi.fn() };
},
};
const defaults: number[] = [];
const candidate = (id: number) =>
({
id,
url: "https://example.test/same.bin",
finalUrl: "https://example.test/same.bin",
filename: "same.bin",
state: "in_progress",
}) as chrome.downloads.DownloadItem;
const result = await captureBrowserDownload({
cdp,
target: { tabId: 4 },
downloads,
browserRelativeDir: "BrowserSkill/tr_ambiguous",
timeoutMs: 100,
trigger: async () => {
cdpEvent?.({ tabId: 4 }, "Page.downloadWillBegin", {
url: "https://example.test/same.bin",
suggestedFilename: "same.bin",
});
for (const id of [31, 32]) {
onDeterminingFilename.emit(candidate(id), (value) => {
if (value === undefined) defaults.push(id);
});
}
return { tab_id: 4, x: 10, y: 10 };
},
});
expect(defaults.sort()).toEqual([31, 32]);
expect(downloads.cancel).not.toHaveBeenCalled();
expect(result).toMatchObject({
code: "cdp_failed",
data: { effect_state: "unknown", phase: "attribution" },
});
});
});
@@ -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 });
});
});
@@ -1,5 +1,5 @@
import { describe, expect, it, vi } from "vitest";
import { resolveNodeGeometry } from "../frame-geometry";
import { resolveFrameProjection, resolveNodeGeometry } from "../frame-geometry";
import {
clipPolygon,
polygonArea,
@@ -10,7 +10,6 @@ import {
rectPolygon,
regionBounds,
} from "../geometry";
import { GeometryContext } from "../geometry/frame-context";
import type { CdpRunner } from "../shared";
describe("frame geometry projection", () => {
@@ -83,24 +82,28 @@ describe("frame geometry projection", () => {
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([
{
@@ -166,7 +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 },
});
});
@@ -259,7 +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,
});
});
});
@@ -21,7 +21,7 @@ function fakeAgentWindow(ids: number[]) {
return id;
}),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
};
}
@@ -456,6 +456,30 @@ describe("handleClick", () => {
expect(res).toMatchObject({ code: "not_found", data: { reason: "selector_not_found" } });
});
it("returns invalid_selector when Chrome rejects non-CSS selector syntax", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
await sm.start("aa11");
const fake = makeFakeCdp({
"DOM.getDocument": () => ({ root: { nodeId: 1 } }),
"DOM.querySelector": () => {
throw new Error('{"code":-32000,"message":"DOM Error while querying"}');
},
});
const res = await handleClick(
sm,
{ session_id: "aa11", selector: "text=下午 12~18点" },
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
);
expect(res).toMatchObject({
code: "invalid_params",
message: "selector is not valid CSS: text=下午 12~18点",
data: {
reason: "invalid_selector",
selector: "text=下午 12~18点",
},
});
});
it("respects the AbortSignal", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
@@ -540,21 +564,6 @@ describe("handleHover", () => {
});
});
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]) });
@@ -601,8 +610,7 @@ 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(
@@ -616,12 +624,13 @@ 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 });
@@ -633,12 +642,12 @@ 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(
@@ -665,8 +674,7 @@ 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 () => {}),
};
}
@@ -28,7 +28,7 @@ function fakeAgentWindow(ids: number[]) {
return id;
}),
remove: vi.fn(async () => {}),
ensureActiveTab: vi.fn(async () => 1),
ensureActiveTab: vi.fn(async () => {}),
};
}
@@ -65,11 +65,7 @@ function makeFakeCdp(handlers: Record<string, (params?: object) => unknown>) {
sent.push({ method, params });
const handler = handlers[method];
if (!handler && method === "Page.getLayoutMetrics") {
return {
visualViewport: { clientWidth: 1000 },
cssVisualViewport: { clientWidth: 1000 },
cssLayoutViewport: { clientWidth: 1280, clientHeight: 720 },
};
return { cssLayoutViewport: { clientWidth: 1280, clientHeight: 720 } };
}
if (!handler) throw new Error(`unexpected CDP call ${method}`);
return handler(params);
@@ -270,15 +266,7 @@ describe("handleScreenshot", () => {
expect(sent.find((c) => c.method === "Page.captureScreenshot")).toBeUndefined();
});
it.each([
{ zoom: 1, scroll: 0, expected: { x: 10, y: 20, width: 100, height: 40 } },
{ zoom: 0.9, scroll: 100, expected: { x: 9, y: 108, width: 90, height: 36 } },
{ zoom: 1.25, scroll: 100, expected: { x: 12.5, y: 150, width: 125, height: 50 } },
])("captures a ref in page DIP at zoom $zoom and scroll $scroll", async ({
zoom,
scroll,
expected,
}) => {
it("captures a clipped PNG when ref is given", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e5", 999, { tabId: 7 });
@@ -286,10 +274,6 @@ describe("handleScreenshot", () => {
"DOM.scrollIntoViewIfNeeded": () => ({}),
"DOM.getContentQuads": () => ({ quads: [[10, 20, 110, 20, 110, 60, 10, 60]] }),
"Page.captureScreenshot": () => ({ data: TINY_PNG }),
"Page.getLayoutMetrics": () => ({
cssLayoutViewport: { clientWidth: 1280, clientHeight: 720, pageX: 0, pageY: scroll },
cssVisualViewport: { zoom },
}),
});
const captureVisibleTab = vi.fn();
const res = await handleScreenshot(
@@ -313,8 +297,7 @@ describe("handleScreenshot", () => {
clip?: { x: number; y: number; width: number; height: number };
}
)?.clip;
expect(clip).toMatchObject(expected);
expect(sent.filter((c) => c.method === "Page.getLayoutMetrics")).toHaveLength(1);
expect(clip).toMatchObject({ x: 10, y: 20, width: 100, height: 40 });
});
it("returns not_found for unknown ref", async () => {
@@ -672,60 +655,6 @@ describe("buildVomScene", () => {
expect(nestedInput?.parentId).toBe(result.nodes.find((item) => item.backendNodeId === 210)?.id);
});
it("excludes an overlay only in its owning document when target backend ids collide", () => {
const owner = (id: number): CapturedNode => ({
backendNodeId: id,
parentBackendNodeId: null,
frameId: "main",
tag: "iframe",
attrs: {},
rect: { x: id * 10, y: 0, w: 200, h: 100 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
});
const owners = [owner(10), owner(20)];
const result = buildFrameVomScene(
[
{
frameId: "main",
contextScopeId: "main",
target: { tabId: 7 },
domNodes: owners,
axNodes: [],
},
...["left", "right"].map((frameId, i) => ({
frameId,
contextScopeId: frameId,
parentFrameId: "main",
ownerBackendNodeId: owners[i].backendNodeId,
target: { tabId: 7, sessionId: frameId },
excludedBackendNodeIds: new Set(i === 0 ? [7] : []),
domNodes: [],
axNodes: [
{
nodeId: "button",
frameId,
backendDOMNodeId: 7,
role: { type: "role", value: "button" },
name: { type: "computedString", value: frameId + " action" },
},
],
})),
],
{
nodes: owners,
viewport: { width: 800, height: 600 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
},
);
const rendered = renderVom(result);
expect(rendered.text).not.toContain("left action");
expect(rendered.text).toContain("right action");
expect(rendered.refs.find((ref) => ref.backendNodeId === 7)?.frameId).toBe("right");
});
it("does not place a child document at the page root when its frame boundary is unresolved", () => {
const childNode: CapturedNode = {
backendNodeId: 101,
@@ -1975,41 +1904,36 @@ describe("buildVomScene", () => {
backendDOMNodeId: 20,
},
];
const scene = buildVomScene(
axNodes,
{
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
nodes: [
{
backendNodeId: 10,
parentBackendNodeId: null,
tag: "body",
attrs: {},
rect: { x: 0, y: 0, w: 1000, h: 800 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 20,
parentBackendNodeId: 10,
tag: "button",
attrs: {},
rect: { x: 20, y: 20, w: 120, h: 40 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
},
],
},
{
surfaceProbes: [
{ triggerBackendNodeId: 20, triggerAction: "hover", subItems: ["Shoes", "Bags"] },
],
},
);
const scene = buildVomScene(axNodes, {
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
surfaceProbes: [
{ triggerBackendNodeId: 20, triggerAction: "hover", subItems: ["Shoes", "Bags"] },
],
nodes: [
{
backendNodeId: 10,
parentBackendNodeId: null,
tag: "body",
attrs: {},
rect: { x: 0, y: 0, w: 1000, h: 800 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 20,
parentBackendNodeId: 10,
tag: "button",
attrs: {},
rect: { x: 20, y: 20, w: 120, h: 40 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
},
],
});
expect(scene.surfaces).toEqual([
{ triggerId: 20, triggerAction: "hover", subItems: ["Shoes", "Bags"] },
@@ -2033,51 +1957,46 @@ describe("buildVomScene", () => {
backendDOMNodeId: 21,
},
];
const scene = buildVomScene(
axNodes,
{
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
nodes: [
{
backendNodeId: 10,
parentBackendNodeId: null,
tag: "body",
attrs: {},
rect: { x: 0, y: 0, w: 1000, h: 800 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 20,
parentBackendNodeId: 10,
tag: "div",
attrs: { class: "tg-avatar" },
rect: { x: 900, y: 10, w: 30, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 21,
parentBackendNodeId: 20,
tag: "div",
attrs: { class: "tg-avatar__inner" },
rect: { x: 902, y: 12, w: 26, h: 26 },
paintOrder: 2,
position: "static",
pointerEvents: "auto",
},
],
},
{
surfaceProbes: [
{ triggerBackendNodeId: 20, triggerAction: "hover", subItems: ["My profile"] },
],
},
);
const scene = buildVomScene(axNodes, {
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
surfaceProbes: [
{ triggerBackendNodeId: 20, triggerAction: "hover", subItems: ["My profile"] },
],
nodes: [
{
backendNodeId: 10,
parentBackendNodeId: null,
tag: "body",
attrs: {},
rect: { x: 0, y: 0, w: 1000, h: 800 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 20,
parentBackendNodeId: 10,
tag: "div",
attrs: { class: "tg-avatar" },
rect: { x: 900, y: 10, w: 30, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 21,
parentBackendNodeId: 20,
tag: "div",
attrs: { class: "tg-avatar__inner" },
rect: { x: 902, y: 12, w: 26, h: 26 },
paintOrder: 2,
position: "static",
pointerEvents: "auto",
},
],
});
expect(renderVom(scene).text).toContain('@e1 button "image" [hover first: My profile]');
});
@@ -2098,53 +2017,48 @@ describe("buildVomScene", () => {
backendDOMNodeId: 21,
},
];
const scene = buildVomScene(
axNodes,
{
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
nodes: [
{
backendNodeId: 10,
parentBackendNodeId: null,
tag: "body",
attrs: {},
rect: { x: 0, y: 0, w: 1000, h: 800 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 20,
parentBackendNodeId: 10,
tag: "div",
attrs: { class: "tg-avatar" },
rect: { x: 900, y: 10, w: 30, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 21,
parentBackendNodeId: 20,
tag: "div",
attrs: { class: "tg-avatar__inner" },
rect: { x: 902, y: 12, w: 26, h: 26 },
paintOrder: 2,
position: "static",
pointerEvents: "auto",
},
],
},
{
surfaceProbes: [
{ triggerBackendNodeId: 20, triggerAction: "hover", subItems: ["My profile"] },
{ triggerBackendNodeId: 20, triggerAction: "hover", subItems: ["Sign out"] },
{ triggerBackendNodeId: 21, triggerAction: "hover", subItems: ["Settings"] },
],
},
);
const scene = buildVomScene(axNodes, {
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
surfaceProbes: [
{ triggerBackendNodeId: 20, triggerAction: "hover", subItems: ["My profile"] },
{ triggerBackendNodeId: 20, triggerAction: "hover", subItems: ["Sign out"] },
{ triggerBackendNodeId: 21, triggerAction: "hover", subItems: ["Settings"] },
],
nodes: [
{
backendNodeId: 10,
parentBackendNodeId: null,
tag: "body",
attrs: {},
rect: { x: 0, y: 0, w: 1000, h: 800 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 20,
parentBackendNodeId: 10,
tag: "div",
attrs: { class: "tg-avatar" },
rect: { x: 900, y: 10, w: 30, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 21,
parentBackendNodeId: 20,
tag: "div",
attrs: { class: "tg-avatar__inner" },
rect: { x: 902, y: 12, w: 26, h: 26 },
paintOrder: 2,
position: "static",
pointerEvents: "auto",
},
],
});
expect(scene.surfaces).toEqual([
{ triggerId: 21, triggerAction: "hover", subItems: ["My profile"] },
@@ -2167,59 +2081,54 @@ describe("buildVomScene", () => {
backendDOMNodeId: 21,
},
];
const scene = buildVomScene(
axNodes,
{
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
nodes: [
{
backendNodeId: 10,
parentBackendNodeId: null,
tag: "body",
attrs: {},
rect: { x: 0, y: 0, w: 1000, h: 800 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
cursor: "auto",
},
{
backendNodeId: 20,
parentBackendNodeId: 10,
tag: "div",
attrs: { class: "tg-avatar" },
rect: { x: 900, y: 10, w: 30, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
cursor: "pointer",
},
{
backendNodeId: 21,
parentBackendNodeId: 20,
tag: "div",
attrs: { class: "tg-avatar__inner" },
rect: { x: 902, y: 12, w: 26, h: 26 },
paintOrder: 2,
position: "static",
pointerEvents: "auto",
cursor: "pointer",
},
],
},
{
surfaceProbes: [
{
triggerBackendNodeId: 20,
triggerPoint: { x: 915, y: 25 },
triggerAction: "hover",
subItems: ["My profile", "Sign out"],
},
],
},
);
const scene = buildVomScene(axNodes, {
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
surfaceProbes: [
{
triggerBackendNodeId: 20,
triggerPoint: { x: 915, y: 25 },
triggerAction: "hover",
subItems: ["My profile", "Sign out"],
},
],
nodes: [
{
backendNodeId: 10,
parentBackendNodeId: null,
tag: "body",
attrs: {},
rect: { x: 0, y: 0, w: 1000, h: 800 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
cursor: "auto",
},
{
backendNodeId: 20,
parentBackendNodeId: 10,
tag: "div",
attrs: { class: "tg-avatar" },
rect: { x: 900, y: 10, w: 30, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
cursor: "pointer",
},
{
backendNodeId: 21,
parentBackendNodeId: 20,
tag: "div",
attrs: { class: "tg-avatar__inner" },
rect: { x: 902, y: 12, w: 26, h: 26 },
paintOrder: 2,
position: "static",
pointerEvents: "auto",
cursor: "pointer",
},
],
});
expect(scene.surfaces).toEqual([
{ triggerId: 20, triggerAction: "hover", subItems: ["My profile", "Sign out"] },
@@ -2245,46 +2154,41 @@ describe("buildVomScene", () => {
backendDOMNodeId: 42,
},
];
const scene = buildVomScene(
axNodes,
{
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
nodes: [
{
backendNodeId: 10,
parentBackendNodeId: null,
tag: "body",
attrs: {},
rect: { x: 0, y: 0, w: 1000, h: 800 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 42,
parentBackendNodeId: 10,
tag: "a",
attrs: {},
rect: { x: 860, y: 120, w: 40, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
},
],
},
{
surfaceProbes: [
{
triggerBackendNodeId: 999,
triggerPoint: { x: 900, y: 20 },
triggerAction: "hover",
subItems: ["My profile"],
},
],
},
);
const scene = buildVomScene(axNodes, {
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
surfaceProbes: [
{
triggerBackendNodeId: 999,
triggerPoint: { x: 900, y: 20 },
triggerAction: "hover",
subItems: ["My profile"],
},
],
nodes: [
{
backendNodeId: 10,
parentBackendNodeId: null,
tag: "body",
attrs: {},
rect: { x: 0, y: 0, w: 1000, h: 800 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 42,
parentBackendNodeId: 10,
tag: "a",
attrs: {},
rect: { x: 860, y: 120, w: 40, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
},
],
});
expect(scene.surfaces).toBeUndefined();
expect(renderVom(scene).text).not.toContain("[hover first:");
@@ -2552,11 +2456,7 @@ describe("handleSnapshot", () => {
if (method === "Accessibility.enable") return {};
if (method === "Accessibility.getFullAXTree") return { nodes };
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 === "DOMSnapshot.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") throw new Error("snapshot unsupported");
@@ -2643,11 +2543,7 @@ describe("handleSnapshot", () => {
if (method === "Accessibility.enable") return {};
if (method === "Accessibility.getFullAXTree") return { nodes: [root, button] };
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 === "DOMSnapshot.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") {
@@ -2710,110 +2606,7 @@ describe("handleSnapshot", () => {
);
});
it("hovers the page only after the accessibility tree has been captured", async () => {
// Hovering can open menus and reflow the page. Probing between the DOM and
// AX captures would leave the two halves of one observation describing the
// page on either side of that change.
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
await sm.start("aa11");
const root: CdpAxNode = {
nodeId: "1",
role: { type: "role", value: "RootWebArea" },
name: { type: "computedString", value: "Example" },
backendDOMNodeId: 100,
childIds: ["2"],
};
const button: CdpAxNode = {
nodeId: "2",
parentId: "1",
role: { type: "role", value: "button" },
name: { type: "computedString", value: "Products" },
backendDOMNodeId: 200,
};
const strings = ["body", "button", "position", "static", "pointer-events", "auto", "cursor"];
const i = (s: string) => strings.indexOf(s);
const methodOrder: string[] = [];
const send = vi.fn(async (_tabId: number, method: string, params?: object) => {
methodOrder.push(method);
if (method === "Accessibility.enable") return {};
if (method === "Accessibility.getFullAXTree") return { nodes: [root, button] };
if (method === "Page.getLayoutMetrics") {
return {
visualViewport: { clientWidth: 1000 },
cssVisualViewport: { clientWidth: 1000 },
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
};
}
if (method === "DOMSnapshot.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") {
return {
strings,
documents: [
{
nodes: {
parentIndex: [-1, 0],
nodeName: [i("body"), i("button")],
backendNodeId: [100, 200],
attributes: [[], []],
},
layout: {
nodeIndex: [0, 1],
styles: [
[i("static"), i("auto"), i("auto")],
[i("static"), i("auto"), i("auto")],
],
bounds: [
[0, 0, 1000, 800],
[20, 20, 120, 40],
],
paintOrders: [0, 1],
},
},
],
};
}
if (method === "Input.dispatchMouseEvent") return {};
if (method === "Runtime.evaluate") {
const expression = (params as { expression?: string } | undefined)?.expression ?? "";
// Report the button as a `:hover` rule target so a real hover fires.
if (expression.includes("document.styleSheets")) {
return { result: { value: [{ x: 80, y: 40 }] } };
}
return { result: { value: [] } };
}
throw new Error(`unexpected CDP method ${method}`);
});
const res = await handleObserve(
sm,
{ session_id: "aa11", probe_hover: true },
{
cdp: {
send: send as unknown as <T = unknown>(
tabId: number,
method: string,
params?: object,
) => Promise<T>,
trackSessionTab: vi.fn(),
},
tabsApi: {
get: vi.fn(
async (tabId: number) =>
({ id: tabId, windowId: 100, active: true }) as chrome.tabs.Tab,
),
query: vi.fn(async () => [{ id: 4, windowId: 100, active: true } as chrome.tabs.Tab]),
},
},
);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
const firstHover = methodOrder.indexOf("Input.dispatchMouseEvent");
expect(firstHover).toBeGreaterThan(-1);
expect(methodOrder.lastIndexOf("DOMSnapshot.captureSnapshot")).toBeLessThan(firstHover);
expect(methodOrder.lastIndexOf("Accessibility.getFullAXTree")).toBeLessThan(firstHover);
});
it("runs conditional surface probing only when observe opts in", async () => {
it("enables conditional surface probing for semantic observe", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
await sm.start("aa11");
const root: CdpAxNode = {
@@ -2836,11 +2629,7 @@ describe("handleSnapshot", () => {
if (method === "Accessibility.enable") return {};
if (method === "Accessibility.getFullAXTree") return { nodes: [root, button] };
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 === "DOMSnapshot.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") {
@@ -2873,46 +2662,30 @@ describe("handleSnapshot", () => {
if (method === "Runtime.evaluate") return { result: { value: [] } };
throw new Error(`unexpected CDP method ${method}`);
});
const deps = {
cdp: {
send: send as unknown as <T = unknown>(
tabId: number,
method: string,
params?: object,
) => Promise<T>,
trackSessionTab: vi.fn(),
},
tabsApi: {
get: vi.fn(
async (tabId: number) => ({ id: tabId, windowId: 100, active: true }) as chrome.tabs.Tab,
),
query: vi.fn(async () => [{ id: 4, windowId: 100, active: true } as chrome.tabs.Tab]),
},
};
const withoutProbe = await handleObserve(
const res = await handleObserve(
sm,
{ session_id: "aa11", debug_surfaces: true },
deps,
);
if ("code" in withoutProbe) {
throw new Error(`unexpected error: ${JSON.stringify(withoutProbe)}`);
}
expect(withoutProbe.hover_probe).toBeUndefined();
expect(send).not.toHaveBeenCalledWith(
4,
"Runtime.evaluate",
expect.objectContaining({ returnByValue: true }),
{
cdp: {
send: send as unknown as <T = unknown>(
tabId: number,
method: string,
params?: object,
) => Promise<T>,
trackSessionTab: vi.fn(),
},
tabsApi: {
get: vi.fn(
async (tabId: number) =>
({ id: tabId, windowId: 100, active: true }) as chrome.tabs.Tab,
),
query: vi.fn(async () => [{ id: 4, windowId: 100, active: true } as chrome.tabs.Tab]),
},
},
);
const withProbe = await handleObserve(
sm,
{ session_id: "aa11", debug_surfaces: true, probe_hover: true },
deps,
);
if ("code" in withProbe) throw new Error(`unexpected error: ${JSON.stringify(withProbe)}`);
expect(withProbe.debug).toEqual({ surface_probes: [] });
expect(withProbe.hover_probe).toEqual({ performed: true, revealed_content: false });
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
expect(res.debug).toEqual({ surface_probes: [] });
expect(send).toHaveBeenCalledWith(
4,
"Runtime.evaluate",
@@ -3005,11 +2778,7 @@ describe("handleSnapshot", () => {
};
}
if (method === "Page.getLayoutMetrics") {
return {
visualViewport: { clientWidth: 1000 },
cssVisualViewport: { clientWidth: 1000 },
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 },
};
return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
}
if (method === "DOMSnapshot.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") {
@@ -3222,14 +2991,10 @@ describe("handleSnapshot", () => {
}
const VP_METRICS = {
visualViewport: { clientWidth: 1000 },
cssVisualViewport: { clientWidth: 1000 },
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
};
function makeFrameAwareDeps(
ownerGeometry: "unavailable" | "available" | "clipped" = "unavailable",
) {
function makeFrameAwareDeps() {
const strings = ["html", "body", "iframe", "button", "title", "Remote", "static", "auto"];
const i = (value: string) => strings.indexOf(value);
const styles = [i("static"), i("auto"), i("auto")];
@@ -3237,8 +3002,6 @@ describe("handleSnapshot", () => {
strings,
documents: [
{
scrollOffsetX: 0,
scrollOffsetY: 0,
frameId: "main",
nodes: {
parentIndex: [-1, 0, 1],
@@ -3259,8 +3022,6 @@ describe("handleSnapshot", () => {
},
},
{
scrollOffsetX: 0,
scrollOffsetY: 0,
frameId: "child",
nodes: {
parentIndex: [-1, 0, 1],
@@ -3313,16 +3074,6 @@ describe("handleSnapshot", () => {
];
const send = vi.fn(async (_tabId: number, method: string) => {
if (method === "Page.getLayoutMetrics") return VP_METRICS;
if (ownerGeometry !== "unavailable") {
if (method === "DOM.getBoxModel") {
const x = ownerGeometry === "clipped" ? 10000 : 100;
return { model: { content: [x, 100, x + 400, 100, x + 400, 400, x, 400] } };
}
if (method === "DOM.resolveNode") return { object: { objectId: "owner" } };
if (method === "Runtime.callFunctionOn")
return { result: { value: { width: 400, height: 300 } } };
if (method === "Runtime.releaseObject") return {};
}
if (method === "DOMSnapshot.enable" || method === "Accessibility.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
if (method === "Accessibility.getFullAXTree") return { nodes: mainAx };
@@ -3563,43 +3314,6 @@ describe("handleSnapshot", () => {
expect(result.text).toContain("•••");
});
it.each([
undefined,
100,
0,
])("reports unavailable iframe geometry within the observation budget %s", async (maxTokens) => {
const result = await captureVomObservation(makeFrameAwareDeps().cdp, 4, "https://example.com", {
maxTokens,
});
expect(result.text.match(/@warning/g)).toHaveLength(1);
expect(result.text).toContain("geometry incomplete");
expect(result.text.startsWith("@vom 1\n")).toBe(true);
if (maxTokens === undefined) {
expect(result.truncated).toBe(false);
expect(result.text).toContain("Frame action");
expect(result.matchNodes.find((node) => node.backendNodeId === 22)).toMatchObject({
rect: null,
localRect: { x: 20, y: 30, w: 120, h: 40 },
});
}
if (maxTokens === 100) expect(Math.ceil(result.text.length / 4)).toBeLessThanOrEqual(maxTokens);
});
it.each([
"available",
"clipped",
] as const)("does not report successful %s geometry as an observation failure", async (ownerGeometry) => {
const result = await captureVomObservation(
makeFrameAwareDeps(ownerGeometry).cdp,
4,
"https://example.com",
);
expect(result.text).not.toContain("@warning");
const node = result.matchNodes.find((item) => item.backendNodeId === 22);
if (ownerGeometry === "clipped") expect(node?.rect).toBeNull();
else expect(node?.rect).toEqual({ x: 120, y: 130, w: 120, h: 40 });
});
it("keeps frames and rendered refs on the same frame identity", async () => {
const deps = makeFrameAwareDeps();
@@ -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 () => {}),
};
}
@@ -1,237 +0,0 @@
// @vitest-environment node
import { describe, expect, it } from "vitest";
import type { CdpFrame, CdpFrameGraph, CdpTarget } from "@/browser-driver/frame-graph";
import { GeometryContext } from "../geometry/frame-context";
import type { CdpRunner } from "../shared";
import { captureViewModel } from "../vom/capture";
import { captureFrameData } from "../vom/frame-capture";
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 = { probe: Rect; owners: Record<string, { x: number; y: number; scale: number }> };
// 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 box = document.querySelector('#probe').getBoundingClientRect();
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 { probe: { x: box.x, y: box.y, w: box.width, h: box.height }, 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 },
])("matches DOM geometry at device scale $deviceScale and zoom $zoom", async (configuration) => {
const evalRoot = new URL("../../../../../evals/browser/", import.meta.url);
const { createEvalServer } = await import(new URL("lib/server.mjs", evalRoot).href);
const { withChrome } = await import(
new URL("cases/regression/snapshot-coordinates/chrome.mjs", evalRoot).href
);
const server = createEvalServer();
const { baseUrl } = await server.start();
try {
await withChrome(
{ executable: process.env.BSK_GEOMETRY_CHROME, ...configuration },
async (send: Send) => {
const { targetId } = await send<{ targetId: string }>("Target.createTarget", {
url: "about:blank",
});
const { sessionId: rootSession } = await send<{ sessionId: string }>(
"Target.attachToTarget",
{ targetId, flatten: true },
);
await send(
"Page.navigate",
{ url: `${baseUrl}/snapshot-coordinates?run=coordinates` },
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(2); // The cross-site fixture must actually be an OOPIF.
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(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}`);
return send(method, params, sessionFor(target));
},
getFrameGraph: async () => graph,
};
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 geometry = new GeometryContext(cdp, 1, graph);
const captured = await captureViewModel(cdp, 1, { geometry });
await captureFrameData(cdp, 1, captured, undefined, geometry);
expect(captured.frameGeometryIssues).toEqual([]);
for (const frame of frames) {
const node = captured.frameNodes
?.get(frame.frameId)
?.find((node) => node.attrs.id === "probe");
expect(node, `missing probe in ${names.get(frame.frameId) || "root"}`).toBeDefined();
const local = oracles.get(frame.frameId)!.probe;
const top = { ...local };
let current = frame;
while (current.parentFrameId) {
const owner = oracles.get(current.parentFrameId)!.owners[names.get(current.frameId)!];
top.x = owner.x + top.x * owner.scale;
top.y = owner.y + top.y * owner.scale;
top.w *= owner.scale;
top.h *= owner.scale;
current = frames.find((item) => item.frameId === current.parentFrameId)!;
}
expect(
node!.rect,
JSON.stringify({
frame: names.get(frame.frameId),
local,
top,
viewport: captured.viewport,
}),
).not.toBeNull();
for (const key of ["x", "y", "w", "h"] as const) {
expect(
Math.abs(node!.localRect![key] - local[key]),
`${names.get(frame.frameId)} local ${key}`,
).toBeLessThan(2);
expect(
Math.abs(node!.rect![key] - top[key]),
`${names.get(frame.frameId)} top ${key}`,
).toBeLessThan(2);
}
}
expect(calls.filter((call) => call.endsWith(":Page.getLayoutMetrics"))).toHaveLength(
sessions.length,
);
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 () => {},
};
}
+1 -181
View File
@@ -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");
@@ -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 };
}
@@ -24,7 +24,7 @@ export interface BorrowResponseMessage {
allowed: boolean;
}
export const CONFIRMATION_TIMEOUT_MS = 60_000;
export const CONFIRMATION_TIMEOUT_MS = 5000;
const EXIT_ANIMATION_MS = 150;
/** Matches BorrowConfirmationOverlay progress ring/bar transition (duration-1000). */
export const PROGRESS_TRANSITION_MS = 1000;
@@ -480,13 +480,6 @@ export async function requestBorrowConfirmation(
settle(false);
}, BACKGROUND_TIMEOUT_MS);
// Bring the user window to the front so the overlay is visible even
// when the Agent Window has stolen focus. This is fire-and-forget: if
// it fails the overlay / OS notification still give the user a path.
void windowsApi.update(notificationAnchor.windowId, { focused: true }).catch((err) => {
console.debug("[bsk borrow] proactive focus of user window failed", err);
});
// Surface the OS notification *before* messaging any candidate so the
// user has a parallel signal even if every content script is missing.
// The Allow / Deny buttons let the user authorize explicitly when the
@@ -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);
}
}
+74 -78
View File
@@ -1,10 +1,10 @@
import type { DiagnosticSink } from "@/lib/diagnostics";
import { OVERLAY_AUTOMATION_BYPASS } from "@/lib/overlay-bridge";
import type { SessionManager } from "@/session-manager/manager";
import type { Transport } from "@/transport/transport";
import type {
ClickParams,
ConsoleParams,
DownloadParams,
EmulateParams,
EvaluateParams,
FillParams,
@@ -29,14 +29,11 @@ import type {
ScreenshotParams,
SelectParams,
SnapshotParams,
UploadParams,
WaitForNavigationParams,
} from "@/transport/types";
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 { handleClick, handleFill, handleHover, handlePress, handleSelect } from "./interaction";
@@ -70,7 +67,6 @@ import {
import { chromeTabsApi, lookupSession, resolveTargetTab } from "./shared";
import {
type BorrowConfirmationApprover,
chromeTabMutationApi,
handleTabBorrow,
handleTabClose,
handleTabCreate,
@@ -84,7 +80,6 @@ import {
type TabReturnParams,
type TabSelectParams,
} from "./tabs";
import { handleUpload } from "./upload";
import { handleWaitForNavigation } from "./waits";
import { handleWindowResize, type WindowResizeParams } from "./window";
@@ -120,12 +115,11 @@ 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). */
helpNotificationCopy?: () => { title: string; body: string };
diagnostics?: DiagnosticSink;
}
/**
@@ -151,9 +145,9 @@ 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 readonly diagnostics?: DiagnosticSink;
private subscription: { dispose(): void } | null = null;
private readonly hoverBypassTabs = new Map<number, string>();
private readonly hoverLatches = new Map<number, HoverLatch>();
@@ -172,9 +166,9 @@ 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;
this.diagnostics = deps.diagnostics;
}
start(): void {
@@ -202,6 +196,16 @@ export class ToolDispatcher {
private async dispatch(msg: ProtocolFrame): Promise<void> {
if (!isRequestFrame(msg)) return;
const req = msg as RequestFrame;
const requestSessionId = (req.params as { session_id?: unknown } | undefined)?.session_id;
const startedAt = performance.now();
this.diagnostics?.("dispatcher.rpc.received", {
rpc_id: req.id,
method: req.method,
session_id: typeof requestSessionId === "string" ? requestSessionId : null,
transport_state: this.transport.state,
live_session_ids: this.sessions.list().map((ctx) => ctx.sessionId),
inflight_rpc_ids: Array.from(this.inflightAbortControllers.keys()),
});
// Cancel frames take a fast path: trip the matching controller
// (if any), reply with `{cancelled}` so the daemon can answer
@@ -210,6 +214,12 @@ export class ToolDispatcher {
const params = (req.params as { rpc_id?: string } | undefined) ?? {};
const target = typeof params.rpc_id === "string" ? params.rpc_id : "";
const ac = target ? this.inflightAbortControllers.get(target) : undefined;
this.diagnostics?.("dispatcher.cancel.received", {
rpc_id: req.id,
target_rpc_id: target,
target_found: ac !== undefined,
inflight_rpc_ids: Array.from(this.inflightAbortControllers.keys()),
});
if (ac) {
try {
ac.abort();
@@ -223,7 +233,17 @@ export class ToolDispatcher {
};
try {
this.transport.send(reply);
this.diagnostics?.("dispatcher.cancel.ack_sent", {
rpc_id: req.id,
target_rpc_id: target,
cancelled: ac !== undefined,
});
} catch (sendErr) {
this.diagnostics?.("dispatcher.cancel.ack_failed", {
rpc_id: req.id,
target_rpc_id: target,
error: sendErr,
});
console.warn("[bsk dispatcher] failed to ack cancel", sendErr);
}
return;
@@ -240,7 +260,7 @@ 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") {
@@ -248,6 +268,13 @@ export class ToolDispatcher {
}
}
} catch (err) {
this.diagnostics?.("dispatcher.rpc.invoke_failed", {
rpc_id: req.id,
method: req.method,
session_id: typeof requestSessionId === "string" ? requestSessionId : null,
abort_signal: ac.signal.aborted,
error: err,
});
if (isAbortLikeError(err)) {
body = {
id: req.id,
@@ -268,8 +295,27 @@ export class ToolDispatcher {
let sent = true;
try {
this.transport.send(body);
this.diagnostics?.("dispatcher.rpc.response_sent", {
rpc_id: req.id,
method: req.method,
session_id: typeof requestSessionId === "string" ? requestSessionId : null,
response_kind: "error" in body ? "error" : "ok",
error_code: "error" in body ? body.error.code : null,
elapsed_ms: Math.round(performance.now() - startedAt),
transport_state: this.transport.state,
live_session_ids: this.sessions.list().map((ctx) => ctx.sessionId),
});
} catch (sendErr) {
sent = false;
this.diagnostics?.("dispatcher.rpc.response_send_failed", {
rpc_id: req.id,
method: req.method,
session_id: typeof requestSessionId === "string" ? requestSessionId : null,
started_session_id: startedSession,
elapsed_ms: Math.round(performance.now() - startedAt),
transport_state: this.transport.state,
error: sendErr,
});
// Transport is dead by the time we want to reply. Drop the link
// proactively so the alarm-driven keepalive reconnects sooner
// and the daemon's pending RPC times out cleanly instead of
@@ -288,12 +334,23 @@ export class ToolDispatcher {
try {
const ctx = await this.sessions.stop(startedSession);
if (ctx) {
this.diagnostics?.("dispatcher.session_start.rolled_back", {
rpc_id: req.id,
session_id: startedSession,
agent_window_id: ctx.agentWindowId,
reason: "response_send_failed",
});
console.warn(
"[bsk dispatcher] rolled back orphan session after send failure",
startedSession,
);
}
} catch (rollbackErr) {
this.diagnostics?.("dispatcher.session_start.rollback_failed", {
rpc_id: req.id,
session_id: startedSession,
error: rollbackErr,
});
console.warn("[bsk dispatcher] session rollback after send failure failed", rollbackErr);
}
}
@@ -308,25 +365,13 @@ 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,
@@ -335,22 +380,13 @@ 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,
@@ -414,11 +450,7 @@ export class ToolDispatcher {
? {
cdp: this.cdp,
tabsApi: chromeTabsCaptureApi,
// Active hover probing is opt-in. A held hover latch still
// suppresses it, because probing would move the cursor off
// the element the caller is deliberately holding.
conditionalSurfaceProbe:
params.probe_hover === true && !this.hasHoverLatchForScope(hoverScope),
conditionalSurfaceProbe: !this.hasHoverLatchForScope(hoverScope),
hoverProbeBypassOverlay: bypassOverlay,
}
: undefined,
@@ -548,40 +580,6 @@ export class ToolDispatcher {
),
signal,
);
case "tool.upload":
return this.withHoverReleaseForRequest(
req.params as UploadParams,
() =>
this.cdp
? handleUpload(this.sessions, req.params as UploadParams, {
cdp: this.cdp,
tabsApi: chromeTabsApi,
signal,
bypassOverlay,
})
: Promise.resolve({
code: "unsupported",
message: "upload requires CDP",
} satisfies RpcError),
signal,
);
case "tool.download":
return this.withHoverReleaseForRequest(
req.params as DownloadParams,
() =>
this.cdp
? handleDownload(this.sessions, req.params as DownloadParams, {
cdp: this.cdp,
tabsApi: chromeTabsApi,
signal,
bypassOverlay,
})
: Promise.resolve({
code: "unsupported",
message: "download requires CDP",
} satisfies RpcError),
signal,
);
case "tool.evaluate":
return handleEvaluate(
this.sessions,
@@ -788,8 +786,6 @@ function sessionIdForBrowserControlMethod(req: RequestFrame): string | null {
case "tool.fill":
case "tool.press":
case "tool.select":
case "tool.upload":
case "tool.download":
case "tool.evaluate":
case "tool.observe":
case "tool.request_help":
@@ -1,364 +0,0 @@
// Order-independent coordinator for one browser download. CDP supplies the
// exact target/frame intent while chrome.downloads supplies the download id
// and filename routing hook; neither event is assumed to arrive first.
import type { CdpTarget } from "@/browser-driver/frame-graph";
import type { ClickResult, RpcError, TransferEffectState } from "@/transport/types";
import { transferError } from "./errors";
import { type CdpRunner, isRpcError } from "./shared";
const CORRELATION_GRACE_MS = 750;
const UNIQUE_SETTLE_MS = 50;
const SIZE_POLL_MS = 250;
type DeterminingFilenameListener = (
item: chrome.downloads.DownloadItem,
suggest: (suggestion?: chrome.downloads.DownloadFilenameSuggestion) => void,
) => void | true;
interface ListenerEvent<T> {
addListener(listener: T): void;
removeListener(listener: T): void;
}
export interface DownloadsApi {
onCreated: ListenerEvent<(item: chrome.downloads.DownloadItem) => void>;
onChanged: ListenerEvent<(delta: chrome.downloads.DownloadDelta) => void>;
onDeterminingFilename: ListenerEvent<DeterminingFilenameListener>;
search(query: chrome.downloads.DownloadQuery): Promise<chrome.downloads.DownloadItem[]>;
cancel(downloadId: number): Promise<void>;
removeFile(downloadId: number): Promise<void>;
}
export const chromeDownloadsApi: DownloadsApi = {
get onCreated() {
return chrome.downloads.onCreated;
},
get onChanged() {
return chrome.downloads.onChanged;
},
get onDeterminingFilename() {
return chrome.downloads.onDeterminingFilename;
},
search: (query) => chrome.downloads.search(query),
cancel: (id) => chrome.downloads.cancel(id),
removeFile: (id) => chrome.downloads.removeFile(id),
};
export interface DownloadCaptureOptions {
cdp: CdpRunner;
target: CdpTarget;
expectedFrameId?: string;
downloads: DownloadsApi;
browserRelativeDir: string;
maxByteSize?: number;
timeoutMs: number;
signal?: AbortSignal;
trigger(): Promise<ClickResult | RpcError>;
}
export interface DownloadCaptureResult {
click: ClickResult;
item: chrome.downloads.DownloadItem;
}
interface DownloadIntent {
url: string;
suggestedFilename: string;
frameId?: string;
}
interface DownloadCandidate {
item: chrome.downloads.DownloadItem;
suggest: (suggestion?: chrome.downloads.DownloadFilenameSuggestion) => void;
suggested: boolean;
graceTimer: ReturnType<typeof setTimeout>;
}
function safeBasename(filename: string): string {
const basename = filename.split(/[\\/]/).pop()?.trim();
return basename && basename !== "." && basename !== ".." ? basename : "download";
}
function sameTarget(source: { tabId?: number; sessionId?: string }, target: CdpTarget): boolean {
return source.tabId === target.tabId && source.sessionId === target.sessionId;
}
function matchesIntent(item: chrome.downloads.DownloadItem, intent: DownloadIntent): boolean {
const urlMatches = item.url === intent.url || item.finalUrl === intent.url;
return urlMatches && safeBasename(item.filename) === safeBasename(intent.suggestedFilename);
}
function knownSize(item: chrome.downloads.DownloadItem): number | undefined {
if (item.fileSize >= 0) return item.fileSize;
if (item.totalBytes >= 0) return item.totalBytes;
return undefined;
}
function captureError(
message: string,
effectState: TransferEffectState,
phase: string,
cleanupFailed = false,
): RpcError {
return transferError("cdp_failed", "download_capture_failed", message, {
effectState,
phase,
...(cleanupFailed ? { cleanupState: "failed" } : {}),
});
}
async function cleanupClaimedDownload(downloads: DownloadsApi, downloadId: number): Promise<void> {
const lookup = async () => (await downloads.search({ id: downloadId }))[0];
const item = await lookup();
if (!item || item.state === "interrupted") return;
if (item.state === "complete") {
await downloads.removeFile(downloadId);
return;
}
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") {
await downloads.removeFile(downloadId);
return;
}
throw cancelError;
}
}
export async function captureBrowserDownload(
options: DownloadCaptureOptions,
): Promise<DownloadCaptureResult | RpcError> {
let click: ClickResult | undefined;
let intent: DownloadIntent | undefined;
let capturedId: number | undefined;
let settled = false;
let succeeded = false;
let failureResult: RpcError | undefined;
let uniquenessTimer: ReturnType<typeof setTimeout> | undefined;
let operationTimer: ReturnType<typeof setTimeout> | undefined;
let sizePoll: ReturnType<typeof setInterval> | undefined;
const candidates = new Map<number, DownloadCandidate>();
const createdItems = new Map<number, chrome.downloads.DownloadItem>();
let resolveCompletion!: (item: chrome.downloads.DownloadItem) => void;
let rejectCompletion!: (error: Error) => void;
const completion = new Promise<chrome.downloads.DownloadItem>((resolve, reject) => {
resolveCompletion = resolve;
rejectCompletion = reject;
});
const fail = (error: Error) => {
if (settled) return;
settled = true;
rejectCompletion(error);
};
const complete = (item: chrome.downloads.DownloadItem) => {
if (settled) return;
const size = knownSize(item);
if (size !== undefined && options.maxByteSize !== undefined && size > options.maxByteSize) {
fail(new Error(`download exceeds transfer limit ${options.maxByteSize}`));
return;
}
settled = true;
resolveCompletion(item);
};
const suggestDefault = (candidate: DownloadCandidate) => {
if (candidate.suggested) return;
candidate.suggested = true;
candidate.suggest();
};
const matchingCandidates = (): DownloadCandidate[] => {
const currentIntent = intent;
return currentIntent
? [...candidates.values()].filter(
(candidate) => !candidate.suggested && matchesIntent(candidate.item, currentIntent),
)
: [];
};
const claimUnique = () => {
uniquenessTimer = undefined;
if (settled || capturedId !== undefined || !intent) return;
const matches = matchingCandidates();
if (matches.length !== 1) {
if (matches.length > 1) {
for (const candidate of matches) suggestDefault(candidate);
fail(new Error("download attribution is ambiguous"));
}
return;
}
const candidate = matches[0];
candidate.suggested = true;
clearTimeout(candidate.graceTimer);
capturedId = candidate.item.id;
candidate.suggest({
filename: `${options.browserRelativeDir}/${safeBasename(intent.suggestedFilename)}`,
conflictAction: "overwrite",
});
const size = knownSize(candidate.item);
if (size !== undefined && options.maxByteSize !== undefined && size > options.maxByteSize) {
fail(new Error(`download exceeds transfer limit ${options.maxByteSize}`));
return;
}
const created = createdItems.get(candidate.item.id);
if (created?.state === "interrupted") {
fail(new Error(created.error ?? "download interrupted"));
} else if (created?.state === "complete") {
complete(created);
}
};
const reconcile = () => {
if (settled || capturedId !== undefined || !intent) return;
const matches = matchingCandidates();
if (matches.length > 1) {
for (const candidate of matches) suggestDefault(candidate);
fail(new Error("download attribution is ambiguous"));
return;
}
if (matches.length === 1 && !uniquenessTimer) {
uniquenessTimer = setTimeout(claimUnique, UNIQUE_SETTLE_MS);
}
};
const determiningListener: DeterminingFilenameListener = (item, suggest) => {
const candidate: DownloadCandidate = {
item,
suggest,
suggested: false,
graceTimer: setTimeout(() => {
suggestDefault(candidate);
candidates.delete(item.id);
if (intent && matchesIntent(item, intent) && capturedId === undefined) {
fail(new Error("download correlation grace elapsed before unique attribution"));
}
}, CORRELATION_GRACE_MS),
};
candidates.set(item.id, candidate);
reconcile();
return true;
};
const createdListener = (item: chrome.downloads.DownloadItem) => {
createdItems.set(item.id, item);
if (capturedId !== item.id) return;
if (item.state === "interrupted") {
fail(new Error(item.error ?? "download interrupted"));
} else if (item.state === "complete") {
complete(item);
}
};
const changedListener = async (delta: chrome.downloads.DownloadDelta) => {
if (capturedId === undefined || delta.id !== capturedId || settled) return;
if (delta.state?.current === "interrupted" || delta.error?.current) {
fail(new Error(delta.error?.current ?? "download interrupted"));
return;
}
if (delta.state?.current === "complete") {
try {
const [item] = await options.downloads.search({ id: delta.id });
if (item) complete(item);
else fail(new Error("completed download disappeared"));
} catch (err) {
fail(err instanceof Error ? err : new Error(String(err)));
}
}
};
const onAbort = () => fail(new DOMException("aborted", "AbortError"));
const cdpSubscription = options.cdp.onEvent?.((source, method, raw) => {
if (method !== "Page.downloadWillBegin" || !sameTarget(source, options.target)) return;
const event = raw as { url?: unknown; suggestedFilename?: unknown; frameId?: unknown };
if (typeof event.url !== "string" || typeof event.suggestedFilename !== "string") return;
if (options.expectedFrameId && event.frameId !== options.expectedFrameId) {
fail(new Error("download originated from a different frame"));
return;
}
if (intent) {
fail(new Error("download trigger produced more than one browser download intent"));
return;
}
intent = {
url: event.url,
suggestedFilename: event.suggestedFilename,
...(typeof event.frameId === "string" ? { frameId: event.frameId } : {}),
};
reconcile();
});
if (!cdpSubscription) {
return captureError("CDP download intent subscription unavailable", "none", "arm");
}
options.downloads.onDeterminingFilename.addListener(determiningListener);
options.downloads.onCreated.addListener(createdListener);
options.downloads.onChanged.addListener(changedListener);
options.signal?.addEventListener("abort", onAbort, { once: true });
operationTimer = setTimeout(
() => fail(new Error("download did not complete before timeout")),
options.timeoutMs,
);
sizePoll = setInterval(() => {
if (capturedId === undefined || settled || options.maxByteSize === undefined) return;
void options.downloads
.search({ id: capturedId })
.then(([item]) => {
if (!item || settled) return;
if (item.bytesReceived > (options.maxByteSize as number)) {
fail(new Error(`download exceeds transfer limit ${options.maxByteSize}`));
}
})
.catch((err) => fail(err instanceof Error ? err : new Error(String(err))));
}, SIZE_POLL_MS);
try {
const triggered = await options.trigger();
if (isRpcError(triggered)) {
void completion.catch(() => undefined);
const effect: TransferEffectState =
capturedId !== undefined ? "committed" : intent ? "unknown" : "none";
failureResult = {
...triggered,
data: { ...triggered.data, effect_state: effect, phase: "trigger" },
};
return failureResult;
}
click = triggered;
const item = await completion;
succeeded = true;
return { click, item };
} catch (err) {
const effect: TransferEffectState =
capturedId !== undefined ? "committed" : click ? "unknown" : "none";
failureResult = captureError(
err instanceof Error ? err.message : String(err),
effect,
capturedId !== undefined ? "download" : "attribution",
);
return failureResult;
} finally {
settled = true;
if (operationTimer) clearTimeout(operationTimer);
if (uniquenessTimer) clearTimeout(uniquenessTimer);
if (sizePoll) clearInterval(sizePoll);
options.signal?.removeEventListener("abort", onAbort);
options.downloads.onDeterminingFilename.removeListener(determiningListener);
options.downloads.onCreated.removeListener(createdListener);
options.downloads.onChanged.removeListener(changedListener);
cdpSubscription.dispose();
for (const candidate of candidates.values()) {
clearTimeout(candidate.graceTimer);
if (candidate.item.id !== capturedId) suggestDefault(candidate);
}
if (!succeeded && capturedId !== undefined) {
try {
await cleanupClaimedDownload(options.downloads, capturedId);
} catch {
if (failureResult?.data) failureResult.data.cleanup_state = "failed";
}
}
}
}
-64
View File
@@ -1,64 +0,0 @@
// Download orchestration: validate session/tab ownership, then delegate one
// browser-global chrome.downloads transaction to download-capture.ts.
import type { SessionManager } from "@/session-manager/manager";
import type { DownloadParams, DownloadResult, RpcError } from "@/transport/types";
import { captureBrowserDownload, chromeDownloadsApi, type DownloadsApi } from "./download-capture";
import { clickResolvedTarget, type InteractionDeps, resolveActionTarget } from "./interaction";
import { enforceAgentWindow, isRpcError, lookupSession, resolveTargetTab } from "./shared";
let downloadActive = false;
export type { DownloadsApi } from "./download-capture";
export interface DownloadDeps extends InteractionDeps {
downloads?: DownloadsApi;
}
export async function handleDownload(
manager: SessionManager,
params: DownloadParams,
deps: DownloadDeps,
): Promise<DownloadResult | RpcError> {
if (downloadActive) return { code: "invalid_params", message: "another bsk download is active" };
downloadActive = true;
try {
const ctx = lookupSession(manager, params, "download");
if (isRpcError(ctx)) return ctx;
const target = await resolveTargetTab(manager, ctx, params.tab_id, deps.tabsApi);
if (isRpcError(target)) return target;
const denied = enforceAgentWindow(ctx, target, "download");
if (denied) return denied;
if (!params.browser_relative_dir) {
return { code: "invalid_params", message: "download requires a daemon capability directory" };
}
const address = await resolveActionTarget(deps.cdp, ctx, target, params, "download");
if (isRpcError(address)) return address;
const capture = await captureBrowserDownload({
cdp: deps.cdp,
target: address.cdpTarget,
downloads: deps.downloads ?? chromeDownloadsApi,
browserRelativeDir: params.browser_relative_dir,
maxByteSize: params.max_byte_size,
timeoutMs: params.timeout_ms ?? 120_000,
signal: deps.signal,
expectedFrameId: address.frameId,
trigger: () => clickResolvedTarget(ctx, address, {}, deps),
});
if (isRpcError(capture)) return capture;
const { click, item } = capture;
return {
tab_id: target.tabId,
used_ref: click.used_ref,
used_selector: click.used_selector,
suggested_filename: item.filename.split(/[\\/]/).pop() ?? "download",
byte_size: item.fileSize >= 0 ? item.fileSize : item.totalBytes,
mime: item.mime || undefined,
danger: item.danger,
browser_path: item.filename,
};
} finally {
downloadActive = false;
}
}
+1 -55
View File
@@ -2,51 +2,10 @@
// rendering. Extension handlers attach reasons here; human-facing copy
// lives in bsk-cli `render_error.rs`.
import type {
ErrorCode,
RpcError,
RpcErrorData,
RpcErrorReason,
TransferCleanupState,
TransferEffectState,
} from "@/transport/types";
import type { ErrorCode, RpcError, RpcErrorData, RpcErrorReason } from "@/transport/types";
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;
cleanupState?: TransferCleanupState;
}
export function rpcError(
code: ErrorCode,
reason: RpcErrorReason,
@@ -56,16 +15,3 @@ export function rpcError(
const data: RpcErrorData = { reason, ...extra };
return { code, message, data };
}
export function transferError(
code: ErrorCode,
reason: RpcErrorReason,
message: string,
options: TransferErrorOptions,
): RpcError {
return rpcError(code, reason, message, {
effect_state: options.effectState,
phase: options.phase,
...(options.cleanupState ? { cleanup_state: options.cleanupState } : {}),
});
}
@@ -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" };
}
}
}
@@ -1,445 +0,0 @@
// One upload transaction with an explicit browser-side commit boundary.
// Chrome interception prevents a native chooser from escaping automation;
// chooser events and a frame-scoped DOM probe are independent input-location
// signals, so event delivery is not required for standard file inputs.
import type { ClickResult, RpcError, TransferEffectState } from "@/transport/types";
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 ACTIVATION_GRACE_MS = 1_000;
const PROBE_INTERVAL_MS = 20;
type UploadPhase =
| "arm_interception"
| "arm_input_probe"
| "trigger"
| "resolve_input"
| "set_files"
| "cleanup";
interface RuntimeReply {
result?: { value?: unknown; objectId?: string };
exceptionDetails?: { text?: string; exception?: { description?: string } };
}
interface ChooserEvent {
frameId?: string;
backendNodeId?: number;
mode?: "selectSingle" | "selectMultiple";
}
export interface FileInputTransactionOptions {
cdp: CdpRunner;
actionTarget: ResolvedActionTarget;
files: string[];
timeoutMs: number;
signal?: AbortSignal;
trigger(): Promise<ClickResult | RpcError>;
}
export interface FileInputTransactionResult {
click: ClickResult;
multiple: boolean;
}
function runtimeError(reply: RuntimeReply, fallback: string): Error | null {
if (!reply.exceptionDetails) return null;
return new Error(
reply.exceptionDetails.exception?.description ?? reply.exceptionDetails.text ?? fallback,
);
}
function transferFailure(
code: RpcError["code"],
reason: "file_input_probe_failed" | "file_input_not_activated" | "set_file_input_failed",
message: string,
effectState: TransferEffectState,
phase: UploadPhase,
): RpcError {
return transferError(code, reason, message, { effectState, phase });
}
function enrichFailure(
error: RpcError,
effectState: TransferEffectState,
phase: UploadPhase,
): RpcError {
return {
...error,
data: { ...error.data, effect_state: effectState, phase },
};
}
function sameTarget(
source: { tabId?: number; sessionId?: string },
target: { tabId: number; sessionId?: string },
): boolean {
return source.tabId === target.tabId && source.sessionId === target.sessionId;
}
async function delay(ms: number, signal?: AbortSignal): Promise<void> {
await waitBounded(
new Promise((resolve) => setTimeout(resolve, ms)),
Date.now() + ms + 1,
signal,
"upload activation probe timed out",
);
}
async function callOnTrigger<T = RuntimeReply>(
options: FileInputTransactionOptions,
objectId: string,
functionDeclaration: string,
args: unknown[],
returnByValue: boolean,
): Promise<T> {
return sendToCdpTarget<T>(options.cdp, options.actionTarget.cdpTarget, "Runtime.callFunctionOn", {
objectId,
functionDeclaration,
arguments: args.map((value) => ({ value })),
returnByValue,
awaitPromise: false,
});
}
export async function uploadThroughActivatedFileInput(
options: FileInputTransactionOptions,
): Promise<FileInputTransactionResult | RpcError> {
const deadline = Date.now() + options.timeoutMs;
const target = options.actionTarget.cdpTarget;
const objectGroup = `bsk-upload-${crypto.randomUUID()}`;
const stateKey = `__bskUpload_${crypto.randomUUID().replaceAll("-", "")}`;
const chooserEvents: ChooserEvent[] = [];
let interceptionArmed = false;
let probeArmed = false;
let triggerObjectId: string | undefined;
let outcome: FileInputTransactionResult | RpcError = transferFailure(
"protocol_error",
"file_input_probe_failed",
"upload transaction ended without an outcome",
"none",
"cleanup",
);
const chooserSubscription = options.cdp.onEvent?.((source, method, raw) => {
if (method !== "Page.fileChooserOpened" || !sameTarget(source, target)) return;
const event = raw as ChooserEvent;
chooserEvents.push(event);
});
try {
try {
await waitBounded(
sendToCdpTarget(options.cdp, target, "Page.setInterceptFileChooserDialog", {
enabled: true,
}),
deadline,
options.signal,
"arming native file chooser interception timed out",
);
interceptionArmed = true;
} catch (err) {
outcome = transferFailure(
err instanceof BoundedWaitError ? "timeout" : "cdp_failed",
"file_input_probe_failed",
err instanceof Error ? err.message : String(err),
"none",
"arm_interception",
);
return outcome;
}
try {
const resolved = await waitBounded(
sendToCdpTarget<{ object?: { objectId?: string } }>(
options.cdp,
target,
"DOM.resolveNode",
{
backendNodeId: options.actionTarget.backendNodeId,
objectGroup,
},
),
deadline,
options.signal,
"resolving upload trigger timed out",
);
triggerObjectId = resolved.object?.objectId;
if (!triggerObjectId) throw new Error("DOM.resolveNode returned no trigger objectId");
const armed = await waitBounded(
callOnTrigger<RuntimeReply>(
options,
triggerObjectId,
`function(key) {
const doc = this.ownerDocument;
const owner = doc.defaultView;
if (!owner) return false;
const state = { inputs: [], listener: null };
Object.defineProperty(owner, key, { value: state, configurable: true });
state.listener = event => {
const path = typeof event.composedPath === "function" ? event.composedPath() : [];
const candidate = path[0] || event.target;
if (candidate && candidate.nodeType === 1 &&
candidate.localName === "input" && candidate.type === "file") {
if (!state.inputs.includes(candidate)) state.inputs.push(candidate);
event.preventDefault();
}
};
doc.addEventListener("click", state.listener, true);
return true;
}`,
[stateKey],
true,
),
deadline,
options.signal,
"arming frame-scoped file input probe timed out",
);
const armError = runtimeError(armed, "failed to arm file input probe");
if (armError || armed.result?.value !== true) {
throw armError ?? new Error("file input probe did not arm");
}
probeArmed = true;
} catch (err) {
outcome = transferFailure(
err instanceof BoundedWaitError ? "timeout" : "cdp_failed",
"file_input_probe_failed",
err instanceof Error ? err.message : String(err),
"none",
"arm_input_probe",
);
return outcome;
}
let click: ClickResult | RpcError;
try {
click = await waitBounded(
options.trigger(),
deadline,
options.signal,
"upload trigger timed out",
);
} catch (err) {
outcome = transferFailure(
err instanceof BoundedWaitError ? "timeout" : "cdp_failed",
"file_input_probe_failed",
err instanceof Error ? err.message : String(err),
"none",
"trigger",
);
return outcome;
}
if (isRpcError(click)) {
outcome = enrichFailure(click, "none", "trigger");
return outcome;
}
try {
const activationDeadline = Math.min(deadline, Date.now() + ACTIVATION_GRACE_MS);
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 state = this.ownerDocument.defaultView?.[key];
return state
? { count: state.inputs.length, multiple: state.inputs[0]?.multiple === true }
: { count: 0, multiple: false };
}`,
[stateKey],
true,
);
const summaryError = runtimeError(reply, "failed to inspect activated file input");
if (summaryError) throw summaryError;
const value = reply.result?.value as { count?: unknown; multiple?: unknown } | undefined;
summary = {
count: typeof value?.count === "number" ? value.count : 0,
multiple: value?.multiple === true,
};
if (summary.count > 0) break;
await delay(Math.min(PROBE_INTERVAL_MS, remainingMs(activationDeadline)), options.signal);
}
if (chooserEvents.length > 1) {
outcome = transferFailure(
"unsupported",
"file_input_not_activated",
"upload trigger activated more than one file chooser",
"none",
"resolve_input",
);
return outcome;
}
const chooser = chooserEvents[0];
let backendNodeId: number | undefined;
let multiple = summary.multiple;
if (chooser) {
if (options.actionTarget.frameId && chooser.frameId !== options.actionTarget.frameId) {
outcome = transferFailure(
"unsupported",
"file_input_not_activated",
"upload trigger activated a file chooser in a different frame",
"none",
"resolve_input",
);
return outcome;
}
if (typeof chooser.backendNodeId !== "number") {
outcome = transferFailure(
"unsupported",
"file_input_not_activated",
"upload trigger invoked a non-input file picker",
"none",
"resolve_input",
);
return outcome;
}
backendNodeId = chooser.backendNodeId;
multiple = chooser.mode === "selectMultiple";
} else {
if (summary.count !== 1) {
outcome = transferFailure(
"unsupported",
"file_input_not_activated",
summary.count === 0
? "upload trigger did not activate an input[type=file]"
: "upload trigger activated more than one input[type=file]",
"none",
"resolve_input",
);
return outcome;
}
const input = await callOnTrigger<RuntimeReply>(
options,
triggerObjectId,
`function(key) { return this.ownerDocument.defaultView?.[key]?.inputs[0]; }`,
[stateKey],
false,
);
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 },
);
backendNodeId = described.node?.backendNodeId;
if (typeof backendNodeId !== "number") {
throw new Error("DOM.describeNode returned no file input backendNodeId");
}
}
if (!multiple && options.files.length !== 1) {
outcome = enrichFailure(
{ code: "invalid_params", message: "file input accepts exactly one file" },
"none",
"resolve_input",
);
return outcome;
}
try {
await waitBounded(
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",
"set_file_input_failed",
err instanceof Error ? err.message : String(err),
"unknown",
"set_files",
);
return outcome;
}
outcome = { click, multiple };
return outcome;
} catch (err) {
outcome = transferFailure(
err instanceof BoundedWaitError ? "timeout" : "cdp_failed",
"file_input_probe_failed",
err instanceof Error ? err.message : String(err),
"none",
"resolve_input",
);
return outcome;
}
} finally {
chooserSubscription?.dispose();
let cleanupFailed = false;
if (probeArmed && triggerObjectId) {
try {
await waitBounded(
callOnTrigger(
options,
triggerObjectId,
`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,
"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;
}
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" };
}
}
}
+151 -72
View File
@@ -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,
@@ -154,32 +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 = projection.edges[0]?.sourceViewport ?? projection.topViewport;
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) =>
@@ -194,17 +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));
}
+19
View File
@@ -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,
},
};
}
@@ -1,356 +0,0 @@
import {
type CdpFrame,
type CdpFrameGraph,
type CdpTarget,
cdpTargetKey,
} from "@/browser-driver/frame-graph";
import {
type GeometryProjection,
type Polygon,
type ProjectiveEdge,
parseCdpQuad,
type Quad,
type Size,
} 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; clientWidth?: number; clientHeight?: number };
visualViewport?: { zoom?: 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 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;
}
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);
const source = await this.viewport(root.target);
const parentRoot = this.targetRoot(frames, parent);
if (!destinationQuad || !source || !parentRoot) return null;
const destinationClips = await this.clips(frames, parent, parentRoot);
if (!destinationClips) return null;
edges.push({ sourceViewport: source, destinationQuad, destinationClips });
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;
}
+63 -317
View File
@@ -40,7 +40,6 @@ import {
enforceAgentWindow,
isRpcError,
lookupSession,
type ResolvedTargetTab,
resolveTargetTab,
} from "./shared";
import { resolveSnapshotRef } from "./snapshot-ref";
@@ -57,15 +56,6 @@ export interface InteractionDeps {
keepOverlayBypassAfterHover?: boolean;
}
export interface ResolvedActionTarget {
tab: ResolvedTargetTab;
backendNodeId: number;
cdpTarget: CdpTarget;
frameId?: string;
usedRef?: string;
usedSelector?: string;
}
const DEFAULT_TIMEOUT_MS = 30_000;
const DEFAULT_HOVER_SETTLE_MS = 200;
@@ -116,6 +106,14 @@ function isAbortLikeError(err: unknown): boolean {
return err instanceof DOMException && err.name === "AbortError";
}
function isInvalidCssSelectorError(err: unknown): boolean {
const message = err instanceof Error ? err.message : String(err);
return (
message.includes("DOM Error while querying") ||
/invalid selector|not a valid selector|querySelector.*failed/i.test(message)
);
}
async function wait(ms: number, signal?: AbortSignal): Promise<void> {
if (signal?.aborted) throw new DOMException("aborted", "AbortError");
await new Promise<void>((resolve, reject) => {
@@ -138,7 +136,7 @@ async function wait(ms: number, signal?: AbortSignal): Promise<void> {
* `RpcError` if the caller supplied neither (or both), or if neither
* lookup matched.
*/
export async function resolveBackendNode(
async function resolveBackendNode(
cdp: CdpRunner,
ctx: SessionContext,
target: { tabId: number },
@@ -183,8 +181,6 @@ 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,
});
@@ -220,6 +216,14 @@ export async function resolveBackendNode(
}
return { backendNodeId, cdpTarget: { tabId: target.tabId }, usedSelector: params.selector };
} catch (err) {
if (isInvalidCssSelectorError(err)) {
return rpcError(
"invalid_params",
"invalid_selector",
`selector is not valid CSS: ${params.selector}`,
{ selector: params.selector },
);
}
return {
code: "cdp_failed",
message: err instanceof Error ? err.message : String(err),
@@ -227,17 +231,6 @@ export async function resolveBackendNode(
}
}
export async function resolveActionTarget(
cdp: CdpRunner,
ctx: SessionContext,
target: ResolvedTargetTab,
params: { ref?: string; selector?: string },
toolName: string,
): Promise<ResolvedActionTarget | RpcError> {
const node = await resolveBackendNode(cdp, ctx, target, params, toolName);
return isRpcError(node) ? node : { tab: target, ...node };
}
// ---------------------------------------------------------------------------
// tool.click
// ---------------------------------------------------------------------------
@@ -256,20 +249,11 @@ export async function handleClick(
if (isRpcError(target)) return target;
const denied = enforceAgentWindow(ctx, target, "click");
if (denied) return denied;
const resolved = await resolveActionTarget(deps.cdp, ctx, target, params, "click");
if (isRpcError(resolved)) return resolved;
return clickResolvedTarget(ctx, resolved, params, deps);
}
export async function clickResolvedTarget(
ctx: SessionContext,
resolved: ResolvedActionTarget,
params: Pick<ClickParams, "button" | "click_count" | "modifiers">,
deps: InteractionDeps,
): Promise<ClickResult | RpcError> {
const { tab: target } = resolved;
const dialogCursor = markDialogCursor(deps.cdp, target.tabId);
const node = await resolveBackendNode(deps.cdp, ctx, target, params, "click");
if (isRpcError(node)) return node;
if (throwIfAborted(deps.signal)) {
return { code: "cancelled", message: "click aborted" };
}
@@ -279,9 +263,9 @@ export async function clickResolvedTarget(
deps.cdp,
target.tabId,
{
target: resolved.cdpTarget,
backendNodeId: resolved.backendNodeId,
...(resolved.frameId ? { frameId: resolved.frameId } : {}),
target: node.cdpTarget,
backendNodeId: node.backendNodeId,
...(node.frameId ? { frameId: node.frameId } : {}),
},
{ scrollIntoView: true },
);
@@ -369,8 +353,8 @@ export async function clickResolvedTarget(
return attachDialogs(deps.cdp, target.tabId, dialogCursor, {
tab_id: target.tabId,
used_ref: resolved.usedRef,
used_selector: resolved.usedSelector,
used_ref: node.usedRef,
used_selector: node.usedSelector,
x: centre.x,
y: centre.y,
});
@@ -609,53 +593,6 @@ 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,
@@ -707,8 +644,12 @@ 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)) {
@@ -721,252 +662,57 @@ 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,
});
}
// ---------------------------------------------------------------------------
+10 -116
View File
@@ -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),
};
}
}
+41 -141
View File
@@ -17,7 +17,7 @@ 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 {
@@ -34,8 +34,6 @@ import type {
import { attachDialogs, markDialogCursor } from "./dialogs";
import { rpcError } from "./errors";
import { resolveNodeGeometry } from "./frame-geometry";
import { screenshotPageRect } from "./geometry/coordinate-types";
import { cssViewport, GeometryContext } from "./geometry/frame-context";
import {
type ChromeTabsApi,
enforceToolTargetScope,
@@ -51,14 +49,11 @@ import {
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,
@@ -199,14 +194,15 @@ async function captureElementScreenshot(
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" };
try {
const shot = await cdp.send<{ data?: string }>(tabId, "Page.captureScreenshot", {
format: "png",
clip: {
...clip.rect,
x: rect.x,
y: rect.y,
width: rect.width,
height: rect.height,
scale: 1,
},
});
@@ -325,7 +321,7 @@ export async function handleScreenshot(
tabId: target.tabId,
...(node.cdpSessionId ? { sessionId: node.cdpSessionId } : {}),
};
const captured = await withExtensionOverlayHidden(
const captured = await withOverlaysHiddenForCapture(
target.tabId,
() =>
captureElementScreenshot(
@@ -357,7 +353,7 @@ export async function handleScreenshot(
);
}
const captured = await withExtensionOverlayHidden(
const captured = await withOverlaysHiddenForCapture(
target.tabId,
() => captureFullTabPng(deps, ctx, target, signal),
deps.sendToTab,
@@ -529,11 +525,8 @@ function buildActiveScopeBlocks(nodes: VomNode[], signals: VomNodeDomSignals): A
return blocks;
}
function buildConditionalSurfaces(
nodes: VomNode[],
captured: CapturedViewModel,
probes: CapturedSurfaceProbe[],
): CondSurface[] {
function buildConditionalSurfaces(nodes: VomNode[], captured: CapturedViewModel): CondSurface[] {
const probes = captured.surfaceProbes ?? [];
if (probes.length === 0) return [];
const surfaces: CondSurface[] = [];
@@ -656,7 +649,6 @@ function findSurfaceNodeByPoint(
export interface BuildVomSceneOptions {
pageUrl?: string;
supplementalNames?: ReadonlyMap<string, string>;
surfaceProbes?: CapturedSurfaceProbe[];
}
export type VomFrameDocument = CapturedFrameDocument<CdpAxNode>;
@@ -676,7 +668,6 @@ function legacyFrameDocuments(
...(pageUrl ? { url: pageUrl } : {}),
axNodes: [],
domNodes: captured.nodes.map((node) => ({ ...node, frameId: node.frameId ?? rootFrameId })),
excludedBackendNodeIds: captured.frameExcludedBackendNodeIds?.get(rootFrameId),
},
];
const pending = [...captured.iframeNodes.entries()];
@@ -700,7 +691,6 @@ function legacyFrameDocuments(
target: parent.target,
axNodes: [],
domNodes: domNodes.map((node) => ({ ...node, frameId: node.frameId ?? frameId })),
excludedBackendNodeIds: captured.frameExcludedBackendNodeIds?.get(frameId),
});
pending.splice(index, 1);
progress = true;
@@ -827,19 +817,18 @@ export function buildFrameVomScene(
excludedBackendNodeIds: captured.excludedBackendNodeIds,
supplementalNames: options.supplementalNames,
});
return attachCapturedSceneAnnotations(scene, documents, captured, options.surfaceProbes ?? []);
return attachCapturedSceneAnnotations(scene, documents, captured);
}
function attachCapturedSceneAnnotations(
scene: VomScene,
documents: VomFrameDocument[],
captured: CapturedViewModel,
surfaceProbes: CapturedSurfaceProbe[],
): VomScene {
const rootDocument = documents.find((document) => document.frameId === scene.rootFrameId);
const signals = capturedOnlySignals(rootDocument?.domNodes ?? captured.nodes);
const activeScopeBlocks = buildActiveScopeBlocks(scene.nodes, signals);
const surfaces = buildConditionalSurfaces(scene.nodes, captured, surfaceProbes);
const surfaces = buildConditionalSurfaces(scene.nodes, captured);
return {
...scene,
...(surfaces.length > 0 ? { surfaces } : {}),
@@ -987,19 +976,26 @@ function emptyCapturedViewModel(viewport = { width: 0, height: 0 }): CapturedVie
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,
geometry: GeometryContext,
signal?: AbortSignal,
): Promise<CapturedViewModel> {
throwIfAborted(signal, "observation");
let viewport = { width: 0, height: 0 };
try {
const metrics = await geometry.layoutMetrics({ tabId });
const metrics = await cdp.send<LayoutMetricsViewportReply>(tabId, "Page.getLayoutMetrics", {});
throwIfAborted(signal, "observation");
const source = cssViewport(metrics);
viewport = { width: source.width, height: source.height };
const source = metrics.cssLayoutViewport ?? metrics.layoutViewport ?? {};
viewport = {
width: source.clientWidth ?? 0,
height: source.clientHeight ?? 0,
};
} catch (error) {
if (isAbortError(error)) throw error;
}
@@ -1012,72 +1008,19 @@ async function captureForVom(
cdp: CdpRunner,
tabId: number,
options: CaptureVomObservationOptions,
geometry: GeometryContext,
): Promise<CapturedViewModel> {
try {
return await captureViewModel(cdp, tabId, { signal: options.signal, geometry });
return await captureViewModel(cdp, tabId, {
conditionalSurfaceProbe: options.conditionalSurfaceProbe ?? false,
hoverProbeBypassOverlay: options.hoverProbeBypassOverlay,
signal: options.signal,
});
} catch (error) {
if (isAbortError(error)) throw error;
return fallbackCapturedViewModel(cdp, tabId, geometry, options.signal);
return fallbackCapturedViewModel(cdp, tabId, options.signal);
}
}
export interface HoverProbeOutcome {
/** Whether any active hover was dispatched during this observation. */
performed: boolean;
/**
* Whether hovering surfaced content absent from the static snapshot. Cached
* tooltip names count, so this may over-report on repeat observations — it
* errs towards telling the caller the snapshot is less fresh than it looks.
*/
revealedContent: boolean;
surfaceProbes: CapturedSurfaceProbe[];
tooltipNames: Map<string, string>;
}
const NO_HOVER_PROBES: HoverProbeOutcome = {
performed: false,
revealedContent: false,
surfaceProbes: [],
tooltipNames: new Map(),
};
/**
* Runs both active-hover chains back to back.
*
* Ordering matters: this happens after DOM *and* accessibility capture so a
* hover that opens a menu cannot leave one half of the observation describing
* the page before the change and the other half after it. Sharing one overlay
* bypass span also means the agent overlay toggles once per observation
* instead of once per chain.
*/
async function runHoverProbes(
cdp: CdpRunner,
tabId: number,
captured: CapturedViewModel,
documents: VomFrameDocument[],
staticSemantics: ReturnType<typeof resolveSemanticGraph>,
options: CaptureVomObservationOptions,
): Promise<HoverProbeOutcome> {
if (!options.conditionalSurfaceProbe) return NO_HOVER_PROBES;
return withOverlayBypass(options.hoverProbeBypassOverlay, tabId, async () => {
const surfaceProbes = await probeHoverSurfaces(cdp, tabId, captured.nodes, {
signal: options.signal,
});
throwIfAborted(options.signal, "observation");
const tooltipNames = await probeTooltipNames(cdp, tabId, documents, staticSemantics, {
signal: options.signal,
});
return {
performed: true,
revealedContent: surfaceProbes.length > 0 || tooltipNames.size > 0,
surfaceProbes,
tooltipNames,
};
});
}
export interface CaptureVomObservationOptions extends VomOptions {
conditionalSurfaceProbe?: boolean;
hoverProbeBypassOverlay?: (tabId: number, enabled: boolean) => Promise<void>;
@@ -1093,16 +1036,9 @@ export async function captureVomObservation(
throwIfAborted(options.signal, "observation");
await cdp.ensureAttachedToUrl?.(tabId, url);
throwIfAborted(options.signal, "observation");
const geometry = new GeometryContext(cdp, tabId, undefined, options.signal);
const captured = await captureForVom(cdp, tabId, options, geometry);
const captured = await captureForVom(cdp, tabId, options);
throwIfAborted(options.signal, "observation");
const documents = await captureFrameData<CdpAxNode>(
cdp,
tabId,
captured,
options.signal,
geometry,
);
const documents = await captureFrameData<CdpAxNode>(cdp, tabId, captured, options.signal);
throwIfAborted(options.signal, "observation");
const normalizedDocuments =
documents.length === 1 && captured.iframeNodes.size > 0
@@ -1115,51 +1051,31 @@ export async function captureVomObservation(
excludedBackendNodeIds: captured.excludedBackendNodeIds,
});
const staticSemantics = resolveSemanticGraph(semanticGraph, { identifierFallback: false });
const hoverProbes = await runHoverProbes(
cdp,
tabId,
captured,
normalizedDocuments,
staticSemantics,
options,
);
const tooltipNames = options.conditionalSurfaceProbe
? await probeTooltipNames(cdp, tabId, normalizedDocuments, staticSemantics, {
signal: options.signal,
hoverProbeBypassOverlay: options.hoverProbeBypassOverlay,
})
: new Map<string, string>();
throwIfAborted(options.signal, "observation");
const scene = projectSemanticGraph(
normalizeSemanticStructure(
resolveSemanticGraph(semanticGraph, { supplementalNames: hoverProbes.tooltipNames }),
resolveSemanticGraph(semanticGraph, { supplementalNames: tooltipNames }),
),
);
const decoratedScene = attachCapturedSceneAnnotations(
scene,
normalizedDocuments,
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 geometryNotice = captured.frameGeometryIssues?.length
? "@warning geometry incomplete: some page or frame content has no top-level coordinates.\n"
: "";
const decoratedScene = attachCapturedSceneAnnotations(scene, normalizedDocuments, captured);
const rendered = renderVom(decoratedScene, {
maxDepth: options.maxDepth,
maxTokens:
!geometryNotice || options.maxTokens === undefined
? options.maxTokens
: Math.max(0, options.maxTokens - Math.ceil(geometryNotice.length / 4)),
maxTokens: options.maxTokens,
redactValues: options.redactValues,
activeRegionPolicy: options.activeRegionPolicy,
});
if (geometryNotice) rendered.text += `\n${geometryNotice.trimEnd()}`;
throwIfAborted(options.signal, "observation");
return projectRecordSafeObservation({
rootFrameId: captured.rootFrameId ?? normalizedDocuments[0]?.frameId ?? "root",
frameDocuments: normalizedDocuments,
rendered,
surfaceProbes: hoverProbes.surfaceProbes,
hoverProbe: {
performed: hoverProbes.performed,
revealedContent: hoverProbes.revealedContent,
},
surfaceProbes: captured.surfaceProbes,
});
}
@@ -1225,14 +1141,6 @@ async function handleVomObservation(
ref_count: observation.refs.length,
tab_id: target.tabId,
truncated: observation.truncated,
...(toolName === "observe" && observation.hoverProbe?.performed
? {
hover_probe: {
performed: true,
revealed_content: observation.hoverProbe.revealedContent,
},
}
: {}),
...(toolName === "observe" && (params as ObserveParams).debug_surfaces
? {
debug: {
@@ -1271,13 +1179,5 @@ export async function handleObserve(
deps: SnapshotDeps = getDefaultDeps(),
signal?: AbortSignal,
): Promise<ObserveResult | RpcError> {
return handleVomObservation(
manager,
params,
"observe",
"transient_input",
params.probe_hover === true,
deps,
signal,
);
return handleVomObservation(manager, params, "observe", "transient_input", true, deps, signal);
}
+8 -94
View File
@@ -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;
}
-2
View File
@@ -53,11 +53,9 @@ export type { DialogCursor };
export interface CdpRunner {
send<T = unknown>(tabId: number, method: string, params?: object): Promise<T>;
sendToTarget?<T = unknown>(target: CdpTarget, method: string, params?: object): Promise<T>;
detach?(tabId: number): Promise<void>;
getFrameGraph?(tabId: number): Promise<CdpFrameGraph>;
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;
};
+28 -45
View File
@@ -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);
}
}
-85
View File
@@ -1,85 +0,0 @@
// Upload orchestration: validate the session-scoped request, resolve its click
// 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 {
type CdpRunner,
enforceAgentWindow,
isRpcError,
lookupSession,
resolveTargetTab,
} from "./shared";
const DEFAULT_TIMEOUT_MS = 120_000;
export interface UploadDeps extends InteractionDeps {
cdp: CdpRunner;
sendToTab?: CaptureSuppressSendToTab;
}
export async function handleUpload(
manager: SessionManager,
params: UploadParams,
deps: UploadDeps,
): Promise<UploadResult | RpcError> {
const ctx = lookupSession(manager, params, "upload");
if (isRpcError(ctx)) return ctx;
const target = await resolveTargetTab(manager, ctx, params.tab_id, deps.tabsApi);
if (isRpcError(target)) return target;
const denied = enforceAgentWindow(ctx, target, "upload");
if (denied) return denied;
if (
params.files.length === 0 ||
params.files.length > 20 ||
params.files.some((file) => !file.staged_path)
) {
return { code: "invalid_params", message: "upload requires daemon-staged files" };
}
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;
}
return {
tab_id: target.tabId,
used_ref: usedRef,
used_selector: usedSelector,
file_names: params.files.map((file) => file.name),
};
}
@@ -1,7 +1,6 @@
import { describe, expect, it, vi } from "vitest";
import { OVERLAY_HOST_MARKER_ATTR, OVERLAY_HOST_NAME } from "../../../lib/overlay-bridge";
import type { CdpRunner } from "../../shared";
import { captureViewModel, collectOverlayExcludedBackendIds, probeHoverSurfaces } from "../capture";
import { captureViewModel, collectOverlayExcludedBackendIds } from "../capture";
// Minimal but format-accurate captureSnapshot reply: a body with one
// fixed full-screen overlay div carrying a password input.
@@ -211,38 +210,26 @@ 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>,
};
@@ -264,10 +251,11 @@ describe("captureViewModel", () => {
expect(input?.attrs).toEqual({ type: "password" });
});
it("never hovers the page while capturing", async () => {
it("does not run conditional surface probes by default", async () => {
const cdp = makeCdp(fakeSnapshotReply());
await captureViewModel(cdp, 4);
const result = await captureViewModel(cdp, 4);
expect(result.surfaceProbes).toEqual([]);
expect(cdp.send).not.toHaveBeenCalledWith(4, "Input.dispatchMouseEvent", expect.anything());
});
@@ -286,11 +274,8 @@ describe("captureViewModel", () => {
expect(cdp.send).toHaveBeenCalledWith(
4,
"Runtime.evaluate",
expect.objectContaining({
serializationOptions: expect.objectContaining({ serialization: "deep" }),
}),
expect.objectContaining({ returnByValue: true }),
);
expect(cdp.send).toHaveBeenCalledWith(4, "Runtime.releaseObjectGroup", expect.anything());
expect(cdp.send).not.toHaveBeenCalledWith(4, "DOM.resolveNode", expect.anything());
expect(cdp.send).not.toHaveBeenCalledWith(4, "Runtime.callFunctionOn", expect.anything());
});
@@ -303,8 +288,6 @@ describe("captureViewModel", () => {
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 },
};
}
@@ -336,10 +319,9 @@ describe("captureViewModel", () => {
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const captured = await captureViewModel(cdp, 4);
const surfaceProbes = await probeHoverSurfaces(cdp, 4, captured.nodes);
const result = await captureViewModel(cdp, 4, { conditionalSurfaceProbe: true });
expect(surfaceProbes).toEqual([
expect(result.surfaceProbes).toEqual([
{
triggerBackendNodeId: 12,
triggerPoint: { x: 956, y: 32 },
@@ -368,8 +350,6 @@ describe("captureViewModel", () => {
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 },
};
}
@@ -398,10 +378,9 @@ describe("captureViewModel", () => {
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const captured = await captureViewModel(cdp, 4);
const surfaceProbes = await probeHoverSurfaces(cdp, 4, captured.nodes);
const result = await captureViewModel(cdp, 4, { conditionalSurfaceProbe: true });
expect(surfaceProbes).toEqual([
expect(result.surfaceProbes).toEqual([
expect.objectContaining({
triggerBackendNodeId: 12,
subItems: ["My profile", "Sign out"],
@@ -418,8 +397,6 @@ describe("captureViewModel", () => {
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 },
};
}
@@ -445,8 +422,7 @@ describe("captureViewModel", () => {
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const captured = await captureViewModel(cdp, 4);
await probeHoverSurfaces(cdp, 4, captured.nodes);
await captureViewModel(cdp, 4, { conditionalSurfaceProbe: true });
expect(hoverMoves).toBe(1);
});
@@ -538,9 +514,6 @@ describe("captureViewModel", () => {
strings: S,
documents: [
{
scrollOffsetX: 0,
scrollOffsetY: 0,
frameId: "main",
nodes: {
parentIndex: [-1, 0, 1, 0, 3, 4],
nodeName: [i("html"), i("body"), i("div"), i(OVERLAY_HOST_NAME), i("div"), i("button")],
@@ -571,12 +544,8 @@ describe("captureViewModel", () => {
],
};
const { excludedBackendNodeIds, frameExcludedBackendNodeIds } = await captureViewModel(
makeCdp(snapshot),
4,
);
const { excludedBackendNodeIds } = await captureViewModel(makeCdp(snapshot), 4);
expect(excludedBackendNodeIds).toEqual(new Set([13, 14, 15]));
expect(frameExcludedBackendNodeIds?.get("main")).toEqual(excludedBackendNodeIds);
});
it("excludes overlay host matched by tag name only", async () => {
@@ -760,8 +729,6 @@ describe("captureViewModel", () => {
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 },
};
}
@@ -774,46 +741,7 @@ describe("captureViewModel", () => {
expect(div?.rect).toMatchObject({ y: 0, h: 600 });
});
it("normalizes snapshot-owned scroll before using a stale CSS metrics fallback", async () => {
const snapshot = {
strings: ["html", "button"],
documents: [
{
frameId: "root",
scrollOffsetX: 40,
scrollOffsetY: 200,
nodes: {
parentIndex: [-1, 0],
nodeName: [0, 1],
backendNodeId: [10, 11],
attributes: [[], []],
},
layout: { nodeIndex: [1], bounds: [[200, 800, 240, 80]] },
},
],
};
const cdp: CdpRunner = {
send: vi.fn(async (_tab: number, method: string) => {
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
if (method === "Page.getLayoutMetrics")
return {
visualViewport: { clientWidth: 2000 },
cssVisualViewport: { clientWidth: 1000 },
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 999, pageY: 999 },
};
return {};
}) as CdpRunner["send"],
};
const captured = await captureViewModel(cdp, 4);
expect(captured.nodes.find((node) => node.backendNodeId === 11)).toMatchObject({
localRect: { x: 80, y: 300, w: 120, h: 40 },
rect: { x: 80, y: 300, w: 120, h: 40 },
rendered: true,
});
expect(captured.frameGeometryIssues).toEqual([]);
});
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 = {
@@ -847,8 +775,6 @@ describe("captureViewModel", () => {
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 },
};
@@ -863,12 +789,6 @@ describe("captureViewModel", () => {
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 () => {
@@ -924,8 +844,6 @@ describe("captureViewModel", () => {
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 },
};
}
@@ -1016,17 +934,9 @@ describe("captureViewModel", () => {
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>,
};
@@ -1056,7 +966,7 @@ describe("captureViewModel", () => {
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",
@@ -1114,17 +1024,9 @@ describe("captureViewModel", () => {
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>,
};
@@ -1133,7 +1035,7 @@ describe("captureViewModel", () => {
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 () => {
@@ -1175,8 +1077,6 @@ describe("captureViewModel", () => {
},
},
{
scrollOffsetX: 0,
scrollOffsetY: 0,
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i("iframe")],
@@ -1198,8 +1098,6 @@ describe("captureViewModel", () => {
},
},
{
scrollOffsetX: 0,
scrollOffsetY: 0,
nodes: {
parentIndex: [-1, 0],
nodeName: [i("body"), i("input")],
@@ -1216,45 +1114,16 @@ describe("captureViewModel", () => {
],
};
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 { iframeNodes } = await captureViewModel(cdp, 4);
@@ -1268,7 +1137,7 @@ describe("captureViewModel", () => {
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("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 = {
@@ -1302,8 +1171,6 @@ describe("captureViewModel", () => {
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 },
};
@@ -1337,200 +1204,3 @@ describe("captureViewModel", () => {
expect(excluded).toEqual(new Set([200, 201, 202]));
});
});
// Six sibling frames and one nested frame exercise scheduling through the real capture entry.
function siblingCaptureFixture(
beforeReply: (method: string, params: Record<string, unknown>) => Promise<void> = async () => {},
) {
const document = (id: number, owners: number[], childIndexes: number[]) => ({
scrollOffsetX: 0,
scrollOffsetY: 0,
frameId: `frame-${id}`,
nodes: {
parentIndex: [-1, ...owners.map(() => 0)],
nodeName: [0, ...owners.map(() => 1)],
backendNodeId: [1000 + id, ...owners],
attributes: [[], ...owners.map(() => [])],
contentDocumentIndex: { index: owners.map((_, i) => i + 1), value: childIndexes },
},
layout: {
nodeIndex: [0, ...owners.map((_, i) => i + 1)],
bounds: [[0, 0, 200, 100], ...owners.map(() => [0, 0, 200, 100])],
},
});
const snapshot = {
strings: ["body", "iframe"],
documents: [
document(0, [100, 101, 102, 103, 104, 105], [1, 2, 3, 4, 5, 6]),
document(1, [200], [7]),
...Array.from({ length: 6 }, (_, i) => document(i + 2, [], [])),
],
};
let active = 0;
let peak = 0;
const send = vi.fn(async (_tabId: number, method: string, params: object = {}) => {
const args = params as Record<string, unknown>;
active++;
peak = Math.max(peak, active);
try {
await beforeReply(method, args);
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
if (method === "Page.getLayoutMetrics")
return {
visualViewport: { clientWidth: 1000 },
cssVisualViewport: { clientWidth: 1000 },
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 },
};
if (method === "DOM.getBoxModel")
return { model: { content: [0, 0, 200, 0, 200, 100, 0, 100] } };
if (method === "DOM.resolveNode") return { object: { objectId: String(args.backendNodeId) } };
if (method === "Runtime.callFunctionOn")
return { result: { value: { width: 200, height: 100 } } };
return {};
} finally {
active--;
}
});
return {
cdp: { send: send as CdpRunner["send"] },
send,
peak: () => peak,
active: () => active,
measured: () =>
send.mock.calls
.filter(([, method]) => method === "DOM.getBoxModel")
.map(([, , params]) => (params as { backendNodeId: number }).backendNodeId),
};
}
describe("sibling frame measurement scheduling", () => {
it("batches same-target owner sizes without changing projected results", async () => {
const fixture = siblingCaptureFixture();
const original = fixture.cdp.send;
const methods: string[] = [];
fixture.cdp.send = async (tabId, method, params) => {
methods.push(method);
if (method === "Runtime.evaluate")
return {
result: {
deepSerializedValue: {
type: "array",
value: [100, 101, 102, 103, 104, 105, 200].map((backendNodeId) => ({
type: "array",
value: [
{ type: "node", value: { backendNodeId } },
{ type: "string", value: JSON.stringify({ width: 200, height: 100 }) },
],
})),
},
},
} as never;
return original(tabId, method, params);
};
const captured = await captureViewModel(fixture.cdp, 4);
expect(captured.frameGeometryIssues).toEqual([]);
expect([...captured.iframeNodes.keys()]).toEqual([100, 200, 101, 102, 103, 104, 105]);
expect(captured.iframeNodes.get(200)?.[0].rect).toEqual({ x: 0, y: 0, w: 200, h: 100 });
expect(methods.filter((method) => method === "DOM.getBoxModel")).toHaveLength(7);
expect(methods.filter((method) => method === "Runtime.evaluate")).toHaveLength(1);
expect(methods.filter((method) => method === "Runtime.releaseObjectGroup")).toHaveLength(1);
expect(methods).not.toContain("DOM.resolveNode");
expect(methods).not.toContain("Runtime.callFunctionOn");
});
it("bounds concurrent reads, fills free slots and preserves depth-first output despite reordered replies", async () => {
const pending = new Map<number, () => void>();
const fixture = siblingCaptureFixture(async (method, params) => {
if (method === "DOM.getBoxModel" && Number(params.backendNodeId) < 200)
await new Promise<void>((resolve) => pending.set(Number(params.backendNodeId), resolve));
});
const capture = captureViewModel(fixture.cdp, 4);
await vi.waitFor(() => expect(pending.size).toBe(4));
expect(fixture.measured()).toEqual([100, 101, 102, 103]);
pending.get(103)!();
await vi.waitFor(() => expect(pending.has(104)).toBe(true));
pending.get(104)!();
await vi.waitFor(() => expect(pending.has(105)).toBe(true));
expect(fixture.measured()).not.toContain(200);
for (const id of [105, 102, 101, 100]) pending.get(id)!();
const captured = await capture;
expect(captured.frameGeometryIssues).toEqual([]);
expect(fixture.peak()).toBe(4);
expect(fixture.active()).toBe(0);
expect(fixture.measured()).toEqual([100, 101, 102, 103, 104, 105, 200]);
expect([...captured.iframeNodes.keys()]).toEqual([100, 200, 101, 102, 103, 104, 105]);
expect(captured.iframeNodes.get(200)?.[0].rect).toEqual({ x: 0, y: 0, w: 200, h: 100 });
for (const method of [
"DOM.getBoxModel",
"DOM.resolveNode",
"Runtime.callFunctionOn",
"Runtime.releaseObject",
])
expect(fixture.send.mock.calls.filter(([, name]) => name === method)).toHaveLength(7);
});
it("does not measure descendants of a failed owner and retains sibling geometry and local nodes", async () => {
const fixture = siblingCaptureFixture(async (method, params) => {
if (method === "DOM.resolveNode" && params.backendNodeId === 100)
throw new Error("owner replaced");
});
const captured = await captureViewModel(fixture.cdp, 4);
expect(captured.frameGeometryIssues).toEqual([
{
status: "unavailable",
source: { target: { tabId: 4 }, frameId: "frame-1" },
ownerBackendNodeId: 100,
},
{
status: "blocked",
source: { target: { tabId: 4 }, frameId: "frame-7" },
cause: captured.frameGeometryIssues?.[0],
},
]);
expect(fixture.measured()).not.toContain(200);
expect(captured.iframeNodes.get(200)?.[0]).toMatchObject({
tag: "body",
rect: null,
localRect: { x: 0, y: 0, w: 200, h: 100 },
});
expect(captured.iframeNodes.get(101)?.[0].rect).toEqual({ x: 0, y: 0, w: 200, h: 100 });
expect([...captured.iframeNodes.keys()]).toEqual([100, 200, 101, 102, 103, 104, 105]);
});
it("stops scheduling on cancellation and waits for resolved objects to be released", async () => {
const controller = new AbortController();
const resolutions = new Map<string, () => void>();
const releases = new Map<string, () => void>();
const fixture = siblingCaptureFixture(async (method, params) => {
if (method === "DOM.resolveNode")
await new Promise<void>((resolve) =>
resolutions.set(String(params.backendNodeId), resolve),
);
if (method === "Runtime.releaseObject")
await new Promise<void>((resolve) => releases.set(String(params.objectId), resolve));
});
let settled = false;
const capture = captureViewModel(fixture.cdp, 4, { signal: controller.signal });
const rejected = expect(capture).rejects.toMatchObject({ name: "AbortError" });
void capture.then(
() => {
settled = true;
},
() => {
settled = true;
},
);
await vi.waitFor(() => expect(resolutions.size).toBe(4));
controller.abort();
for (const resolve of resolutions.values()) resolve();
await vi.waitFor(() => expect(releases.size).toBe(4));
expect(settled).toBe(false);
expect(fixture.measured()).toEqual([100, 101, 102, 103]);
for (const release of releases.values()) release();
await rejected;
expect(fixture.active()).toBe(0);
expect(fixture.send.mock.calls.some(([, method]) => method === "Runtime.callFunctionOn")).toBe(
false,
);
});
});
@@ -1,127 +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 } 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);
});
});
@@ -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());
});
});
@@ -1,5 +1,4 @@
import { describe, expect, it, vi } from "vitest";
import { OVERLAY_HOST_MARKER_ATTR } from "@/lib/overlay-bridge";
import type { CdpRunner } from "../../shared";
import type { CapturedNode, CapturedViewModel } from "../capture";
import { captureFrameData } from "../frame-capture";
@@ -26,14 +25,12 @@ function childSnapshot(frameId: string, backendNodeId: number) {
strings,
documents: [
{
scrollOffsetX: 0,
scrollOffsetY: 0,
frameId,
nodes: {
parentIndex: [-1, 0],
nodeName: [1, 2],
backendNodeId: [backendNodeId - 1, backendNodeId],
attributes: [[], []] as number[][],
attributes: [[], []],
},
layout: {
nodeIndex: [0, 1],
@@ -53,72 +50,6 @@ function childSnapshot(frameId: string, backendNodeId: number) {
}
describe("captureFrameData", () => {
it("retains nested owner failures when merging a captured OOPIF", async () => {
const owner = ownerNode(10, 50);
const captured: CapturedViewModel = {
nodes: [owner],
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
frameNodes: new Map([["main", [owner]]]),
rootFrameId: "main",
excludedBackendNodeIds: new Set(),
};
const child = childSnapshot("child", 101);
const nested = childSnapshot("nested", 201);
const document = child.documents[0];
const snapshot = {
strings: child.strings,
documents: [
{
...document,
nodes: { ...document.nodes, contentDocumentIndex: { index: [1], value: [1] } },
},
nested.documents[0],
],
};
const reply = async (_target: unknown, method: string) => {
if (method === "Page.getLayoutMetrics")
return {
visualViewport: { clientWidth: 1000 },
cssVisualViewport: { clientWidth: 1000 },
cssLayoutViewport: { clientWidth: 300, clientHeight: 200 },
};
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
if (method === "DOM.getBoxModel")
return { model: { content: [50, 100, 350, 100, 350, 300, 50, 300] } };
if (method === "DOM.resolveNode") throw new Error("nested owner replaced");
return {};
};
const cdp: CdpRunner = {
send: vi.fn(reply) as CdpRunner["send"],
sendToTarget: vi.fn(reply) 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" },
},
],
})),
};
await captureFrameData(cdp, 4, captured);
expect(captured.frameGeometryIssues).toEqual([
{
status: "unavailable",
source: { target: { tabId: 4, sessionId: "child-session" }, frameId: "nested" },
ownerBackendNodeId: 101,
},
]);
expect(captured.frameNodes?.get("nested")?.[1]).toMatchObject({
rect: null,
localRect: { x: 10, y: 20, w: 100, h: 40 },
});
});
it("captures and positions multiple OOPIF documents missing from the root snapshot", async () => {
const leftOwner = ownerNode(10, 50);
const rightOwner = ownerNode(20, 500);
@@ -133,23 +64,13 @@ describe("captureFrameData", () => {
};
const sendToTarget = vi.fn(async (target, method) => {
if (method === "Page.getLayoutMetrics") {
return {
visualViewport: { clientWidth: 1000 },
cssVisualViewport: { clientWidth: 1000 },
cssLayoutViewport: { clientWidth: 300, clientHeight: 200, pageX: 0, pageY: 0 },
};
return { cssLayoutViewport: { clientWidth: 300, clientHeight: 200, pageX: 0, pageY: 0 } };
}
if (method === "DOMSnapshot.enable" || method === "Accessibility.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") {
if (target.sessionId !== "left-session") return childSnapshot("right", 201);
const snapshot = childSnapshot("left", 101);
const marker = snapshot.strings.push(OVERLAY_HOST_MARKER_ATTR) - 1;
const nodes = snapshot.documents[0].nodes;
nodes.backendNodeId.push(201); // Same id as a real button in the other target.
nodes.parentIndex.push(0);
nodes.nodeName.push(2);
nodes.attributes.push([marker, -1]);
return snapshot;
return target.sessionId === "left-session"
? childSnapshot("left", 101)
: childSnapshot("right", 201);
}
if (method === "Accessibility.getFullAXTree") return { nodes: [] };
throw new Error(`unexpected ${method}`);
@@ -164,11 +85,7 @@ describe("captureFrameData", () => {
return { model: { content: [x, 100, x + 300, 100, x + 300, 300, x, 300] } };
}
if (method === "Page.getLayoutMetrics") {
return {
visualViewport: { clientWidth: 1000 },
cssVisualViewport: { clientWidth: 1000 },
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 },
};
return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
}
throw new Error(`unexpected root ${method}`);
}) as CdpRunner["send"],
@@ -195,10 +112,6 @@ describe("captureFrameData", () => {
const trees = await captureFrameData(cdp, 4, captured);
expect(trees.find((tree) => tree.frameId === "left")?.excludedBackendNodeIds).toEqual(
new Set([201]),
);
expect(trees.find((tree) => tree.frameId === "right")?.excludedBackendNodeIds?.size).toBe(0);
expect(trees.map((tree) => tree.frameId)).toEqual(["main", "left", "right"]);
expect(
captured.frameNodes?.get("left")?.find((node) => node.backendNodeId === 101)?.rect,
@@ -236,11 +149,7 @@ describe("captureFrameData", () => {
if (method === "Accessibility.getFullAXTree") return { nodes: [] };
if (method === "DOM.getBoxModel") throw new Error("owner geometry unavailable");
if (method === "Page.getLayoutMetrics") {
return {
visualViewport: { clientWidth: 1000 },
cssVisualViewport: { clientWidth: 1000 },
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 },
};
return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
}
throw new Error(`unexpected root ${method}`);
}) as CdpRunner["send"],
@@ -283,7 +192,7 @@ describe("captureFrameData", () => {
expect.objectContaining({ backendDOMNodeId: 101, frameId: "child" }),
]);
expect(childDocument?.domNodes.find((node) => node.backendNodeId === 101)).toEqual(
expect.objectContaining({ rect: null, localRect: null, rendered: true }),
expect.objectContaining({ rect: null, localRect: { x: 10, y: 20, w: 100, h: 40 } }),
);
});
});
@@ -29,7 +29,7 @@ function captured(frameNodes: Map<string, CapturedNode[]>): CapturedViewModel {
}
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: [
@@ -54,7 +54,7 @@ describe("buildFrameDocuments", () => {
},
];
const documents = await buildFrameDocuments(
const documents = buildFrameDocuments(
graph,
batches,
captured(
@@ -72,7 +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: [
@@ -92,7 +92,7 @@ describe("buildFrameDocuments", () => {
},
];
const documents = await buildFrameDocuments(
const documents = buildFrameDocuments(
graph,
batches,
captured(
@@ -107,7 +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: [
@@ -129,7 +129,7 @@ describe("buildFrameDocuments", () => {
nodes: [{ nodeId: `${frame.frameId}-node`, backendDOMNodeId: 7 }],
}));
const documents = await buildFrameDocuments(
const documents = buildFrameDocuments(
graph,
batches,
captured(
@@ -149,7 +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)]],
@@ -164,25 +164,11 @@ describe("buildFrameDocuments", () => {
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("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");
});
});
@@ -1,84 +0,0 @@
import { afterEach, describe, expect, it, vi } from "vitest";
import { ProbeBudget, resetOverlayBypassDepth, withOverlayBypass } from "../hover-perception";
afterEach(() => {
resetOverlayBypassDepth();
});
describe("ProbeBudget", () => {
it("refuses a candidate that cannot finish inside the budget", () => {
const budget = new ProbeBudget(500);
expect(budget.canAfford(400)).toBe(true);
expect(budget.canAfford(600)).toBe(false);
});
it("stops admitting candidates once the remaining budget is smaller than one", async () => {
const budget = new ProbeBudget(60);
await new Promise((resolve) => setTimeout(resolve, 40));
// A top-of-loop `elapsed > total` check would still admit this candidate
// and then overshoot by its full cost.
expect(budget.canAfford(50)).toBe(false);
});
});
describe("withOverlayBypass", () => {
it("toggles the overlay once around nested probe phases", async () => {
const bypass = vi.fn(async () => {});
await withOverlayBypass(bypass, 4, async () => {
await withOverlayBypass(bypass, 4, async () => {
expect(bypass).toHaveBeenCalledTimes(1);
});
expect(bypass).toHaveBeenCalledTimes(1);
});
expect(bypass.mock.calls).toEqual([
[4, true],
[4, false],
]);
});
it("restores the overlay when the probe throws", async () => {
const bypass = vi.fn(async () => {});
await expect(
withOverlayBypass(bypass, 4, async () => {
throw new Error("probe exploded");
}),
).rejects.toThrow("probe exploded");
expect(bypass).toHaveBeenLastCalledWith(4, false);
});
it("reports a failed restore instead of swallowing it", async () => {
const onRestoreFailure = vi.fn();
const bypass = vi.fn(async (_tabId: number, enabled: boolean) => {
if (!enabled) throw new Error("tab is gone");
});
await withOverlayBypass(bypass, 4, async () => undefined, { onRestoreFailure });
expect(onRestoreFailure).toHaveBeenCalledTimes(1);
});
it("does not pin the overlay off for the tab when a restore fails", async () => {
const failing = vi.fn(async (_tabId: number, enabled: boolean) => {
if (!enabled) throw new Error("tab is gone");
});
await withOverlayBypass(failing, 4, async () => undefined, { onRestoreFailure: () => {} });
const bypass = vi.fn(async () => {});
await withOverlayBypass(bypass, 4, async () => undefined);
expect(bypass.mock.calls).toEqual([
[4, true],
[4, false],
]);
});
it("runs the probe untouched when no bypass is wired up", async () => {
await expect(withOverlayBypass(undefined, 4, async () => "done")).resolves.toBe("done");
});
});
@@ -132,37 +132,6 @@ describe("tooltip name enrichment", () => {
expect(cdp.sendToTarget).not.toHaveBeenCalled();
});
it("remembers controls that revealed no tooltip so the miss is paid once", async () => {
const cdp: CdpRunner = {
send: vi.fn(async () => ({})) as CdpRunner["send"],
sendToTarget: vi.fn(async (_target, method) => {
if (method === "Page.createIsolatedWorld") return { executionContextId: 31 };
if (method === "DOM.resolveNode") return { object: { objectId: "button-801" } };
if (method === "Runtime.callFunctionOn") return { result: { value: [] } };
return {};
}) as CdpRunner["sendToTarget"],
};
const documents = [
document({ tabId: 11, sessionId: "miss-session" }, 801, undefined, "miss-frame"),
];
const graph = semantics(documents);
const first = await probeTooltipNames(cdp, 11, documents, graph);
expect(first.size).toBe(0);
const hoversAfterFirst = vi
.mocked(cdp.send)
.mock.calls.filter(([, method]) => method === "Input.dispatchMouseEvent").length;
expect(hoversAfterFirst).toBeGreaterThan(0);
const second = await probeTooltipNames(cdp, 11, documents, graph);
expect(second.size).toBe(0);
expect(
vi.mocked(cdp.send).mock.calls.filter(([, method]) => method === "Input.dispatchMouseEvent")
.length,
).toBe(hoversAfterFirst);
});
it("keeps tooltip evidence isolated across sibling frame sessions", async () => {
let hoveredX = -10;
const cdp: CdpRunner = {
@@ -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;
});
};
}
@@ -1,37 +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;
}
File diff suppressed because it is too large Load Diff
-94
View File
@@ -1,94 +0,0 @@
import { isOverlayHostNode } from "@/lib/overlay-bridge";
import { createCaptureCheckpoint } from "./capture-abort";
import type { CapturedNode } from "./capture-types";
/** Bounds retain their raw snapshot document layout units until normalization. */
export interface SnapshotLayout {
readonly boundsSpace: "snapshot-document-layout";
bounds?: number[];
styles: Readonly<Record<string, string>>;
}
export interface DecodedNode extends Omit<CapturedNode, "rect" | "localRect" | "rendered"> {
nodeType?: number;
layout?: SnapshotLayout;
}
export interface NodeFacts extends CapturedNode {
nodeType?: number;
layout?: SnapshotLayout;
}
export interface DocumentIndex<T extends DecodedNode = NodeFacts> {
readonly nodes: ReadonlyMap<number, T>;
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,
): Promise<DocumentIndex<T>> {
const checkpoint = createCaptureCheckpoint(signal);
const nodes = new Map<number, T>();
const overlayByNode = new Map<number, boolean>();
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;
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) {
current = undefined;
break;
}
current = nodes.get(current.parentBackendNodeId);
}
if (current && overlayByNode.has(current.backendNodeId))
overlay = overlayByNode.get(current.backendNodeId)!;
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 (overlay) excludedBackendNodeIds.add(item.backendNodeId);
}
}
return { nodes, excludedBackendNodeIds };
}
@@ -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);
}
}
+15 -17
View File
@@ -1,6 +1,6 @@
import type { CdpFrame, CdpFrameGraph } from "@/browser-driver/frame-graph";
import { resolveFrameProjection } from "../frame-geometry";
import { type GeometryProjection, projectRectToViewport } from "../geometry";
import { GeometryContext } from "../geometry/frame-context";
import { type CdpRunner, cdpRunnerForTarget, sendToCdpTarget } from "../shared";
import { type CapturedNode, type CapturedViewModel, captureViewModel } from "./capture";
import {
@@ -21,6 +21,16 @@ 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,
@@ -41,7 +51,6 @@ async function captureMissingFrameDocuments(
tabId: number,
graph: CdpFrameGraph,
captured: CapturedViewModel,
geometry: GeometryContext,
signal?: AbortSignal,
): Promise<void> {
if (!captured.frameNodes) captured.frameNodes = new Map();
@@ -53,20 +62,10 @@ async function captureMissingFrameDocuments(
try {
const child = await captureViewModel(cdpRunnerForTarget(cdp, frame.target), tabId, {
signal,
geometry,
target: frame.target,
});
if (child.frameExcludedBackendNodeIds?.size) {
captured.frameExcludedBackendNodeIds ??= new Map();
for (const [id, excluded] of child.frameExcludedBackendNodeIds)
captured.frameExcludedBackendNodeIds.set(id, excluded);
}
if (child.frameGeometryIssues?.length) {
(captured.frameGeometryIssues ??= []).push(...child.frameGeometryIssues);
}
let projection: GeometryProjection | null = null;
try {
projection = await geometry.targetProjection(frame.frameId);
projection = await resolveFrameProjection(cdp, graph, frame.frameId);
} catch (err) {
if (isAbortError(err)) throw err;
console.debug("[bsk observation] child frame geometry projection failed", {
@@ -172,12 +171,11 @@ export async function captureFrameData<T extends FrameAxNode>(
tabId: number,
captured: CapturedViewModel,
signal?: AbortSignal,
geometry = new GeometryContext(cdp, tabId, undefined, signal),
): Promise<CapturedFrameDocument<T>[]> {
const graph = await geometry.graph();
const graph = await discoverFrameGraph(cdp, tabId);
const frames = graph?.frames ?? [];
if (graph) await captureMissingFrameDocuments(cdp, tabId, graph, captured, geometry, signal);
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, signal);
return buildFrameDocuments(graph, batches, captured);
}
+41 -75
View File
@@ -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;
@@ -24,17 +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[]>;
frameOwnerBackendNodeIds?: ReadonlyMap<string, number>;
frameParentIds?: ReadonlyMap<string, string>;
frameExcludedBackendNodeIds?: ReadonlyMap<string, ReadonlySet<number>>;
}
interface Ownership {
@@ -59,7 +47,7 @@ function targetBackendKey(target: CdpTarget, backendNodeId: number): string {
function frameList<T extends FrameOwnedAxNode>(
graph: CdpFrameGraph | null,
batches: FrameAxBatch<T>[],
captured: FrameDomInput,
captured: CapturedViewModel,
): CdpFrame[] {
const frames = new Map<string, CdpFrame>();
for (const frame of graph?.frames ?? []) frames.set(frame.frameId, frame);
@@ -82,14 +70,11 @@ function frameList<T extends FrameOwnedAxNode>(
});
}
export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
export function buildFrameDocuments<T extends FrameOwnedAxNode>(
graph: CdpFrameGraph | null,
batches: FrameAxBatch<T>[],
captured: FrameDomInput,
signal?: AbortSignal,
): Promise<FrameDocument<T>[]> {
const checkpoint = createCaptureCheckpoint(signal);
let work = 0;
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;
@@ -98,68 +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);
}
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 && frameById.has(current.frameId)) {
ownership = { frameId: current.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);
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) {
@@ -173,10 +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))
@@ -202,6 +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),
}));
}
@@ -35,91 +35,3 @@ export async function clearHover(cdp: CdpRunner, tabId: number): Promise<void> {
}),
);
}
/**
* Wall-clock budget for a probe phase.
*
* Callers ask whether the *next* candidate still fits before starting it,
* rather than checking elapsed time at the top of the loop. A top-of-loop
* check lets a candidate start with 1ms of budget left and then run to
* completion, overshooting by a full settle window.
*/
export class ProbeBudget {
private readonly startedAt = Date.now();
constructor(private readonly totalMs: number) {}
get elapsedMs(): number {
return Date.now() - this.startedAt;
}
/** True when a candidate costing `estimatedMs` still fits in the budget. */
canAfford(estimatedMs: number): boolean {
return this.elapsedMs + estimatedMs <= this.totalMs;
}
}
export type OverlayBypass = (tabId: number, enabled: boolean) => Promise<void>;
export interface OverlayBypassScopeOptions {
/**
* Called when the overlay could not be restored. Defaults to `console.error`
* so a stuck-bypassed overlay is never silent; tests inject a spy.
*/
onRestoreFailure?: (error: unknown) => void;
}
const overlayBypassDepth = new Map<number, number>();
/**
* Runs `body` with the agent overlay bypassed, restoring it afterwards.
*
* Reference counted per tab so nested probe phases share a single bypass span
* instead of toggling the overlay once per phase. Restore failures are
* reported rather than swallowed, and the depth is released even when restore
* throws so a failure cannot pin the overlay off for the tab's lifetime.
*/
export async function withOverlayBypass<T>(
bypass: OverlayBypass | undefined,
tabId: number,
body: () => Promise<T>,
options: OverlayBypassScopeOptions = {},
): Promise<T> {
if (!bypass) return body();
const depth = overlayBypassDepth.get(tabId) ?? 0;
overlayBypassDepth.set(tabId, depth + 1);
if (depth === 0) {
try {
await bypass(tabId, true);
} catch (error) {
// Failing to hide the overlay only risks probing our own UI, so continue.
console.debug("[bsk hover] overlay bypass could not be enabled", error);
}
}
try {
return await body();
} finally {
const current = overlayBypassDepth.get(tabId) ?? 1;
if (current <= 1) {
overlayBypassDepth.delete(tabId);
try {
await bypass(tabId, false);
} catch (error) {
(options.onRestoreFailure ?? defaultRestoreFailure)(error);
}
} else {
overlayBypassDepth.set(tabId, current - 1);
}
}
}
function defaultRestoreFailure(error: unknown): void {
console.error("[bsk hover] agent overlay could not be restored after probing", error);
}
/** Test seam: drops any bypass depth left behind by a crashed probe. */
export function resetOverlayBypassDepth(): void {
overlayBypassDepth.clear();
}
+15 -26
View File
@@ -1,7 +1,7 @@
import { isVomReferenceNode } from "@browser-skill/vom";
import { type CdpRunner, sendToCdpTarget } from "../shared";
import type { FrameDocument, FrameOwnedAxNode } from "./frame-document";
import { clearHover, ProbeBudget, waitForHover } from "./hover-perception";
import { clearHover, waitForHover } from "./hover-perception";
import { stableIdentifierName } from "./semantic-graph/name-evidence";
import { frameBackendKey, type ResolvedSemanticGraph } from "./semantic-graph/types";
@@ -9,18 +9,11 @@ const MAX_TOOLTIP_CANDIDATES = 8;
const MAX_TOOLTIP_PROBE_MS = 2_400;
const TOOLTIP_SETTLE_MS = 250;
const CACHE_TTL_MS = 5 * 60_000;
/**
* Misses expire sooner than hits: a control that gains a tooltip once the app
* finishes booting should still be discoverable, but not at the cost of
* re-probing every unlabelled control on every observation.
*/
const MISS_CACHE_TTL_MS = 60_000;
const MAX_CACHE_ENTRIES = 500;
const FORM_CONTROL_TAGS = new Set(["input", "select", "textarea"]);
interface TooltipCacheEntry {
/** `null` records "probed, revealed no tooltip" so the miss is not re-paid. */
name: string | null;
name: string;
expiresAt: number;
}
@@ -34,6 +27,7 @@ interface TooltipCandidate<T extends FrameOwnedAxNode> {
export interface TooltipNameProbeOptions {
signal?: AbortSignal;
hoverProbeBypassOverlay?: (tabId: number, enabled: boolean) => Promise<void>;
}
const tooltipCache = new Map<string, TooltipCacheEntry>();
@@ -45,11 +39,10 @@ function cacheKey<T extends FrameOwnedAxNode>(
return `${document.target.tabId}\u0000${document.frameId}\u0000${document.url ?? ""}\u0000${backendNodeId}`;
}
/** Returns the cache entry, or `undefined` when this control was never probed. */
function cachedEntry<T extends FrameOwnedAxNode>(
function cachedName<T extends FrameOwnedAxNode>(
document: FrameDocument<T>,
backendNodeId: number,
): TooltipCacheEntry | undefined {
): string | undefined {
const key = cacheKey(document, backendNodeId);
const entry = tooltipCache.get(key);
if (!entry) return undefined;
@@ -57,13 +50,13 @@ function cachedEntry<T extends FrameOwnedAxNode>(
tooltipCache.delete(key);
return undefined;
}
return entry;
return entry.name;
}
function storeName<T extends FrameOwnedAxNode>(
document: FrameDocument<T>,
backendNodeId: number,
name: string | null,
name: string,
): void {
if (tooltipCache.size >= MAX_CACHE_ENTRIES) {
const oldest = tooltipCache.keys().next().value;
@@ -71,7 +64,7 @@ function storeName<T extends FrameOwnedAxNode>(
}
tooltipCache.set(cacheKey(document, backendNodeId), {
name,
expiresAt: Date.now() + (name === null ? MISS_CACHE_TTL_MS : CACHE_TTL_MS),
expiresAt: Date.now() + CACHE_TTL_MS,
});
}
@@ -244,27 +237,22 @@ export async function probeTooltipNames<T extends FrameOwnedAxNode>(
const names = new Map<string, string>();
const pending: TooltipCandidate<T>[] = [];
for (const candidate of candidates(documents, graph)) {
const cached = cachedEntry(candidate.document, candidate.backendNodeId);
const cached = cachedName(candidate.document, candidate.backendNodeId);
if (cached) {
// A cached miss is still a decision: skip the control instead of re-probing.
if (cached.name !== null) {
names.set(
frameBackendKey(candidate.document.frameId, candidate.backendNodeId),
cached.name,
);
}
names.set(frameBackendKey(candidate.document.frameId, candidate.backendNodeId), cached);
} else if (pending.length < MAX_TOOLTIP_CANDIDATES) {
pending.push(candidate);
}
}
if (pending.length === 0) return names;
const budget = new ProbeBudget(MAX_TOOLTIP_PROBE_MS);
const started = Date.now();
const contexts = new Map<string, number>();
await options.hoverProbeBypassOverlay?.(tabId, true).catch(() => undefined);
try {
for (const candidate of pending) {
if (options.signal?.aborted) throw new DOMException("observation aborted", "AbortError");
if (!budget.canAfford(TOOLTIP_SETTLE_MS)) break;
if (Date.now() - started >= MAX_TOOLTIP_PROBE_MS) break;
let objectId: string | undefined;
try {
let contextId = contexts.get(candidate.document.frameId);
@@ -290,9 +278,9 @@ export async function probeTooltipNames<T extends FrameOwnedAxNode>(
await waitForHover(TOOLTIP_SETTLE_MS, options.signal);
const after = await tooltipTexts(cdp, candidate.document, objectId);
const name = cleanTooltipDiff(before, after);
storeName(candidate.document, candidate.backendNodeId, name ?? null);
if (!name) continue;
names.set(frameBackendKey(candidate.document.frameId, candidate.backendNodeId), name);
storeName(candidate.document, candidate.backendNodeId, name);
} catch (error) {
if (error instanceof Error && error.name === "AbortError") throw error;
} finally {
@@ -302,6 +290,7 @@ export async function probeTooltipNames<T extends FrameOwnedAxNode>(
}
} finally {
await clearHover(cdp, tabId);
await options.hoverProbeBypassOverlay?.(tabId, false).catch(() => undefined);
}
return names;
}
-78
View File
@@ -1,78 +0,0 @@
import type { CdpTarget } from "@/browser-driver/frame-graph";
import {
type FrameProjectionState,
projectSnapshotRect,
type SnapshotCoordinates,
snapshotViewportRect,
} from "../geometry/coordinate-types";
import { createCaptureCheckpoint } from "./capture-abort";
import { buildDocumentIndex, type DocumentIndex, type NodeFacts } from "./facts";
import { decodeDocument, type SnapshotDocument } from "./snapshot";
export interface FrameContext {
frameId?: string;
ownerFrameBackendNodeId: number | null;
projection: FrameProjectionState;
target: CdpTarget;
coordinates: SnapshotCoordinates | null;
layoutUnitsPerCssPixel: number | null;
}
export interface NormalizedDocument {
nodes: NodeFacts[];
index: DocumentIndex;
}
/** 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,
): Promise<NormalizedDocument> {
const decoded = await decodeDocument(doc, strings, signal);
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;
const rect =
input && context.projection.status === "available"
? projectSnapshotRect(input, context.projection.projection)
: 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);
return {
nodes: nodes.filter(
(node) => !node.tag.startsWith("#") && !index.excludedBackendNodeIds.has(node.backendNodeId),
),
index,
};
}
@@ -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 {
@@ -40,17 +37,6 @@ export interface CaptureVomObservationResult {
frames: CaptureVomFrame[];
matchNodes: CaptureVomMatchNode[];
surfaceProbes?: CapturedSurfaceProbe[];
/**
* Whether this observation actively hovered the page, and whether that
* revealed content the static tree does not contain. Lets callers judge how
* far the page may have drifted from the returned snapshot.
*/
hoverProbe?: HoverProbeReport;
}
export interface HoverProbeReport {
performed: boolean;
revealedContent: boolean;
}
function projectFrames(documents: CapturedFrameDocument<FrameAxNode>[]): CaptureVomFrame[] {
@@ -89,7 +75,6 @@ export function projectRecordSafeObservation(input: {
frameDocuments: CapturedFrameDocument<FrameAxNode>[];
rendered: VomResult;
surfaceProbes?: CapturedSurfaceProbe[];
hoverProbe?: HoverProbeReport;
}): CaptureVomObservationResult {
return {
text: input.rendered.text,
@@ -99,6 +84,5 @@ export function projectRecordSafeObservation(input: {
frames: projectFrames(input.frameDocuments),
matchNodes: projectMatchNodes(input.frameDocuments),
surfaceProbes: input.surfaceProbes,
...(input.hoverProbe ? { hoverProbe: input.hoverProbe } : {}),
};
}
@@ -61,9 +61,8 @@ export function buildSemanticGraph(input: BuildSemanticGraphInput): SemanticGrap
dom,
sourceOrder: index,
excluded:
document.excludedBackendNodeIds?.has(dom.backendNodeId) === true ||
(document.frameId === rootFrameId &&
input.excludedBackendNodeIds?.has(dom.backendNodeId) === true),
document.frameId === rootFrameId &&
input.excludedBackendNodeIds?.has(dom.backendNodeId) === true,
};
nodes.set(id, node);
frameNodeIds.push(id);
@@ -91,10 +90,9 @@ export function buildSemanticGraph(input: BuildSemanticGraphInput): SemanticGrap
ax,
sourceOrder: document.domNodes.length + index,
excluded:
document.frameId === rootFrameId &&
typeof ax.backendDOMNodeId === "number" &&
(document.excludedBackendNodeIds?.has(ax.backendDOMNodeId) === true ||
(document.frameId === rootFrameId &&
input.excludedBackendNodeIds?.has(ax.backendDOMNodeId) === true)),
input.excludedBackendNodeIds?.has(ax.backendDOMNodeId) === true,
});
frameNodeIds.push(id);
}
-224
View File
@@ -1,224 +0,0 @@
import { createCaptureCheckpoint } from "./capture-abort";
import type { CapturedNode } from "./capture-types";
import type { DecodedDocument, DecodedNode } from "./facts";
export const REQUESTED_STYLES = [
"position",
"pointer-events",
"cursor",
"visibility",
"opacity",
] as const;
const STYLE_COL = Object.fromEntries(
REQUESTED_STYLES.map((name, index) => [name, index]),
) as Record<(typeof REQUESTED_STYLES)[number], number>;
/** Sparse array format Chrome uses for infrequently-set per-node fields. */
interface SparseArray {
index: number[];
value: number[];
}
interface RareBooleanData {
index: number[];
}
export interface SnapshotDocument {
frameId?: string | number;
scrollOffsetX?: number;
scrollOffsetY?: number;
nodes?: {
parentIndex?: number[];
nodeName?: number[];
nodeType?: 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[];
};
}
export 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;
}
export interface SnapshotReply {
strings?: string[];
documents?: SnapshotDocument[];
}
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";
}
function str(strings: string[], idx: number | undefined): string {
if (idx === undefined || idx < 0) return "";
return strings[idx] ?? "";
}
export 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;
}
export async function decodeDocument(
doc: SnapshotDocument,
strings: string[],
signal?: AbortSignal,
): Promise<DecodedDocument> {
const checkpoint = createCaptureCheckpoint(signal);
const dn = doc.nodes;
const dl = doc.layout;
if (!dn?.backendNodeId) {
return { nodes: [] };
}
const count = dn.backendNodeId.length;
const layoutByNode = new Map<number, number>();
for (let i = 0; i < (dl?.nodeIndex?.length ?? 0); i++) {
if (i % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
layoutByNode.set(dl!.nodeIndex![i], i);
}
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++) {
if (n % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
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);
if (existing) existing.push(text);
else nodeTextContent.set(parentIdx, [text]);
}
}
}
// Decode fields without assigning a coordinate projection or semantic policy.
const nodes: DecodedNode[] = [];
for (let n = 0; n < count; n++) {
if (n % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
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]);
}
const li = layoutByNode.get(n);
const styleRow = li === undefined ? [] : (dl?.styles?.[li] ?? []);
const styles: Record<string, string> = {};
for (const name of REQUESTED_STYLES) styles[name] = str(strings, styleRow[STYLE_COL[name]]);
const layout =
li === undefined
? undefined
: {
boundsSpace: "snapshot-document-layout" as const,
bounds: dl?.bounds?.[li],
styles,
};
const textContent = nodeTextContent.get(n)?.join(" ");
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,
nodeType: dn.nodeType?.[n],
parentBackendNodeId,
tag,
attrs,
layout,
paintOrder: li === undefined ? 0 : (dl?.paintOrders?.[li] ?? 0),
position: styles.position || "static",
pointerEvents: styles["pointer-events"] || "auto",
cursor: styles.cursor || "auto",
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 };
}

Some files were not shown because too many files have changed in this diff Show More