Compare commits

..
Author SHA1 Message Date
“haonan”andCursor f7e08f461b feat(record): capture interactions in embedded frames
Track recording per document so injectable child frames are captured while partial frame failures remain visible in exported traces.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-17 14:41:02 +08:00
“haonan” 61a0e0d218 fix(record): keep committed empty fill steps in exported traces 2026-08-17 11:02:10 +08:00
“haonan” 67b7227abf fix(popup): point record prompt at the ./trace directory bundle 2026-08-13 19:55:34 +08:00
“haonan” 02d1d69379 docs(ux): clarify version mismatches and update record skill docs
Surface actionable update guidance in the popup and connection errors, document
the trace v3 directory bundle in SKILL.md.
2026-08-13 19:40:54 +08:00
“haonan” 025751ef03 feat(cli): write record output as a trace directory bundle
Persist `trace.json` plus per-state page VOM files under `--output`, tolerate
raced session teardown on stop, and clarify version-mismatch recovery hints.
2026-08-13 19:38:05 +08:00
“haonan” 13a61b2688 feat(extension): record user flows as trace v3 page-state observations
Capture settled page observations into a states/steps trace, match targets by
geometry with capture fallbacks, and reuse VOM rendering with richer refs and
optional value redaction for record bundles.
2026-08-13 19:34:37 +08:00
“haonan” 1508839bf9 feat(protocol): bump to 1.1 and redefine record traces as state-linked v3
Replace page-indexed record traces with states/steps + FillCommit/hover/scroll,
and raise daemon/extension protocol floors together so old 1.0 peers are rejected.
2026-08-13 19:31:35 +08:00
239 changed files with 7645 additions and 35330 deletions
-105
View File
@@ -1,105 +0,0 @@
name: Release dsh plugin
on:
push:
tags:
- dsh-plugin-v*
workflow_dispatch:
permissions:
contents: read
concurrency:
group: release-dsh-plugin-${{ github.ref }}
cancel-in-progress: false
env:
PACKAGE_NAME: "@wxg-prc-cpg/browser-skill-dsh-plugin"
PACKAGE_DIR: packages/dsh-plugin-browserskill
jobs:
resolve:
runs-on: ubuntu-latest
outputs:
version: ${{ steps.version.outputs.version }}
tag: ${{ steps.version.outputs.tag }}
steps:
- uses: actions/checkout@v6
- name: Resolve plugin version
id: version
shell: bash
run: |
set -euo pipefail
if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
VERSION="$(node -p "require('./${{ env.PACKAGE_DIR }}/package.json').version")"
else
VERSION="${GITHUB_REF_NAME#dsh-plugin-v}"
fi
VERSION="${VERSION#v}"
echo "version=${VERSION}" >> "$GITHUB_OUTPUT"
echo "tag=dsh-plugin-v${VERSION}" >> "$GITHUB_OUTPUT"
guard:
needs: resolve
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
- name: Verify tag matches package.json name and version
shell: bash
run: |
set -euo pipefail
PKG_NAME="$(node -p "require('./${{ env.PACKAGE_DIR }}/package.json').name")"
PKG_VERSION="$(node -p "require('./${{ env.PACKAGE_DIR }}/package.json').version")"
RELEASE_VERSION="${{ needs.resolve.outputs.version }}"
if [ "$PKG_NAME" != "$PACKAGE_NAME" ]; then
echo "package.json name (${PKG_NAME}) does not match expected ${PACKAGE_NAME}"
exit 1
fi
if [ "$PKG_VERSION" != "$RELEASE_VERSION" ]; then
echo "${PACKAGE_DIR}/package.json version (${PKG_VERSION}) does not match release version (${RELEASE_VERSION})"
exit 1
fi
echo "Version guard passed: ${PKG_NAME}@${RELEASE_VERSION}"
publish:
needs: [resolve, guard]
runs-on: ubuntu-latest
# Secret NPM_TOKEN is stored on the "npm-publish" GitHub Environment.
environment: npm-publish
permissions:
contents: read
steps:
- uses: actions/checkout@v6
- uses: pnpm/action-setup@v6
- uses: actions/setup-node@v6
with:
node-version: 22
cache: pnpm
registry-url: https://registry.npmjs.org
scope: "@wxg-prc-cpg"
- name: Install dependencies
run: pnpm install --frozen-lockfile
- name: Typecheck plugin
run: pnpm --filter "${{ env.PACKAGE_NAME }}" typecheck
- name: Test plugin
run: pnpm --filter "${{ env.PACKAGE_NAME }}" test
- name: Publish to npm
working-directory: ${{ env.PACKAGE_DIR }}
env:
NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
run: |
set -euo pipefail
if [ -z "${NODE_AUTH_TOKEN:-}" ]; then
echo "::error::Environment secret NPM_TOKEN is not configured"
exit 1
fi
pnpm publish --access public --no-git-checks
echo "Published ${PACKAGE_NAME}@${{ needs.resolve.outputs.version }}"
+4
View File
@@ -17,3 +17,7 @@ dist/
# Environment
.env.local
.env.*.local
.pnpm-store/
# Local recording output
/trace/
-3
View File
@@ -3,6 +3,3 @@
**/.output/**
**/target/**
**/node_modules/**
# Generated client CSS (tailwind compile output); built by
# packages/dsh-plugin-browserskill/scripts/build-client-css.mjs.
**/dsh-plugin-browserskill/src/client/bsk-ui.nomodule.css
+5 -9
View File
@@ -34,17 +34,13 @@ where only `extension connected` fails is expected; go to Step 3.
## 3. Open the extension install page
If `extension connected` is `FAIL` (`0 browsers connected`), the user likely
has not installed or enabled the browser extension yet. Open the install page
matching the user's browser —
[Chrome Web Store](https://chromewebstore.google.com/detail/hhcmgoofomhgciiibhipgmgkgnoenaoi)
for Chrome and other Chromium browsers,
[Edge Add-ons](https://microsoftedge.microsoft.com/addons/detail/browserskill/emacgiaaaiojkkpkddmmdfhmokgmnikg)
for Microsoft Edge — then tell the user:
has not installed or enabled the browser extension yet. Open the
[Chrome Web Store install page](https://chromewebstore.google.com/detail/hhcmgoofomhgciiibhipgmgkgnoenaoi)
in the user's browser, then tell the user:
> Install **BrowserSkill** from the
> [Chrome Web Store](https://chromewebstore.google.com/detail/hhcmgoofomhgciiibhipgmgkgnoenaoi)
> (or [Edge Add-ons](https://microsoftedge.microsoft.com/addons/detail/browserskill/emacgiaaaiojkkpkddmmdfhmokgmnikg)
> on Edge), open the popup, and wait until it turns green. Reply when done.
> [Chrome Web Store](https://chromewebstore.google.com/detail/hhcmgoofomhgciiibhipgmgkgnoenaoi),
> open the popup, and wait until it turns green. Reply when done.
If opening the page fails, give the user the same link. Then run `bsk doctor`
once more. All `ok`/`na` → tell the user it's ready.
Generated
+2 -2
View File
@@ -134,7 +134,7 @@ dependencies = [
[[package]]
name = "bsk"
version = "0.1.11"
version = "0.1.10"
dependencies = [
"anyhow",
"bsk-protocol",
@@ -168,7 +168,7 @@ dependencies = [
[[package]]
name = "bsk-protocol"
version = "0.1.11"
version = "0.1.10"
dependencies = [
"schemars",
"semver",
+1 -1
View File
@@ -7,7 +7,7 @@ members = [
default-members = ["crates/bsk-cli"]
[workspace.package]
version = "0.1.11"
version = "0.1.10"
edition = "2024"
rust-version = "1.85"
license = "MIT"
+5 -37
View File
@@ -13,7 +13,7 @@
</p>
**BrowserSkill** connects Cursor, Claude Code, Codex, OpenClaw, CodeBuddy,
WorkBuddy, Pi, Hermes Agent, DeepSeek Harness, and other AI agents to your already logged-in
WorkBuddy, Pi, Hermes Agent, and other shell-capable AI agents to your already logged-in
browser.
Need the agent to touch a tab you already have open? It must borrow that tab
@@ -67,8 +67,7 @@ Set up browser-skill on this machine by following https://raw.githubusercontent.
<br>
Install the CLI, then install the extension from the [Chrome Web Store](https://chromewebstore.google.com/detail/hhcmgoofomhgciiibhipgmgkgnoenaoi)
or [Edge Add-ons](https://microsoftedge.microsoft.com/addons/detail/browserskill/emacgiaaaiojkkpkddmmdfhmokgmnikg).
Install the CLI, then install the extension from the [Chrome Web Store](https://chromewebstore.google.com/detail/hhcmgoofomhgciiibhipgmgkgnoenaoi).
#### 1. Install the `bsk` CLI
@@ -92,14 +91,7 @@ bsk --version
#### 2. Install the browser extension
Install BrowserSkill from your browser's store:
| Browser | Store listing |
| --- | --- |
| Chrome | [Chrome Web Store](https://chromewebstore.google.com/detail/hhcmgoofomhgciiibhipgmgkgnoenaoi) |
| Microsoft Edge | [Edge Add-ons](https://microsoftedge.microsoft.com/addons/detail/browserskill/emacgiaaaiojkkpkddmmdfhmokgmnikg) |
On other Chromium-based browsers, install the Chrome Web Store build.
Install BrowserSkill from the [Chrome Web Store](https://chromewebstore.google.com/detail/hhcmgoofomhgciiibhipgmgkgnoenaoi).
#### 3. Install the skill
@@ -131,8 +123,7 @@ internal variants and install paths.
Other shell-capable agent harnesses are supported too. Copy
[`skill/SKILL.md`](skill/SKILL.md) into your harness's skills directory as
`browser-skill/SKILL.md` to install the skill manually. DeepSeek Harness uses a
dedicated plugin instead — see [DeepSeek Harness plugin](#deepseek-harness-plugin).
`browser-skill/SKILL.md` to install the skill manually.
</details>
@@ -142,26 +133,6 @@ Start a new Agent session and write a prompt that needs the browser, for example
/browser-skill open example.com and summarize what is on the page.
```
## DeepSeek Harness plugin
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 injects native `browser_*` tools (no shelling out to `bsk`) and a live Web UI
overlay of each Agent Window.
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 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
BrowserSkill is a local bridge between your agent harness and your browser.
@@ -195,9 +166,7 @@ flowchart TB
The agent never talks to the browser directly. It asks the `bsk` CLI to perform a
browser task; the local daemon routes that request to the extension; the
extension runs it in an Agent Window. DeepSeek Harness takes the same path
through the [plugin](#deepseek-harness-plugin): the agent calls injected
`browser_*` tools, and the plugin invokes `bsk` on its behalf.
extension runs it in an Agent Window.
## For Developers
@@ -207,7 +176,6 @@ The repository is a Cargo + pnpm workspace:
- `crates/bsk-protocol` — shared wire types and JSON schemas
- `apps/extension` — browser extension
- `packages/ui` and `packages/i18n` — shared extension UI support
- `packages/dsh-plugin-browserskill` — DeepSeek Harness plugin (`@wxg-prc-cpg/browser-skill-dsh-plugin`)
## License
+7 -32
View File
@@ -12,7 +12,7 @@
<a href="README.md">English</a> · 中文
</p>
**BrowserSkill** 把 Cursor、Claude Code、Codex、OpenClaw、CodeBuddy、WorkBuddy、Pi、Hermes Agent、DeepSeek Harness 等 AI Agent 连接到你已登录的浏览器。
**BrowserSkill** 把 Cursor、Claude Code、Codex、OpenClaw、CodeBuddy、WorkBuddy、Pi、Hermes Agent 等支持 Shell 的 AI Agent 连接到你已登录的浏览器。
需要 Agent 操作你已打开的标签页?必须显式借用该标签,任务结束后归还,其余浏览器窗口不受影响。
@@ -54,8 +54,7 @@ BrowserSkill 由两个本地运行组件组成:`bsk` CLI/daemon 和浏览器
<br>
先安装 CLI,再从 [Chrome Web Store](https://chromewebstore.google.com/detail/hhcmgoofomhgciiibhipgmgkgnoenaoi)
或 [Edge 加载项商店](https://microsoftedge.microsoft.com/addons/detail/browserskill/emacgiaaaiojkkpkddmmdfhmokgmnikg) 安装浏览器扩展。
先安装 CLI,再从 [Chrome Web Store](https://chromewebstore.google.com/detail/hhcmgoofomhgciiibhipgmgkgnoenaoi) 安装浏览器扩展。
#### 1. 安装 `bsk` CLI
@@ -65,11 +64,8 @@ BrowserSkill 由两个本地运行组件组成:`bsk` CLI/daemon 和浏览器
curl -fsSL https://raw.githubusercontent.com/Tencent/BrowserSkill/main/install.sh | sh
```
**Windows**(PowerShell,安装到 `~/.local/bin`):
```powershell
irm https://raw.githubusercontent.com/Tencent/BrowserSkill/main/install.ps1 | iex
```
**Windows**:从 [最新 CLI release](https://github.com/Tencent/BrowserSkill/releases/latest)
下载 `bsk-v<version>-x86_64-pc-windows-msvc.zip`,解压后将 `bsk.exe` 加入 `PATH`。
验证二进制:
@@ -79,14 +75,7 @@ bsk --version
#### 2. 安装浏览器扩展
在对应浏览器的商店安装 BrowserSkill:
| 浏览器 | 商店页面 |
| --- | --- |
| Chrome | [Chrome Web Store](https://chromewebstore.google.com/detail/hhcmgoofomhgciiibhipgmgkgnoenaoi) |
| Microsoft Edge | [Edge 加载项商店](https://microsoftedge.microsoft.com/addons/detail/browserskill/emacgiaaaiojkkpkddmmdfhmokgmnikg) |
其他基于 Chromium 的浏览器,安装 Chrome Web Store 版本即可。
从 [Chrome Web Store](https://chromewebstore.google.com/detail/hhcmgoofomhgciiibhipgmgkgnoenaoi) 安装 BrowserSkill。
#### 3. 安装 skill
@@ -113,7 +102,7 @@ bsk install-skill
用 <kbd>Space</kbd> 选择需要安装的 Agent harness,然后按 <kbd>Enter</kbd> 安装 skill。运行 `bsk install-skill --list` 可查看 internal 变体及安装路径。
其他支持 Shell 的 Agent harness 也可使用 BrowserSkill,但需手动将 [`skill/SKILL.md`](skill/SKILL.md) 复制到对应 skills 目录下的 `browser-skill/SKILL.md`。DeepSeek Harness 走独立插件,见 [DeepSeek Harness 插件](#deepseek-harness-插件)。
其他支持 Shell 的 Agent harness 也可使用 BrowserSkill,但需手动将 [`skill/SKILL.md`](skill/SKILL.md) 复制到对应 skills 目录下的 `browser-skill/SKILL.md`。
</details>
@@ -123,19 +112,6 @@ bsk install-skill
/browser-skill open example.com and summarize what is on the page.
```
## 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。
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 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
BrowserSkill 是 Agent 运行时与浏览器之间的本地桥接层。
@@ -167,7 +143,7 @@ flowchart TB
style UserWindows fill:#f8fafc,stroke:#cbd5e1,color:#334155
```
Agent 不直接与浏览器通信。它通过 `bsk` CLI 下发浏览器任务;本地 daemon 把请求路由到扩展;扩展在 Agent Window 中执行。DeepSeek Harness 走同一条链路,只是经由 [插件](#deepseek-harness-插件):Agent 调用注入的 `browser_*` 工具,由插件代为执行 `bsk`。
Agent 不直接与浏览器通信。它通过 `bsk` CLI 下发浏览器任务;本地 daemon 把请求路由到扩展;扩展在 Agent Window 中执行。
## 面向开发者
@@ -177,7 +153,6 @@ Agent 不直接与浏览器通信。它通过 `bsk` CLI 下发浏览器任务;
- `crates/bsk-protocol` — 共享协议类型与 JSON Schema
- `apps/extension` — 浏览器扩展
- `packages/ui` 和 `packages/i18n` — 扩展 UI 共享支持
- `packages/dsh-plugin-browserskill` — DeepSeek Harness 插件(`@wxg-prc-cpg/browser-skill-dsh-plugin`)
## 许可证
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@browser-skill/extension",
"version": "0.1.7",
"version": "0.1.6",
"private": true,
"type": "module",
"scripts": {
@@ -1,5 +1,5 @@
import { describe, expect, it, vi } from "vitest";
import { type CdpDebuggee, type CdpDebuggerApi, ChromiumCdp } from "../chromium-cdp";
import { type CdpDebuggerApi, ChromiumCdp } from "../chromium-cdp";
function fakeChromeEvent<TArgs extends unknown[]>() {
const listeners = new Set<(...args: TArgs) => void>();
@@ -14,7 +14,7 @@ function fakeChromeEvent<TArgs extends unknown[]>() {
}
function fakeApi() {
const onEvent = fakeChromeEvent<[CdpDebuggee, string, unknown]>();
const onEvent = fakeChromeEvent<[chrome.debugger.Debuggee, string, unknown]>();
const onDetach = fakeChromeEvent<[chrome.debugger.Debuggee, string]>();
const api: CdpDebuggerApi = {
attach: vi.fn(async () => {}),
@@ -29,135 +29,6 @@ function fakeApi() {
}
describe("ChromiumCdp", () => {
it("discovers multiple iframe targets and recursively routes nested OOPIF commands", async () => {
const { api, onEvent } = fakeApi();
(api.sendCommand as ReturnType<typeof vi.fn>).mockImplementation(
async (
target: chrome.debugger.Debuggee & { sessionId?: string },
method: string,
params?: { frameId?: string },
) => {
if (method === "DOM.getFrameOwner") {
return { backendNodeId: params?.frameId === "nested" ? 300 : 200 };
}
if (method !== "Page.getFrameTree") return {};
if (target.sessionId === "right-session") {
return {
frameTree: {
frame: { id: "right", url: "https://right.test" },
childFrames: [
{ frame: { id: "nested", parentId: "right", url: "https://nested.test" } },
],
},
};
}
if (target.sessionId === "nested-session") {
return { frameTree: { frame: { id: "nested", url: "https://nested.test" } } };
}
return {
frameTree: {
frame: { id: "main", url: "https://app.test" },
childFrames: [
{ frame: { id: "left", parentId: "main", url: "https://left.test" } },
{
frame: { id: "right", parentId: "main", url: "https://right.test" },
childFrames: [
{ frame: { id: "nested", parentId: "right", url: "https://nested.test" } },
],
},
],
},
};
},
);
const cdp = new ChromiumCdp(api);
await cdp.ensureAttached(4);
onEvent.fire({ tabId: 4 }, "Target.attachedToTarget", { sessionId: "right-session" });
onEvent.fire({ tabId: 4 } as chrome.debugger.Debuggee, "Target.attachedToTarget", {
sessionId: "nested-session",
});
const graph = await cdp.getFrameGraph(4);
expect(graph.frames).toHaveLength(4);
expect(graph.frames.find((frame) => frame.frameId === "left")?.target).toEqual({ tabId: 4 });
expect(graph.frames.find((frame) => frame.frameId === "right")?.target.sessionId).toBe(
"right-session",
);
expect(graph.frames.find((frame) => frame.frameId === "nested")?.target.sessionId).toBe(
"nested-session",
);
expect(graph.frames.find((frame) => frame.frameId === "right")?.ownerBackendNodeId).toBe(200);
expect(graph.frames.find((frame) => frame.frameId === "nested")?.ownerBackendNodeId).toBe(300);
expect(api.sendCommand).toHaveBeenCalledWith(
{ tabId: 4, sessionId: "right-session" },
"DOM.getFrameOwner",
{ frameId: "nested" },
);
expect(api.sendCommand).toHaveBeenCalledWith(
{ tabId: 4, sessionId: "nested-session" },
"Target.setAutoAttach",
expect.objectContaining({ flatten: true }),
);
});
it("waits for recursively attached iframe targets without a depth limit", async () => {
const { api, onEvent } = fakeApi();
const depth = 6;
const scheduled = new Set<string>();
const nestedTree = (index: number): Record<string, unknown> => ({
frame: {
id: index === 0 ? "main" : `frame-${index}`,
...(index > 0 ? { parentId: index === 1 ? "main" : `frame-${index - 1}` } : {}),
},
...(index < depth ? { childFrames: [nestedTree(index + 1)] } : {}),
});
(api.sendCommand as ReturnType<typeof vi.fn>).mockImplementation(
async (target: CdpDebuggee, method: string, params?: { frameId?: string }) => {
if (method === "Target.setAutoAttach") {
const parentIndex = target.sessionId
? Number(target.sessionId.replace("session-", ""))
: 0;
const nextIndex = parentIndex + 1;
const key = `${target.sessionId ?? "root"}:${nextIndex}`;
if (nextIndex <= depth && !scheduled.has(key)) {
scheduled.add(key);
setTimeout(() => {
onEvent.fire(
{ tabId: 4, ...(target.sessionId ? { sessionId: target.sessionId } : {}) },
"Target.attachedToTarget",
{
sessionId: `session-${nextIndex}`,
targetInfo: { type: "iframe" },
},
);
}, 5);
}
return {};
}
if (method === "Page.getFrameTree") {
if (!target.sessionId) return { frameTree: nestedTree(0) };
const index = Number(target.sessionId.replace("session-", ""));
return { frameTree: nestedTree(index) };
}
if (method === "DOM.getFrameOwner") {
return { backendNodeId: Number(params?.frameId?.replace("frame-", "")) + 100 };
}
return {};
},
);
const cdp = new ChromiumCdp(api);
const graph = await cdp.getFrameGraph(4);
expect(graph.frames).toHaveLength(depth + 1);
for (let index = 1; index <= depth; index += 1) {
expect(
graph.frames.find((frame) => frame.frameId === `frame-${index}`)?.target.sessionId,
).toBe(`session-${index}`);
}
});
it("coalesces concurrent attach calls for the same tab", async () => {
const { api } = fakeApi();
let releaseAttach!: () => void;
@@ -1,136 +0,0 @@
import { describe, expect, it } from "vitest";
import { buildFrameGraph, type CdpFrameTreeNode, type CdpFrameTreeSource } from "../frame-graph";
describe("buildFrameGraph", () => {
it("keeps sibling frames distinct and routes nested OOPIFs to their child sessions", () => {
const graph = buildFrameGraph([
{
target: { tabId: 4 },
tree: {
frame: { id: "main", url: "https://app.test" },
childFrames: [
{ frame: { id: "left", parentId: "main", url: "https://left.test" } },
{
frame: { id: "right", parentId: "main", url: "https://right.test" },
childFrames: [
{ frame: { id: "nested", parentId: "right", url: "https://nested.test" } },
],
},
],
},
},
{
target: { tabId: 4, sessionId: "right-session" },
tree: {
frame: { id: "right", url: "https://right.test" },
childFrames: [{ frame: { id: "nested", parentId: "right", url: "https://nested.test" } }],
},
},
{
target: { tabId: 4, sessionId: "nested-session" },
tree: { frame: { id: "nested", url: "https://nested.test" } },
},
]);
expect(graph?.frames).toHaveLength(4);
expect(graph?.frames.find((frame) => frame.frameId === "left")?.target).toEqual({ tabId: 4 });
expect(graph?.frames.find((frame) => frame.frameId === "right")).toMatchObject({
parentFrameId: "main",
target: { tabId: 4, sessionId: "right-session" },
});
expect(graph?.frames.find((frame) => frame.frameId === "nested")).toMatchObject({
parentFrameId: "right",
target: { tabId: 4, sessionId: "nested-session" },
});
});
it("propagates each target boundary to its same-process descendants", () => {
const sources: CdpFrameTreeSource[] = [
{
target: { tabId: 4 },
tree: {
frame: { id: "main" },
childFrames: [
{
frame: { id: "oopif-a", parentId: "main" },
childFrames: [
{
frame: { id: "same-process-b", parentId: "oopif-a" },
childFrames: [
{
frame: { id: "oopif-c", parentId: "same-process-b" },
childFrames: [{ frame: { id: "same-process-d", parentId: "oopif-c" } }],
},
],
},
],
},
],
},
},
{
target: { tabId: 4, sessionId: "session-a" },
tree: {
frame: { id: "oopif-a" },
childFrames: [
{
frame: { id: "same-process-b", parentId: "oopif-a" },
childFrames: [{ frame: { id: "oopif-c", parentId: "same-process-b" } }],
},
],
},
},
{
target: { tabId: 4, sessionId: "session-c" },
tree: {
frame: { id: "oopif-c" },
childFrames: [{ frame: { id: "same-process-d", parentId: "oopif-c" } }],
},
},
];
const graph = buildFrameGraph(sources);
expect(graph?.frames.map((frame) => [frame.frameId, frame.target.sessionId])).toEqual([
["main", undefined],
["oopif-a", "session-a"],
["same-process-b", "session-a"],
["oopif-c", "session-c"],
["same-process-d", "session-c"],
]);
expect(graph?.frames.find((frame) => frame.frameId === "oopif-a")?.parentFrameId).toBe("main");
expect(graph?.frames.find((frame) => frame.frameId === "oopif-c")?.parentFrameId).toBe(
"same-process-b",
);
const reordered = buildFrameGraph([sources[2], sources[1], sources[0]]);
expect(reordered).toEqual(graph);
});
it("walks deeply nested frame trees without consuming the JavaScript call stack", () => {
const depth = 5_000;
const root: CdpFrameTreeNode = { frame: { id: "frame-0" } };
let parent = root;
for (let index = 1; index <= depth; index += 1) {
const child: CdpFrameTreeNode = {
frame: { id: `frame-${index}`, parentId: `frame-${index - 1}` },
};
parent.childFrames = [child];
parent = child;
}
const graph = buildFrameGraph([{ target: { tabId: 4 }, tree: root }]);
expect(graph?.frames).toHaveLength(depth + 1);
expect(graph?.frames.at(-1)?.frameId).toBe(`frame-${depth}`);
});
it("does not loop when an in-memory frame tree contains an object cycle", () => {
const root: CdpFrameTreeNode = { frame: { id: "main" } };
root.childFrames = [root];
expect(buildFrameGraph([{ target: { tabId: 4 }, tree: root }])?.frames).toEqual([
{ frameId: "main", target: { tabId: 4 } },
]);
});
});
+12 -211
View File
@@ -31,15 +31,6 @@ import type {
NetworkEntryKind,
NetworkResult,
} from "@/transport/types";
import {
buildFrameGraph,
type CdpFrameGraph,
type CdpFrameTreeNode,
type CdpFrameTreeSource,
type CdpTarget,
} from "./frame-graph";
export type CdpDebuggee = chrome.debugger.Debuggee & { sessionId?: string };
/**
* Minimal slice of `chrome.debugger` the rest of the extension
@@ -47,15 +38,21 @@ export type CdpDebuggee = chrome.debugger.Debuggee & { sessionId?: string };
* fake without monkey-patching the real `chrome` global.
*/
export interface CdpDebuggerApi {
attach(target: CdpDebuggee, requiredVersion: string): Promise<void>;
detach(target: CdpDebuggee): Promise<void>;
sendCommand(target: CdpDebuggee, method: string, commandParams?: object): Promise<unknown>;
attach(target: chrome.debugger.Debuggee, requiredVersion: string): Promise<void>;
detach(target: chrome.debugger.Debuggee): Promise<void>;
sendCommand(
target: chrome.debugger.Debuggee,
method: string,
commandParams?: object,
): Promise<unknown>;
/**
* Fires for every CDP event (`Page.lifecycleEvent`, `DOM.documentUpdated`,
* …). The first callback argument is the source debuggee; the second
* is the CDP method name; the third is the payload.
*/
onEvent: chrome.events.Event<(source: CdpDebuggee, method: string, params: unknown) => void>;
onEvent: chrome.events.Event<
(source: chrome.debugger.Debuggee, method: string, params: unknown) => void
>;
/**
* Fires when Chrome unilaterally detaches us — most commonly because
* the tab navigated to a chrome:// URL or the user clicked
@@ -113,8 +110,6 @@ const MAX_CONSOLE_STACK_FRAMES = 20;
const MAX_NETWORK_BUFFER = 200;
const MAX_NETWORK_FIELD_LENGTH = 4096;
const MAX_NETWORK_REQUEST_META = 1024;
const FRAME_DISCOVERY_TIMEOUT_MS = 1000;
const FRAME_DISCOVERY_QUIET_MS = 20;
interface ParsedDialogOpening {
type: JavaScriptDialogType;
@@ -136,27 +131,6 @@ interface NetworkRequestMeta {
truncated: boolean;
}
interface FrameDiscoveryState {
sessions: Set<string>;
pending: Set<Promise<void>>;
generation: number;
}
async function settleBeforeDeadline(promises: Promise<void>[], deadline: number): Promise<boolean> {
if (promises.length === 0) return true;
const remaining = deadline - Date.now();
if (remaining <= 0) return false;
let timer: ReturnType<typeof setTimeout> | undefined;
const timedOut = await Promise.race([
Promise.allSettled(promises).then(() => false),
new Promise<boolean>((resolve) => {
timer = setTimeout(() => resolve(true), remaining);
}),
]);
if (timer) clearTimeout(timer);
return !timedOut;
}
/**
* Wrapper around `chrome.debugger` that owns the "attach once per
* tabId" cache and exposes typed `send<T>()`.
@@ -175,12 +149,10 @@ export class ChromiumCdp {
private readonly networkSequences = new Map<number, number>();
private readonly networkDomainsEnabledTabs = new Set<number>();
private readonly networkRequestMeta = new Map<number, Map<string, NetworkRequestMeta>>();
private readonly frameDiscovery = new Map<number, FrameDiscoveryState>();
private detachSubscription: { dispose(): void } | null = null;
private dialogSubscription: { dispose(): void } | null = null;
private consoleSubscription: { dispose(): void } | null = null;
private networkSubscription: { dispose(): void } | null = null;
private frameTargetSubscription: { dispose(): void } | null = null;
constructor(api: CdpDebuggerApi = chromeDebuggerApi) {
this.api = api;
@@ -188,7 +160,6 @@ export class ChromiumCdp {
this.bindDialogHandler();
this.bindConsoleHandler();
this.bindNetworkHandler();
this.bindFrameTargetHandler();
}
/** Attach to `tabId` if we haven't already in this driver. */
@@ -206,9 +177,6 @@ export class ChromiumCdp {
await this.enableConsoleDomains(tabId);
await this.enableNetworkDomainBestEffort(tabId);
this.attachedTabs.add(tabId);
await this.enableFrameDiscovery({ tabId }).catch((err) => {
console.debug("[bsk cdp] frame discovery unavailable", { tabId, err });
});
} catch (err) {
// A CDP domain enable failed after the raw attach succeeded
// (e.g. `Page.enable` rejects because the tab just navigated to
@@ -254,73 +222,6 @@ export class ChromiumCdp {
}
}
async sendToTarget<T = unknown>(target: CdpTarget, method: string, params?: object): Promise<T> {
if (!this.attachedTabs.has(target.tabId)) {
await this.ensureAttached(target.tabId);
}
try {
return (await this.api.sendCommand(target, method, params ?? {})) as T;
} catch (err) {
throw normalizeError(err);
}
}
async getFrameGraph(tabId: number): Promise<CdpFrameGraph> {
await this.ensureAttached(tabId);
await this.enableFrameDiscovery({ tabId }).catch(() => {});
await this.drainFrameAttachTasks(tabId);
const sources: CdpFrameTreeSource[] = [];
const root = await this.sendToTarget<{ frameTree?: CdpFrameTreeNode }>(
{ tabId },
"Page.getFrameTree",
{},
);
if (root.frameTree) sources.push({ target: { tabId }, tree: root.frameTree });
const sessions = [...(this.frameDiscovery.get(tabId)?.sessions ?? [])];
const childTrees = await Promise.all(
sessions.map(async (sessionId): Promise<CdpFrameTreeSource | null> => {
const target = { tabId, sessionId };
try {
const reply = await this.sendToTarget<{ frameTree?: CdpFrameTreeNode }>(
target,
"Page.getFrameTree",
{},
);
return reply.frameTree ? { target, tree: reply.frameTree } : null;
} catch {
return null;
}
}),
);
for (const source of childTrees) {
if (source) sources.push(source);
}
const graph = buildFrameGraph(sources);
if (!graph) throw new Error("Page.getFrameTree returned no root frame");
const frameById = new Map(graph.frames.map((frame) => [frame.frameId, frame]));
await Promise.all(
graph.frames.map(async (frame) => {
if (!frame.parentFrameId) return;
const parent = frameById.get(frame.parentFrameId);
if (!parent) return;
try {
const owner = await this.sendToTarget<{ backendNodeId?: number }>(
parent.target,
"DOM.getFrameOwner",
{ frameId: frame.frameId },
);
if (owner.backendNodeId !== undefined) frame.ownerBackendNodeId = owner.backendNodeId;
} catch {
// The frame may have navigated between tree capture and owner lookup.
}
}),
);
return graph;
}
/** Return a cursor marking the current dialog sequence for `tabId`. */
dialogCursor(tabId: number): DialogCursor {
return this.dialogSequences.get(tabId) ?? 0;
@@ -431,7 +332,6 @@ export class ChromiumCdp {
this.clearDialogState(tabId);
this.clearConsoleState(tabId);
this.clearNetworkState(tabId);
this.clearFrameState(tabId);
try {
await this.api.detach({ tabId });
} catch (err) {
@@ -454,7 +354,7 @@ export class ChromiumCdp {
}
/** Subscribe to all CDP events. Returned disposable removes the listener. */
onEvent(handler: (source: CdpDebuggee, method: string, params: unknown) => void): {
onEvent(handler: (source: chrome.debugger.Debuggee, method: string, params: unknown) => void): {
dispose(): void;
} {
this.api.onEvent.addListener(handler);
@@ -478,7 +378,6 @@ export class ChromiumCdp {
this.networkSequences.clear();
this.networkDomainsEnabledTabs.clear();
this.networkRequestMeta.clear();
this.frameDiscovery.clear();
await Promise.all(
tabs.map(async (tabId) => {
try {
@@ -529,104 +428,9 @@ export class ChromiumCdp {
}
}
private async enableFrameDiscovery(target: CdpTarget): Promise<void> {
await this.api.sendCommand(target, "Target.setAutoAttach", {
autoAttach: true,
waitForDebuggerOnStart: false,
flatten: true,
filter: [{ type: "iframe", exclude: false }],
});
}
private bindFrameTargetHandler(): void {
if (this.frameTargetSubscription) return;
const listener = (source: CdpDebuggee, method: string, params: unknown) => {
const tabId = source.tabId;
if (typeof tabId !== "number") return;
const raw = (params ?? {}) as Record<string, unknown>;
const sessionId = typeof raw.sessionId === "string" ? raw.sessionId : undefined;
if (!sessionId) return;
if (method === "Target.detachedFromTarget") {
const state = this.frameDiscovery.get(tabId);
if (state?.sessions.delete(sessionId)) state.generation += 1;
return;
}
if (method !== "Target.attachedToTarget") return;
const targetInfo = raw.targetInfo as { type?: string } | undefined;
if (targetInfo?.type && targetInfo.type !== "iframe") return;
const state = this.frameDiscoveryState(tabId);
if (state.sessions.has(sessionId)) return;
state.sessions.add(sessionId);
state.generation += 1;
const task = this.initializeFrameTarget({ tabId, sessionId });
state.pending.add(task);
void task.finally(() => {
state.pending.delete(task);
});
};
this.api.onEvent.addListener(listener);
this.frameTargetSubscription = {
dispose: () => this.api.onEvent.removeListener(listener),
};
}
private async initializeFrameTarget(target: CdpTarget): Promise<void> {
try {
await this.enableFrameDiscovery(target);
} catch (err) {
const state = this.frameDiscovery.get(target.tabId);
if (state?.sessions.delete(target.sessionId as string)) state.generation += 1;
console.debug("[bsk cdp] child frame target initialization failed", { target, err });
}
}
private async drainFrameAttachTasks(tabId: number): Promise<void> {
const deadline = Date.now() + FRAME_DISCOVERY_TIMEOUT_MS;
while (Date.now() < deadline) {
const state = this.frameDiscovery.get(tabId);
const generation = state?.generation ?? 0;
if (state?.pending.size && !(await settleBeforeDeadline([...state.pending], deadline))) break;
// Target.setAutoAttach may enqueue the next attachedToTarget event after
// its command promise settles. Wait for a short quiet window, then finish
// only if neither the state object nor its generation changed.
const quietTime = Math.min(FRAME_DISCOVERY_QUIET_MS, deadline - Date.now());
if (quietTime <= 0) break;
await new Promise<void>((resolve) => setTimeout(resolve, quietTime));
const current = this.frameDiscovery.get(tabId);
if (
current === state &&
(current?.generation ?? 0) === generation &&
!current?.pending.size
) {
return;
}
}
console.debug("[bsk cdp] frame discovery did not reach quiescence before timeout", { tabId });
}
private frameDiscoveryState(tabId: number): FrameDiscoveryState {
const existing = this.frameDiscovery.get(tabId);
if (existing) return existing;
const created: FrameDiscoveryState = {
sessions: new Set(),
pending: new Set(),
generation: 0,
};
this.frameDiscovery.set(tabId, created);
return created;
}
private clearFrameState(tabId: number): void {
this.frameDiscovery.delete(tabId);
}
private bindDialogHandler(): void {
if (this.dialogSubscription) return;
const listener = (source: CdpDebuggee, method: string, params: unknown) => {
const listener = (source: chrome.debugger.Debuggee, method: string, params: unknown) => {
if (method !== "Page.javascriptDialogOpening") return;
const tabId = source.tabId;
if (typeof tabId !== "number") return;
@@ -810,7 +614,6 @@ export class ChromiumCdp {
this.clearDialogState(source.tabId);
this.clearConsoleState(source.tabId);
this.clearNetworkState(source.tabId);
this.clearFrameState(source.tabId);
}
};
this.api.onDetach.addListener(listener);
@@ -829,8 +632,6 @@ export class ChromiumCdp {
this.consoleSubscription = null;
this.networkSubscription?.dispose();
this.networkSubscription = null;
this.frameTargetSubscription?.dispose();
this.frameTargetSubscription = null;
}
/** Detach tabs only when no other live session has claimed them. */
@@ -1,107 +0,0 @@
export interface CdpTarget {
tabId: number;
sessionId?: string;
}
export interface CdpFrame {
frameId: string;
parentFrameId?: string;
ownerBackendNodeId?: number;
url?: string;
target: CdpTarget;
}
export interface CdpFrameGraph {
rootFrameId: string;
frames: CdpFrame[];
}
export interface CdpFrameTreeNode {
frame: {
id: string;
parentId?: string;
url?: string;
};
childFrames?: CdpFrameTreeNode[];
}
export interface CdpFrameTreeSource {
target: CdpTarget;
tree: CdpFrameTreeNode;
}
export function cdpTargetKey(target: CdpTarget): string {
return `${target.tabId}:${target.sessionId ?? "root"}`;
}
function mergeFrame(
frames: Map<string, CdpFrame>,
order: string[],
node: CdpFrameTreeNode,
target: CdpTarget,
): void {
const existing = frames.get(node.frame.id);
if (!existing) order.push(node.frame.id);
const parentFrameId = node.frame.parentId || existing?.parentFrameId;
const url = node.frame.url || existing?.url;
frames.set(node.frame.id, {
frameId: node.frame.id,
...(parentFrameId ? { parentFrameId } : {}),
...(url ? { url } : {}),
target,
});
}
function walkFrameTree(
source: CdpFrameTreeSource,
targetByRootFrameId: ReadonlyMap<string, CdpTarget>,
frames: Map<string, CdpFrame>,
order: string[],
): void {
const stack: Array<{ node: CdpFrameTreeNode; inheritedTarget: CdpTarget }> = [
{ node: source.tree, inheritedTarget: source.target },
];
const expanded = new WeakSet<CdpFrameTreeNode>();
while (stack.length > 0) {
const current = stack.pop();
if (!current || expanded.has(current.node)) continue;
expanded.add(current.node);
const target = targetByRootFrameId.get(current.node.frame.id) ?? current.inheritedTarget;
mergeFrame(frames, order, current.node, target);
const children = current.node.childFrames ?? [];
for (let index = children.length - 1; index >= 0; index -= 1) {
stack.push({ node: children[index], inheritedTarget: target });
}
}
}
export function buildFrameGraph(sources: CdpFrameTreeSource[]): CdpFrameGraph | null {
const rootSource = sources.find((source) => source.target.sessionId === undefined) ?? sources[0];
if (!rootSource) return null;
const frames = new Map<string, CdpFrame>();
const order: string[] = [];
const targetByRootFrameId = new Map(
sources.map((source) => [source.tree.frame.id, source.target] as const),
);
// The top-level source is authoritative if malformed input reports the same
// frame as both a root target and a child target.
targetByRootFrameId.set(rootSource.tree.frame.id, rootSource.target);
walkFrameTree(rootSource, targetByRootFrameId, frames, order);
for (const source of sources) {
if (source === rootSource) continue;
walkFrameTree(source, targetByRootFrameId, frames, order);
}
return {
rootFrameId: rootSource.tree.frame.id,
frames: order.flatMap((frameId) => {
const frame = frames.get(frameId);
return frame ? [frame] : [];
}),
};
}
@@ -8,7 +8,6 @@ import {
useRef,
useState,
} from "react";
import type { HelpHighlightRect } from "@/lib/help-bridge";
import logoUrl from "../../assets/logo.png";
export interface HelpRequestData {
@@ -20,10 +19,6 @@ export interface HelpRequestData {
displayMode?: "full" | "compact";
/** CSS selectors to scroll to + flash-highlight. */
selectors: string[];
/** Pre-resolved top-viewport rectangles, used for cross-frame targets. */
rects?: HelpHighlightRect[];
/** Re-resolve cross-frame rectangles after scroll, resize, or layout changes. */
refreshRects?: () => Promise<HelpHighlightRect[] | undefined>;
onContinue: (note: string) => void;
onCancel: () => void;
}
@@ -54,7 +49,6 @@ const PANEL_WIDTH = 420;
const FALLBACK_PANEL_H = 180;
const FALLBACK_PANEL_H_COLLAPSED = 44;
const EMPTY_SELECTORS: string[] = [];
const EMPTY_RECTS: HelpHighlightRect[] = [];
function clamp(value: number, min: number, max: number): number {
return Math.max(min, Math.min(max, value));
@@ -185,8 +179,6 @@ export function HelpRequestOverlay({ request }: Props) {
const { t } = useTranslation("extension");
const isCompact = request?.displayMode === "compact";
const effectiveSelectors = isCompact ? EMPTY_SELECTORS : (request?.selectors ?? EMPTY_SELECTORS);
const [liveRects, setLiveRects] = useState<HelpHighlightRect[] | null>(null);
const effectiveRects = isCompact ? EMPTY_RECTS : (liveRects ?? request?.rects ?? EMPTY_RECTS);
const [note, setNote] = useState("");
const [collapsed, setCollapsed] = useState(false);
const [boxes, setBoxes] = useState<Box[]>([]);
@@ -209,7 +201,6 @@ export function HelpRequestOverlay({ request }: Props) {
// Reset the note and collapse state whenever a new request appears.
useEffect(() => {
setNote("");
setLiveRects(null);
setCollapsed(false);
placementRef.current = null;
setDragPos(null);
@@ -218,32 +209,6 @@ export function HelpRequestOverlay({ request }: Props) {
dragStartRef.current = null;
}, [request?.id]);
useEffect(() => {
if (!request || isCompact || !request.refreshRects) return;
let disposed = false;
let resolving = false;
const refresh = async () => {
if (resolving) return;
resolving = true;
try {
const rects = await request.refreshRects?.();
if (!disposed && rects) setLiveRects(rects);
} finally {
resolving = false;
}
};
const onViewportChange = () => void refresh();
window.addEventListener("scroll", onViewportChange, true);
window.addEventListener("resize", onViewportChange);
const interval = window.setInterval(onViewportChange, 500);
return () => {
disposed = true;
window.removeEventListener("scroll", onViewportChange, true);
window.removeEventListener("resize", onViewportChange);
window.clearInterval(interval);
};
}, [request, isCompact]);
// Scroll the first matched target into view once per distinct request id.
useLayoutEffect(() => {
if (!request) return;
@@ -266,7 +231,7 @@ export function HelpRequestOverlay({ request }: Props) {
return;
}
const update = () => {
const nextBoxes = [...measure(effectiveSelectors), ...effectiveRects];
const nextBoxes = measure(effectiveSelectors);
setBoxes((prev) => (boxesEqual(prev, nextBoxes) ? prev : nextBoxes));
};
update();
@@ -278,7 +243,7 @@ export function HelpRequestOverlay({ request }: Props) {
window.removeEventListener("resize", update);
window.clearInterval(interval);
};
}, [request, effectiveSelectors, effectiveRects]);
}, [request, effectiveSelectors]);
const onHeaderPointerDown = useCallback(
(e: ReactPointerEvent<HTMLDivElement>) => {
@@ -340,7 +305,7 @@ export function HelpRequestOverlay({ request }: Props) {
return;
}
if (userMovedRef.current) return;
const measured = boxes.length > 0 ? boxes : [...measure(effectiveSelectors), ...effectiveRects];
const measured = boxes.length > 0 ? boxes : measure(effectiveSelectors);
const anchor = unionBox(measured);
const banner = bannerRef.current;
if (!anchor || !banner) {
@@ -364,7 +329,7 @@ export function HelpRequestOverlay({ request }: Props) {
}
const nextPos = placePanel(anchor, panelW, panelH, placementRef.current.placement);
setPanelPos((prev) => (panelPosEqual(prev, nextPos) ? prev : nextPos));
}, [request, boxes, collapsed, isCompact, effectiveSelectors, effectiveRects]);
}, [request, boxes, collapsed, isCompact, effectiveSelectors]);
if (!request) return null;
+63 -38
View File
@@ -1,4 +1,5 @@
import { useTranslation } from "@browser-skill/i18n/react";
import type { FrameCaptureFailure, FrameCaptureStatus } from "@/transport/types";
import {
type PointerEvent as ReactPointerEvent,
useCallback,
@@ -21,6 +22,8 @@ export interface RecordRequestData {
type Props = {
request: RecordRequestData | null;
captureStatus?: FrameCaptureStatus;
captureFailures?: FrameCaptureFailure[];
};
const VIEWPORT_MARGIN = 16;
@@ -52,7 +55,11 @@ function clampDragPos(
};
}
export function RecordOverlay({ request }: Props) {
export function RecordOverlay({
request,
captureStatus = "complete",
captureFailures = [],
}: Props) {
const { t } = useTranslation("extension");
const [show, setShow] = useState(false);
const [elapsedSeconds, setElapsedSeconds] = useState(0);
@@ -154,6 +161,7 @@ export function RecordOverlay({ request }: Props) {
const introVisible = elapsedSeconds * 1_000 < INTRO_DURATION_MS;
const positioned = dragPos !== null;
const partialCapture = captureStatus === "partial" || captureFailures.length > 0;
const defaultTransform = show
? "translateX(-50%) translateY(0)"
: "translateX(-50%) translateY(8px)";
@@ -208,8 +216,9 @@ export function RecordOverlay({ request }: Props) {
data-slot="record-overlay-status"
style={{
display: "flex",
alignItems: "center",
gap: 8,
flexDirection: "column",
alignItems: "flex-start",
gap: 2,
minWidth: 0,
flex: 1,
borderRadius: 9999,
@@ -218,41 +227,57 @@ export function RecordOverlay({ request }: Props) {
paddingRight: 4,
}}
>
<span
data-slot="record-overlay-indicator"
style={{
width: 9,
height: 9,
borderRadius: "50%",
backgroundColor: "#ef4444",
flexShrink: 0,
animation: "bsk-rec-pulse 1.4s ease-in-out infinite",
}}
/>
<span
data-slot="record-overlay-label"
style={{
display: "block",
flex: "0 1 auto",
fontSize: 16,
fontWeight: 500,
color: "#333",
whiteSpace: "nowrap",
userSelect: "none",
overflow: "hidden",
textOverflow: "ellipsis",
width: introVisible ? "auto" : 48,
maxWidth: introVisible ? 280 : 48,
fontVariantNumeric: introVisible ? undefined : "tabular-nums",
textAlign: introVisible ? "left" : "center",
margin: 0,
padding: 0,
minWidth: 0,
transition: "max-width 180ms ease-out",
}}
>
{introVisible ? t("recordOverlay.recording") : formatElapsed(elapsedSeconds)}
</span>
<div style={{ display: "flex", alignItems: "center", gap: 8, minWidth: 0, width: "100%" }}>
<span
data-slot="record-overlay-indicator"
style={{
width: 9,
height: 9,
borderRadius: "50%",
backgroundColor: "#ef4444",
flexShrink: 0,
animation: "bsk-rec-pulse 1.4s ease-in-out infinite",
}}
/>
<span
data-slot="record-overlay-label"
style={{
display: "block",
flex: "0 1 auto",
fontSize: 16,
fontWeight: 500,
color: "#333",
whiteSpace: "nowrap",
userSelect: "none",
overflow: "hidden",
textOverflow: "ellipsis",
width: introVisible ? "auto" : 48,
maxWidth: introVisible ? 280 : 48,
fontVariantNumeric: introVisible ? undefined : "tabular-nums",
textAlign: introVisible ? "left" : "center",
margin: 0,
padding: 0,
minWidth: 0,
transition: "max-width 180ms ease-out",
}}
>
{introVisible ? t("recordOverlay.recording") : formatElapsed(elapsedSeconds)}
</span>
</div>
{partialCapture ? (
<span
data-slot="record-overlay-partial-warning"
style={{
fontSize: 12,
lineHeight: "16px",
color: "#b45309",
whiteSpace: "normal",
maxWidth: 280,
}}
>
{t("recordOverlay.partialCapture")}
</span>
) : null}
</div>
<button
type="button"
@@ -1,6 +1,6 @@
import { i18n } from "@browser-skill/i18n";
import { I18nextProvider } from "@browser-skill/i18n/react";
import { cleanup, fireEvent, render, screen, waitFor } from "@testing-library/react";
import { cleanup, fireEvent, render, screen } from "@testing-library/react";
import { createElement } from "react";
import { afterEach, describe, expect, it, vi } from "vitest";
import { type HelpRequestData, HelpRequestOverlay } from "../HelpRequestOverlay";
@@ -38,36 +38,6 @@ describe("HelpRequestOverlay", () => {
expect(screen.getByText("Please complete the captcha")).toBeTruthy();
});
it("renders explicit viewport rectangles for cross-frame targets", () => {
const { container } = renderOverlay(
baseRequest({ rects: [{ top: 30, left: 40, width: 120, height: 50 }] }),
);
const highlight = container.querySelector<HTMLElement>("[data-slot='help-highlight']");
expect(highlight?.style.top).toBe("30px");
expect(highlight?.style.left).toBe("40px");
expect(highlight?.style.width).toBe("120px");
expect(highlight?.style.height).toBe("50px");
});
it("re-resolves cross-frame rectangles after the viewport changes", async () => {
const refreshRects = vi.fn(async () => [{ top: 80, left: 90, width: 140, height: 60 }]);
const { container } = renderOverlay(
baseRequest({
rects: [{ top: 30, left: 40, width: 120, height: 50 }],
refreshRects,
}),
);
window.dispatchEvent(new Event("scroll"));
await waitFor(() => {
const highlight = container.querySelector<HTMLElement>("[data-slot='help-highlight']");
expect(highlight?.style.top).toBe("80px");
expect(highlight?.style.left).toBe("90px");
});
expect(refreshRects).toHaveBeenCalledTimes(1);
});
it("keeps the inactive render stable", () => {
const { container, rerender } = renderOverlay(null);
@@ -178,4 +178,30 @@ describe("RecordOverlay", () => {
expect(pill.style.bottom).toBe("auto");
expect(pill.style.transform).toBe("none");
});
it("shows a persistent partial-capture warning when frame capture is incomplete", () => {
const { container } = render(
createElement(
I18nextProvider,
{ i18n },
createElement(RecordOverlay, {
request: { id: "rec-1", onFinish: vi.fn() },
captureStatus: "partial",
captureFailures: [
{
reason: "not_injectable",
frame_id: 2,
url: "chrome://settings",
},
],
}),
),
);
const warning = container.querySelector("[data-slot='record-overlay-partial-warning']");
expect(warning).toBeTruthy();
expect(warning?.textContent).toBe(
i18n.t("recordOverlay.partialCapture", { ns: "extension" }),
);
});
});
@@ -1,64 +0,0 @@
import { describe, expect, it, vi } from "vitest";
import { createHelpRequestData } from "../help-request";
describe("createHelpRequestData", () => {
it("gives live delivery and recovery the same rectangle refresh mechanism", async () => {
const finish = vi.fn();
const query = vi.fn(async () => ({
active: true,
request: {
requestId: "help-1",
prompt: "complete the challenge",
selectors: [],
rects: [{ top: 80, left: 90, width: 140, height: 60 }],
timeoutMs: 1_000,
},
}));
const request = createHelpRequestData(
{
requestId: "help-1",
prompt: "complete the challenge",
selectors: [],
rects: [{ top: 10, left: 20, width: 30, height: 40 }],
timeoutMs: 1_000,
},
{ finish, query },
);
await expect(request.refreshRects?.()).resolves.toEqual([
{ top: 80, left: 90, width: 140, height: 60 },
]);
request.onContinue(" done ");
request.onCancel();
expect(query).toHaveBeenCalledOnce();
expect(finish).toHaveBeenNthCalledWith(1, "help-1", "continued", " done ");
expect(finish).toHaveBeenNthCalledWith(2, "help-1", "cancelled");
});
it("ignores rectangle replies for a replaced request", async () => {
const request = createHelpRequestData(
{
requestId: "help-1",
prompt: "complete the challenge",
selectors: [],
timeoutMs: 1_000,
},
{
finish: vi.fn(),
query: vi.fn(async () => ({
active: true,
request: {
requestId: "help-2",
prompt: "new challenge",
selectors: [],
rects: [{ top: 1, left: 2, width: 3, height: 4 }],
timeoutMs: 1_000,
},
})),
},
);
await expect(request.refreshRects?.()).resolves.toBeUndefined();
});
});
@@ -1,12 +1,10 @@
import { beforeEach, describe, expect, it, vi } from "vitest";
import type { RecordStepPayload } from "@/lib/record-bridge";
import { startRecordCapture } from "../record-capture";
import { RECORD_START, RECORD_STOP, type RecordStepPayload } from "@/lib/record-bridge";
import { handleRecordContentMessage, startRecordCapture } from "../record-capture";
vi.stubGlobal("chrome", {
runtime: {
sendMessage: vi.fn((message: { sequence?: number }) =>
Promise.resolve({ ok: true, sequence: message.sequence }),
),
sendMessage: vi.fn(() => Promise.resolve()),
},
});
@@ -48,6 +46,117 @@ function click(el: Element): void {
el.dispatchEvent(new MouseEvent("click", { bubbles: true, button: 0, detail: 1 }));
}
describe("handleRecordContentMessage stop/cancel", () => {
it("ignores STOP when no recording is active", () => {
const dispose = vi.fn();
const onStop = vi.fn();
const setActiveRequestId = vi.fn();
const setCapture = vi.fn();
const sendResponse = vi.fn();
const needsAsync = handleRecordContentMessage(
{ type: RECORD_STOP, requestId: "rec-stale" },
{
activeRequestId: null,
capture: { dispose },
setActiveRequestId,
setCapture,
onStart: vi.fn(),
onStop,
},
sendResponse,
);
expect(needsAsync).toBe(false);
expect(dispose).not.toHaveBeenCalled();
expect(onStop).not.toHaveBeenCalled();
expect(setActiveRequestId).not.toHaveBeenCalled();
expect(setCapture).not.toHaveBeenCalled();
expect(sendResponse).not.toHaveBeenCalled();
});
it("ignores STOP for a mismatched requestId", () => {
const dispose = vi.fn();
const onStop = vi.fn();
const needsAsync = handleRecordContentMessage(
{ type: RECORD_STOP, requestId: "rec-other" },
{
activeRequestId: "rec-1",
capture: { dispose },
setActiveRequestId: vi.fn(),
setCapture: vi.fn(),
onStart: vi.fn(),
onStop,
},
vi.fn(),
);
expect(needsAsync).toBe(false);
expect(dispose).not.toHaveBeenCalled();
expect(onStop).not.toHaveBeenCalled();
});
it("keeps a failed STOP retryable and redelivers its recorded step", async () => {
document.body.innerHTML = `<label for="retry">Draft</label><input id="retry" />`;
const sendMessage = vi.mocked(chrome.runtime.sendMessage);
sendMessage.mockReset();
sendMessage.mockRejectedValueOnce(new Error("service worker unavailable"));
sendMessage.mockResolvedValueOnce(undefined);
let activeRequestId: string | null = null;
let capture: ReturnType<typeof startRecordCapture> | null = null;
const onStop = vi.fn();
const dispatch = (
message:
| { type: typeof RECORD_START; requestId: string; startedAtMs?: number }
| { type: typeof RECORD_STOP; requestId: string },
sendResponse?: (response: unknown) => void,
) =>
handleRecordContentMessage(
message,
{
activeRequestId,
capture,
setActiveRequestId: (id) => {
activeRequestId = id;
},
setCapture: (next) => {
capture = next;
},
onStart: vi.fn(),
onStop,
},
sendResponse,
);
dispatch({ type: RECORD_START, requestId: "rec-retry" });
const input = document.querySelector("input")!;
input.dispatchEvent(new FocusEvent("focusin", { bubbles: true }));
input.value = "dirty final value";
input.dispatchEvent(new Event("input", { bubbles: true }));
const firstResponse = vi.fn();
expect(dispatch({ type: RECORD_STOP, requestId: "rec-retry" }, firstResponse)).toBe(true);
await vi.waitFor(() =>
expect(firstResponse).toHaveBeenCalledWith({
ok: false,
error: "failed to deliver one or more recorded steps",
}),
);
expect(activeRequestId).toBe("rec-retry");
expect(onStop).not.toHaveBeenCalled();
const retryResponse = vi.fn();
expect(dispatch({ type: RECORD_STOP, requestId: "rec-retry" }, retryResponse)).toBe(true);
await vi.waitFor(() => expect(retryResponse).toHaveBeenCalledWith({ ok: true }));
expect(sendMessage).toHaveBeenCalledTimes(2);
expect(activeRequestId).toBeNull();
expect(onStop).toHaveBeenCalledTimes(1);
});
});
describe("record-capture semantic", () => {
let steps: RecordStepPayload[];
@@ -124,19 +233,6 @@ describe("record-capture semantic", () => {
]);
});
it("does not emit page navigation from a child Document capture", () => {
const originalUrl = location.href;
const capture = startRecordCapture("rec-child", (step) => steps.push(step), {
captureNavigation: false,
});
history.pushState({}, "", "#inside-frame");
expect(steps).toEqual([]);
capture.dispose();
history.replaceState({}, "", originalUrl);
});
it("does not record clicks on anonymous layout divs", () => {
document.body.innerHTML = `
<div id="chrome">page chrome</div>
@@ -1518,3 +1614,79 @@ describe("record-capture semantic", () => {
expect(steps.map((s) => s.op)).toEqual(["click"]);
});
});
describe("record-capture child frame", () => {
let steps: RecordStepPayload[];
beforeEach(() => {
steps = [];
document.body.innerHTML = `
<label for="child-q">Child query</label>
<input id="child-q" name="child-q" />
<button type="button" aria-label="Child search">Search</button>
<select aria-label="Child status">
<option value="on">On</option>
<option value="off">Off</option>
</select>
`;
});
it("stamps a document token on start and clears it on dispose", () => {
const capture = startRecordCapture("rec-child-token", (step) => steps.push(step), {
frameMode: "child",
});
const token = document.documentElement.getAttribute("data-bsk-record-document");
expect(token).toBeTruthy();
click(document.querySelector("button")!);
expect(steps[0]?.documentToken).toBe(token);
expect(steps[0]?.frame_url).toBeTruthy();
capture.dispose();
expect(document.documentElement.hasAttribute("data-bsk-record-document")).toBe(false);
});
it("records click, fill, select, and press in child frame mode", () => {
const capture = startRecordCapture("rec-child-ops", (step) => steps.push(step), {
frameMode: "child",
});
const input = document.querySelector("input")!;
const select = document.querySelector("select")!;
input.dispatchEvent(new FocusEvent("focusin", { bubbles: true }));
input.value = "child value";
input.dispatchEvent(new Event("input", { bubbles: true }));
input.dispatchEvent(new FocusEvent("focusout", { bubbles: true }));
select.value = "off";
select.dispatchEvent(new Event("change", { bubbles: true }));
input.dispatchEvent(new FocusEvent("focusin", { bubbles: true }));
input.dispatchEvent(new KeyboardEvent("keydown", { key: "Enter", bubbles: true }));
click(document.querySelector("button")!);
capture.dispose();
expect(steps.map((s) => s.op)).toEqual(
expect.arrayContaining(["fill", "select", "press", "click"]),
);
expect(steps.every((s) => s.documentToken)).toBe(true);
});
it("commits the last fill when dispose runs in child frame mode", () => {
const capture = startRecordCapture("rec-child-fill-stop", (step) => steps.push(step), {
frameMode: "child",
});
const input = document.querySelector("input")!;
input.dispatchEvent(new FocusEvent("focusin", { bubbles: true }));
input.value = "pending child fill";
input.dispatchEvent(new Event("input", { bubbles: true }));
capture.dispose();
expect(steps.some((s) => s.op === "fill" && s.value === "pending child fill")).toBe(true);
});
it("does not emit navigate steps for child frame navigations", () => {
const capture = startRecordCapture("rec-child-nav", (step) => steps.push(step), {
frameMode: "child",
});
history.pushState({}, "", "/child-frame-path");
capture.dispose();
expect(steps.filter((s) => s.op === "navigate")).toHaveLength(0);
});
});
@@ -1,102 +0,0 @@
import { afterEach, describe, expect, it, vi } from "vitest";
import type { RecordFramePortMessage } from "@/lib/recording/frame-bridge";
import { RECORD_FRAME_START } from "@/lib/recording/frame-bridge";
import { RECORD_DOCUMENT_ATTRIBUTE } from "@/shared/recording-document-identity";
import { RecordFrameAgent } from "../recording/frame-agent";
class PortListeners<T extends (...args: never[]) => unknown> {
readonly values = new Set<T>();
addListener = (listener: T) => this.values.add(listener);
removeListener = (listener: T) => this.values.delete(listener);
}
function portHarness() {
const onMessage = new PortListeners<(message: unknown) => void>();
const onDisconnect = new PortListeners<() => void>();
const outbound: RecordFramePortMessage[] = [];
const port = {
name: "bsk-record-frame",
onMessage,
onDisconnect,
postMessage(message: RecordFramePortMessage) {
outbound.push(message);
if (message.type === "ready") {
queueMicrotask(() => {
for (const listener of onMessage.values) {
listener({
type: "ready_ack",
requestId: message.requestId,
producerId: message.producerId,
});
}
});
}
},
disconnect: vi.fn(),
} as unknown as chrome.runtime.Port;
return {
port,
outbound,
receive(message: RecordFramePortMessage) {
for (const listener of onMessage.values) listener(message);
},
};
}
describe("RecordFrameAgent", () => {
afterEach(() => {
document.documentElement.removeAttribute(RECORD_DOCUMENT_ATTRIBUTE);
document.body.replaceChildren();
});
it("keeps a failed stop retryable and flushes the final dirty fill", async () => {
const harness = portHarness();
const sendMessage = vi
.fn<(message: { sequence: number }) => Promise<unknown>>()
.mockRejectedValueOnce(new Error("offline"))
.mockRejectedValueOnce(new Error("still offline"))
.mockImplementation(async (message) => ({ ok: true, sequence: message.sequence }));
vi.stubGlobal("chrome", {
runtime: {
connect: vi.fn(() => harness.port),
sendMessage,
},
});
document.body.innerHTML = `<label for="draft">Draft</label><input id="draft" />`;
const agent = new RecordFrameAgent();
await expect(
agent.start({ type: RECORD_FRAME_START, requestId: "rec-1", startedAtMs: 10 }),
).resolves.toEqual({ ok: true });
expect(document.documentElement.hasAttribute(RECORD_DOCUMENT_ATTRIBUTE)).toBe(true);
const input = document.querySelector("input")!;
input.dispatchEvent(new FocusEvent("focusin", { bubbles: true }));
input.value = "final value";
input.dispatchEvent(new Event("input", { bubbles: true }));
harness.receive({ type: "stop", requestId: "rec-1", commandId: "stop-1" });
await vi.waitFor(() =>
expect(harness.outbound).toContainEqual({
type: "stopped",
requestId: "rec-1",
commandId: "stop-1",
ok: false,
error: "failed to deliver one or more recorded steps",
}),
);
expect(document.documentElement.hasAttribute(RECORD_DOCUMENT_ATTRIBUTE)).toBe(true);
harness.receive({ type: "stop", requestId: "rec-1", commandId: "stop-2" });
await vi.waitFor(() =>
expect(harness.outbound).toContainEqual({
type: "stopped",
requestId: "rec-1",
commandId: "stop-2",
ok: true,
}),
);
expect(sendMessage).toHaveBeenCalledTimes(3);
expect(document.documentElement.hasAttribute(RECORD_DOCUMENT_ATTRIBUTE)).toBe(false);
});
});
@@ -1,36 +0,0 @@
import { describe, expect, it, vi } from "vitest";
import type { RecordStepMessage } from "@/lib/record-bridge";
import { RecordStepDelivery } from "../record-step-delivery";
describe("RecordStepDelivery", () => {
it("retries from the first unacknowledged sequence before sending later steps", async () => {
const sent: RecordStepMessage[] = [];
const send = vi.fn(async (message: RecordStepMessage) => {
sent.push(message);
if (sent.length === 1) throw new Error("service worker unavailable");
return { ok: true, sequence: message.sequence };
});
const delivery = new RecordStepDelivery("rec-ordered", send, "document-1");
delivery.enqueue({ op: "click", target: { tag: "button", name: "First" } });
delivery.enqueue({ op: "click", target: { tag: "button", name: "Second" } });
await expect(delivery.flush()).resolves.toBe(true);
expect(sent.map((message) => message.sequence)).toEqual([1, 1, 2]);
expect(sent.map((message) => message.step.target?.name)).toEqual(["First", "First", "Second"]);
});
it("keeps unacknowledged steps pending for a later flush", async () => {
const send = vi
.fn<(message: RecordStepMessage) => Promise<unknown>>()
.mockRejectedValueOnce(new Error("offline"))
.mockRejectedValueOnce(new Error("still offline"))
.mockImplementation(async (message) => ({ ok: true, sequence: message.sequence }));
const delivery = new RecordStepDelivery("rec-retry", send, "document-1");
delivery.enqueue({ op: "click", target: { tag: "button", name: "Save" } });
await expect(delivery.flush()).resolves.toBe(false);
await expect(delivery.flush()).resolves.toBe(true);
expect(send).toHaveBeenCalledTimes(3);
});
});
@@ -1,31 +0,0 @@
import type { HelpQueryResponse, HelpRequestMessage } from "@/lib/help-bridge";
import type { HelpRequestData } from "./HelpRequestOverlay";
export interface HelpRequestDataDeps {
finish(requestId: string, outcome: "continued" | "cancelled", note?: string): void;
query(): Promise<HelpQueryResponse | undefined>;
}
/** Build the content-side representation shared by live delivery and recovery. */
export function createHelpRequestData(
message: Omit<HelpRequestMessage, "type">,
deps: HelpRequestDataDeps,
): HelpRequestData {
return {
id: message.requestId,
prompt: message.prompt,
...(message.title ? { title: message.title } : {}),
...(message.displayMode ? { displayMode: message.displayMode } : {}),
selectors: message.selectors,
rects: message.rects,
refreshRects: async () => {
const response = await deps.query();
return response?.active && response.request?.requestId === message.requestId
? response.request.rects
: undefined;
},
onContinue: (note: string) =>
deps.finish(message.requestId, "continued", note.trim() ? note : undefined),
onCancel: () => deps.finish(message.requestId, "cancelled"),
};
}
+216 -36
View File
@@ -12,8 +12,28 @@ import {
hasDirectHoverInteractiveSignal,
hasStrongHoverExpansionSignal,
} from "@/lib/hover-trigger-policy";
import type { RecordStepPayload } from "@/lib/record-bridge";
import { shouldRecordPress } from "@/lib/recording/draft-policy";
import {
isRecordCancelMessage,
isRecordStartMessage,
isRecordStopMessage,
RECORD_CANCEL,
RECORD_START,
RECORD_STEP,
RECORD_STOP,
type RecordCancelMessage,
type RecordFrameMode,
type RecordStartAck,
type RecordStartMessage,
type RecordStepPayload,
type RecordStopAck,
type RecordStopMessage,
} from "@/lib/record-bridge";
import {
clearRecordDocumentToken,
createRecordDocumentToken,
stampRecordDocumentToken,
} from "@/lib/record-document-token";
import { shouldRecordPress } from "@/lib/trace-reducer";
import {
closestHoverSurfaceCandidate,
collectHoverSurfaceStates,
@@ -23,6 +43,37 @@ import {
isLikelyHoverSurfaceOwner,
} from "./record-hover-surface";
const pendingStepSends = new Map<string, Set<Promise<boolean>>>();
const failedStepDeliveries = new Set<string>();
const failedStepPayloads = new Map<string, RecordStepPayload[]>();
const pendingStopFlushes = new Map<string, Promise<RecordStopAck>>();
const knownRecordRequests = new Set<string>();
function deliverRecordStep(requestId: string, step: RecordStepPayload): Promise<boolean> {
const payload = { type: RECORD_STEP, requestId, step };
return Promise.resolve(chrome.runtime.sendMessage(payload)).then(
() => true,
() => {
failedStepDeliveries.add(requestId);
const failed = failedStepPayloads.get(requestId) ?? [];
failed.push(step);
failedStepPayloads.set(requestId, failed);
return false;
},
);
}
function sendRecordStep(requestId: string, step: RecordStepPayload): void {
const pending = deliverRecordStep(requestId, step);
const sends = pendingStepSends.get(requestId) ?? new Set<Promise<boolean>>();
sends.add(pending);
pendingStepSends.set(requestId, sends);
void pending.then(() => {
sends.delete(pending);
if (sends.size === 0) pendingStepSends.delete(requestId);
});
}
export interface RecordCaptureController {
dispose(): void;
}
@@ -124,8 +175,12 @@ function nearbyFillableFromSearchChrome(target: Element): FillableElement | null
function captureGeometry(el: Element): RecordStepPayload["geometry"] {
const rect = el.getBoundingClientRect();
const style = window.getComputedStyle(el);
return {
rect: { x: rect.x, y: rect.y, w: rect.width, h: rect.height },
scrollX: window.scrollX,
scrollY: window.scrollY,
position: style.position,
tag: el.tagName.toLowerCase(),
};
}
@@ -215,10 +270,7 @@ function collectHoverTriggerLabelText(root: Element): string {
return normalizeLabelText(text);
}
function compactHoverTargetName(
el: Element,
desc: CaptureTargetDescriptor,
): CaptureTargetDescriptor {
function compactHoverTargetName(el: Element, desc: CaptureTargetDescriptor): CaptureTargetDescriptor {
if (!desc.name) return desc;
const fullText = normalizeLabelText(el.textContent ?? "");
const compactName = collectHoverTriggerLabelText(el);
@@ -356,13 +408,37 @@ function scheduleInputCompletionCommit(
setTimeout(syncAndCommit, 0);
}
export interface RecordCaptureOptions {
frameMode?: RecordFrameMode;
}
export function startRecordCapture(
_requestId: string,
sendStep: (step: RecordStepPayload) => void,
options: { captureNavigation?: boolean } = {},
options: RecordCaptureOptions = {},
): RecordCaptureController {
const frameMode = options.frameMode ?? "top";
const emitNavigate = frameMode === "top";
const documentToken = createRecordDocumentToken();
stampRecordDocumentToken(documentToken);
const capturedAtMs = () => Date.now();
const resolveTopPageUrl = (): string => {
try {
return window.top?.location.href ?? location.href;
} catch {
return location.href;
}
};
const emitStep = (step: RecordStepPayload) => {
sendStep({ page_url: location.href, ...step });
sendStep({
page_url: resolveTopPageUrl(),
frame_url: location.href,
documentToken,
capturedAtMs: capturedAtMs(),
...step,
});
};
const hoverSurfaceStateMap = (states: HoverSurfaceState[]): Map<Element, string> =>
new Map(states.map((state) => [state.element, state.signature]));
@@ -433,6 +509,7 @@ export function startRecordCapture(
};
const emitNavigateIfChanged = (causedByAction?: boolean) => {
if (!emitNavigate) return;
if (location.href === lastUrl) return;
commitFillSession();
lastUrl = location.href;
@@ -896,37 +973,31 @@ export function startRecordCapture(
document.addEventListener("change", onChange, true);
document.addEventListener("keydown", onKeyDown, true);
const captureNavigation = options.captureNavigation ?? true;
const urlObserver = captureNavigation
? new MutationObserver(() => emitNavigateIfChanged())
: null;
urlObserver?.observe(document, { subtree: true, childList: true });
const urlObserver = new MutationObserver(() => emitNavigateIfChanged());
urlObserver.observe(document, { subtree: true, childList: true });
const onUrlEvent = () => emitNavigateIfChanged();
// Wrap: passing commitFillSession directly would forward the DOM event as
// the `commit` argument and stamp it onto the recorded fill step.
const onPageHide = () => commitFillSession();
if (captureNavigation) {
window.addEventListener("hashchange", onUrlEvent);
window.addEventListener("popstate", onUrlEvent);
}
window.addEventListener("hashchange", onUrlEvent);
window.addEventListener("popstate", onUrlEvent);
window.addEventListener("pagehide", onPageHide);
const originalPushState = history.pushState;
const originalReplaceState = history.replaceState;
if (captureNavigation) {
history.pushState = function (...args: Parameters<History["pushState"]>) {
originalPushState.apply(this, args);
emitNavigateIfChanged(navigationActionPending ? true : undefined);
};
history.replaceState = function (...args: Parameters<History["replaceState"]>) {
originalReplaceState.apply(this, args);
emitNavigateIfChanged(navigationActionPending ? true : undefined);
};
}
history.pushState = function (...args: Parameters<History["pushState"]>) {
originalPushState.apply(this, args);
emitNavigateIfChanged(navigationActionPending ? true : undefined);
};
history.replaceState = function (...args: Parameters<History["replaceState"]>) {
originalReplaceState.apply(this, args);
emitNavigateIfChanged(navigationActionPending ? true : undefined);
};
return {
dispose() {
commitFillSession();
clearRecordDocumentToken();
document.removeEventListener("click", onClick, true);
document.removeEventListener("mouseover", onMouseOver, true);
document.removeEventListener("focusin", onFocusIn, true);
@@ -936,16 +1007,125 @@ export function startRecordCapture(
document.removeEventListener("compositionend", onCompositionEnd, true);
document.removeEventListener("change", onChange, true);
document.removeEventListener("keydown", onKeyDown, true);
urlObserver?.disconnect();
if (captureNavigation) {
window.removeEventListener("hashchange", onUrlEvent);
window.removeEventListener("popstate", onUrlEvent);
}
urlObserver.disconnect();
window.removeEventListener("hashchange", onUrlEvent);
window.removeEventListener("popstate", onUrlEvent);
window.removeEventListener("pagehide", onPageHide);
if (captureNavigation) {
history.pushState = originalPushState;
history.replaceState = originalReplaceState;
}
history.pushState = originalPushState;
history.replaceState = originalReplaceState;
},
};
}
export type RecordContentMessage = RecordStartMessage | RecordStopMessage | RecordCancelMessage;
export function isRecordContentMessage(msg: unknown): msg is RecordContentMessage {
return isRecordStartMessage(msg) || isRecordStopMessage(msg) || isRecordCancelMessage(msg);
}
export function handleRecordContentMessage(
message: RecordContentMessage,
state: {
activeRequestId: string | null;
capture: RecordCaptureController | null;
setActiveRequestId(id: string | null): void;
setCapture(capture: RecordCaptureController | null): void;
onStart?(requestId: string, startedAtMs?: number): void;
onStop?(): void;
},
sendResponse?: (response: RecordStartAck | RecordStopAck) => void,
): boolean {
if (isRecordStartMessage(message)) {
if (!knownRecordRequests.has(message.requestId)) {
knownRecordRequests.add(message.requestId);
failedStepDeliveries.delete(message.requestId);
failedStepPayloads.delete(message.requestId);
}
state.capture?.dispose();
const frameMode = message.frameMode ?? "top";
state.setCapture(
startRecordCapture(
message.requestId,
(step) => {
sendRecordStep(message.requestId, step);
},
{ frameMode },
),
);
state.setActiveRequestId(message.requestId);
if (message.showOverlay !== false && frameMode === "top") {
state.onStart?.(message.requestId, message.startedAtMs);
}
sendResponse?.({ ok: true });
return sendResponse !== undefined;
}
if (isRecordStopMessage(message) || isRecordCancelMessage(message)) {
// Require an active recording that matches this requestId — otherwise a
// stray STOP/CANCEL (e.g. after teardown) would still run finishStop and
// clear overlay state even though nothing was capturing.
if (!state.activeRequestId || state.activeRequestId !== message.requestId) {
return false;
}
state.capture?.dispose();
state.setCapture(null);
const finishStop = () => {
state.onStop?.();
state.setActiveRequestId(null);
};
if (isRecordStopMessage(message) && sendResponse) {
const existingFlush = pendingStopFlushes.get(message.requestId);
if (existingFlush) {
void existingFlush.then(sendResponse);
return true;
}
const failedBeforeStop = [...(failedStepPayloads.get(message.requestId) ?? [])];
if (failedBeforeStop.length > 0) {
failedStepPayloads.delete(message.requestId);
failedStepDeliveries.delete(message.requestId);
}
const pending = [...(pendingStepSends.get(message.requestId) ?? [])];
const flush = Promise.all(pending).then(async (delivered): Promise<RecordStopAck> => {
const retried = await Promise.all(
failedBeforeStop.map((step) => deliverRecordStep(message.requestId, step)),
);
const succeeded =
delivered.every(Boolean) &&
retried.every(Boolean) &&
!failedStepDeliveries.has(message.requestId);
if (succeeded) {
failedStepDeliveries.delete(message.requestId);
failedStepPayloads.delete(message.requestId);
knownRecordRequests.delete(message.requestId);
finishStop();
}
return succeeded
? { ok: true }
: {
ok: false,
error: "failed to deliver one or more recorded steps",
};
});
pendingStopFlushes.set(message.requestId, flush);
void flush.then(sendResponse).finally(() => {
if (pendingStopFlushes.get(message.requestId) === flush) {
pendingStopFlushes.delete(message.requestId);
}
});
return true;
}
if (isRecordCancelMessage(message)) {
failedStepDeliveries.delete(message.requestId);
failedStepPayloads.delete(message.requestId);
pendingStopFlushes.delete(message.requestId);
knownRecordRequests.delete(message.requestId);
}
finishStop();
return false;
}
return false;
}
export { RECORD_CANCEL, RECORD_START, RECORD_STEP, RECORD_STOP };
@@ -1,65 +0,0 @@
import {
isAcceptedRecordStepAck,
RECORD_STEP,
type RecordStepMessage,
type RecordStepPayload,
} from "@/lib/record-bridge";
export type SendRecordStepMessage = (message: RecordStepMessage) => Promise<unknown>;
export class RecordStepDelivery {
readonly #requestId: string;
readonly #producerId: string;
readonly #send: SendRecordStepMessage;
readonly #pending = new Map<number, RecordStepPayload>();
#nextSequence = 1;
#tail = Promise.resolve();
constructor(
requestId: string,
send: SendRecordStepMessage = (message) => chrome.runtime.sendMessage(message),
producerId: string = crypto.randomUUID(),
) {
this.#requestId = requestId;
this.#producerId = producerId;
this.#send = send;
}
enqueue(step: RecordStepPayload): void {
const sequence = this.#nextSequence;
this.#nextSequence += 1;
this.#pending.set(sequence, step);
void this.#schedule();
}
async flush(): Promise<boolean> {
await this.#tail;
await this.#schedule();
return this.#pending.size === 0;
}
#schedule(): Promise<void> {
const drain = () => this.#drain();
this.#tail = this.#tail.then(drain, drain);
return this.#tail;
}
async #drain(): Promise<void> {
for (const [sequence, step] of this.#pending) {
const message: RecordStepMessage = {
type: RECORD_STEP,
requestId: this.#requestId,
producerId: this.#producerId,
sequence,
step,
};
try {
const response = await this.#send(message);
if (!isAcceptedRecordStepAck(response, sequence)) return;
this.#pending.delete(sequence);
} catch {
return;
}
}
}
}
@@ -1,209 +0,0 @@
import {
markRecordingDocument,
type RecordingDocumentMarker,
waitForDocumentElement,
} from "@/lib/recording/document-marker";
import {
isRecordFrameStartMessage,
RECORD_FRAME_PORT,
RECORD_FRAME_QUERY,
RECORD_FRAME_START,
type RecordFramePortMessage,
type RecordFrameQueryResponse,
type RecordFrameStartMessage,
} from "@/lib/recording/frame-bridge";
import { type RecordCaptureController, startRecordCapture } from "../record-capture";
import { RecordStepDelivery } from "../record-step-delivery";
interface ActiveFrameRecording {
requestId: string;
producerId: string;
port: chrome.runtime.Port;
delivery: RecordStepDelivery;
capture: RecordCaptureController;
marker: RecordingDocumentMarker;
}
const RECORD_FRAME_REGISTER_TIMEOUT_MS = 5_000;
export class RecordFrameAgent {
#active: ActiveFrameRecording | null = null;
#startPromise: Promise<{ ok: true } | { ok: false; error: string }> | null = null;
#disposed = false;
async start(
message: RecordFrameStartMessage,
): Promise<{ ok: true } | { ok: false; error: string }> {
if (this.#active?.requestId === message.requestId) return { ok: true };
if (this.#disposed) return { ok: false, error: "recording document is disposed" };
if (this.#startPromise) {
await this.#startPromise;
return this.start(message);
}
if (this.#active) this.cancel(this.#active.requestId);
const starting = this.#start(message);
this.#startPromise = starting;
try {
return await starting;
} finally {
if (this.#startPromise === starting) this.#startPromise = null;
}
}
cancel(requestId: string): void {
const active = this.#active;
if (!active || active.requestId !== requestId) return;
active.capture.dispose();
active.marker.restore();
active.port.disconnect();
this.#active = null;
}
dispose(): void {
this.#disposed = true;
if (this.#active) this.cancel(this.#active.requestId);
}
async #start(
message: RecordFrameStartMessage,
): Promise<{ ok: true } | { ok: false; error: string }> {
const producerId = crypto.randomUUID();
const root = await waitForDocumentElement();
if (this.#disposed) return { ok: false, error: "recording document is disposed" };
const marker = markRecordingDocument(producerId, root);
const port = chrome.runtime.connect({ name: RECORD_FRAME_PORT });
try {
await registerPort(port, message.requestId, producerId);
} catch {
marker.restore();
port.disconnect();
return { ok: false, error: "failed to register recording document" };
}
if (this.#disposed) {
marker.restore();
port.disconnect();
return { ok: false, error: "recording document is disposed" };
}
const delivery = new RecordStepDelivery(message.requestId, undefined, producerId);
const capture = startRecordCapture(
message.requestId,
(step) => {
marker.ensure();
delivery.enqueue(step);
},
{ captureNavigation: window.top === window },
);
const active: ActiveFrameRecording = {
requestId: message.requestId,
producerId,
port,
delivery,
capture,
marker,
};
this.#active = active;
port.onMessage.addListener((raw: unknown) => {
const command = raw as Partial<RecordFramePortMessage>;
if (command.type === "stop" && command.requestId === active.requestId) {
void this.#stop(active, command.commandId);
} else if (command.type === "cancel" && command.requestId === active.requestId) {
this.cancel(active.requestId);
}
});
port.onDisconnect.addListener(() => {
if (this.#active !== active) return;
active.capture.dispose();
active.marker.restore();
this.#active = null;
});
return { ok: true };
}
async #stop(active: ActiveFrameRecording, commandId: string | undefined): Promise<void> {
if (!commandId || this.#active !== active) return;
active.capture.dispose();
const succeeded = await active.delivery.flush();
try {
active.port.postMessage({
type: "stopped",
requestId: active.requestId,
commandId,
ok: succeeded,
...(succeeded ? {} : { error: "failed to deliver one or more recorded steps" }),
} satisfies RecordFramePortMessage);
} catch {
return;
}
if (!succeeded || this.#active !== active) return;
active.marker.restore();
this.#active = null;
active.port.disconnect();
}
}
function registerPort(
port: chrome.runtime.Port,
requestId: string,
producerId: string,
): Promise<void> {
return new Promise((resolve, reject) => {
const timer = setTimeout(() => {
cleanup();
reject(new Error("recording document registration timed out"));
}, RECORD_FRAME_REGISTER_TIMEOUT_MS);
const cleanup = () => {
clearTimeout(timer);
port.onMessage.removeListener(onMessage);
port.onDisconnect.removeListener(onDisconnect);
};
const onMessage = (raw: unknown) => {
const message = raw as Partial<RecordFramePortMessage>;
if (
message.type !== "ready_ack" ||
message.requestId !== requestId ||
message.producerId !== producerId
) {
return;
}
cleanup();
resolve();
};
const onDisconnect = () => {
cleanup();
reject(new Error("recording document port disconnected"));
};
port.onMessage.addListener(onMessage);
port.onDisconnect.addListener(onDisconnect);
port.postMessage({ type: "ready", requestId, producerId } satisfies RecordFramePortMessage);
});
}
export function attachRecordFrameAgent(): () => void {
const agent = new RecordFrameAgent();
const onMessage = (
message: unknown,
_sender: chrome.runtime.MessageSender,
sendResponse: (response: { ok: true } | { ok: false; error: string }) => void,
) => {
if (!isRecordFrameStartMessage(message)) return false;
void agent.start(message).then(sendResponse);
return true;
};
chrome.runtime.onMessage.addListener(onMessage);
void chrome.runtime
.sendMessage({ type: RECORD_FRAME_QUERY })
.then((response: RecordFrameQueryResponse | undefined) => {
if (!response?.active || !response.requestId || response.startedAtMs === undefined) return;
return agent.start({
type: RECORD_FRAME_START,
requestId: response.requestId,
startedAtMs: response.startedAtMs,
});
})
.catch(() => {});
return () => {
chrome.runtime.onMessage.removeListener(onMessage);
agent.dispose();
};
}
+43 -25
View File
@@ -21,7 +21,6 @@ import {
type OverlayMode,
} from "@/lib/overlay-bridge";
import { POPUP_PORT_NAME, type PopupInbound, type PopupOutbound } from "@/lib/popup-bridge";
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";
@@ -34,12 +33,14 @@ import {
defaultBorrowChromeWindows,
requestBorrowConfirmation,
} from "@/tools/borrow-confirmation";
import {
type RecordCaptureStatusMessage,
} from "@/lib/record-bridge";
import { ToolDispatcher } from "@/tools/dispatcher";
import {
attachRecordFinishListener,
attachRecordQueryListener,
attachRecordStepListener,
type RecordRuntimeDeps,
} from "@/tools/record";
import { detectBrowserMeta } from "@/transport/handshake";
import type { Transport } from "@/transport/transport";
@@ -147,33 +148,10 @@ export default defineBackground(() => {
void sessionsLive.syncFromManager();
},
});
const recordDeps = {
tabsApi: chrome.tabs,
cdp,
frameCoordinator: recordFrameCoordinator,
sendToTab: (tabId: number, msg: Parameters<typeof chrome.tabs.sendMessage>[1]) =>
chrome.tabs.sendMessage(tabId, msg),
bypassOverlay: async (tabId: number, enabled: boolean) => {
try {
await chrome.tabs.sendMessage(tabId, {
type: OVERLAY_AUTOMATION_BYPASS,
enabled,
});
} catch {
// Content script may be unavailable on restricted pages.
}
},
} satisfies RecordRuntimeDeps;
recordFrameCoordinator.attach();
attachRecordStepListener(recordDeps);
attachRecordFinishListener(recordDeps);
attachRecordQueryListener(recordDeps);
const dispatcher = new ToolDispatcher({
transport,
sessions,
cdp,
recording: recordDeps,
onSessionsChanged: onOverlaySessionStateChanged,
onBrowserControlResumed,
approveBorrow: (ctx) =>
@@ -195,6 +173,46 @@ export default defineBackground(() => {
}),
});
dispatcher.start();
const recordDeps = {
tabsApi: chrome.tabs,
cdp,
sendToTab: (tabId: number, msg: Parameters<typeof chrome.tabs.sendMessage>[1]) =>
chrome.tabs.sendMessage(tabId, msg),
sendToDocument: (
tabId: number,
documentId: string,
msg: Parameters<typeof chrome.tabs.sendMessage>[1],
) => chrome.tabs.sendMessage(tabId, msg, { documentId }),
getAllFrames: async (tabId: number) => {
if (!chrome.webNavigation?.getAllFrames) return [];
const frames = await chrome.webNavigation.getAllFrames({ tabId });
return (frames ?? []).map((frame) => ({
frameId: frame.frameId,
documentId: frame.documentId,
url: frame.url,
parentFrameId: frame.parentFrameId,
}));
},
broadcastCaptureStatus: async (tabId: number, msg: RecordCaptureStatusMessage) => {
await chrome.tabs.sendMessage(tabId, msg, { frameId: 0 });
},
bypassOverlay: async (tabId: number, enabled: boolean) => {
try {
await chrome.tabs.sendMessage(tabId, {
type: OVERLAY_AUTOMATION_BYPASS,
enabled,
});
} catch {
// Content script may be unavailable on restricted pages.
}
},
};
// Message listeners stay up (cheap; fire only for record message types).
// Tab / webNavigation observation attaches lazily while a recording is
// active — see ensureBrowserObservationListeners in tools/record.ts.
attachRecordStepListener(recordDeps);
attachRecordFinishListener(recordDeps);
attachRecordQueryListener(recordDeps);
if (typeof chrome.notifications?.onClicked?.addListener === "function") {
attachBorrowNotificationClickHandler({
onClicked: chrome.notifications.onClicked,
+86 -47
View File
@@ -7,10 +7,14 @@ import { BorrowConfirmationOverlay } from "@/content/BorrowConfirmationOverlay";
import { ControlOverlay } from "@/content/ControlOverlay";
import { createCaptureSuppressController } from "@/content/capture-suppress";
import { HelpRequestOverlay } from "@/content/HelpRequestOverlay";
import { createHelpRequestData } from "@/content/help-request";
import overlayCss from "@/content/overlay.css?inline";
import { OverlayController, shouldShowAgentControlOverlay } from "@/content/overlay-controller";
import { RecordOverlay } from "@/content/RecordOverlay";
import {
handleRecordContentMessage,
isRecordContentMessage,
type RecordCaptureController,
} from "@/content/record-capture";
import {
type CaptureSuppressAck,
type CaptureSuppressMessage,
@@ -40,18 +44,15 @@ import {
} from "@/lib/overlay-bridge";
import { sendInterrupt } from "@/lib/overlay-interrupt-client";
import {
isRecordCancelMessage,
isRecordStartMessage,
isRecordStopMessage,
isRecordCaptureStatusMessage,
RECORD_FINISH,
RECORD_QUERY,
type RecordCancelMessage,
type RecordCaptureStatusMessage,
type RecordQueryResponse,
type RecordStartAck,
type RecordStartMessage,
type RecordStopAck,
type RecordStopMessage,
} from "@/lib/record-bridge";
import type { FrameCaptureFailure, FrameCaptureStatus } from "@/transport/types";
import type {
BorrowCancelMessage,
BorrowRequestMessage,
@@ -70,7 +71,10 @@ export default defineContentScript({
if (window.top !== window) return;
const overlays = new OverlayController();
let recordCapture: RecordCaptureController | null = null;
let activeRecordRequestId: string | null = null;
let recordCaptureStatus: FrameCaptureStatus = "complete";
let recordCaptureFailures: FrameCaptureFailure[] = [];
let reactRoot: ReactDOM.Root | null = null;
let overlayHost: HTMLElement | null = null;
let overlayContainer: HTMLElement | null = null;
@@ -189,7 +193,11 @@ export default defineContentScript({
requests: overlayState.borrowRequests,
}),
React.createElement(HelpRequestOverlay, { request: overlayState.activeHelp }),
React.createElement(RecordOverlay, { request: overlayState.activeRecord }),
React.createElement(RecordOverlay, {
request: overlayState.activeRecord,
captureStatus: recordCaptureStatus,
captureFailures: recordCaptureFailures,
}),
React.createElement(ControlOverlay, {
visible: controlOverlayVisible,
interrupting: overlayState.interrupting,
@@ -228,6 +236,8 @@ export default defineContentScript({
if (previousHelp) {
void sendHelpFinish(previousHelp.id, "cancelled");
}
recordCapture?.dispose();
recordCapture = null;
activeRecordRequestId = null;
renderAll();
}
@@ -257,12 +267,10 @@ export default defineContentScript({
| HelpRequestMessage
| HelpCancelMessage
| CaptureSuppressMessage
| RecordStartMessage
| RecordStopMessage
| RecordCancelMessage
| OverlayAgentOverlayResetMessage
| OverlayAgentStateMessage
| OverlayAutomationBypassMessage,
| OverlayAutomationBypassMessage
| RecordCaptureStatusMessage,
_sender: chrome.runtime.MessageSender,
sendResponse: (response: BorrowResponseMessage | HelpAckMessage | CaptureSuppressAck) => void,
) => {
@@ -270,32 +278,50 @@ export default defineContentScript({
return captureSuppress.handleMessage(message, sendResponse);
}
if (isRecordStartMessage(message)) {
activeRecordRequestId = message.requestId;
overlays.setAgentRecordRequest({
id: message.requestId,
...(typeof message.startedAtMs === "number" ? { startedAtMs: message.startedAtMs } : {}),
onFinish: () => {
void chrome.runtime.sendMessage({
type: RECORD_FINISH,
requestId: message.requestId,
});
},
});
if (isRecordCaptureStatusMessage(message)) {
recordCaptureStatus = message.status;
recordCaptureFailures = message.failures ?? [];
renderAll();
(sendResponse as unknown as (response: RecordStartAck) => void)({ ok: true });
return false;
}
if (isRecordStopMessage(message) || isRecordCancelMessage(message)) {
if (activeRecordRequestId !== message.requestId) return false;
overlays.clearAgentRecordRequest(message.requestId);
activeRecordRequestId = null;
renderAll();
if (isRecordStopMessage(message)) {
(sendResponse as unknown as (response: RecordStopAck) => void)({ ok: true });
}
return false;
if (isRecordContentMessage(message)) {
const needsAsync = handleRecordContentMessage(
message,
{
activeRequestId: activeRecordRequestId,
capture: recordCapture,
setActiveRequestId: (id) => {
activeRecordRequestId = id;
},
setCapture: (capture) => {
recordCapture = capture;
},
onStart: (requestId, startedAtMs) => {
overlays.setAgentRecordRequest({
id: requestId,
...(typeof startedAtMs === "number" ? { startedAtMs } : {}),
onFinish: () => {
void chrome.runtime.sendMessage({
type: RECORD_FINISH,
requestId,
});
},
});
renderAll();
},
onStop: () => {
overlays.clearAgentRecordRequest(activeRecordRequestId ?? undefined);
recordCaptureStatus = "complete";
recordCaptureFailures = [];
renderAll();
},
},
sendResponse as unknown as
| ((response: RecordStartAck | RecordStopAck) => void)
| undefined,
);
return needsAsync;
}
if (
@@ -337,7 +363,16 @@ export default defineContentScript({
if (isHelpRequestMessage(message)) {
const helpMsg = message as HelpRequestMessage;
const previousHelp = mountHelpRequest(helpMsg);
const previousHelp = overlays.setAgentHelpRequest({
id: helpMsg.requestId,
prompt: helpMsg.prompt,
...(helpMsg.title ? { title: helpMsg.title } : {}),
...(helpMsg.displayMode ? { displayMode: helpMsg.displayMode } : {}),
selectors: helpMsg.selectors,
onContinue: (note: string) =>
void sendHelpFinish(helpMsg.requestId, "continued", note.trim() ? note : undefined),
onCancel: () => void sendHelpFinish(helpMsg.requestId, "cancelled"),
});
if (previousHelp && previousHelp.id !== helpMsg.requestId) {
void sendHelpFinish(previousHelp.id, "cancelled");
}
@@ -390,18 +425,17 @@ export default defineContentScript({
});
}
function mountHelpRequest(helpMsg: Omit<HelpRequestMessage, "type">) {
return overlays.setAgentHelpRequest(
createHelpRequestData(helpMsg, {
finish: (requestId, outcome, note) => {
void sendHelpFinish(requestId, outcome, note);
},
query: () =>
chrome.runtime.sendMessage({ type: HELP_QUERY }) as Promise<
HelpQueryResponse | undefined
>,
}),
);
function mountHelpRequest(helpMsg: Omit<HelpRequestMessage, "type">): void {
overlays.setAgentHelpRequest({
id: helpMsg.requestId,
prompt: helpMsg.prompt,
...(helpMsg.title ? { title: helpMsg.title } : {}),
...(helpMsg.displayMode ? { displayMode: helpMsg.displayMode } : {}),
selectors: helpMsg.selectors,
onContinue: (note: string) =>
void sendHelpFinish(helpMsg.requestId, "continued", note.trim() ? note : undefined),
onCancel: () => void sendHelpFinish(helpMsg.requestId, "cancelled"),
});
}
async function queryActiveHelpWithRetry(): Promise<void> {
@@ -434,6 +468,8 @@ export default defineContentScript({
) {
const requestId = recordQuery.requestId;
const startedAtMs = recordQuery.startedAtMs;
recordCaptureStatus = recordQuery.captureStatus ?? "complete";
recordCaptureFailures = recordQuery.captureFailures ?? [];
overlays.setAgentRecordRequest({
id: requestId,
...(typeof startedAtMs === "number" ? { startedAtMs } : {}),
@@ -518,6 +554,9 @@ export default defineContentScript({
chrome.runtime.onMessage.removeListener(onMessage);
chrome.storage.onChanged.removeListener(onStorageChange);
window.removeEventListener("pageshow", onPageShow);
// Restore history hooks / remove capture listeners before the CS unloads.
recordCapture?.dispose();
recordCapture = null;
activeRecordRequestId = null;
});
},
@@ -100,6 +100,24 @@ describe("App", () => {
expect(screen.queryByText("录制你的操作,供 Agent 参考")).toBeNull();
});
it("renders localized copy for a version failure instead of protocol details", () => {
mockUseConnectionState.mockReturnValue({
snapshot: {
...baseSnapshot,
lastError:
"[handshake] daemon rejected handshake: version_too_old — peer protocol 1.0 is below local min_compatible_protocol 1.1",
},
statusState: "disconnected",
setLabel,
setConnectionEnabled,
});
render(<App />);
const error = screen.getByText(/bsk 与 BrowserSkill 扩展版本不兼容/);
expect(error.textContent).not.toContain("min_compatible_protocol");
});
it("shows single-line compact metadata and copies the instance id", async () => {
mockUseConnectionState.mockReturnValue({
snapshot: {
@@ -202,7 +220,11 @@ describe("App", () => {
expect(copied).not.toMatch(/bsk record start[^\n]*--url/);
expect(copied).toContain("./trace");
expect(copied).toContain("trace.json");
expect(copied).toContain("states/");
expect(copied).toContain("pages/");
expect(copied).toContain("总结我做了什么");
expect(copied).not.toContain("不要重跑");
expect(copied).not.toContain("pages + steps");
expect(copied).not.toContain("@eN");
// Button label stays static; a transient toast confirms the copy.
expect(copyButton.textContent).toContain("复制录制指令");
await waitFor(() => expect(screen.getByRole("status").textContent).toContain("已复制"));
+5 -2
View File
@@ -83,6 +83,9 @@ export function App() {
const daemonProtocol = snapshot.handshake?.protocol_version ?? "—";
const extensionVersion = snapshot.extensionVersion || "—";
const instanceId = snapshot.instanceId || "—";
const errorMessage = snapshot.lastError?.includes("version_too_old")
? t("popup.versionIncompatibleError")
: snapshot.lastError;
const copyInstanceId = async () => {
if (!snapshot.instanceId || !navigator.clipboard?.writeText) return;
@@ -252,12 +255,12 @@ export function App() {
</div>
</section>
{snapshot.lastError && (
{errorMessage && (
<div
className="rounded-lg border border-destructive/25 bg-destructive/10 px-3 py-2 text-xs leading-snug text-destructive"
data-slot="popup-error"
>
{snapshot.lastError}
{errorMessage}
</div>
)}
@@ -1,14 +1,77 @@
import { attachRecordFrameAgent } from "@/content/recording/frame-agent";
import {
handleRecordContentMessage,
isRecordContentMessage,
type RecordCaptureController,
} from "@/content/record-capture";
import {
RECORD_QUERY,
type RecordQueryResponse,
} from "@/lib/record-bridge";
/** Capture-only content script for child frames (no React overlay). */
export default defineContentScript({
matches: ["<all_urls>"],
runAt: "document_start",
runAt: "document_end",
allFrames: true,
matchAboutBlank: true,
matchOriginAsFallback: true,
main(ctx) {
const dispose = attachRecordFrameAgent();
ctx.onInvalidated(dispose);
if (window.top === window) return;
let recordCapture: RecordCaptureController | null = null;
let activeRecordRequestId: string | null = null;
const onMessage = (
message: unknown,
_sender: chrome.runtime.MessageSender,
sendResponse: (response: unknown) => void,
) => {
if (isRecordContentMessage(message)) {
const needsAsync = handleRecordContentMessage(
message,
{
activeRequestId: activeRecordRequestId,
capture: recordCapture,
setActiveRequestId: (id) => {
activeRecordRequestId = id;
},
setCapture: (capture) => {
recordCapture = capture;
},
},
sendResponse as never,
);
return needsAsync;
}
return false;
};
async function queryActiveRecord(): Promise<void> {
try {
const recordQuery = (await chrome.runtime.sendMessage({
type: RECORD_QUERY,
})) as RecordQueryResponse | undefined;
if (
recordQuery?.active &&
typeof recordQuery.requestId === "string" &&
activeRecordRequestId === null
) {
// Background rearm sends RECORD_START; nothing to mount locally.
}
} catch (err) {
console.debug("[bsk record-frame] record query failed", err);
}
}
chrome.runtime.onMessage.addListener(onMessage);
void queryActiveRecord();
ctx.onInvalidated(() => {
chrome.runtime.onMessage.removeListener(onMessage);
recordCapture?.dispose();
recordCapture = null;
activeRecordRequestId = null;
});
},
});
@@ -26,20 +26,20 @@ function handshake(
}
describe("computeConnectedState (protocol-based compat)", () => {
it("returns connected when daemon protocol equals extension protocol", () => {
expect(computeConnectedState(handshake("1.1", "1.0"), MIN_COMPATIBLE_PROTOCOL)).toEqual({
it("returns connected when protocol strings match", () => {
expect(computeConnectedState(handshake("1.1", "1.1"), MIN_COMPATIBLE_PROTOCOL)).toEqual({
kind: "connected",
});
});
it("returns version_skew when daemon protocol minor is newer", () => {
expect(computeConnectedState(handshake("1.2", "1.0"))).toEqual({
expect(computeConnectedState(handshake("1.2", "1.1"))).toEqual({
kind: "version_skew",
});
});
it("returns version_skew when daemon protocol string differs but floor is satisfied", () => {
expect(computeConnectedState(handshake("1.1.0", "1.0"))).toEqual({
expect(computeConnectedState(handshake("1.1.0", "1.1"))).toEqual({
kind: "version_skew",
});
});
@@ -48,7 +48,9 @@ describe("computeConnectedState (protocol-based compat)", () => {
const result = computeConnectedState(handshake("2.0", "1.0"));
expect(result.kind).toBe("rejected");
if (result.kind === "rejected") {
expect(result.reason).toContain("protocol-major mismatch");
expect(result.reason).toContain("bsk CLI");
expect(result.reason).toContain("BrowserSkill extension");
expect(result.reason).not.toContain("protocol");
}
});
@@ -56,8 +58,9 @@ describe("computeConnectedState (protocol-based compat)", () => {
const result = computeConnectedState(handshake("1.1", "1.5"));
expect(result.kind).toBe("rejected");
if (result.kind === "rejected") {
expect(result.reason).toContain("min_compatible_protocol");
expect(result.reason).toContain("1.5");
expect(result.reason).toContain("BrowserSkill extension is out of date");
expect(result.reason).toContain("Update and reload the extension");
expect(result.reason).not.toContain("min_compatible_protocol");
}
});
@@ -75,16 +78,23 @@ describe("computeConnectedState (protocol-based compat)", () => {
const result = computeConnectedState(handshake("1.0", "1.0"), "1.1");
expect(result.kind).toBe("rejected");
if (result.kind === "rejected") {
expect(result.reason).toContain("below extension min_compatible_protocol");
expect(result.reason).toContain("bsk CLI is out of date");
expect(result.reason).toContain("bsk daemon restart");
expect(result.reason).not.toContain("min_compatible_protocol");
}
});
it("rejects a pre-Trace-v3 daemon using the configured extension floor", () => {
const result = computeConnectedState(handshake("1.0", "1.0"));
expect(result.kind).toBe("rejected");
});
it("rejects malformed daemon min_compatible_protocol with a daemon-floor reason", () => {
const result = computeConnectedState(handshake("1.1", "not-a-protocol"));
expect(result.kind).toBe("rejected");
if (result.kind === "rejected") {
expect(result.reason).toContain("daemon min_compatible_protocol");
expect(result.reason).toContain("not-a-protocol");
expect(result.reason).toContain("could not verify version compatibility");
expect(result.reason).not.toContain("min_compatible_protocol");
}
});
@@ -242,11 +252,11 @@ describe("ConnectionController connectionEnabled", () => {
const second = transport.send.mock.calls[1]?.[0] as { id: string };
expect(second.id).not.toBe(first.id);
transport.emitMessage({ id: first.id, result: handshake("1.1", "1.0") });
transport.emitMessage({ id: first.id, result: handshake("1.1", "1.1") });
await Promise.resolve();
expect(controller.snapshot().state).not.toBe("connected");
transport.emitMessage({ id: second.id, result: handshake("1.1", "1.0") });
transport.emitMessage({ id: second.id, result: handshake("1.1", "1.1") });
await vi.waitFor(() => expect(controller.snapshot().state).toBe("connected"));
});
});
@@ -1,101 +0,0 @@
import { afterEach, describe, expect, it, vi } from "vitest";
import type { CdpRunner } from "@/tools/shared";
import { waitForDocumentSettled } from "../recording/document-settle";
function quietCdp(): { cdp: CdpRunner; send: ReturnType<typeof vi.fn> } {
const send = vi.fn(async () => ({
result: { value: { idleMs: 1_000, readyState: "complete" } },
}));
return {
cdp: { send: send as unknown as CdpRunner["send"] },
send,
};
}
describe("waitForDocumentSettled", () => {
afterEach(() => {
vi.useRealTimers();
});
it("waits through the minimum observation floor before accepting a quiet page", async () => {
vi.useFakeTimers();
const { cdp, send } = quietCdp();
const settled = waitForDocumentSettled(cdp, { target: { tabId: 7 } });
await vi.advanceTimersByTimeAsync(180);
await expect(settled).resolves.toBe("quiet");
expect(send).toHaveBeenCalledTimes(3);
});
it("cancels before probing a superseded observation", async () => {
vi.useFakeTimers();
const { cdp, send } = quietCdp();
const controller = new AbortController();
const settled = waitForDocumentSettled(
cdp,
{ target: { tabId: 7 } },
{
signal: controller.signal,
},
);
controller.abort();
await vi.advanceTimersByTimeAsync(60);
await expect(settled).resolves.toBe("cancelled");
expect(send).not.toHaveBeenCalled();
});
it("probes a same-process iframe through its isolated execution context", async () => {
vi.useFakeTimers();
const send = vi.fn(async (_tabId: number, method: string) => {
if (method === "Page.createIsolatedWorld") return { executionContextId: 91 };
return { result: { value: { idleMs: 1_000, readyState: "complete" } } };
});
const cdp: CdpRunner = { send: send as unknown as CdpRunner["send"] };
const settled = waitForDocumentSettled(cdp, {
target: { tabId: 7 },
frameId: "child-frame",
});
await vi.advanceTimersByTimeAsync(180);
await expect(settled).resolves.toBe("quiet");
expect(send).toHaveBeenCalledWith(
7,
"Page.createIsolatedWorld",
expect.objectContaining({ frameId: "child-frame" }),
);
expect(send).toHaveBeenCalledWith(
7,
"Runtime.evaluate",
expect.objectContaining({ contextId: 91 }),
);
});
it("routes an OOPIF probe through its CDP target session", async () => {
vi.useFakeTimers();
const send = vi.fn();
const sendToTarget = vi.fn(async (_target, method: string) => {
if (method === "Page.createIsolatedWorld") return { executionContextId: 27 };
return { result: { value: { idleMs: 1_000, readyState: "complete" } } };
});
const cdp: CdpRunner = {
send: send as unknown as CdpRunner["send"],
sendToTarget: sendToTarget as unknown as NonNullable<CdpRunner["sendToTarget"]>,
};
const target = { tabId: 7, sessionId: "oopif-session" };
const settled = waitForDocumentSettled(cdp, { target, frameId: "oopif-frame" });
await vi.advanceTimersByTimeAsync(180);
await expect(settled).resolves.toBe("quiet");
expect(send).not.toHaveBeenCalled();
expect(sendToTarget).toHaveBeenCalledWith(
target,
"Runtime.evaluate",
expect.objectContaining({ contextId: 27 }),
);
});
});
@@ -32,7 +32,6 @@ describe("help-bridge", () => {
prompt: "log in",
displayMode: "compact",
selectors: ["#login"],
rects: [{ top: 10, left: 20, width: 100, height: 40 }],
timeoutMs: 1000,
}),
).toBe(true);
@@ -0,0 +1,172 @@
import type { RenderedRef } from "@browser-skill/vom";
import { describe, expect, it } from "vitest";
import type { CapturedNode } from "@/tools/vom/capture";
import { matchTarget } from "../match-target";
function node(backendNodeId: number, overrides: Partial<CapturedNode> = {}): CapturedNode {
return {
backendNodeId,
parentBackendNodeId: null,
tag: "button",
attrs: {},
rect: { x: 10, y: 20, w: 100, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
...overrides,
};
}
describe("matchTarget", () => {
const refs: RenderedRef[] = [
{ ref: "e1", backendNodeId: 42, role: "button", name: "发布", line: 3 },
];
it("matches a unique node by viewport coordinates", () => {
const target = matchTarget({
geometry: {
rect: { x: 10, y: 20, w: 100, h: 30 },
scrollX: 0,
scrollY: 0,
position: "static",
tag: "button",
},
captured: [node(42)],
refs,
fallback: { tag: "button", name: "发布" },
});
expect(target).toEqual({ ref: "e1", role: "button", name: "发布" });
});
it("matches a non-fixed node after the top frame scrolls", () => {
const target = matchTarget({
geometry: {
rect: { x: 10, y: 20, w: 100, h: 30 },
scrollX: 40,
scrollY: 300,
position: "static",
tag: "button",
},
captured: [
node(42, {
documentRect: { x: 50, y: 320, w: 100, h: 30 },
localRect: { x: 10, y: 20, w: 100, h: 30 },
rect: { x: 10, y: 20, w: 100, h: 30 },
}),
],
refs,
fallback: { tag: "button", name: "发布" },
});
expect(target).toEqual({ ref: "e1", role: "button", name: "发布" });
});
it("matches a static node by document coordinates when scroll changed after observation", () => {
const target = matchTarget({
geometry: {
rect: { x: 10, y: 50, w: 100, h: 30 },
scrollX: 0,
scrollY: 250,
position: "static",
tag: "button",
},
captured: [
node(42, {
documentRect: { x: 10, y: 300, w: 100, h: 30 },
localRect: { x: 10, y: 200, w: 100, h: 30 },
rect: { x: 10, y: 200, w: 100, h: 30 },
}),
],
refs,
fallback: { tag: "button", name: "发布" },
});
expect(target).toEqual({ ref: "e1", role: "button", name: "发布" });
});
it("returns unmatched when multiple candidates match", () => {
const target = matchTarget({
geometry: {
rect: { x: 10, y: 20, w: 100, h: 30 },
scrollX: 0,
scrollY: 0,
position: "static",
tag: "button",
},
captured: [node(42), node(43)],
refs,
});
expect(target.unmatched).toBe(true);
});
it("uses viewport coordinates for fixed elements", () => {
const target = matchTarget({
geometry: {
rect: { x: 5, y: 5, w: 80, h: 24 },
scrollX: 100,
scrollY: 200,
position: "fixed",
tag: "button",
},
captured: [node(42, { position: "fixed", rect: { x: 5, y: 5, w: 80, h: 24 } })],
refs,
});
expect(target.ref).toBe("e1");
});
it("isolates geometry matching to the owner iframe backend node", () => {
const sharedRect = { x: 10, y: 20, w: 100, h: 30 };
const iframeRefs: RenderedRef[] = [
{ ref: "e1", backendNodeId: 42, role: "button", name: "Top", line: 1 },
{ ref: "e2", backendNodeId: 99, role: "button", name: "Iframe", line: 2 },
];
const target = matchTarget({
geometry: {
rect: sharedRect,
scrollX: 0,
scrollY: 0,
position: "static",
tag: "button",
ownerFrameBackendNodeId: 13,
},
captured: [
node(42, { rect: sharedRect, documentRect: sharedRect }),
node(99, {
rect: sharedRect,
documentRect: sharedRect,
ownerFrameBackendNodeId: 13,
}),
],
refs: iframeRefs,
fallback: { tag: "button", name: "Iframe" },
});
expect(target).toEqual({ ref: "e2", role: "button", name: "Iframe" });
});
it("matches iframe static elements using frame scroll and document coordinates", () => {
const iframeRefs: RenderedRef[] = [
{ ref: "e2", backendNodeId: 99, role: "button", name: "Iframe", line: 2 },
];
const target = matchTarget({
geometry: {
rect: { x: 10, y: 50, w: 100, h: 30 },
scrollX: 0,
scrollY: 120,
position: "static",
tag: "button",
ownerFrameBackendNodeId: 13,
},
captured: [
node(99, {
ownerFrameBackendNodeId: 13,
documentRect: { x: 10, y: 170, w: 100, h: 30 },
localRect: { x: 10, y: 50, w: 100, h: 30 },
rect: { x: 10, y: 50, w: 100, h: 30 },
}),
],
refs: iframeRefs,
fallback: { tag: "button", name: "Iframe" },
});
expect(target).toEqual({ ref: "e2", role: "button", name: "Iframe" });
});
});
@@ -1,32 +0,0 @@
import { describe, expect, it } from "vitest";
import {
isAcceptedRecordStepAck,
isRecordStepMessage,
RECORD_STEP,
type RecordStepMessage,
} from "../record-bridge";
const message: RecordStepMessage = {
type: RECORD_STEP,
requestId: "rec-1",
producerId: "document-1",
sequence: 1,
step: { op: "click", target: { tag: "button", name: "Submit" } },
};
describe("record step delivery protocol", () => {
it("requires a producer and a positive integer sequence", () => {
expect(isRecordStepMessage(message)).toBe(true);
expect(isRecordStepMessage({ ...message, producerId: "" })).toBe(false);
expect(isRecordStepMessage({ ...message, sequence: 0 })).toBe(false);
expect(isRecordStepMessage({ ...message, sequence: 1.5 })).toBe(false);
});
it("accepts only the acknowledgement for the sent sequence", () => {
expect(isAcceptedRecordStepAck({ ok: true, sequence: 2 }, 2)).toBe(true);
expect(isAcceptedRecordStepAck({ ok: true, sequence: 1 }, 2)).toBe(false);
expect(isAcceptedRecordStepAck({ ok: false, expectedSequence: 2, error: "gap" }, 2)).toBe(
false,
);
});
});
@@ -1,213 +0,0 @@
import { beforeEach, describe, expect, it, vi } from "vitest";
import { RECORD_FRAME_PORT, RECORD_FRAME_QUERY } from "../recording/frame-bridge";
import { RecordFrameCoordinator } from "../recording/frame-coordinator";
class ListenerSet<T extends (...args: never[]) => unknown> {
readonly listeners = new Set<T>();
addListener = (listener: T) => this.listeners.add(listener);
removeListener = (listener: T) => this.listeners.delete(listener);
}
function fakePort(sender: chrome.runtime.MessageSender) {
const messages: unknown[] = [];
const onMessage = new ListenerSet<(message: unknown) => void>();
const onDisconnect = new ListenerSet<() => void>();
return {
port: {
name: RECORD_FRAME_PORT,
sender,
onMessage,
onDisconnect,
postMessage: vi.fn((message: unknown) => messages.push(message)),
disconnect: vi.fn(),
} as unknown as chrome.runtime.Port,
messages,
receive(message: unknown) {
for (const listener of onMessage.listeners) listener(message);
},
};
}
describe("RecordFrameCoordinator", () => {
const onConnect = new ListenerSet<(port: chrome.runtime.Port) => void>();
const onMessage = new ListenerSet<
(
message: unknown,
sender: chrome.runtime.MessageSender,
sendResponse: (response: unknown) => void,
) => boolean
>();
beforeEach(() => {
onConnect.listeners.clear();
onMessage.listeners.clear();
vi.stubGlobal("chrome", {
runtime: { onConnect, onMessage },
});
});
it("answers child-document queries for the initial tab before it is armed", () => {
const coordinator = new RecordFrameCoordinator({
getAllFrames: async () => [],
sendToDocument: async () => ({ ok: true }),
});
coordinator.attach();
coordinator.begin("rec-1", 10, 3);
const query = (tabId: number) => {
let response: unknown;
for (const listener of onMessage.listeners) {
listener(
{ type: RECORD_FRAME_QUERY },
{
tab: { id: tabId },
frameId: 7,
documentId: "child-document",
} as chrome.runtime.MessageSender,
(value) => {
response = value;
},
);
}
return response;
};
expect(query(3)).toEqual({ active: true, requestId: "rec-1", startedAtMs: 10 });
expect(query(4)).toEqual({ active: false });
});
it("starts a child Document that appears after the initial frame snapshot", async () => {
let notifyFrameNavigation:
| ((frame: {
tabId: number;
frameId: number;
documentId?: string;
lifecycle: "committed" | "completed";
}) => void)
| undefined;
const sendToDocument = vi.fn(async () => ({ ok: true }));
const coordinator = new RecordFrameCoordinator({
getAllFrames: async () => [{ frameId: 0, documentId: "top-document" }],
sendToDocument,
subscribeFrameNavigation(listener) {
notifyFrameNavigation = listener;
return () => {};
},
});
coordinator.attach();
const onDocumentReady = vi.fn();
coordinator.begin("rec-1", 10, 3, onDocumentReady);
await coordinator.armTab("rec-1", 3);
sendToDocument.mockClear();
notifyFrameNavigation?.({
tabId: 3,
frameId: 7,
documentId: "late-child",
lifecycle: "completed",
});
await vi.waitFor(() => {
expect(sendToDocument).toHaveBeenCalledWith(
3,
{ type: "bsk-record-frame-start", requestId: "rec-1", startedAtMs: 10 },
{ documentId: "late-child" },
);
});
expect(onDocumentReady).not.toHaveBeenCalled();
const child = fakePort({
tab: { id: 3 },
frameId: 7,
documentId: "late-child",
} as chrome.runtime.MessageSender);
for (const listener of onConnect.listeners) listener(child.port);
child.receive({ type: "ready", requestId: "rec-1", producerId: "producer-1" });
notifyFrameNavigation?.({
tabId: 3,
frameId: 7,
documentId: "late-child",
lifecycle: "completed",
});
await vi.waitFor(() => {
expect(onDocumentReady).toHaveBeenCalledWith({
tabId: 3,
documentId: "late-child",
browserFrameId: 7,
producerId: "producer-1",
});
});
});
it("binds a producer to its sender Document and keeps final steps valid while stopping", async () => {
const sendToDocument = vi.fn(async () => ({ ok: true }));
const coordinator = new RecordFrameCoordinator({
getAllFrames: async () => [
{ frameId: 0, documentId: "top-document" },
{ frameId: 7, documentId: "child-document" },
],
sendToDocument,
});
coordinator.attach();
coordinator.begin("rec-1", 10, 3);
await expect(coordinator.armTab("rec-1", 3)).resolves.toBe(true);
const sender = {
tab: { id: 3 },
frameId: 7,
documentId: "child-document",
} as chrome.runtime.MessageSender;
const frame = fakePort(sender);
for (const listener of onConnect.listeners) listener(frame.port);
frame.receive({ type: "ready", requestId: "rec-1", producerId: "producer-1" });
expect(coordinator.sourceFor("rec-1", "producer-1", sender)).toEqual({
tabId: 3,
documentId: "child-document",
browserFrameId: 7,
producerId: "producer-1",
});
const stopping = coordinator.stop("rec-1");
expect(coordinator.sourceFor("rec-1", "producer-1", sender)).not.toBeNull();
const stop = frame.messages.find(
(message): message is { type: "stop"; commandId: string } =>
typeof message === "object" &&
message !== null &&
(message as { type?: string }).type === "stop",
);
expect(stop).toBeDefined();
frame.receive({
type: "stopped",
requestId: "rec-1",
commandId: stop!.commandId,
ok: true,
});
await expect(stopping).resolves.toBe(true);
expect(coordinator.sourceFor("rec-1", "producer-1", sender)).toBeNull();
});
it("rejects a producer used from another Document", async () => {
const coordinator = new RecordFrameCoordinator({
getAllFrames: async () => [{ frameId: 0, documentId: "top-document" }],
sendToDocument: async () => ({ ok: true }),
});
coordinator.attach();
coordinator.begin("rec-1", 10, 3);
await coordinator.armTab("rec-1", 3);
const sender = {
tab: { id: 3 },
frameId: 0,
documentId: "top-document",
} as chrome.runtime.MessageSender;
const frame = fakePort(sender);
for (const listener of onConnect.listeners) listener(frame.port);
frame.receive({ type: "ready", requestId: "rec-1", producerId: "producer-1" });
expect(
coordinator.sourceFor("rec-1", "producer-1", {
...sender,
documentId: "other-document",
}),
).toBeNull();
});
});
@@ -0,0 +1,116 @@
import { beforeEach, describe, expect, it } from "vitest";
import type { CapturedNode } from "@/tools/vom/capture";
import type { DraftTraceStep } from "@/transport/types";
import { resetStateIdCounterForTests } from "../record-constants";
import {
applyTargetMatching,
buildTraceV3,
createObservationState,
rememberStepOnPage,
} from "../record-observation";
import { registerObservation } from "../trace-reducer";
const URL = "https://example.com/login";
function capturedInput(): CapturedNode {
return {
backendNodeId: 42,
parentBackendNodeId: null,
tag: "input",
attrs: {},
rect: { x: 20, y: 40, w: 200, h: 30 },
localRect: { x: 20, y: 40, w: 200, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
};
}
function finalizedFillBody(value: string, redactValues: boolean): string {
const obs = createObservationState({ redactValues });
const rawVomText = '@vom 1\ntextbox "Password" value="••••••" [ref=e1]';
const stateId = registerObservation(obs.stateRegistry, { url: URL, rawVomText });
obs.lastSettled = {
stateId,
captured: [capturedInput()],
matchNodes: [capturedInput()],
documentTokenOwners: new Map(),
refs: [{ ref: "e1", backendNodeId: 42, role: "textbox", name: "Password", line: 1 }],
url: URL,
vomText: rawVomText,
};
const draft: DraftTraceStep = {
op: "fill",
target: { unmatched: true },
value,
geometry: {
rect: { x: 20, y: 40, w: 200, h: 30 },
scrollX: 0,
scrollY: 0,
position: "static",
tag: "input",
},
};
applyTargetMatching(obs, draft, 1);
draft.postStateId = stateId;
rememberStepOnPage(obs, draft, 1);
return (
buildTraceV3({
obs,
steps: [draft],
startedAt: "2026-08-12T00:00:00.000Z",
stoppedBy: "user_finish",
bskVersion: "test",
}).states[0]?.body ?? ""
);
}
describe("record observation annotations", () => {
beforeEach(() => {
resetStateIdCounterForTests();
});
it("omits a fill literal from finalized state bodies when values are redacted", () => {
const secret = "hunter2-private";
const body = finalizedFillBody(secret, true);
expect(body).toContain("step 1: fill");
expect(body).not.toContain(secret);
});
it("keeps fill details in ordinary recording annotations", () => {
const value = "ordinary text";
const body = finalizedFillBody(value, false);
expect(body).toContain(`step 1: fill: ${JSON.stringify(value)}`);
});
});
describe("applyTargetMatching without a settled observation", () => {
it("keeps the capture role/name instead of a bare unmatched target", () => {
const obs = createObservationState();
const draft: DraftTraceStep = {
op: "hover",
target: { unmatched: true },
captureTarget: { tag: "button", role: "button", name: "新建" },
geometry: {
rect: { x: 900, y: 8, w: 60, h: 32 },
scrollX: 0,
scrollY: 0,
position: "static",
tag: "button",
},
};
applyTargetMatching(obs, draft, 1);
expect(draft.preStateId).toBeUndefined();
expect(draft.target).toEqual({
role: "button",
name: "新建",
unmatched: true,
});
});
});
@@ -1,70 +0,0 @@
import { describe, expect, it } from "vitest";
import {
RECORD_DOCUMENT_ATTRIBUTE,
recordingDocumentMarkerValue,
} from "@/shared/recording-document-identity";
import { markRecordingDocument } from "../recording/document-marker";
import { ObservationNodeIndex } from "../recording/observation-capture";
describe("recording document marker", () => {
it("rejects a non-random Document identity", () => {
expect(() => markRecordingDocument("user@example.com")).toThrow(
"recording Document identity must be a random UUID",
);
});
it("restores the Document attribute exactly", () => {
document.documentElement.setAttribute(RECORD_DOCUMENT_ATTRIBUTE, "page-value");
const producerId = "123e4567-e89b-42d3-a456-426614174000";
const marker = markRecordingDocument(producerId);
expect(document.documentElement.getAttribute(RECORD_DOCUMENT_ATTRIBUTE)).toBe(
recordingDocumentMarkerValue(producerId),
);
marker.restore();
expect(document.documentElement.getAttribute(RECORD_DOCUMENT_ATTRIBUTE)).toBe("page-value");
document.documentElement.removeAttribute(RECORD_DOCUMENT_ATTRIBUTE);
});
it("indexes the CDP scope from the safe frame identity", () => {
const index = new ObservationNodeIndex({
rootFrameId: "root",
frames: [
{
frameId: "child",
target: { tabId: 3, sessionId: "oopif-session" },
recordingDocumentId: "producer-1",
},
],
matchNodes: [],
refs: [],
});
expect(index.documentScope("producer-1")).toEqual({
frameId: "child",
target: { tabId: 3, sessionId: "oopif-session" },
});
});
it("fails closed when a recording identity maps to multiple Documents", () => {
const index = new ObservationNodeIndex({
rootFrameId: "root",
frames: [
{
frameId: "left",
target: { tabId: 3, sessionId: "left-session" },
recordingDocumentId: "duplicate",
},
{
frameId: "right",
target: { tabId: 3, sessionId: "right-session" },
recordingDocumentId: "duplicate",
},
],
matchNodes: [],
refs: [],
});
expect(index.documentScope("duplicate")).toBeUndefined();
});
});
@@ -1,146 +0,0 @@
import { describe, expect, it } from "vitest";
import { ObservationNodeIndex } from "../recording/observation-capture";
import { RecordingObservationSession } from "../recording/observation-session";
import { RecordingStateRegistry } from "../recording/state-registry";
import { buildTraceV3 } from "../recording/trace-builder-v3";
import type { RecordingDraftStep } from "../recording/types";
const URL = "https://example.com/login";
function sessionWithInput(redactValues = false): RecordingObservationSession {
const session = new RecordingObservationSession({ redactValues });
const state = session.registry.register({
url: URL,
vomText: '@vom 1\ntextbox "Password" value="••••••" [ref=e1]',
});
session.cursor.lastSettled = {
stateId: state.id,
rootFrameId: "root",
index: new ObservationNodeIndex({
rootFrameId: "root",
matchNodes: [
{
frameId: "root",
backendNodeId: 42,
tag: "input",
rect: { x: 20, y: 40, w: 200, h: 30 },
localRect: { x: 20, y: 40, w: 200, h: 30 },
},
],
refs: [{ ref: "e1", backendNodeId: 42, role: "textbox", name: "Password", line: 1 }],
}),
url: URL,
};
return session;
}
function finalizedFillTrace(value: string, redactValues: boolean) {
const session = sessionWithInput(redactValues);
const draft: RecordingDraftStep = {
op: "fill",
captureTarget: { tag: "input", role: "textbox", name: "Password" },
value,
targetHint: {
geometry: { rect: { x: 20, y: 40, w: 200, h: 30 }, tag: "input" },
},
};
session.bindDraft(draft, 1);
draft.postStateId = draft.preStateId;
return buildTraceV3({
registry: session.registry,
drafts: [draft],
annotations: session.annotations,
startedAt: "2026-08-12T00:00:00.000Z",
stoppedBy: "user_finish",
bskVersion: "test",
redactValues,
});
}
function finalizedFillBody(value: string, redactValues: boolean): string {
return finalizedFillTrace(value, redactValues).states[0]!.body;
}
describe("record observation annotations", () => {
it("omits a fill literal when values are redacted", () => {
const secret = "hunter2-private";
const dumped = JSON.stringify(finalizedFillTrace(secret, true));
expect(dumped).toContain("step 1: fill");
expect(dumped).not.toContain(secret);
});
it("keeps ordinary fill details", () => {
expect(finalizedFillBody("ordinary text", false)).toContain('step 1: fill: "ordinary text"');
});
it("encodes title and URL so line breaks cannot corrupt state metadata", () => {
const registry = new RecordingStateRegistry();
const state = registry.register({
url: "https://example.com/a\nb",
title: "hello\nworld",
vomText: "@vom 1",
});
const trace = buildTraceV3({
registry,
drafts: [{ op: "scroll", preStateId: state.id, postStateId: state.id }],
startedAt: "2026-08-12T00:00:00.000Z",
stoppedBy: "user_finish",
bskVersion: "test",
});
expect(trace.states[0]?.body).toContain('url: "https://example.com/a\\nb"');
expect(trace.states[0]?.body).toContain('title: "hello\\nworld"');
});
});
describe("recording state ownership", () => {
it("deduplicates within one recording and isolates ids between recordings", () => {
const first = new RecordingStateRegistry();
const second = new RecordingStateRegistry();
expect(first.register({ url: URL, vomText: "same" }).id).toBe("s1");
expect(first.register({ url: URL, vomText: "same" }).id).toBe("s1");
expect(second.register({ url: URL, vomText: "other" }).id).toBe("s1");
});
it("enriches metadata when a deduplicated observation becomes more complete", () => {
const registry = new RecordingStateRegistry();
registry.register({ url: URL, vomText: "same" });
const state = registry.register({
url: URL,
title: "Login",
vomText: "same",
truncated: true,
});
expect(state).toMatchObject({ id: "s1", title: "Login", truncated: true });
});
});
describe("draft binding", () => {
it("keeps capture semantics when no observation exists", () => {
const session = new RecordingObservationSession();
const draft: RecordingDraftStep = {
op: "hover",
captureTarget: { tag: "button", role: "button", name: "新建" },
};
session.bindDraft(draft, 1);
expect(draft.matchedTarget).toEqual({ role: "button", name: "新建", unmatched: true });
expect(draft.preStateId).toBeUndefined();
});
it("does not bind an unmatched new action to a stale observation", () => {
const session = sessionWithInput();
const draft: RecordingDraftStep = {
op: "click",
captureTarget: { tag: "button", role: "button", name: "Confirm" },
targetHint: {
geometry: { rect: { x: 400, y: 300, w: 80, h: 30 }, tag: "button" },
},
};
session.bindDraft(draft, 2, true);
expect(draft.preStateId).toBeUndefined();
expect("matchedTarget" in draft ? draft.matchedTarget : undefined).toEqual({
role: "button",
name: "Confirm",
unmatched: true,
});
});
});
@@ -1,289 +0,0 @@
import { afterEach, describe, expect, it, vi } from "vitest";
import type { CdpRunner, ChromeTabsApi } from "@/tools/shared";
const captureRecordingObservation = vi.hoisted(() => vi.fn());
const waitForDocumentSettled = vi.hoisted(() => vi.fn(async () => "quiet" as const));
vi.mock("../recording/observation-capture", async (importOriginal) => {
const actual = await importOriginal<typeof import("../recording/observation-capture")>();
return { ...actual, captureRecordingObservation };
});
vi.mock("../recording/document-settle", async (importOriginal) => {
const actual = await importOriginal<typeof import("../recording/document-settle")>();
return { ...actual, waitForDocumentSettled };
});
import { ObservationNodeIndex } from "../recording/observation-capture";
import { RecordingObservationRuntime } from "../recording/recording-runtime";
import type { RecordingDraftStep } from "../recording/types";
function observation(url = "https://example.com/") {
return {
rootFrameId: "root",
index: new ObservationNodeIndex({ rootFrameId: "root", matchNodes: [], refs: [] }),
url,
title: "Example",
vomText: '@vom 1\nRootWebArea "Example"',
truncated: false,
};
}
function runtime(): RecordingObservationRuntime {
return new RecordingObservationRuntime({
cdp: { send: vi.fn() as unknown as CdpRunner["send"] },
tabsApi: { get: vi.fn(), query: vi.fn() } as unknown as ChromeTabsApi,
});
}
describe("RecordingObservationRuntime", () => {
afterEach(() => {
captureRecordingObservation.mockReset();
waitForDocumentSettled.mockClear();
});
it("shares one initial capture and includes it in flush", async () => {
let release!: (value: ReturnType<typeof observation>) => void;
captureRecordingObservation.mockReturnValueOnce(
new Promise((resolve) => {
release = resolve;
}),
);
const recording = runtime();
const first = recording.captureInitial(7);
const second = recording.captureInitial(7);
const flushed = recording.flush();
let flushCompleted = false;
void flushed.then(() => {
flushCompleted = true;
});
await Promise.resolve();
expect(captureRecordingObservation).toHaveBeenCalledTimes(1);
expect(flushCompleted).toBe(false);
release(observation());
await Promise.all([first, second, flushed]);
expect(flushCompleted).toBe(true);
});
it("cancels an in-flight initial capture", async () => {
captureRecordingObservation.mockImplementationOnce(
(input: { signal?: AbortSignal }) =>
new Promise((_, reject) => {
input.signal?.addEventListener(
"abort",
() => reject(new DOMException("observation aborted", "AbortError")),
{ once: true },
);
}),
);
const recording = runtime();
const pending = recording.captureInitial(7);
recording.cancel();
await expect(pending).rejects.toMatchObject({ name: "AbortError" });
});
it("retries a failed initial capture when the recording settles at stop", async () => {
captureRecordingObservation
.mockRejectedValueOnce(new Error("document swapped"))
.mockResolvedValueOnce(observation());
const recording = runtime();
await expect(recording.captureInitial(7)).rejects.toThrow("document swapped");
await recording.settleTrailing(7, []);
const trace = recording.buildTrace({
drafts: [],
startedAt: "2026-08-19T00:00:00.000Z",
stoppedBy: "user_finish",
bskVersion: "0.1.6",
});
expect(captureRecordingObservation).toHaveBeenCalledTimes(2);
expect(trace.states).toHaveLength(1);
});
it("keeps runtime matching data out of the serialized trace", async () => {
const captured = observation();
captured.index = new ObservationNodeIndex({
rootFrameId: "root",
matchNodes: [
{
frameId: "root",
backendNodeId: 42,
tag: "button",
rect: { x: 10, y: 20, w: 100, h: 30 },
localRect: { x: 10, y: 20, w: 100, h: 30 },
},
],
refs: [{ ref: "e1", backendNodeId: 42, role: "button", name: "Submit", line: 1 }],
});
captureRecordingObservation.mockResolvedValueOnce(captured);
const recording = runtime();
await recording.captureInitial(7);
const dumped = JSON.stringify(
recording.buildTrace({
drafts: [],
startedAt: "2026-08-19T00:00:00.000Z",
stoppedBy: "user_finish",
bskVersion: "0.1.6",
}),
);
expect(dumped).toContain("RootWebArea");
expect(dumped).not.toContain("matchNodes");
expect(dumped).not.toContain("localRect");
expect(dumped).not.toContain("backendNodeId");
expect(dumped).not.toContain("ObservationNodeIndex");
});
it("captures a tab transition without sharing observation cursors", async () => {
captureRecordingObservation
.mockResolvedValueOnce(observation("https://example.com/first"))
.mockResolvedValueOnce(observation("https://example.com/second"));
const recording = runtime();
await recording.captureInitial(4);
const transition = await recording.captureTabTransition(4, 5);
await recording.captureInitial(4);
await recording.captureInitial(5);
expect(transition).toEqual({
preStateId: "s1",
postStateId: "s2",
targetUrl: "https://example.com/second",
});
expect(captureRecordingObservation.mock.calls.map(([input]) => input.tabId)).toEqual([4, 5]);
});
it("binds an iframe draft to its marked CDP Document scope", async () => {
captureRecordingObservation.mockResolvedValueOnce({
...observation(),
index: new ObservationNodeIndex({
rootFrameId: "root",
frames: [
{
frameId: "child",
target: { tabId: 7, sessionId: "oopif-session" },
recordingDocumentId: "producer-1",
},
],
matchNodes: [
{
backendNodeId: 42,
frameId: "child",
tag: "button",
rect: { x: 410, y: 20, w: 100, h: 30 },
localRect: { x: 10, y: 20, w: 100, h: 30 },
},
],
refs: [{ ref: "e1", backendNodeId: 42, frameId: "child", line: 1 }],
}),
});
const recording = runtime();
const drafts: RecordingDraftStep[] = [
{
op: "click" as const,
captureTarget: { tag: "button", role: "button", name: "Save" },
targetHint: {
geometry: { rect: { x: 10, y: 20, w: 100, h: 30 }, tag: "button" },
},
},
];
await recording.captureInitial(7);
await recording.processDraft(7, drafts, 0, "producer-1");
recording.cancel();
const draft = drafts[0];
expect(draft?.op).toBe("click");
if (!draft || draft.op !== "click") throw new Error("expected click draft");
expect(draft.targetHint).toMatchObject({
frameId: "child",
geometrySpace: "local",
});
expect(draft.matchedTarget?.ref).toBe("e1");
});
it("refreshes a late iframe before matching its first action", async () => {
const iframeObservation = {
...observation(),
index: new ObservationNodeIndex({
rootFrameId: "root",
frames: [
{
frameId: "child",
target: { tabId: 7, sessionId: "oopif-session" },
recordingDocumentId: "producer-1",
},
],
matchNodes: [
{
backendNodeId: 42,
frameId: "child",
tag: "button",
rect: { x: 410, y: 20, w: 100, h: 30 },
localRect: { x: 10, y: 20, w: 100, h: 30 },
},
],
refs: [
{
ref: "e1",
backendNodeId: 42,
frameId: "child",
role: "button",
name: "表格视图",
line: 1,
},
],
}),
};
captureRecordingObservation
.mockResolvedValueOnce(observation())
.mockResolvedValueOnce(iframeObservation)
.mockResolvedValueOnce(iframeObservation);
const recording = runtime();
await recording.captureInitial(7);
await recording.refreshDocument(7, "producer-1");
const drafts: RecordingDraftStep[] = [
{
op: "click",
captureTarget: { tag: "button", role: "button", name: "表格视图" },
targetHint: {
geometry: { rect: { x: 10, y: 20, w: 100, h: 30 }, tag: "button" },
},
},
];
await recording.processDraft(7, drafts, 0, "producer-1");
recording.cancel();
expect(captureRecordingObservation).toHaveBeenCalledTimes(3);
expect(waitForDocumentSettled).toHaveBeenCalledWith(
expect.anything(),
{ frameId: "child", target: { tabId: 7, sessionId: "oopif-session" } },
{ signal: expect.any(AbortSignal) },
);
const draft = drafts[0];
expect(draft?.op).toBe("click");
if (!draft || draft.op !== "click") throw new Error("expected click draft");
expect(draft.matchedTarget).toMatchObject({ ref: "e1", name: "表格视图" });
});
it("does not poison final flush when a frame readiness refresh fails", async () => {
captureRecordingObservation
.mockResolvedValueOnce(observation())
.mockRejectedValueOnce(new Error("child Document replaced"));
const recording = runtime();
await recording.captureInitial(7);
await expect(recording.refreshDocument(7, "producer-1")).rejects.toThrow(
"child Document replaced",
);
await expect(recording.flush()).resolves.toBeUndefined();
});
});
@@ -1,9 +1,9 @@
import { describe, expect, it } from "vitest";
import { appendRecordedPayload, observeRecordedNavigation } from "../recording/step-buffer";
import { appendRecordedPayload, observeRecordedNavigation } from "../recording-step-buffer";
describe("recording-step-buffer", () => {
it("stores semantic click without summary", () => {
const buffer = { steps: [], navigation: { pendingNavigation: false } };
const buffer = { steps: [], pendingNavigation: false };
appendRecordedPayload(buffer, {
op: "click",
target: { tag: "button", role: "button", name: "发布" },
@@ -12,40 +12,37 @@ describe("recording-step-buffer", () => {
expect(buffer.steps).toEqual([
{
op: "click",
target: { unmatched: true },
captureTarget: { tag: "button", role: "button", name: "发布" },
},
]);
expect(buffer.navigation.pendingNavigation).toBe(true);
expect(buffer.pendingNavigation).toBe(true);
});
it("keeps the hovered element description as a capture fallback", () => {
const buffer = { steps: [], navigation: { pendingNavigation: false } };
appendRecordedPayload(
buffer,
{
op: "hover",
target: { tag: "button", role: "button", name: "新建" },
geometry: {
rect: { x: 900, y: 8, w: 60, h: 32 },
tag: "button",
},
const buffer = { steps: [], pendingNavigation: false };
appendRecordedPayload(buffer, {
op: "hover",
target: { tag: "button", role: "button", name: "新建" },
geometry: {
rect: { x: 900, y: 8, w: 60, h: 32 },
scrollX: 0,
scrollY: 0,
position: "static",
tag: "button",
},
{
geometry: {
rect: { x: 900, y: 8, w: 60, h: 32 },
tag: "button",
},
},
);
});
expect(buffer.steps).toEqual([
{
op: "hover",
target: { unmatched: true },
captureTarget: { tag: "button", role: "button", name: "新建" },
targetHint: {
geometry: {
rect: { x: 900, y: 8, w: 60, h: 32 },
tag: "button",
},
geometry: {
rect: { x: 900, y: 8, w: 60, h: 32 },
scrollX: 0,
scrollY: 0,
position: "static",
tag: "button",
},
},
]);
@@ -56,21 +53,19 @@ describe("recording-step-buffer", () => {
steps: [
{
op: "click" as const,
captureTarget: { tag: "button", role: "button", name: "发布" },
target: { tag: "button", role: "button", name: "发布" },
},
],
navigation: {
currentUrl: "https://example.com/a",
pendingNavigation: true,
pendingNavigationDeadline: Date.now() + 5_000,
},
currentUrl: "https://example.com/a",
pendingNavigation: true,
pendingNavigationDeadline: Date.now() + 5_000,
};
observeRecordedNavigation(buffer, "https://example.com/b", true);
expect(buffer.steps).toEqual([
{
op: "click",
captureTarget: { tag: "button", role: "button", name: "发布" },
navigatedTo: "https://example.com/b",
target: { tag: "button", role: "button", name: "发布" },
navigated_to: "https://example.com/b",
},
]);
expect(JSON.stringify(buffer.steps)).not.toContain("wait_for_navigation");
@@ -81,23 +76,21 @@ describe("recording-step-buffer", () => {
steps: [
{
op: "select" as const,
captureTarget: { tag: "select", role: "combobox", name: "分类" },
target: { tag: "select", role: "combobox", name: "分类" },
values: ["tech"],
},
],
navigation: {
currentUrl: "https://example.com/list",
pendingNavigation: true,
pendingNavigationDeadline: Date.now() + 5_000,
},
currentUrl: "https://example.com/list",
pendingNavigation: true,
pendingNavigationDeadline: Date.now() + 5_000,
};
observeRecordedNavigation(buffer, "https://example.com/list?cat=tech", true);
expect(buffer.steps).toEqual([
{
op: "select",
captureTarget: { tag: "select", role: "combobox", name: "分类" },
target: { tag: "select", role: "combobox", name: "分类" },
values: ["tech"],
navigatedTo: "https://example.com/list?cat=tech",
navigated_to: "https://example.com/list?cat=tech",
},
]);
});
@@ -105,7 +98,8 @@ describe("recording-step-buffer", () => {
it("emits navigate for uncaused URL changes", () => {
const buffer = {
steps: [],
navigation: { currentUrl: "https://example.com/a", pendingNavigation: false },
currentUrl: "https://example.com/a",
pendingNavigation: false,
};
const result = observeRecordedNavigation(buffer, "https://example.com/b", false);
expect(result).toEqual({ kind: "appended", index: 0 });
@@ -118,10 +112,8 @@ describe("recording-step-buffer", () => {
it("asks the recorder to coalesce redirect hops instead of emitting each one", () => {
const buffer = {
steps: [],
navigation: {
currentUrl: "https://passport.example/login",
pendingNavigation: false,
},
currentUrl: "https://passport.example/login",
pendingNavigation: false,
};
const hop1 = observeRecordedNavigation(
buffer,
@@ -144,21 +136,6 @@ describe("recording-step-buffer", () => {
url: "https://app.example/dashboard",
});
expect(buffer.steps).toEqual([]);
expect(buffer.navigation.currentUrl).toBe("https://app.example/dashboard");
});
it("does not reuse redirect metadata for a later content-observed URL change", () => {
const buffer = {
steps: [],
navigation: {
currentUrl: "https://example.com/redirect",
pendingNavigation: false,
},
};
const result = observeRecordedNavigation(buffer, "https://example.com/spa");
expect(result).toEqual({ kind: "appended", index: 0 });
expect(buffer.steps[0]).toMatchObject({ op: "navigate", url: "https://example.com/spa" });
expect(buffer.currentUrl).toBe("https://app.example/dashboard");
});
});
@@ -1,136 +0,0 @@
import { afterEach, describe, expect, it, vi } from "vitest";
import type { CdpRunner, ChromeTabsApi } from "@/tools/shared";
import { ObservationNodeIndex, type RegisteredObservation } from "../recording/observation-capture";
import { RecordingObservationSession } from "../recording/observation-session";
import { SettleController } from "../recording/settle-controller";
import type { RecordingDraftStep } from "../recording/types";
const OBSERVATION: RegisteredObservation = {
stateId: "s-next",
rootFrameId: "root",
index: new ObservationNodeIndex({ rootFrameId: "root", matchNodes: [], refs: [] }),
url: "https://example.com/next",
};
describe("SettleController", () => {
afterEach(() => vi.useRealTimers());
it("aborts superseded capture work and lands the prior action on the next origin", async () => {
vi.useFakeTimers();
const cdp: CdpRunner = {
send: vi.fn(async () => ({
result: { value: { idleMs: 1_000, readyState: "complete" } },
})) as unknown as CdpRunner["send"],
};
const tabsApi: ChromeTabsApi = {
get: vi.fn(async () => ({ id: 7, url: OBSERVATION.url }) as chrome.tabs.Tab),
query: vi.fn(async () => []),
};
const session = new RecordingObservationSession();
let firstSignal: AbortSignal | undefined;
vi.spyOn(session, "capture")
.mockImplementationOnce(async (_cdp, _tabs, _tabId, signal) => {
firstSignal = signal;
return new Promise<RegisteredObservation>((_resolve, reject) => {
signal?.addEventListener(
"abort",
() => reject(new DOMException("observation aborted", "AbortError")),
{ once: true },
);
});
})
.mockResolvedValueOnce(OBSERVATION);
const drafts: RecordingDraftStep[] = [
{ op: "click", captureTarget: { tag: "button", name: "First" }, preStateId: "s1" },
];
const controller = new SettleController({ session, cdp, tabsApi, tabId: 7 });
controller.schedule(drafts, 0);
await vi.advanceTimersByTimeAsync(180);
drafts.push({
op: "click",
captureTarget: { tag: "button", name: "Second" },
preStateId: "s-next",
});
controller.schedule(drafts, 1);
expect(firstSignal?.aborted).toBe(true);
expect(drafts[0]?.postStateId).toBe("s-next");
await vi.advanceTimersByTimeAsync(500);
await controller.flush();
expect(drafts[1]?.postStateId).toBe("s-next");
});
it("does not consume a newer redirect while reading the prior landing URL", async () => {
vi.useFakeTimers();
const cdp: CdpRunner = {
send: vi.fn(async () => ({
result: { value: { idleMs: 1_000, readyState: "complete" } },
})) as unknown as CdpRunner["send"],
};
let resolveFirstTab!: (tab: chrome.tabs.Tab) => void;
const firstTab = new Promise<chrome.tabs.Tab>((resolve) => {
resolveFirstTab = resolve;
});
const tabsApi: ChromeTabsApi = {
get: vi
.fn()
.mockImplementationOnce(() => firstTab)
.mockResolvedValue({ id: 7, url: OBSERVATION.url }),
query: vi.fn(async () => []),
};
const session = new RecordingObservationSession();
session.cursor.lastSettled = OBSERVATION;
const drafts: RecordingDraftStep[] = [];
const controller = new SettleController({ session, cdp, tabsApi, tabId: 7 });
controller.scheduleRedirect(drafts, "https://example.com/intermediate");
await vi.advanceTimersByTimeAsync(180);
expect(tabsApi.get).toHaveBeenCalledTimes(1);
controller.scheduleRedirect(drafts, OBSERVATION.url);
resolveFirstTab({ id: 7, url: "https://example.com/intermediate" } as chrome.tabs.Tab);
await vi.advanceTimersByTimeAsync(500);
await controller.flushRedirects();
expect(drafts).toEqual([]);
expect(controller.hasPending).toBe(false);
});
it("settles an action in its own OOPIF document scope", async () => {
vi.useFakeTimers();
const send = vi.fn();
const sendToTarget = vi.fn(async (_target, method: string) => {
if (method === "Page.createIsolatedWorld") return { executionContextId: 39 };
return { result: { value: { idleMs: 1_000, readyState: "complete" } } };
});
const cdp: CdpRunner = {
send: send as unknown as CdpRunner["send"],
sendToTarget: sendToTarget as unknown as NonNullable<CdpRunner["sendToTarget"]>,
};
const tabsApi: ChromeTabsApi = {
get: vi.fn(async () => ({ id: 7, url: OBSERVATION.url }) as chrome.tabs.Tab),
query: vi.fn(async () => []),
};
const session = new RecordingObservationSession();
vi.spyOn(session, "capture").mockResolvedValue(OBSERVATION);
const drafts: RecordingDraftStep[] = [
{ op: "click", captureTarget: { tag: "button", name: "Inside frame" } },
];
const controller = new SettleController({ session, cdp, tabsApi, tabId: 7 });
const target = { tabId: 7, sessionId: "oopif-session" };
controller.schedule(drafts, 0, { target, frameId: "oopif-frame" });
await vi.advanceTimersByTimeAsync(180);
await controller.flush();
expect(send).not.toHaveBeenCalled();
expect(sendToTarget).toHaveBeenCalledWith(
target,
"Runtime.evaluate",
expect.objectContaining({ contextId: 39 }),
);
expect(drafts[0]?.postStateId).toBe("s-next");
});
});
@@ -1,39 +0,0 @@
import { describe, expect, it } from "vitest";
import { RecordingTabCoordinator } from "../recording/tab-coordinator";
describe("RecordingTabCoordinator", () => {
it("keeps navigation state isolated per tab", () => {
const tabs = new RecordingTabCoordinator(4, "https://example.com/first");
const first = tabs.navigation(4);
first.pendingNavigation = true;
const second = tabs.navigation(5, "https://example.com/second");
expect(second).toEqual({
currentUrl: "https://example.com/second",
pendingNavigation: false,
});
expect(tabs.navigation(4)).toBe(first);
expect(tabs.navigation(4).pendingNavigation).toBe(true);
});
it("invalidates an earlier activation when a newer tab becomes active", () => {
const tabs = new RecordingTabCoordinator(4);
const second = tabs.noteActivation(5);
const third = tabs.noteActivation(6);
expect(tabs.isLatest(second)).toBe(false);
expect(tabs.isLatest(third)).toBe(true);
tabs.commit(6);
expect(tabs.currentTabId).toBe(6);
});
it("commits the freshly observed URL when returning to an existing tab", () => {
const tabs = new RecordingTabCoordinator(4);
tabs.navigation(5, "https://example.com/old");
tabs.commit(5, "https://example.com/new");
expect(tabs.currentTabId).toBe(5);
expect(tabs.navigation(5).currentUrl).toBe("https://example.com/new");
});
});
@@ -1,159 +0,0 @@
import type { RenderedRef } from "@browser-skill/vom";
import { describe, expect, it } from "vitest";
import type { CaptureVomMatchNode } from "@/tools/capture-vom-observation";
import { ObservationNodeIndex, type RegisteredObservation } from "../recording/observation-capture";
import { matchObservationTarget } from "../recording/target-matcher";
function node(backendNodeId: number, frameId: string, x = 10): CaptureVomMatchNode {
return {
backendNodeId,
frameId,
tag: "button",
rect: { x, y: 20, w: 100, h: 30 },
localRect: { x, y: 20, w: 100, h: 30 },
};
}
function observation(
matchNodes: CaptureVomMatchNode[],
refs: RenderedRef[],
): RegisteredObservation {
return {
stateId: "s1",
rootFrameId: "root",
index: new ObservationNodeIndex({ rootFrameId: "root", matchNodes, refs }),
url: "https://example.com",
};
}
describe("matchObservationTarget", () => {
it("indexes the safe geometry DTO without discarding frame-local geometry", () => {
const geometry = node(42, "child");
geometry.localRect = { x: 5, y: 6, w: 100, h: 30 };
const ref: RenderedRef = {
ref: "e1",
backendNodeId: 42,
frameId: "child",
line: 1,
};
const candidate = observation([geometry], [ref]).index.candidates("child", "button")[0];
expect(candidate).toEqual({ frameId: "child", geometry, ref });
});
it("matches a unique node using canonical top-level viewport geometry", () => {
const target = matchObservationTarget({
observation: observation(
[node(42, "root")],
[{ ref: "e1", backendNodeId: 42, role: "button", name: "发布", line: 1 }],
),
hint: { geometry: { rect: { x: 10, y: 20, w: 100, h: 30 }, tag: "button" } },
});
expect(target).toEqual({ ref: "e1", role: "button", name: "发布" });
});
it("uses frame id with backend node id so sibling frames cannot collide", () => {
const target = matchObservationTarget({
observation: observation(
[node(42, "left"), node(42, "right")],
[
{ ref: "e1", backendNodeId: 42, frameId: "left", line: 1 },
{ ref: "e2", backendNodeId: 42, frameId: "right", line: 2 },
],
),
hint: {
frameId: "right",
geometry: { rect: { x: 10, y: 20, w: 100, h: 30 }, tag: "button" },
},
});
expect(target.ref).toBe("e2");
});
it("matches iframe capture geometry in the child viewport coordinate space", () => {
const child = node(42, "child", 410);
child.localRect = { x: 10, y: 20, w: 100, h: 30 };
const target = matchObservationTarget({
observation: observation(
[child],
[{ ref: "e1", backendNodeId: 42, frameId: "child", line: 1 }],
),
hint: {
frameId: "child",
geometrySpace: "local",
geometry: { rect: { x: 10, y: 20, w: 100, h: 30 }, tag: "button" },
},
});
expect(target.ref).toBe("e1");
});
it("restricts a missing frame hint to the root frame", () => {
const target = matchObservationTarget({
observation: observation(
[node(42, "child")],
[{ ref: "e1", backendNodeId: 42, frameId: "child", line: 1 }],
),
hint: { geometry: { rect: { x: 10, y: 20, w: 100, h: 30 }, tag: "button" } },
fallback: { tag: "button", name: "发布" },
});
expect(target).toEqual({ name: "发布", unmatched: true });
});
it("fails closed when the source Document has no VOM frame mapping", () => {
const target = matchObservationTarget({
observation: observation(
[node(42, "root")],
[{ ref: "e1", backendNodeId: 42, role: "button", name: "发布", line: 1 }],
),
hint: {
frameId: null,
geometry: { rect: { x: 10, y: 20, w: 100, h: 30 }, tag: "button" },
},
fallback: { tag: "button", role: "button", name: "发布" },
});
expect(target).toEqual({ role: "button", name: "发布", unmatched: true });
});
it("returns unmatched for ambiguous geometry", () => {
const target = matchObservationTarget({
observation: observation(
[node(42, "root"), node(43, "root")],
[
{ ref: "e1", backendNodeId: 42, line: 1 },
{ ref: "e2", backendNodeId: 43, line: 2 },
],
),
hint: { geometry: { rect: { x: 10, y: 20, w: 100, h: 30 }, tag: "button" } },
});
expect(target.unmatched).toBe(true);
});
it("uses semantics when geometry is unavailable without crossing frame boundaries", () => {
const target = matchObservationTarget({
observation: observation(
[node(41, "root"), node(42, "child")],
[
{ ref: "e1", backendNodeId: 41, role: "button", name: "保存", line: 1 },
{ ref: "e2", backendNodeId: 42, frameId: "child", role: "button", name: "保存", line: 2 },
],
),
hint: { frameId: "child" },
fallback: { tag: "button", role: "button", name: "保存" },
});
expect(target.ref).toBe("e2");
});
it("uses semantics to disambiguate equal geometry in one frame", () => {
const target = matchObservationTarget({
observation: observation(
[node(42, "root"), node(43, "root")],
[
{ ref: "e1", backendNodeId: 42, role: "button", name: "保存", line: 1 },
{ ref: "e2", backendNodeId: 43, role: "button", name: "取消", line: 2 },
],
),
hint: { geometry: { rect: { x: 10, y: 20, w: 100, h: 30 }, tag: "button" } },
fallback: { tag: "button", role: "button", name: "取消" },
});
expect(target.ref).toBe("e2");
});
});
@@ -1,202 +0,0 @@
import { describe, expect, it } from "vitest";
import type { RecordingDraftStep } from "@/lib/recording/types";
import { shouldRecordPress } from "../recording/draft-policy";
import { buildTraceV2 } from "../recording/trace-reducer-v2";
function reduceTraceSteps(steps: RecordingDraftStep[], startUrl?: string) {
return buildTraceV2({
steps,
startedAt: "2026-01-01T00:00:00.000Z",
...(startUrl ? { startUrl } : {}),
});
}
describe("shouldRecordPress", () => {
it("keeps Enter and Escape", () => {
expect(shouldRecordPress("Enter")).toBe(true);
expect(shouldRecordPress("Escape")).toBe(true);
});
it("drops modifiers, clipboard shortcuts, and bare typing", () => {
expect(shouldRecordPress("Meta")).toBe(false);
expect(shouldRecordPress("c", ["meta"])).toBe(false);
expect(shouldRecordPress("a", ["ctrl"])).toBe(false);
expect(shouldRecordPress("x")).toBe(false);
expect(shouldRecordPress("中")).toBe(false);
});
});
describe("reduceTraceSteps", () => {
it("does not expose internal tab transitions in trace v2", () => {
const trace = reduceTraceSteps([
{
op: "switch_tab",
preStateId: "s1",
postStateId: "s2",
},
]);
expect(trace.steps).toEqual([]);
});
it("builds steps with pages dictionary and page id references", () => {
const drafts: RecordingDraftStep[] = [
{
op: "navigate",
url: "https://example.com/search?q=hello&utm_source=x",
pageUrl: "https://example.com/search?q=hello&utm_source=x",
},
{
op: "fill",
captureTarget: { tag: "input", role: "textbox", name: "搜索", name_attr: "q" },
value: "browser skill",
pageUrl: "https://example.com/search?q=hello&utm_source=x",
},
{
op: "press",
key: "Enter",
captureTarget: { tag: "input", role: "textbox", name: "搜索", name_attr: "q" },
navigatedTo: "https://example.com/results/42",
pageUrl: "https://example.com/search?q=hello&utm_source=x",
},
{
op: "click",
captureTarget: { tag: "button", role: "button", name: "发布" },
navigatedTo: "https://example.com/p/99",
pageUrl: "https://example.com/results/42",
},
{
op: "press",
key: "a",
pageUrl: "https://example.com/p/99",
},
];
const { pages, steps } = reduceTraceSteps(
drafts,
"https://example.com/search?q=hello&utm_source=x",
);
expect(JSON.stringify(steps)).not.toContain("parameters");
expect(JSON.stringify(steps)).not.toContain("intent");
expect(JSON.stringify(steps)).not.toContain("summary");
expect(steps.map((s) => s.op)).toEqual(["navigate", "fill", "press", "click"]);
expect(pages.map((p) => p.url)).toEqual([
"https://example.com/search?q=hello&utm_source=x",
"https://example.com/results/42",
"https://example.com/p/99",
]);
expect(steps[0]).toMatchObject({
id: 1,
op: "navigate",
page: "p1",
to: "https://example.com/search?q=hello&utm_source=x",
});
expect(steps[1]).toMatchObject({
op: "fill",
page: "p1",
value: "browser skill",
});
expect(steps[2]).toMatchObject({
op: "press",
key: "Enter",
page: "p1",
effect: { navigated_to: "p2" },
});
expect(steps[3]).toMatchObject({
op: "click",
page: "p2",
effect: { navigated_to: "p3" },
});
});
it("collapses consecutive navigations", () => {
const { steps } = reduceTraceSteps([
{ op: "navigate", url: "https://a.example/redirect1" },
{ op: "navigate", url: "https://a.example/final" },
]);
expect(steps).toHaveLength(1);
expect(steps[0]).toMatchObject({
op: "navigate",
to: "https://a.example/final",
});
});
it("keeps committed empty fill steps", () => {
const { steps } = reduceTraceSteps(
[
{
op: "fill",
captureTarget: { tag: "input", role: "textbox", name: "Search query" },
value: "",
pageUrl: "https://example.com/search",
},
],
"https://example.com/search",
);
expect(steps).toEqual([
expect.objectContaining({
op: "fill",
value: "",
}),
]);
});
it("maps select navigatedTo onto effect.navigatedTo (page id)", () => {
const { pages, steps } = reduceTraceSteps(
[
{
op: "select",
captureTarget: { tag: "select", role: "combobox", name: "分类" },
values: ["tech"],
labels: ["技术"],
navigatedTo: "https://example.com/list?cat=tech",
pageUrl: "https://example.com/list",
},
],
"https://example.com/list",
);
expect(pages.map((p) => p.url)).toEqual([
"https://example.com/list",
"https://example.com/list?cat=tech",
]);
expect(steps[0]).toMatchObject({
op: "select",
page: "p1",
selection: [{ value: "tech", label: "技术" }],
effect: { navigated_to: "p2" },
});
});
it("drops hover steps, which only exist in trace v3", () => {
const { steps } = reduceTraceSteps(
[
{
op: "hover",
captureTarget: { tag: "span", role: "button", name: "Account" },
pageUrl: "https://example.com/app",
},
{
op: "click",
captureTarget: { tag: "a", role: "link", name: "Profile" },
pageUrl: "https://example.com/app",
},
],
"https://example.com/app",
);
expect(steps.map((s) => s.op)).toEqual(["click"]);
});
it("resolveTraceStartUrl prefers explicit start URL", () => {
expect(
buildTraceV2({
steps: [{ op: "navigate", url: "https://example.com/other" }],
startedAt: "2026-01-01T00:00:00.000Z",
startUrl: "https://example.com/start",
}).entry.start_url,
).toBe("https://example.com/start");
});
});
@@ -1,132 +0,0 @@
import { describe, expect, it } from "vitest";
import { TRACE_VERSION_V3, VOM_FORMAT_VERSION } from "@/transport/types";
import { RecordingStateRegistry } from "../recording/state-registry";
import { buildTraceV3 } from "../recording/trace-builder-v3";
import { reduceTraceStepsV3 } from "../recording/trace-reducer-v3";
import type { RecordingDraftStep } from "../recording/types";
describe("trace reducer v3", () => {
it("removes form literals when value redaction is requested", () => {
const reduced = reduceTraceStepsV3(
[
{
op: "fill",
value: "private@example.com",
preStateId: "s1",
postStateId: "s1",
},
{
op: "select",
values: ["private-account-id"],
labels: ["Private account"],
preStateId: "s1",
postStateId: "s1",
},
],
{ redactValues: true },
);
expect(reduced.steps[0]).toMatchObject({ op: "fill", value: "***", redacted: true });
expect(reduced.steps[1]).toMatchObject({ op: "select" });
expect(reduced.steps[1]).not.toHaveProperty("selection");
expect(JSON.stringify(reduced.steps)).not.toContain("private@example.com");
expect(JSON.stringify(reduced.steps)).not.toContain("private-account-id");
});
it("emits tab transitions only for callers that advertised support", () => {
const drafts: RecordingDraftStep[] = [
{
op: "switch_tab",
preStateId: "s1",
postStateId: "s2",
},
];
expect(reduceTraceStepsV3(drafts).steps).toEqual([]);
expect(reduceTraceStepsV3(drafts, { includeTabSwitches: true }).steps).toEqual([
{ op: "switch_tab", id: 1, state: "s1", result: { state: "s2" } },
]);
});
it("keeps hover steps before menu clicks", () => {
const drafts: RecordingDraftStep[] = [
{
op: "hover",
captureTarget: { tag: "span", role: "button", name: "Account" },
preStateId: "s1",
postStateId: "s1",
},
{
op: "click",
captureTarget: { tag: "a", role: "link", name: "Profile" },
preStateId: "s1",
postStateId: "s1",
},
];
expect(reduceTraceStepsV3(drafts).steps.map((s) => s.op)).toEqual(["hover", "click"]);
});
it("does not export a tab transition without both observation endpoints", () => {
const sourceOnly: RecordingDraftStep = { op: "switch_tab", preStateId: "s1" };
const targetOnly: RecordingDraftStep = { op: "switch_tab", postStateId: "s2" };
expect(
reduceTraceStepsV3([sourceOnly, targetOnly], { includeTabSwitches: true }).steps,
).toEqual([]);
});
it("collapses redirect hops while retaining draft-to-step identity", () => {
const drafts: RecordingDraftStep[] = [
{ op: "navigate", url: "https://example.com/start", preStateId: "s1", postStateId: "s2" },
{
op: "navigate",
url: "https://example.com/final",
transitionQualifiers: ["server_redirect"],
preStateId: "s2",
postStateId: "s3",
},
];
const before = structuredClone(drafts);
const reduced = reduceTraceStepsV3(drafts);
expect(drafts).toEqual(before);
expect(reduced.steps).toEqual([
expect.objectContaining({
id: 1,
op: "navigate",
state: "s1",
to: "https://example.com/final",
result: { state: "s3" },
}),
]);
expect(reduced.stepIdByDraftId.get(1)).toBe(1);
expect(reduced.stepIdByDraftId.get(2)).toBe(1);
});
it("builds the wire model from protocol constants", () => {
const registry = new RecordingStateRegistry();
const state = registry.register({ url: "https://example.com", vomText: "@vom 1" });
const trace = buildTraceV3({
registry,
drafts: [
{
op: "click",
captureTarget: { tag: "button", role: "button", name: "Save" },
preStateId: state.id,
postStateId: state.id,
},
],
startedAt: "2026-08-12T00:00:00.000Z",
stoppedBy: "user_finish",
bskVersion: "test",
});
expect(trace.version).toBe(TRACE_VERSION_V3);
expect(trace.recorder.vom).toBe(VOM_FORMAT_VERSION);
expect(trace.steps[0]).toMatchObject({
op: "click",
target: { role: "button", name: "Save", unmatched: true },
});
});
});
@@ -0,0 +1,241 @@
import { describe, expect, it } from "vitest";
import { resetStateIdCounterForTests } from "@/lib/record-constants";
import {
reduceTraceSteps,
registerObservation,
resolveTraceStartUrl,
shouldRecordPress,
} from "../trace-reducer";
describe("shouldRecordPress", () => {
it("keeps Enter and Escape", () => {
expect(shouldRecordPress("Enter")).toBe(true);
expect(shouldRecordPress("Escape")).toBe(true);
});
it("drops modifiers, clipboard shortcuts, and bare typing", () => {
expect(shouldRecordPress("Meta")).toBe(false);
expect(shouldRecordPress("c", ["meta"])).toBe(false);
expect(shouldRecordPress("a", ["ctrl"])).toBe(false);
expect(shouldRecordPress("x")).toBe(false);
expect(shouldRecordPress("中")).toBe(false);
});
});
describe("reduceTraceSteps v3", () => {
it("builds steps with state/result references and deduped states", () => {
resetStateIdCounterForTests();
const registry = new Map();
const body = "@vom 1\nL1 page";
const s1 = registerObservation(registry, {
url: "https://example.com/search",
rawVomText: body,
});
const s2 = registerObservation(registry, {
url: "https://example.com/results/42",
rawVomText: "@vom 1\nL1 results",
});
const { states, steps } = reduceTraceSteps(
[
{
op: "navigate",
url: "https://example.com/search",
preStateId: s1,
postStateId: s1,
},
{
op: "fill",
target: { ref: "e1", role: "textbox", name: "搜索" },
value: "browser skill",
commit: "enter",
preStateId: s1,
postStateId: s1,
},
{
op: "press",
key: "Enter",
target: { ref: "e1", role: "textbox", name: "搜索" },
preStateId: s1,
postStateId: s2,
navigated_to: "https://example.com/results/42",
},
{
op: "click",
target: { ref: "e2", role: "button", name: "发布" },
preStateId: s2,
postStateId: s2,
},
],
registry,
);
expect(states).toHaveLength(2);
expect(steps.map((s) => s.op)).toEqual(["navigate", "fill", "press", "click"]);
expect(steps[1]).toMatchObject({
op: "fill",
state: s1,
result: { state: s1 },
commit: "enter",
});
expect(steps[2]).toMatchObject({
op: "press",
state: s1,
result: { state: s2 },
});
expect(JSON.stringify(steps)).not.toContain("page");
expect(JSON.stringify(steps)).not.toContain("effect");
});
it("collapses consecutive navigations", () => {
resetStateIdCounterForTests();
const registry = new Map();
const s1 = registerObservation(registry, {
url: "https://a.example/redirect1",
rawVomText: "a",
});
const { steps } = reduceTraceSteps(
[
{ op: "navigate", url: "https://a.example/redirect1", preStateId: s1, postStateId: s1 },
{ op: "navigate", url: "https://a.example/final", preStateId: s1, postStateId: s1 },
],
registry,
);
expect(steps).toHaveLength(1);
expect(steps[0]).toMatchObject({
op: "navigate",
to: "https://a.example/final",
});
});
it("keeps the origin state and cause of the hop that started a redirect chain", () => {
resetStateIdCounterForTests();
const registry = new Map();
const start = registerObservation(registry, {
url: "https://example.com/",
rawVomText: "start",
});
const hop = registerObservation(registry, {
url: "https://iwiki.woa.com/",
rawVomText: "hop",
});
const landing = registerObservation(registry, {
url: "https://iwiki.woa.com/dashboard",
rawVomText: "landing",
});
const { steps, stepIdByDraftId } = reduceTraceSteps(
[
{
op: "navigate",
url: "https://iwiki.woa.com/",
preStateId: start,
postStateId: hop,
transitionType: "typed",
},
{
op: "navigate",
url: "https://iwiki.woa.com/dashboard",
preStateId: hop,
postStateId: landing,
transitionType: "link",
},
],
registry,
);
expect(steps).toHaveLength(1);
expect(steps[0]).toMatchObject({
op: "navigate",
id: 1,
state: start,
result: { state: landing },
to: "https://iwiki.woa.com/dashboard",
cause: "user_typed",
});
// Both drafts fold into step 1, so anything tagged with either draft id
// must resolve to it.
expect(stepIdByDraftId.get(1)).toBe(1);
expect(stepIdByDraftId.get(2)).toBe(1);
});
it("maps draft ids to published step ids across dropped drafts", () => {
resetStateIdCounterForTests();
const registry = new Map();
const s1 = registerObservation(registry, { url: "https://a.example/", rawVomText: "a" });
const { steps, stepIdByDraftId } = reduceTraceSteps(
[
// Dropped: bare typing press.
{ op: "press", key: "a", preStateId: s1, postStateId: s1 },
{ op: "click", target: { ref: "e2" }, preStateId: s1, postStateId: s1 },
],
registry,
);
expect(steps.map((step) => step.op)).toEqual(["click"]);
expect(stepIdByDraftId.get(1)).toBeUndefined();
expect(stepIdByDraftId.get(2)).toBe(1);
});
it("keeps committed empty fills", () => {
resetStateIdCounterForTests();
const registry = new Map();
const s1 = registerObservation(registry, { url: "https://a.example/", rawVomText: "a" });
const { steps } = reduceTraceSteps(
[
{ op: "fill", target: { ref: "e1", role: "textbox", name: "Search" }, value: "", preStateId: s1, postStateId: s1 },
{ op: "click", target: { ref: "e2", role: "button", name: "Apply" }, preStateId: s1, postStateId: s1 },
],
registry,
);
expect(steps.map((step) => step.op)).toEqual(["fill", "click"]);
expect(steps[0]).toMatchObject({ op: "fill", value: "" });
});
it("keeps hover steps before menu clicks", () => {
resetStateIdCounterForTests();
const registry = new Map();
const state = registerObservation(registry, {
url: "https://example.com/app",
rawVomText: '@e1 button "Account"\n@e2 link "Profile"',
});
const { steps } = reduceTraceSteps(
[
{
op: "hover",
target: { ref: "e1", role: "button", name: "Account" },
page_url: "https://example.com/app",
preStateId: state,
postStateId: state,
},
{
op: "click",
target: { ref: "e2", role: "link", name: "Profile" },
page_url: "https://example.com/app",
preStateId: state,
postStateId: state,
},
],
registry,
);
expect(steps.map((s) => s.op)).toEqual(["hover", "click"]);
expect(steps[0]).toMatchObject({
op: "hover",
state,
result: { state },
target: { name: "Account" },
});
});
it("resolveTraceStartUrl prefers explicit start URL", () => {
expect(
resolveTraceStartUrl(
[{ op: "navigate", url: "https://example.com/other", preStateId: "s1", postStateId: "s1" }],
"https://example.com/start",
),
).toBe("https://example.com/start");
});
});
@@ -313,6 +313,15 @@ export type HandshakeVerdict =
| { kind: "version_skew" }
| { kind: "rejected"; reason: string };
const UPDATE_BOTH_VERSION_MESSAGE =
"The installed bsk CLI and BrowserSkill extension are incompatible. Update both, reload the extension, then run `bsk daemon restart`.";
const UPDATE_BSK_VERSION_MESSAGE =
"The installed bsk CLI is out of date for this BrowserSkill extension. Update bsk, then run `bsk daemon restart`.";
const UPDATE_EXTENSION_VERSION_MESSAGE =
"This BrowserSkill extension is out of date for the installed bsk CLI. Update and reload the extension, then try again.";
const INVALID_VERSION_MESSAGE =
"BrowserSkill could not verify version compatibility. Update bsk and the BrowserSkill extension, reload the extension, then run `bsk daemon restart`.";
/**
* Symmetric extension-side **protocol** compat check.
*
@@ -339,19 +348,19 @@ export function computeConnectedState(
if (daemonMajor === null || ourMajor === null || daemonMajor !== ourMajor) {
return {
kind: "rejected",
reason: `protocol-major mismatch (daemon protocol v${handshake.protocol_version}, extension protocol v${PROTOCOL_VERSION})`,
reason: UPDATE_BOTH_VERSION_MESSAGE,
};
}
if (compareProtocol(handshake.protocol_version, localMinCompatibleProtocol) === null) {
return {
kind: "rejected",
reason: `daemon protocol v${handshake.protocol_version} is unparseable`,
reason: INVALID_VERSION_MESSAGE,
};
}
if (compareProtocol(handshake.protocol_version, localMinCompatibleProtocol)! < 0) {
return {
kind: "rejected",
reason: `daemon protocol v${handshake.protocol_version} below extension min_compatible_protocol ${localMinCompatibleProtocol}`,
reason: UPDATE_BSK_VERSION_MESSAGE,
};
}
const peerFloor = handshake.min_compatible_protocol;
@@ -359,13 +368,13 @@ export function computeConnectedState(
if (compareProtocol(PROTOCOL_VERSION, peerFloor) === null) {
return {
kind: "rejected",
reason: `daemon min_compatible_protocol ${peerFloor} is unparseable`,
reason: INVALID_VERSION_MESSAGE,
};
}
if (compareProtocol(PROTOCOL_VERSION, peerFloor)! < 0) {
return {
kind: "rejected",
reason: `extension protocol v${PROTOCOL_VERSION} below daemon min_compatible_protocol ${peerFloor}`,
reason: UPDATE_EXTENSION_VERSION_MESSAGE,
};
}
}
+1 -1
View File
@@ -1,5 +1,5 @@
/**
* Build a semantic capture descriptor for an interacted element.
* Build a semantic TargetDescriptor for an interacted element.
*
* Trace steps are an LLM *textbook*: each click must say what to look for
* on screen (usually a short visible name). Tag-only noise like
@@ -0,0 +1,62 @@
import type { Step } from "@/transport/types";
import { OBSERVATION_FILE_VERSION } from "./record-constants";
export interface ObservationAnnotation {
stepId: number;
op: Step["op"];
line: number;
stateId: string;
detail?: string;
}
function formatAnnotation({ stepId, op, detail }: ObservationAnnotation): string {
const suffix = detail ? `: ${detail}` : "";
return ` ⟵ step ${stepId}: ${op}${suffix}`;
}
/** Serialize a page observation file (front matter + VOM body + step annotations). */
export function formatObservationFile(input: {
stateId: string;
url: string;
title?: string;
stepsHere: number[];
body: string;
annotations?: ObservationAnnotation[];
}): string {
const lines: string[] = [
`# bsk-observation ${OBSERVATION_FILE_VERSION}`,
`state: ${input.stateId}`,
`url: ${input.url}`,
];
if (input.title) lines.push(`title: ${input.title}`);
if (input.stepsHere.length > 0) {
lines.push(`steps_here: [${input.stepsHere.join(", ")}]`);
}
lines.push("---");
const bodyLines = input.body.split("\n");
const annotationMap = new Map<number, ObservationAnnotation[]>();
for (const ann of input.annotations ?? []) {
const bucket = annotationMap.get(ann.line) ?? [];
bucket.push(ann);
annotationMap.set(ann.line, bucket);
}
for (let i = 0; i < bodyLines.length; i += 1) {
let line = bodyLines[i] ?? "";
const anns = annotationMap.get(i);
if (anns) {
for (const ann of anns) {
line += formatAnnotation(ann);
}
}
lines.push(line);
}
return `${lines.join("\n")}\n`;
}
/** Hash input: VOM body **before** annotations are inserted. */
export function observationBodyForHash(vomText: string): string {
return vomText;
}
-19
View File
@@ -16,13 +16,6 @@ export const HELP_ACK = "bsk-help-ack";
export const HELP_QUERY = "bsk-help-query";
export const HELP_FINISH = "bsk-help-finish";
export interface HelpHighlightRect {
top: number;
left: number;
width: number;
height: number;
}
export interface HelpRequestMessage {
type: typeof HELP_REQUEST;
requestId: string;
@@ -33,8 +26,6 @@ export interface HelpRequestMessage {
displayMode?: "full" | "compact";
/** CSS selectors to scroll to + flash-highlight (may be empty). */
selectors: string[];
/** Top-viewport rectangles for targets that cannot be represented by a root selector. */
rects?: HelpHighlightRect[];
timeoutMs: number;
}
@@ -83,16 +74,6 @@ export function isHelpRequestMessage(msg: unknown): msg is HelpRequestMessage {
(m.displayMode === undefined || m.displayMode === "full" || m.displayMode === "compact") &&
Array.isArray(m.selectors) &&
m.selectors.every((selector) => typeof selector === "string") &&
(m.rects === undefined ||
(Array.isArray(m.rects) &&
m.rects.every(
(rect) =>
typeof rect === "object" &&
rect !== null &&
["top", "left", "width", "height"].every((key) =>
Number.isFinite((rect as Record<string, unknown>)[key]),
),
))) &&
typeof m.timeoutMs === "number"
);
}
+102
View File
@@ -0,0 +1,102 @@
import type { RenderedRef } from "@browser-skill/vom";
import type { CapturedNode } from "@/tools/vom/capture";
import type { CaptureGeometry, TargetDescriptor } from "@/transport/types";
import type { CaptureTargetDescriptor } from "./describe-target";
import { GEOM_MATCH_TOLERANCE_PX } from "./record-constants";
export interface MatchTargetInput {
geometry: CaptureGeometry;
captured: CapturedNode[];
refs: RenderedRef[];
fallback?: CaptureTargetDescriptor;
}
function withinTolerance(a: number, b: number): boolean {
return Math.abs(a - b) <= GEOM_MATCH_TOLERANCE_PX;
}
function rectsMatch(
a: { x: number; y: number; w: number; h: number },
b: { x: number; y: number; w: number; h: number },
): boolean {
return (
withinTolerance(a.x, b.x) &&
withinTolerance(a.y, b.y) &&
withinTolerance(a.w, b.w) &&
withinTolerance(a.h, b.h)
);
}
function nodeViewportRect(
node: CapturedNode,
): { x: number; y: number; w: number; h: number } | null {
return node.localRect ?? node.rect;
}
function matchingRects(
geometry: CaptureGeometry,
node: CapturedNode,
): {
target: { x: number; y: number; w: number; h: number };
node: { x: number; y: number; w: number; h: number } | null;
} {
const viewportPosition = geometry.position === "fixed" || geometry.position === "sticky";
if (viewportPosition || !node.documentRect) {
return { target: geometry.rect, node: nodeViewportRect(node) };
}
return {
target: {
x: geometry.rect.x + geometry.scrollX,
y: geometry.rect.y + geometry.scrollY,
w: geometry.rect.w,
h: geometry.rect.h,
},
node: node.documentRect,
};
}
function tagMatches(geometryTag: string, nodeTag: string): boolean {
return geometryTag.toLowerCase() === nodeTag.toLowerCase();
}
/** Best description available when the element cannot be located in the VOM. */
export function fallbackDescriptor(fallback?: CaptureTargetDescriptor): TargetDescriptor {
if (!fallback) {
return { unmatched: true };
}
return {
...(fallback.role ? { role: fallback.role } : {}),
...(fallback.name ? { name: fallback.name } : {}),
unmatched: true,
};
}
/** Locate the interacted element in the last settled observation by geometry. */
export function matchTarget(input: MatchTargetInput): TargetDescriptor {
const ownerFrame = input.geometry.ownerFrameBackendNodeId ?? null;
const candidates = input.captured.filter((node) => {
if (ownerFrame !== (node.ownerFrameBackendNodeId ?? null)) return false;
if (!tagMatches(input.geometry.tag, node.tag)) return false;
const rects = matchingRects(input.geometry, node);
if (!rects.node) return false;
return rectsMatch(rects.target, rects.node);
});
if (candidates.length !== 1) {
return fallbackDescriptor(input.fallback);
}
const backendNodeId = candidates[0]!.backendNodeId;
const refEntry = input.refs.find((r) => r.backendNodeId === backendNodeId);
if (!refEntry) {
return fallbackDescriptor(input.fallback);
}
return {
ref: refEntry.ref,
...(refEntry.role ? { role: refEntry.role } : {}),
...(refEntry.name ? { name: refEntry.name } : {}),
...(refEntry.ctx ? { ctx: refEntry.ctx } : {}),
};
}
+92
View File
@@ -0,0 +1,92 @@
// Deciding *when* a page is worth observing.
//
// A fixed delay cannot serve both a modal that toggles in one frame and a
// route change that renders for a second. Instead of guessing, ask the page:
// a document that has stopped mutating and is no longer loading is done
// reacting to whatever the user just did.
import type { CdpRunner } from "@/tools/shared";
import { SETTLE_MAX_MS, SETTLE_MIN_MS, SETTLE_POLL_MS, SETTLE_QUIET_MS } from "./record-constants";
/**
* Installed once per document. Records only the timestamp of the last DOM
* change so each poll stays O(1) no matter how large the page is.
*/
const QUIET_PROBE = `(() => {
const scope = window;
let probe = scope.__bskRecordQuiet;
if (!probe) {
probe = { changedAt: Date.now() };
const observer = new MutationObserver(() => {
probe.changedAt = Date.now();
});
observer.observe(document.documentElement, {
subtree: true,
childList: true,
attributes: true,
characterData: true,
});
scope.__bskRecordQuiet = probe;
}
return { idleMs: Date.now() - probe.changedAt, readyState: document.readyState };
})()`;
export type SettleOutcome =
/** The page stopped changing on its own. */
| "quiet"
/** Still changing when the budget ran out; observe it as it is. */
| "timeout"
/** A newer action took over; this observation is no longer wanted. */
| "cancelled";
interface QuietProbe {
idleMs: number;
readyState: string;
}
function sleep(ms: number): Promise<void> {
return new Promise((resolve) => setTimeout(resolve, ms));
}
async function readQuietProbe(cdp: CdpRunner, tabId: number): Promise<QuietProbe | null> {
try {
const reply = await cdp.send<{ result?: { value?: unknown } }>(tabId, "Runtime.evaluate", {
expression: QUIET_PROBE,
returnByValue: true,
});
const value = reply.result?.value;
if (!value || typeof value !== "object") return null;
const { idleMs, readyState } = value as { idleMs?: unknown; readyState?: unknown };
if (typeof idleMs !== "number" || typeof readyState !== "string") return null;
return { idleMs, readyState };
} catch {
// An unreadable page is a page mid-swap; that is a reason to keep waiting,
// not a reason to give up.
return null;
}
}
/** Wait until the page has finished reacting, or until the budget runs out. */
export async function waitForPageSettled(
cdp: CdpRunner,
tabId: number,
options: { cancelled?: () => boolean } = {},
): Promise<SettleOutcome> {
const startedAt = Date.now();
const floor = startedAt + SETTLE_MIN_MS;
const deadline = startedAt + SETTLE_MAX_MS;
for (;;) {
if (options.cancelled?.()) return "cancelled";
await sleep(SETTLE_POLL_MS);
if (options.cancelled?.()) return "cancelled";
const probe = await readQuietProbe(cdp, tabId);
const now = Date.now();
if (now < floor) continue;
if (now >= deadline) return "timeout";
if (!probe) continue;
if (probe.readyState === "loading") continue;
if (probe.idleMs >= SETTLE_QUIET_MS) return "quiet";
}
}
+40 -31
View File
@@ -4,6 +4,7 @@
*/
import type { CaptureTargetDescriptor } from "./describe-target";
import type { FrameCaptureFailure, FrameCaptureStatus } from "@/transport/types";
export const RECORD_START = "bsk-record-start";
export const RECORD_STEP = "bsk-record-step";
@@ -11,15 +12,12 @@ export const RECORD_STOP = "bsk-record-stop";
export const RECORD_CANCEL = "bsk-record-cancel";
export const RECORD_FINISH = "bsk-record-finish";
export const RECORD_QUERY = "bsk-record-query";
export const RECORD_CAPTURE_STATUS = "bsk-record-capture-status";
export interface RecordStartAck {
ok: true;
}
export type RecordStepAck =
| { ok: true; sequence: number }
| { ok: false; expectedSequence: number; error: string };
export type RecordStopAck = { ok: true } | { ok: false; error: string };
export interface RecordQueryMessage {
@@ -31,8 +29,12 @@ export interface RecordQueryResponse {
requestId?: string;
/** Epoch ms when the recording began; see `RecordStartMessage.startedAtMs`. */
startedAtMs?: number;
captureStatus?: FrameCaptureStatus;
captureFailures?: FrameCaptureFailure[];
}
export type RecordFrameMode = "top" | "child";
export interface RecordStartMessage {
type: typeof RECORD_START;
requestId: string;
@@ -42,10 +44,14 @@ export interface RecordStartMessage {
* content-script remounts instead of restarting per page.
*/
startedAtMs?: number;
/** When true, the top-frame overlay should mount. Child frames omit this. */
showOverlay?: boolean;
/** Whether this document runs top-frame or child-frame capture semantics. */
frameMode?: RecordFrameMode;
}
export interface RecordStepPayload {
op: "click" | "hover" | "fill" | "press" | "select" | "navigate";
op: "click" | "hover" | "fill" | "press" | "select" | "navigate" | "scroll";
target?: CaptureTargetDescriptor;
value?: string;
key?: string;
@@ -55,12 +61,22 @@ export interface RecordStepPayload {
url?: string;
redacted?: boolean;
commit?: "enter" | "suggestion" | "blur";
/** Page URL when the step was captured. */
/** Top-level tab URL when the step was captured. */
page_url?: string;
/** Event-target bounds in the source frame's viewport coordinate space. */
/** URL of the frame document where the interaction occurred. */
frame_url?: string;
/** Ephemeral token stamped on the active document root; not persisted in trace steps. */
documentToken?: string;
/** Epoch ms when the step was captured in the content script. */
capturedAtMs?: number;
/** Document geometry at capture time for background geometric matching. */
geometry?: {
rect: { x: number; y: number; w: number; h: number };
scrollX: number;
scrollY: number;
position: string;
tag: string;
ownerFrameBackendNodeId?: number | null;
};
/** Capture-only hint; never persisted unless converted to navigated_to. */
expects_navigation?: boolean;
@@ -74,10 +90,6 @@ export interface RecordStepPayload {
export interface RecordStepMessage {
type: typeof RECORD_STEP;
requestId: string;
/** Stable for the lifetime of one content-script document. */
producerId: string;
/** Monotonic within one content-script producer and recording request. */
sequence: number;
step: RecordStepPayload;
}
@@ -96,6 +108,12 @@ export interface RecordFinishMessage {
requestId: string;
}
export interface RecordCaptureStatusMessage {
type: typeof RECORD_CAPTURE_STATUS;
status: FrameCaptureStatus;
failures?: FrameCaptureFailure[];
}
export function isRecordStartMessage(msg: unknown): msg is RecordStartMessage {
if (typeof msg !== "object" || msg === null) return false;
const m = msg as Record<string, unknown>;
@@ -126,30 +144,21 @@ export function isRecordQueryMessage(msg: unknown): msg is RecordQueryMessage {
return m.type === RECORD_QUERY;
}
export function isRecordCaptureStatusMessage(msg: unknown): msg is RecordCaptureStatusMessage {
if (typeof msg !== "object" || msg === null) return false;
const m = msg as Record<string, unknown>;
return (
m.type === RECORD_CAPTURE_STATUS &&
(m.status === "complete" || m.status === "partial") &&
(m.failures === undefined || Array.isArray(m.failures))
);
}
export function isRecordStepMessage(msg: unknown): msg is RecordStepMessage {
if (typeof msg !== "object" || msg === null) return false;
const m = msg as Record<string, unknown>;
if (
m.type !== RECORD_STEP ||
typeof m.requestId !== "string" ||
typeof m.producerId !== "string" ||
m.producerId.length === 0 ||
typeof m.sequence !== "number" ||
!Number.isSafeInteger(m.sequence) ||
m.sequence < 1
) {
return false;
}
if (m.type !== RECORD_STEP || typeof m.requestId !== "string") return false;
const step = m.step;
if (typeof step !== "object" || step === null) return false;
return typeof (step as RecordStepPayload).op === "string";
}
export function isAcceptedRecordStepAck(
value: unknown,
sequence: number,
): value is Extract<RecordStepAck, { ok: true }> {
if (typeof value !== "object" || value === null) return false;
const ack = value as Partial<RecordStepAck>;
return ack.ok === true && ack.sequence === sequence;
}
@@ -0,0 +1,97 @@
import type { FillCommit, NavigationCause } from "@/transport/types";
/**
* Floor before a post-action observation may be taken. A page usually has not
* started reacting in the first frames after an action, and capturing then
* would record the page as it was, not as the action left it.
*/
export const SETTLE_MIN_MS = 150;
/** How long the DOM must stop changing before a page counts as settled. */
export const SETTLE_QUIET_MS = 250;
/** Upper bound on waiting for a page to settle; animations never stop. */
export const SETTLE_MAX_MS = 2_000;
/** How often to ask the page whether it has gone quiet. */
export const SETTLE_POLL_MS = 60;
/** Minimum interval between consecutive observations on the same tab. */
export const OBSERVATION_MIN_INTERVAL_MS = 200;
/** Delay before retrying a capture that lost its execution context. */
export const CAPTURE_RETRY_DELAY_MS = 250;
/** Document-coordinate matching tolerance in CSS pixels. */
export const GEOM_MATCH_TOLERANCE_PX = 2;
/** Default max tokens per page observation when CLI omits `--max-page-tokens`. */
export const DEFAULT_MAX_PAGE_TOKENS = 3000;
/** VOM observation file format version (front matter header). */
export const OBSERVATION_FILE_VERSION = 1;
/** FNV-1a 64-bit offset basis. */
const FNV_OFFSET = 0xcbf29ce484222325n;
/** FNV-1a 64-bit prime. */
const FNV_PRIME = 0x100000001b3n;
/** Content-hash for state deduplication (sync, non-cryptographic). */
export function fnv1a64(text: string): string {
let hash = FNV_OFFSET;
for (let i = 0; i < text.length; i += 1) {
hash ^= BigInt(text.charCodeAt(i));
hash = (hash * FNV_PRIME) & 0xffffffffffffffffn;
}
return hash.toString(16).padStart(16, "0");
}
let nextStateSerial = 0;
/** Monotonic state id generator (`s1`, `s2`, …). */
export function nextStateId(): string {
nextStateSerial += 1;
return `s${nextStateSerial}`;
}
/** Test seam: reset the state id counter. */
export function resetStateIdCounterForTests(): void {
nextStateSerial = 0;
}
const REDIRECT_QUALIFIERS = new Set(["client_redirect", "server_redirect"]);
const TRANSITION_TO_CAUSE: Record<string, NavigationCause> = {
typed: "user_typed",
generated: "user_typed",
keyword: "user_typed",
keyword_generated: "user_typed",
link: "link",
form_submit: "form_submit",
reload: "reload",
auto_bookmark: "browser",
start_page: "browser",
};
export interface NavigationTransitionMeta {
transitionType?: string;
transitionQualifiers?: string[];
navigationActionPending?: boolean;
}
/** Map webNavigation metadata to protocol `NavigationCause`. Returns null for redirects. */
export function mapNavigationCause(meta: NavigationTransitionMeta): NavigationCause | null {
const qualifiers = meta.transitionQualifiers ?? [];
if (qualifiers.includes("forward_back")) return "history";
if (qualifiers.some((q) => REDIRECT_QUALIFIERS.has(q))) return null;
if (qualifiers.includes("from_address_bar")) return "user_typed";
const type = meta.transitionType ?? "";
const mapped = TRANSITION_TO_CAUSE[type];
if (mapped) return mapped;
if (!type && meta.navigationActionPending === false) return "script";
return "browser";
}
export const DEFAULT_FILL_COMMIT: FillCommit = "blur";
@@ -0,0 +1,24 @@
/** Attribute written on `<html>` while a document is actively recording. */
export const RECORD_DOCUMENT_TOKEN_ATTR = "data-bsk-record-document";
export function createRecordDocumentToken(): string {
if (typeof crypto !== "undefined" && typeof crypto.randomUUID === "function") {
return crypto.randomUUID();
}
return `doc-${Date.now().toString(36)}-${Math.random().toString(36).slice(2, 10)}`;
}
export function stampRecordDocumentToken(token: string): void {
document.documentElement.setAttribute(RECORD_DOCUMENT_TOKEN_ATTR, token);
}
export function clearRecordDocumentToken(): void {
document.documentElement.removeAttribute(RECORD_DOCUMENT_TOKEN_ATTR);
}
export function readRecordDocumentTokenFromAttrs(
attrs: Record<string, string> | undefined,
): string | undefined {
const token = attrs?.[RECORD_DOCUMENT_TOKEN_ATTR];
return token?.trim() ? token : undefined;
}
@@ -0,0 +1,250 @@
import {
RECORD_CANCEL,
RECORD_START,
RECORD_STOP,
type RecordCancelMessage,
type RecordStartAck,
type RecordStartMessage,
type RecordStopAck,
type RecordStopMessage,
} from "@/lib/record-bridge";
import type { FrameCaptureFailure, FrameCaptureFailureReason } from "@/transport/types";
export interface WebNavigationFrameInfo {
frameId: number;
documentId?: string;
url?: string;
parentFrameId: number;
}
export interface ArmedDocument {
tabId: number;
frameId: number;
documentId: string;
url?: string;
parentFrameId: number;
}
export interface RecordFrameSendDeps {
sendToDocument(
tabId: number,
documentId: string,
msg: RecordStartMessage | RecordStopMessage | RecordCancelMessage,
): Promise<unknown>;
getAllFrames(tabId: number): Promise<WebNavigationFrameInfo[]>;
}
const RECORD_START_RETRIES = 3;
const RECORD_START_RETRY_DELAY_MS = 500;
function sleep(ms: number): Promise<void> {
return new Promise((resolve) => setTimeout(resolve, ms));
}
export function isFrameUrlRestricted(url: string | undefined): boolean {
if (!url) return false;
const lower = url.toLowerCase();
return (
lower.startsWith("chrome://") ||
lower.startsWith("chrome-extension://") ||
lower.startsWith("edge://") ||
lower.startsWith("devtools://") ||
lower.startsWith("devtools:") ||
lower.startsWith("https://chrome.google.com/webstore")
);
}
function isRecordStartAck(response: unknown): response is RecordStartAck {
return (
typeof response === "object" &&
response !== null &&
"ok" in response &&
(response as RecordStartAck).ok === true
);
}
function isRecordStopAckOk(response: unknown): boolean {
return (
typeof response === "object" &&
response !== null &&
"ok" in response &&
(response as RecordStopAck).ok === true
);
}
export function makeFrameCaptureFailure(
reason: FrameCaptureFailureReason,
input: { frameId: number; documentId?: string; url?: string; detail?: string },
): FrameCaptureFailure {
return {
reason,
frame_id: input.frameId,
...(input.documentId ? { document_id: input.documentId } : {}),
...(input.url ? { url: input.url } : {}),
...(input.detail ? { detail: input.detail } : {}),
};
}
export async function listInjectableFrames(
tabId: number,
deps: RecordFrameSendDeps,
): Promise<{ injectable: WebNavigationFrameInfo[]; failures: FrameCaptureFailure[] }> {
const failures: FrameCaptureFailure[] = [];
let frames: WebNavigationFrameInfo[] = [];
try {
frames = await deps.getAllFrames(tabId);
} catch (err) {
failures.push(
makeFrameCaptureFailure("arm_failed", {
frameId: 0,
detail: err instanceof Error ? err.message : "webNavigation.getAllFrames failed",
}),
);
return { injectable: [], failures };
}
const injectable = frames.filter((frame) => {
if (!frame.documentId) {
failures.push(
makeFrameCaptureFailure("not_injectable", {
frameId: frame.frameId,
url: frame.url,
detail: "missing documentId",
}),
);
return false;
}
if (isFrameUrlRestricted(frame.url)) {
failures.push(
makeFrameCaptureFailure("not_injectable", {
frameId: frame.frameId,
documentId: frame.documentId,
url: frame.url,
}),
);
return false;
}
return true;
});
return { injectable, failures };
}
export async function sendRecordStartWithAckToDocument(
tabId: number,
documentId: string,
msg: RecordStartMessage,
deps: RecordFrameSendDeps,
): Promise<void> {
let lastError: unknown;
for (let attempt = 0; attempt < RECORD_START_RETRIES; attempt += 1) {
try {
const response = await deps.sendToDocument(tabId, documentId, msg);
if (isRecordStartAck(response)) return;
lastError = new Error("content script did not ack RECORD_START");
} catch (err) {
lastError = err;
}
if (attempt + 1 < RECORD_START_RETRIES) {
await sleep(RECORD_START_RETRY_DELAY_MS);
}
}
throw lastError ?? new Error("failed to start recording in content script");
}
export async function armDocumentCapture(
tabId: number,
frame: WebNavigationFrameInfo,
startMsg: RecordStartMessage,
deps: RecordFrameSendDeps,
): Promise<{ armed?: ArmedDocument; failure?: FrameCaptureFailure }> {
if (!frame.documentId) {
return {
failure: makeFrameCaptureFailure("not_injectable", {
frameId: frame.frameId,
url: frame.url,
detail: "missing documentId",
}),
};
}
if (isFrameUrlRestricted(frame.url)) {
return {
failure: makeFrameCaptureFailure("not_injectable", {
frameId: frame.frameId,
documentId: frame.documentId,
url: frame.url,
}),
};
}
try {
await sendRecordStartWithAckToDocument(tabId, frame.documentId, startMsg, deps);
return {
armed: {
tabId,
frameId: frame.frameId,
documentId: frame.documentId,
url: frame.url,
parentFrameId: frame.parentFrameId,
},
};
} catch (err) {
return {
failure: makeFrameCaptureFailure("arm_failed", {
frameId: frame.frameId,
documentId: frame.documentId,
url: frame.url,
detail: err instanceof Error ? err.message : "RECORD_START failed",
}),
};
}
}
export async function armAllDocumentsForTab(
tabId: number,
startMsg: RecordStartMessage,
deps: RecordFrameSendDeps,
): Promise<{ armed: ArmedDocument[]; failures: FrameCaptureFailure[] }> {
const { injectable, failures } = await listInjectableFrames(tabId, deps);
const armed: ArmedDocument[] = [];
for (const frame of injectable) {
const result = await armDocumentCapture(tabId, frame, startMsg, deps);
if (result.armed) armed.push(result.armed);
if (result.failure) failures.push(result.failure);
}
return { armed, failures };
}
export async function stopDocumentCapture(
armed: ArmedDocument,
stopMsg: RecordStopMessage,
deps: RecordFrameSendDeps,
): Promise<{ ok: true } | FrameCaptureFailure> {
try {
const response = await deps.sendToDocument(armed.tabId, armed.documentId, stopMsg);
if (isRecordStopAckOk(response)) return { ok: true };
return makeFrameCaptureFailure("flush_failed", {
frameId: armed.frameId,
documentId: armed.documentId,
url: armed.url,
detail: "content script did not confirm recorded steps",
});
} catch (err) {
return makeFrameCaptureFailure("flush_failed", {
frameId: armed.frameId,
documentId: armed.documentId,
url: armed.url,
detail: err instanceof Error ? err.message : "RECORD_STOP failed",
});
}
}
export async function cancelDocumentCapture(
armed: ArmedDocument,
cancelMsg: RecordCancelMessage,
deps: RecordFrameSendDeps,
): Promise<void> {
try {
await deps.sendToDocument(armed.tabId, armed.documentId, cancelMsg);
} catch {
// Best-effort cleanup.
}
}
@@ -0,0 +1,673 @@
import type { RenderedRef } from "@browser-skill/vom";
import { formatObservationFile, type ObservationAnnotation } from "@/lib/format-observation-file";
import { fallbackDescriptor, matchTarget } from "@/lib/match-target";
import { waitForPageSettled } from "@/lib/page-settled";
import {
CAPTURE_RETRY_DELAY_MS,
DEFAULT_MAX_PAGE_TOKENS,
OBSERVATION_MIN_INTERVAL_MS,
} from "@/lib/record-constants";
import { registerObservation, type StateRegistryEntry } from "@/lib/trace-reducer";
import { captureVomObservation } from "@/tools/capture-vom-observation";
import type { CdpRunner, ChromeTabsApi } from "@/tools/shared";
import type { CapturedNode } from "@/tools/vom/capture";
import type { DraftTraceStep, Step, StopReason, Trace, TraceState } from "@/transport/types";
import { reduceTraceSteps, resolveTraceStartUrl } from "./trace-reducer";
export interface LastSettledObservation {
stateId: string;
captured: CapturedNode[];
matchNodes: CapturedNode[];
documentTokenOwners: Map<string, number | null>;
refs: RenderedRef[];
url: string;
title?: string;
vomText: string;
}
/** A post-action observation that has been queued but not yet written down. */
interface PendingSettle {
draftIndex: number;
/** Set when a newer action has already decided where this step landed. */
cancelled: boolean;
}
/** Latest URL in an in-flight redirect chain awaiting coalesce + settle. */
export interface PendingRedirectLanding {
url: string;
/** Bumped on every hop so an in-flight `waitForPageSettled` can cancel. */
generation: number;
}
export interface RecordingObservationState {
stateRegistry: Map<string, StateRegistryEntry>;
lastSettled: LastSettledObservation | null;
/** Latest token→owner map from the most recent observation capture. */
documentTokenOwners: Map<string, number | null>;
maxPageTokens: number;
redactValues: boolean;
lastCaptureAtMs: number;
/**
* Tail of the settle chain. Observations run one at a time so that a slow
* capture can never land after a faster one and report the pages out of the
* order the user visited them.
*/
settleQueue: Promise<void>;
/** Queued and in-flight settles, by draft index, so newer actions can supersede them. */
settles: Map<number, PendingSettle>;
stepAnnotations: Map<number, ObservationAnnotation[]>;
/**
* OAuth / server redirects are coalesced here: intermediate hops only update
* `url`+`generation`, and one `navigate` is emitted after the page settles.
*/
pendingRedirect: PendingRedirectLanding | null;
redirectFlushQueue: Promise<void>;
}
export function createObservationState(options?: {
maxPageTokens?: number;
redactValues?: boolean;
}): RecordingObservationState {
return {
stateRegistry: new Map(),
lastSettled: null,
documentTokenOwners: new Map(),
maxPageTokens: options?.maxPageTokens ?? DEFAULT_MAX_PAGE_TOKENS,
redactValues: options?.redactValues ?? false,
lastCaptureAtMs: 0,
settleQueue: Promise.resolve(),
settles: new Map(),
stepAnnotations: new Map(),
pendingRedirect: null,
redirectFlushQueue: Promise.resolve(),
};
}
function sleep(ms: number): Promise<void> {
return new Promise((resolve) => setTimeout(resolve, ms));
}
async function readTabMeta(
tabsApi: ChromeTabsApi,
tabId: number,
): Promise<{ url: string; title?: string }> {
try {
const tab = await tabsApi.get(tabId);
return { url: tab.url ?? "about:blank", title: tab.title };
} catch {
return { url: "about:blank" };
}
}
export async function captureAndRegisterObservation(
obs: RecordingObservationState,
cdp: CdpRunner,
tabId: number,
tabsApi: ChromeTabsApi,
urlOverride?: string,
): Promise<LastSettledObservation> {
const now = Date.now();
const waitMs = Math.max(0, OBSERVATION_MIN_INTERVAL_MS - (now - obs.lastCaptureAtMs));
if (waitMs > 0) await sleep(waitMs);
const { url, title } = urlOverride
? { url: urlOverride, title: undefined }
: await readTabMeta(tabsApi, tabId);
const meta = urlOverride ? await readTabMeta(tabsApi, tabId) : { url, title };
const resolvedTitle = title ?? meta.title;
const rendered = await captureVomObservation(cdp, tabId, url, {
maxTokens: obs.maxPageTokens,
redactValues: obs.redactValues,
conditionalSurfaceProbe: false,
});
const stateId = registerObservation(obs.stateRegistry, {
url,
title: resolvedTitle,
rawVomText: rendered.text,
truncated: rendered.truncated,
});
obs.lastCaptureAtMs = Date.now();
obs.documentTokenOwners = rendered.documentTokenOwners;
const settled: LastSettledObservation = {
stateId,
captured: rendered.captured,
matchNodes: rendered.matchNodes,
documentTokenOwners: rendered.documentTokenOwners,
refs: rendered.refs,
url,
title: resolvedTitle,
vomText: rendered.text,
};
obs.lastSettled = settled;
return settled;
}
/**
* Bind a draft to the page it was performed on: origin state, geometric target
* match, and the inline annotation. All three read the *current* observation,
* which is only the page the user acted on while the draft is still fresh —
* once the action settles, `lastSettled` is the destination page instead.
*/
export function applyTargetMatching(
obs: RecordingObservationState,
draft: DraftTraceStep,
stepId: number,
): void {
if (!obs.lastSettled) {
// Initial observation can fail or race the first action. Keep whatever
// the content script captured so the exported step is still teachable.
if ("target" in draft && "captureTarget" in draft) {
draft.target = fallbackDescriptor(draft.captureTarget);
}
rememberStepAnnotation(obs, stepId, draft);
return;
}
draft.preStateId = obs.lastSettled.stateId;
if ("target" in draft) {
draft.target =
"geometry" in draft && draft.geometry
? matchTarget({
geometry: draft.geometry,
captured: obs.lastSettled.matchNodes,
refs: obs.lastSettled.refs,
fallback: draft.captureTarget,
})
: // No geometry to match on, but the capture still knew what the user
// touched — keep that instead of an anonymous unmatched target.
fallbackDescriptor(draft.captureTarget);
}
rememberStepAnnotation(obs, stepId, draft);
}
function fillDetailForDraft(
obs: RecordingObservationState,
draft: DraftTraceStep,
): string | undefined {
if (obs.redactValues) return undefined;
if (draft.op === "fill") return JSON.stringify(draft.value);
return undefined;
}
function refLineForDraft(
obs: RecordingObservationState,
draft: DraftTraceStep,
): number | undefined {
if (!("target" in draft) || !obs.lastSettled) return undefined;
const targetRef = draft.target?.ref;
if (!targetRef) return undefined;
return obs.lastSettled.refs.find((r) => r.ref === targetRef)?.line;
}
function rememberStepAnnotation(
obs: RecordingObservationState,
stepId: number,
draft: DraftTraceStep,
): void {
const line = refLineForDraft(obs, draft);
if (line === undefined || draft.op === "navigate" || draft.op === "scroll") return;
if (!draft.preStateId) return;
const ann: ObservationAnnotation = {
stepId,
op: draft.op,
line,
stateId: draft.preStateId,
detail: fillDetailForDraft(obs, draft),
};
const bucket = obs.stepAnnotations.get(line) ?? [];
bucket.push(ann);
obs.stepAnnotations.set(line, bucket);
}
/** Record the step under the page it was performed on, not the one it led to. */
export function rememberStepOnPage(
obs: RecordingObservationState,
draft: DraftTraceStep,
stepId: number,
): void {
const stateId = draft.preStateId;
if (!stateId) return;
const entry = obs.stateRegistry.get(stateId);
if (entry && !entry.stepsHere.includes(stepId)) {
entry.stepsHere.push(stepId);
}
}
/** Drop an in-flight redirect coalesce (e.g. a real navigate superseded it). */
export function clearPendingRedirectLanding(obs: RecordingObservationState): void {
obs.pendingRedirect = null;
}
function enqueueRedirectFlush(obs: RecordingObservationState, task: () => Promise<void>): void {
obs.redirectFlushQueue = obs.redirectFlushQueue.then(task, task).catch(() => {});
}
/**
* Remember a redirect hop and schedule a settle-then-emit of a single navigate
* to the final URL. Later hops only bump `generation` / replace `url`.
*/
export function scheduleRedirectLandingFlush(
obs: RecordingObservationState,
steps: DraftTraceStep[],
cdp: CdpRunner,
tabId: number,
tabsApi: ChromeTabsApi,
url: string,
options: { cancelled?: () => boolean } = {},
): void {
const generation = (obs.pendingRedirect?.generation ?? 0) + 1;
obs.pendingRedirect = { url, generation };
enqueueRedirectFlush(obs, () =>
coalesceRedirectLanding(obs, steps, cdp, tabId, tabsApi, options),
);
}
/**
* Drain any coalesced redirect so the next action matches against the real
* landing page. Safe to call when nothing is pending.
*/
export async function flushPendingRedirectLanding(
obs: RecordingObservationState,
steps: DraftTraceStep[],
cdp: CdpRunner | undefined,
tabId: number,
tabsApi: ChromeTabsApi,
options: { cancelled?: () => boolean } = {},
): Promise<void> {
if (obs.pendingRedirect && cdp) {
enqueueRedirectFlush(obs, () =>
coalesceRedirectLanding(obs, steps, cdp, tabId, tabsApi, options),
);
}
await obs.redirectFlushQueue;
}
/**
* Wait until the redirect chain stops changing the document, then emit one
* `navigate` (cause `browser`) to the tab's final URL and settle its observation.
*/
async function coalesceRedirectLanding(
obs: RecordingObservationState,
steps: DraftTraceStep[],
cdp: CdpRunner,
tabId: number,
tabsApi: ChromeTabsApi,
options: { cancelled?: () => boolean },
): Promise<void> {
while (obs.pendingRedirect) {
if (options.cancelled?.()) {
obs.pendingRedirect = null;
return;
}
const snap = obs.pendingRedirect;
const outcome = await waitForPageSettled(cdp, tabId, {
cancelled: () =>
!!options.cancelled?.() ||
obs.pendingRedirect === null ||
obs.pendingRedirect.generation !== snap.generation,
});
if (options.cancelled?.()) {
obs.pendingRedirect = null;
return;
}
// A newer hop cancelled this wait — loop and settle against the latest URL.
if (outcome === "cancelled") continue;
if (!obs.pendingRedirect || obs.pendingRedirect.generation !== snap.generation) {
continue;
}
const finalUrl = (await readTabMeta(tabsApi, tabId)).url || snap.url;
obs.pendingRedirect = null;
if (!finalUrl || finalUrl === "about:blank") return;
if (obs.lastSettled?.url === finalUrl) return;
const last = steps[steps.length - 1];
if (last?.op === "navigate" && last.url === finalUrl) {
if (!last.postStateId) {
const draftIndex = steps.length - 1;
scheduleDraftSettle(obs, draftIndex, draftIndex + 1, cdp, tabId, tabsApi, steps);
await obs.settleQueue;
}
return;
}
if (outcome === "timeout") {
console.debug(
`[bsk record] redirect landing still changing after settle budget; ` +
`recording navigate to ${finalUrl}`,
);
}
const draft: DraftTraceStep = {
op: "navigate",
url: finalUrl,
page_url: finalUrl,
cause: "browser",
preStateId: obs.lastSettled?.stateId,
};
steps.push(draft);
const draftIndex = steps.length - 1;
const stepId = draftIndex + 1;
rememberStepOnPage(obs, draft, stepId);
scheduleDraftSettle(obs, draftIndex, stepId, cdp, tabId, tabsApi, steps);
// Callers that flush before the next action need `lastSettled` to already
// be the landing page so target matching does not use the pre-redirect view.
await obs.settleQueue;
return;
}
}
/**
* A capture that lands mid-navigation fails on a destroyed execution context.
* That is transient, so give it one more chance before the step has to fall
* back to a stale state.
*/
async function captureWithRetry(
obs: RecordingObservationState,
cdp: CdpRunner,
tabId: number,
tabsApi: ChromeTabsApi,
urlOverride?: string,
): Promise<LastSettledObservation> {
try {
return await captureAndRegisterObservation(obs, cdp, tabId, tabsApi, urlOverride);
} catch (err) {
console.debug("[bsk record] observation failed, retrying once", err);
await sleep(CAPTURE_RETRY_DELAY_MS);
return captureAndRegisterObservation(obs, cdp, tabId, tabsApi, urlOverride);
}
}
export async function settleDraftObservation(
obs: RecordingObservationState,
cdp: CdpRunner,
tabId: number,
tabsApi: ChromeTabsApi,
steps: DraftTraceStep[],
draftIndex: number,
pending?: PendingSettle,
): Promise<void> {
const cancelled = () => pending?.cancelled === true;
const outcome = await waitForPageSettled(cdp, tabId, { cancelled });
if (outcome === "cancelled") return;
if (outcome === "timeout") {
console.debug(
`[bsk record] step ${draftIndex + 1} was still changing the page after the settle ` +
"budget; observing it as it stands",
);
}
const started = steps[draftIndex];
if (!started) return;
// The URL attached to the draft may only be an intermediate redirect hop.
// Once the page is settled, register the capture against live tab metadata.
const settled = await captureWithRetry(obs, cdp, tabId, tabsApi);
// The observation still counts as the latest view of the page even when this
// step no longer wants it — the next action will start from it.
if (cancelled()) return;
// Re-read the slot: a navigation observed while the capture ran may have
// rewritten this draft, and the observation belongs to whatever occupies the
// slot now — writing to the object we started with would strand it.
const draft = steps[draftIndex] ?? started;
draft.postStateId = settled.stateId;
}
/**
* Recover landing states from the shape of the recording itself: wherever the
* next action was performed is, by definition, where the previous one landed.
* Only the immediately following draft counts — a later one would claim a page
* that several unobserved actions away, which is worse than admitting we saw
* no change.
*/
export function inferMissingPostStates(steps: DraftTraceStep[]): void {
for (let i = 0; i < steps.length - 1; i += 1) {
const draft = steps[i];
const next = steps[i + 1];
if (!draft || !next || draft.postStateId || !next.preStateId) continue;
draft.postStateId = next.preStateId;
console.debug(
`[bsk record] step ${i + 1} (${draft.op}) had no post-action observation; ` +
`using where step ${i + 2} started (${next.preStateId})`,
);
}
}
/**
* Last chance for the closing actions of a recording. Stopping right after the
* final action is normal, and so is that action navigating away, so take one
* final look at the page. Only trailing drafts may claim it: an earlier step
* did not land on whatever the user happens to be looking at when they stop.
*/
export async function settleUnsettledDrafts(
obs: RecordingObservationState,
cdp: CdpRunner,
tabId: number,
tabsApi: ChromeTabsApi,
steps: DraftTraceStep[],
): Promise<void> {
const trailing: DraftTraceStep[] = [];
for (let i = steps.length - 1; i >= 0; i -= 1) {
const draft = steps[i];
if (!draft || draft.postStateId) break;
trailing.push(draft);
}
if (trailing.length === 0) return;
let settled: LastSettledObservation;
try {
settled = await captureWithRetry(obs, cdp, tabId, tabsApi);
} catch (err) {
console.warn("[bsk record] final observation at stop failed", err);
return;
}
for (const draft of trailing) draft.postStateId = settled.stateId;
console.debug(
`[bsk record] settled ${trailing.length} trailing step(s) against the page at stop ` +
`(${settled.stateId} ${settled.url})`,
);
}
/**
* Performing a new action ends the previous one: the page the user reached for
* is, by definition, where the earlier step left them. Taking the landing from
* the newer step also keeps the trace monotonic — a capture that finished late
* would otherwise credit an earlier step with a page that only exists because
* of the newer action.
*/
function supersedeEarlierSettles(
obs: RecordingObservationState,
draftIndex: number,
steps: DraftTraceStep[],
): void {
const landing = steps[draftIndex]?.preStateId;
for (const [index, pending] of obs.settles) {
if (index >= draftIndex) continue;
pending.cancelled = true;
obs.settles.delete(index);
const draft = steps[index];
if (!draft || draft.postStateId) continue;
if (!landing) continue;
draft.postStateId = landing;
console.debug(
`[bsk record] step ${index + 1} (${draft.op}) was still settling when step ` +
`${draftIndex + 1} started; landing it on ${landing}`,
);
}
}
export function scheduleDraftSettle(
obs: RecordingObservationState,
draftIndex: number,
stepId: number,
cdp: CdpRunner,
tabId: number,
tabsApi: ChromeTabsApi,
steps: DraftTraceStep[],
): void {
supersedeEarlierSettles(obs, draftIndex, steps);
// Rescheduling the same step (a navigation showed up after the action)
// replaces the pending observation rather than racing it.
const superseded = obs.settles.get(draftIndex);
if (superseded) superseded.cancelled = true;
const pending: PendingSettle = { draftIndex, cancelled: false };
obs.settles.set(draftIndex, pending);
enqueueSettle(obs, async () => {
if (pending.cancelled) return;
try {
await settleDraftObservation(obs, cdp, tabId, tabsApi, steps, draftIndex, pending);
} catch (err) {
// Recoverable: stop-time repair still gives the step a landing page.
const op = steps[draftIndex]?.op ?? "?";
console.warn(`[bsk record] post-action observation failed for step ${stepId} (${op})`, err);
} finally {
if (obs.settles.get(draftIndex) === pending) obs.settles.delete(draftIndex);
}
});
}
function enqueueSettle(obs: RecordingObservationState, task: () => Promise<void>): void {
obs.settleQueue = obs.settleQueue.then(task, task).catch(() => {});
}
export function cancelPendingSettles(obs: RecordingObservationState): void {
for (const pending of obs.settles.values()) pending.cancelled = true;
obs.settles.clear();
}
/** Bound the drain loop so a self-rescheduling settle cannot block stop. */
const MAX_SETTLE_FLUSH_ROUNDS = 10;
/**
* Drain settle work before exporting, including work queued while draining —
* a navigation observed during the last capture schedules another one, and
* the trace would drop it if stop did not wait.
*/
export async function flushPendingSettles(obs: RecordingObservationState): Promise<void> {
for (let round = 0; round < MAX_SETTLE_FLUSH_ROUNDS; round += 1) {
const drained = obs.settleQueue;
await drained;
if (obs.settleQueue === drained) return;
}
console.warn("[bsk record] settle queue kept growing at stop; exporting what has been observed");
}
function finalizeStateBodies(
entries: StateRegistryEntry[],
annotationsByState: Map<string, ObservationAnnotation[]>,
stepIdByDraftId: Map<number, number>,
idByOldId: Map<string, string>,
): TraceState[] {
return entries.map((entry) => {
const id = idByOldId.get(entry.id) ?? entry.id;
const body = formatObservationFile({
stateId: id,
url: entry.url,
title: entry.title,
stepsHere: remapStepIds(entry.stepsHere, stepIdByDraftId),
body: entry.rawVomText,
annotations: annotationsByState.get(entry.id) ?? [],
});
return {
id,
url: entry.url,
...(entry.title ? { title: entry.title } : {}),
body,
...(entry.truncated ? { truncated: true } : {}),
};
});
}
/** Draft ids only become step ids after collapsing and filtering. */
function remapStepIds(draftIds: number[], stepIdByDraftId: Map<number, number>): number[] {
const mapped = new Set<number>();
for (const draftId of draftIds) {
const stepId = stepIdByDraftId.get(draftId);
if (stepId !== undefined) mapped.add(stepId);
}
return [...mapped].sort((a, b) => a - b);
}
function collectAnnotationsByState(
obs: RecordingObservationState,
stepIdByDraftId: Map<number, number>,
): Map<string, ObservationAnnotation[]> {
const byState = new Map<string, ObservationAnnotation[]>();
for (const anns of obs.stepAnnotations.values()) {
for (const ann of anns) {
const stepId = stepIdByDraftId.get(ann.stepId);
if (stepId === undefined) continue;
const bucket = byState.get(ann.stateId) ?? [];
bucket.push({ ...ann, stepId });
byState.set(ann.stateId, bucket);
}
}
return byState;
}
/**
* Keep only the pages the published steps point at. Redirect hops and
* mid-load captures land in the registry too, and shipping them would invite
* a reader to treat a page the flow merely passed through as a real stop.
* With no steps at all the first observation is the whole artifact, so it
* stays.
*/
function selectPublishedStates(
registry: Map<string, StateRegistryEntry>,
steps: Step[],
): StateRegistryEntry[] {
const entries = [...registry.values()];
if (steps.length === 0) return entries.slice(0, 1);
const referenced = new Set<string>();
for (const step of steps) {
referenced.add(step.state);
referenced.add(step.result.state);
}
return entries.filter((entry) => referenced.has(entry.id));
}
export function buildTraceV3(input: {
obs: RecordingObservationState;
steps: DraftTraceStep[];
startedAt: string;
purpose?: string;
startUrl?: string;
stoppedBy: StopReason;
bskVersion: string;
frameCapture?: Trace["frame_capture"];
}): Trace {
const { steps, stepIdByDraftId } = reduceTraceSteps(input.steps, input.obs.stateRegistry);
const published = selectPublishedStates(input.obs.stateRegistry, steps);
// Renumber so the shipped dictionary reads s1..sN without holes where the
// dropped captures used to be.
const idByOldId = new Map(published.map((entry, index) => [entry.id, `s${index + 1}`]));
for (const step of steps) {
step.state = idByOldId.get(step.state) ?? step.state;
step.result.state = idByOldId.get(step.result.state) ?? step.result.state;
}
const annotationsByState = collectAnnotationsByState(input.obs, stepIdByDraftId);
const states = finalizeStateBodies(published, annotationsByState, stepIdByDraftId, idByOldId);
const startUrl = resolveTraceStartUrl(input.steps, input.startUrl, states);
return {
version: 3,
...(input.purpose ? { purpose: input.purpose } : {}),
recorded_at: new Date().toISOString(),
started_at: input.startedAt,
stopped_by: input.stoppedBy,
entry: { start_url: startUrl },
recorder: { bsk: input.bskVersion, vom: 1 },
...(input.frameCapture ? { frame_capture: input.frameCapture } : {}),
states,
steps,
};
}
@@ -0,0 +1,212 @@
import type { DraftTraceStep, NavigationCause } from "@/transport/types";
import type { RecordStepPayload } from "./record-bridge";
import { mapNavigationCause } from "./record-constants";
export interface RecordingStepBuffer {
steps: DraftTraceStep[];
currentUrl?: string;
pendingNavigation: boolean;
pendingNavigationDeadline?: number;
lastTransitionType?: string;
lastTransitionQualifiers?: string[];
}
const NAVIGATION_TRIGGER_WINDOW_MS = 3_000;
function toDraftStep(payload: RecordStepPayload): DraftTraceStep | null {
const pageUrl = payload.page_url;
const geometry = payload.geometry;
switch (payload.op) {
case "click":
return payload.target
? {
op: "click",
target: { unmatched: true },
captureTarget: payload.target,
...(geometry ? { geometry } : {}),
...(pageUrl ? { page_url: pageUrl } : {}),
}
: null;
case "hover":
return payload.target
? {
op: "hover",
target: { unmatched: true },
captureTarget: payload.target,
...(geometry ? { geometry } : {}),
...(pageUrl ? { page_url: pageUrl } : {}),
}
: null;
case "fill":
return payload.target
? {
op: "fill",
target: { unmatched: true },
captureTarget: payload.target,
...(geometry ? { geometry } : {}),
value: payload.value ?? "",
...(payload.commit ? { commit: payload.commit } : {}),
...(payload.redacted ? { redacted: true } : {}),
...(pageUrl ? { page_url: pageUrl } : {}),
}
: null;
case "press":
return payload.key
? {
op: "press",
key: payload.key,
...(payload.target
? { target: { unmatched: true }, captureTarget: payload.target }
: {}),
...(geometry ? { geometry } : {}),
...(payload.modifiers?.length ? { modifiers: payload.modifiers } : {}),
...(pageUrl ? { page_url: pageUrl } : {}),
}
: null;
case "select":
return payload.target && payload.values
? {
op: "select",
target: { unmatched: true },
captureTarget: payload.target,
...(geometry ? { geometry } : {}),
values: payload.values,
...(payload.labels?.length ? { labels: payload.labels } : {}),
...(pageUrl ? { page_url: pageUrl } : {}),
}
: null;
case "scroll":
return { op: "scroll", ...(pageUrl ? { page_url: pageUrl } : {}) };
case "navigate":
return null;
}
}
/** Annotate the latest action with `navigated_to`. Returns its index, or -1. */
function annotateLastStepNavigation(buffer: RecordingStepBuffer, url: string): number {
for (let i = buffer.steps.length - 1; i >= 0; i -= 1) {
const step = buffer.steps[i];
if (!step) continue;
if (step.op === "click" || step.op === "press" || step.op === "select" || step.op === "fill") {
// Mutate in place: an in-flight settle holds this object, and replacing
// it would strand that settle's observation on the discarded copy.
step.navigated_to = url;
return i;
}
break;
}
return -1;
}
function causeFromBuffer(buffer: RecordingStepBuffer): NavigationCause | null {
return mapNavigationCause({
transitionType: buffer.lastTransitionType,
transitionQualifiers: buffer.lastTransitionQualifiers,
});
}
/** Outcome of folding a main-frame URL change into the draft buffer. */
export type NavigationObserveResult =
| { kind: "noop" }
| { kind: "annotated"; index: number }
| { kind: "appended"; index: number }
/**
* Redirect hop: do not emit a step yet. The recorder coalesces the chain and
* emits one `navigate` after `waitForPageSettled` on the final URL.
*/
| { kind: "coalesce_redirect"; url: string };
export function observeRecordedNavigation(
buffer: RecordingStepBuffer,
url: string,
causedByAction?: boolean,
transitionType?: string,
transitionQualifiers?: string[],
): NavigationObserveResult {
if (!url || url === buffer.currentUrl) return { kind: "noop" };
buffer.currentUrl = url;
if (transitionType !== undefined) buffer.lastTransitionType = transitionType;
if (transitionQualifiers !== undefined) {
buffer.lastTransitionQualifiers = transitionQualifiers;
}
const pendingIsCurrent =
buffer.pendingNavigation &&
(buffer.pendingNavigationDeadline === undefined ||
buffer.pendingNavigationDeadline >= Date.now());
if (causedByAction === true || (causedByAction === undefined && pendingIsCurrent)) {
buffer.pendingNavigation = false;
buffer.pendingNavigationDeadline = undefined;
const annotatedIndex = annotateLastStepNavigation(buffer, url);
if (annotatedIndex >= 0) {
return { kind: "annotated", index: annotatedIndex };
}
const cause = causeFromBuffer(buffer);
if (cause === null) {
return { kind: "coalesce_redirect", url };
}
buffer.steps.push({
op: "navigate",
url,
page_url: url,
cause,
transitionType: buffer.lastTransitionType,
transitionQualifiers: buffer.lastTransitionQualifiers,
});
return { kind: "appended", index: buffer.steps.length - 1 };
}
buffer.pendingNavigation = false;
buffer.pendingNavigationDeadline = undefined;
const cause = causeFromBuffer(buffer);
if (cause === null) {
return { kind: "coalesce_redirect", url };
}
buffer.steps.push({
op: "navigate",
url,
page_url: url,
cause,
transitionType: buffer.lastTransitionType,
transitionQualifiers: buffer.lastTransitionQualifiers,
});
return { kind: "appended", index: buffer.steps.length - 1 };
}
/**
* Buffer one captured payload. Returns the index of the draft it appended, or
* `null` when the payload produced none (an unnamed click target, a navigation
* that only annotated the previous draft, …). Callers must not fall back to
* "the last draft" on `null`: that would re-match an already recorded step
* against a newer observation and overwrite its origin state.
*/
export function appendRecordedPayload(
buffer: RecordingStepBuffer,
payload: RecordStepPayload,
): number | null {
if (payload.op === "navigate") {
if (!payload.url) return null;
const result = observeRecordedNavigation(
buffer,
payload.url,
payload.navigation_caused_by_action,
payload.transitionType,
payload.transitionQualifiers,
);
return result.kind === "appended" ? result.index : null;
}
const step = toDraftStep({
...payload,
page_url: payload.page_url ?? buffer.currentUrl,
});
if (!step) return null;
buffer.steps.push(step);
if (step.op === "click" || step.op === "press" || step.op === "select" || step.op === "fill") {
buffer.pendingNavigation = payload.expects_navigation === true;
buffer.pendingNavigationDeadline = buffer.pendingNavigation
? Date.now() + NAVIGATION_TRIGGER_WINDOW_MS
: undefined;
}
return buffer.steps.length - 1;
}
@@ -1,39 +0,0 @@
import {
RECORD_DOCUMENT_ATTRIBUTE,
recordingDocumentMarkerValue,
} from "@/shared/recording-document-identity";
export interface RecordingDocumentMarker {
restore(): void;
ensure(): void;
}
export function waitForDocumentElement(): Promise<HTMLElement> {
if (document.documentElement) return Promise.resolve(document.documentElement);
return new Promise((resolve) => {
const observer = new MutationObserver(() => {
if (!document.documentElement) return;
observer.disconnect();
resolve(document.documentElement);
});
observer.observe(document, { childList: true });
});
}
export function markRecordingDocument(
producerId: string,
root: HTMLElement = document.documentElement,
): RecordingDocumentMarker {
const previous = root.getAttribute(RECORD_DOCUMENT_ATTRIBUTE);
const markerValue = recordingDocumentMarkerValue(producerId);
const ensure = () => root.setAttribute(RECORD_DOCUMENT_ATTRIBUTE, markerValue);
ensure();
return {
ensure,
restore() {
if (root.getAttribute(RECORD_DOCUMENT_ATTRIBUTE) !== markerValue) return;
if (previous === null) root.removeAttribute(RECORD_DOCUMENT_ATTRIBUTE);
else root.setAttribute(RECORD_DOCUMENT_ATTRIBUTE, previous);
},
};
}
@@ -1,134 +0,0 @@
import type { CdpTarget } from "@/browser-driver/frame-graph";
import { type CdpRunner, sendToCdpTarget } from "@/tools/shared";
const SETTLE_MIN_MS = 150;
const SETTLE_QUIET_MS = 250;
const SETTLE_MAX_MS = 2_000;
const SETTLE_POLL_MS = 60;
const SETTLE_WORLD_NAME = "__bsk_record_settle__";
const QUIET_PROBE = `(() => {
const scope = window;
let probe = scope.__bskRecordQuiet;
if (!probe) {
probe = { changedAt: Date.now() };
const observer = new MutationObserver(() => {
probe.changedAt = Date.now();
});
observer.observe(document.documentElement, {
subtree: true,
childList: true,
attributes: true,
characterData: true,
});
scope.__bskRecordQuiet = probe;
}
return { idleMs: Date.now() - probe.changedAt, readyState: document.readyState };
})()`;
export interface DocumentSettleScope {
target: CdpTarget;
/** Omit only for the target's root document. */
frameId?: string;
}
type SettleOutcome = "quiet" | "timeout" | "cancelled";
interface QuietProbe {
idleMs: number;
readyState: string;
}
interface ProbeContext {
executionContextId?: number;
}
function sleep(ms: number, signal?: AbortSignal): Promise<void> {
return new Promise((resolve) => {
if (signal?.aborted) return resolve();
const timer = setTimeout(resolve, ms);
signal?.addEventListener(
"abort",
() => {
clearTimeout(timer);
resolve();
},
{ once: true },
);
});
}
async function executionContextForScope(
cdp: CdpRunner,
scope: DocumentSettleScope,
): Promise<number | undefined> {
if (!scope.frameId) return undefined;
const result = await sendToCdpTarget<{ executionContextId?: number }>(
cdp,
scope.target,
"Page.createIsolatedWorld",
{
frameId: scope.frameId,
worldName: SETTLE_WORLD_NAME,
grantUniveralAccess: false,
},
);
return result.executionContextId;
}
async function readQuietProbe(
cdp: CdpRunner,
scope: DocumentSettleScope,
context: ProbeContext,
): Promise<QuietProbe | null> {
try {
if (scope.frameId && context.executionContextId === undefined) {
context.executionContextId = await executionContextForScope(cdp, scope);
if (context.executionContextId === undefined) return null;
}
const reply = await sendToCdpTarget<{ result?: { value?: unknown } }>(
cdp,
scope.target,
"Runtime.evaluate",
{
expression: QUIET_PROBE,
returnByValue: true,
...(context.executionContextId !== undefined
? { contextId: context.executionContextId }
: {}),
},
);
const value = reply.result?.value;
if (!value || typeof value !== "object") return null;
const { idleMs, readyState } = value as { idleMs?: unknown; readyState?: unknown };
if (typeof idleMs !== "number" || typeof readyState !== "string") return null;
return { idleMs, readyState };
} catch {
context.executionContextId = undefined;
return null;
}
}
export async function waitForDocumentSettled(
cdp: CdpRunner,
scope: DocumentSettleScope,
options: { signal?: AbortSignal } = {},
): Promise<SettleOutcome> {
const startedAt = Date.now();
const floor = startedAt + SETTLE_MIN_MS;
const deadline = startedAt + SETTLE_MAX_MS;
const context: ProbeContext = {};
for (;;) {
if (options.signal?.aborted) return "cancelled";
await sleep(SETTLE_POLL_MS, options.signal);
if (options.signal?.aborted) return "cancelled";
const probe = await readQuietProbe(cdp, scope, context);
const now = Date.now();
if (now < floor) continue;
if (now >= deadline) return "timeout";
if (!probe || probe.readyState === "loading") continue;
if (probe.idleMs >= SETTLE_QUIET_MS) return "quiet";
}
}
@@ -1,34 +0,0 @@
import type { RecordingDraftStep } from "./types";
const CLIPBOARD_KEYS = new Set(["a", "c", "v", "x", "A", "C", "V", "X"]);
const MODIFIER_ONLY_KEYS = new Set(["Meta", "Control", "Alt", "Shift", "OS", "Hyper", "Super"]);
export function shouldRecordPress(
key: string,
modifiers?: Array<"alt" | "ctrl" | "meta" | "shift">,
): boolean {
if (MODIFIER_ONLY_KEYS.has(key)) return false;
const mods = modifiers ?? [];
const hasCtrlOrMeta = mods.includes("ctrl") || mods.includes("meta");
if (hasCtrlOrMeta && CLIPBOARD_KEYS.has(key)) return false;
if (key === "Enter" || key === "Escape") return true;
if (key.length === 1 && !hasCtrlOrMeta && !mods.includes("alt")) return false;
return false;
}
export function shouldIncludeDraft(step: RecordingDraftStep): boolean {
return step.op !== "press" || shouldRecordPress(step.key, step.modifiers);
}
export function resolveDraftStartUrl(
drafts: RecordingDraftStep[],
explicitStartUrl?: string,
fallbackUrl?: string,
): string {
if (explicitStartUrl) return explicitStartUrl;
const navigation = drafts.find(
(step): step is Extract<RecordingDraftStep, { op: "navigate" }> => step.op === "navigate",
);
if (navigation) return navigation.url;
return drafts.find((step) => step.pageUrl)?.pageUrl ?? fallbackUrl ?? "about:blank";
}
@@ -1,65 +0,0 @@
export const RECORD_FRAME_PORT = "bsk-record-frame";
export const RECORD_FRAME_QUERY = "bsk-record-frame-query";
export const RECORD_FRAME_START = "bsk-record-frame-start";
export interface RecordFrameQueryMessage {
type: typeof RECORD_FRAME_QUERY;
}
export interface RecordFrameQueryResponse {
active: boolean;
requestId?: string;
startedAtMs?: number;
}
export interface RecordFrameStartMessage {
type: typeof RECORD_FRAME_START;
requestId: string;
startedAtMs: number;
}
export type RecordFramePortMessage =
| {
type: "ready";
requestId: string;
producerId: string;
}
| {
type: "ready_ack";
requestId: string;
producerId: string;
}
| {
type: "stop";
requestId: string;
commandId: string;
}
| {
type: "cancel";
requestId: string;
}
| {
type: "stopped";
requestId: string;
commandId: string;
ok: boolean;
error?: string;
};
export function isRecordFrameQueryMessage(value: unknown): value is RecordFrameQueryMessage {
return (
typeof value === "object" &&
value !== null &&
(value as { type?: unknown }).type === RECORD_FRAME_QUERY
);
}
export function isRecordFrameStartMessage(value: unknown): value is RecordFrameStartMessage {
if (typeof value !== "object" || value === null) return false;
const message = value as Partial<RecordFrameStartMessage>;
return (
message.type === RECORD_FRAME_START &&
typeof message.requestId === "string" &&
typeof message.startedAtMs === "number"
);
}
@@ -1,399 +0,0 @@
import {
isRecordFrameQueryMessage,
RECORD_FRAME_PORT,
RECORD_FRAME_START,
type RecordFramePortMessage,
type RecordFrameQueryResponse,
type RecordFrameStartMessage,
} from "./frame-bridge";
export interface RecordingCaptureScope {
tabId: number;
documentId: string;
browserFrameId: number;
producerId: string;
}
interface ArmedRecording {
requestId: string;
startedAtMs: number;
tabIds: Set<number>;
agents: Map<string, FrameAgent>;
onDocumentReady?: (scope: RecordingCaptureScope) => void | Promise<void>;
finishing: boolean;
}
interface FrameAgent extends RecordingCaptureScope {
requestId: string;
port: chrome.runtime.Port;
stopWaiters: Map<string, (ok: boolean) => void>;
}
interface BrowserFrame {
frameId: number;
documentId?: string;
}
interface BrowserFrameNavigation extends BrowserFrame {
tabId: number;
lifecycle: "committed" | "completed";
}
const RECORD_FRAME_STOP_TIMEOUT_MS = 5_000;
export interface RecordFrameCoordinatorDeps {
getAllFrames(tabId: number): Promise<BrowserFrame[]>;
sendToDocument(
tabId: number,
message: RecordFrameStartMessage,
target: { documentId?: string; frameId?: number },
): Promise<unknown>;
subscribeFrameNavigation?(listener: (frame: BrowserFrameNavigation) => void): () => void;
}
function documentKey(tabId: number, documentId: string): string {
return `${tabId}:${documentId}`;
}
function senderAddress(
sender: chrome.runtime.MessageSender,
): { tabId: number; documentId: string; browserFrameId: number } | null {
const tabId = sender.tab?.id;
const documentId = sender.documentId;
const browserFrameId = sender.frameId;
if (
typeof tabId !== "number" ||
typeof documentId !== "string" ||
typeof browserFrameId !== "number"
) {
return null;
}
return { tabId, documentId, browserFrameId };
}
function defaultDeps(): RecordFrameCoordinatorDeps {
return {
async getAllFrames(tabId) {
return (await chrome.webNavigation.getAllFrames({ tabId })) ?? [];
},
sendToDocument(tabId, message, target) {
return chrome.tabs.sendMessage(tabId, message, target);
},
subscribeFrameNavigation(listener) {
const onCommitted = (details: chrome.webNavigation.WebNavigationTransitionCallbackDetails) =>
listener({ ...details, lifecycle: "committed" });
const onCompleted = (details: chrome.webNavigation.WebNavigationFramedCallbackDetails) =>
listener({ ...details, lifecycle: "completed" });
chrome.webNavigation.onCommitted.addListener(onCommitted);
chrome.webNavigation.onCompleted.addListener(onCompleted);
return () => {
chrome.webNavigation.onCommitted.removeListener(onCommitted);
chrome.webNavigation.onCompleted.removeListener(onCompleted);
};
},
};
}
export class RecordFrameCoordinator {
readonly #deps: RecordFrameCoordinatorDeps;
readonly #recordings = new Map<string, ArmedRecording>();
#attached = false;
#detachFrameNavigation: (() => void) | null = null;
constructor(deps: RecordFrameCoordinatorDeps = defaultDeps()) {
this.#deps = deps;
}
attach(): () => void {
if (this.#attached) return () => {};
this.#attached = true;
chrome.runtime.onConnect.addListener(this.#onConnect);
chrome.runtime.onMessage.addListener(this.#onMessage);
this.#detachFrameNavigation =
this.#deps.subscribeFrameNavigation?.(this.#onFrameNavigation) ?? null;
return () => {
if (!this.#attached) return;
this.#attached = false;
chrome.runtime.onConnect.removeListener(this.#onConnect);
chrome.runtime.onMessage.removeListener(this.#onMessage);
this.#detachFrameNavigation?.();
this.#detachFrameNavigation = null;
for (const recording of this.#recordings.values()) this.#cancelAgents(recording);
this.#recordings.clear();
};
}
begin(
requestId: string,
startedAtMs: number,
initialTabId: number,
onDocumentReady?: (scope: RecordingCaptureScope) => void | Promise<void>,
): void {
const previous = this.#recordings.get(requestId);
if (previous) this.#cancelAgents(previous);
this.#recordings.set(requestId, {
requestId,
startedAtMs,
// Register the initial tab before navigation begins. A newly-created
// child document can query at document_start before armTab's frame
// snapshot sees it, especially when Chromium promotes it to an OOPIF.
tabIds: new Set([initialTabId]),
agents: new Map(),
...(onDocumentReady ? { onDocumentReady } : {}),
finishing: false,
});
}
async armTab(requestId: string, tabId: number): Promise<boolean> {
const recording = this.#recordings.get(requestId);
if (!recording || recording.finishing) return false;
recording.tabIds.add(tabId);
let frames: BrowserFrame[];
try {
frames = await this.#deps.getAllFrames(tabId);
} catch {
frames = [{ frameId: 0 }];
}
if (!frames.some((frame) => frame.frameId === 0)) frames.unshift({ frameId: 0 });
const results = await Promise.all(
frames.map(async (frame) => {
const started = await this.#startFrame(recording, tabId, frame);
return { frameId: frame.frameId, started };
}),
);
return results.some((result) => result.frameId === 0 && result.started);
}
sourceFor(
requestId: string,
producerId: string,
sender: chrome.runtime.MessageSender,
): RecordingCaptureScope | null {
const address = senderAddress(sender);
const recording = this.#recordings.get(requestId);
if (!address || !recording) return null;
const agent = recording.agents.get(documentKey(address.tabId, address.documentId));
if (!agent || agent.producerId !== producerId) return null;
return {
tabId: agent.tabId,
documentId: agent.documentId,
browserFrameId: agent.browserFrameId,
producerId: agent.producerId,
};
}
async stop(requestId: string): Promise<boolean> {
const recording = this.#recordings.get(requestId);
if (!recording) return true;
recording.finishing = true;
const commandId = crypto.randomUUID();
const results = await Promise.all(
[...recording.agents.values()].map((agent) => this.#stopAgent(agent, requestId, commandId)),
);
const succeeded = results.every(Boolean);
if (succeeded) this.#recordings.delete(requestId);
else recording.finishing = false;
return succeeded;
}
cancel(requestId: string): void {
const recording = this.#recordings.get(requestId);
if (!recording) return;
this.#cancelAgents(recording);
this.#recordings.delete(requestId);
}
readonly #onMessage = (
message: unknown,
sender: chrome.runtime.MessageSender,
sendResponse: (response: RecordFrameQueryResponse) => void,
): boolean => {
if (!isRecordFrameQueryMessage(message)) return false;
const tabId = sender.tab?.id;
const recording =
typeof tabId === "number"
? [...this.#recordings.values()].find(
(candidate) => !candidate.finishing && candidate.tabIds.has(tabId),
)
: undefined;
sendResponse(
recording
? {
active: true,
requestId: recording.requestId,
startedAtMs: recording.startedAtMs,
}
: { active: false },
);
return false;
};
readonly #onFrameNavigation = (frame: BrowserFrameNavigation): void => {
if (frame.frameId === 0) return;
for (const recording of this.#recordings.values()) {
if (recording.finishing || !recording.tabIds.has(frame.tabId)) continue;
// onCommitted can race document_start, while onCompleted runs after the
// content script is available. Starting twice is safe and closes both
// the early-query and late-SPA-frame gaps.
void (async () => {
const started = await this.#startFrame(recording, frame.tabId, frame);
if (!started || frame.lifecycle !== "completed" || recording.finishing) return;
const agent = frame.documentId
? recording.agents.get(documentKey(frame.tabId, frame.documentId))
: [...recording.agents.values()].find(
(candidate) =>
candidate.tabId === frame.tabId && candidate.browserFrameId === frame.frameId,
);
if (!agent) return;
await recording.onDocumentReady?.({
tabId: agent.tabId,
documentId: agent.documentId,
browserFrameId: agent.browserFrameId,
producerId: agent.producerId,
});
})();
}
};
readonly #onConnect = (port: chrome.runtime.Port): void => {
if (port.name !== RECORD_FRAME_PORT) return;
const address = senderAddress(port.sender ?? {});
if (!address) {
port.disconnect();
return;
}
let registered: FrameAgent | null = null;
port.onMessage.addListener((raw: unknown) => {
const message = raw as Partial<RecordFramePortMessage>;
if (message.type === "ready") {
if (typeof message.requestId !== "string" || typeof message.producerId !== "string") {
port.disconnect();
return;
}
const requestId = message.requestId;
const producerId = message.producerId;
if (registered) {
if (registered.requestId === requestId && registered.producerId === producerId) {
port.postMessage({
type: "ready_ack",
requestId,
producerId,
} satisfies RecordFramePortMessage);
} else {
port.disconnect();
}
return;
}
const recording = this.#recordings.get(requestId);
if (
!recording ||
recording.finishing ||
!recording.tabIds.has(address.tabId) ||
producerId.length === 0
) {
port.disconnect();
return;
}
const agent: FrameAgent = {
...address,
requestId,
producerId,
port,
stopWaiters: new Map(),
};
registered = agent;
const key = documentKey(address.tabId, address.documentId);
const previous = recording.agents.get(key);
if (previous && previous !== agent) previous.port.disconnect();
recording.agents.set(key, agent);
port.postMessage({
type: "ready_ack",
requestId,
producerId,
} satisfies RecordFramePortMessage);
return;
}
if (
message.type === "stopped" &&
registered &&
message.requestId === registered.requestId &&
typeof message.commandId === "string"
) {
registered.stopWaiters.get(message.commandId)?.(message.ok === true);
registered.stopWaiters.delete(message.commandId);
}
});
port.onDisconnect.addListener(() => {
if (!registered) return;
for (const resolve of registered.stopWaiters.values()) resolve(true);
const recording = this.#recordings.get(registered.requestId);
const key = documentKey(registered.tabId, registered.documentId);
if (recording?.agents.get(key) === registered) recording.agents.delete(key);
});
};
#stopAgent(agent: FrameAgent, requestId: string, commandId: string): Promise<boolean> {
return new Promise((resolve) => {
const timer = setTimeout(() => {
agent.stopWaiters.delete(commandId);
resolve(false);
}, RECORD_FRAME_STOP_TIMEOUT_MS);
agent.stopWaiters.set(commandId, (ok) => {
clearTimeout(timer);
resolve(ok);
});
try {
agent.port.postMessage({
type: "stop",
requestId,
commandId,
} satisfies RecordFramePortMessage);
} catch {
clearTimeout(timer);
agent.stopWaiters.delete(commandId);
resolve(true);
}
});
}
async #startFrame(
recording: ArmedRecording,
tabId: number,
frame: BrowserFrame,
): Promise<boolean> {
const message: RecordFrameStartMessage = {
type: RECORD_FRAME_START,
requestId: recording.requestId,
startedAtMs: recording.startedAtMs,
};
try {
const response = await this.#deps.sendToDocument(tabId, message, {
...(frame.documentId ? { documentId: frame.documentId } : { frameId: frame.frameId }),
});
return isStarted(response);
} catch {
return false;
}
}
#cancelAgents(recording: ArmedRecording): void {
for (const agent of recording.agents.values()) {
try {
agent.port.postMessage({
type: "cancel",
requestId: recording.requestId,
} satisfies RecordFramePortMessage);
} catch {
// A destroyed Document has no remaining capture state to cancel.
}
}
}
}
function isStarted(value: unknown): boolean {
return typeof value === "object" && value !== null && (value as { ok?: unknown }).ok === true;
}
export const recordFrameCoordinator = new RecordFrameCoordinator();
@@ -1,5 +0,0 @@
const REDIRECT_QUALIFIERS = new Set(["client_redirect", "server_redirect"]);
export function hasRedirectQualifier(qualifiers?: readonly string[]): boolean {
return (qualifiers ?? []).some((qualifier) => REDIRECT_QUALIFIERS.has(qualifier));
}
@@ -1,140 +0,0 @@
import type { RenderedRef } from "@browser-skill/vom";
import type { CdpTarget } from "@/browser-driver/frame-graph";
import {
type CaptureVomMatchNode,
type CaptureVomObservationResult,
captureVomObservation,
} from "@/tools/capture-vom-observation";
import type { CdpRunner, ChromeTabsApi } from "@/tools/shared";
export interface IndexedObservationNode {
frameId: string;
geometry: CaptureVomMatchNode;
ref?: RenderedRef;
}
export interface CapturedRecordingObservation {
rootFrameId: string;
index: ObservationNodeIndex;
url: string;
title?: string;
vomText: string;
truncated: boolean;
}
export interface RegisteredObservation {
stateId: string;
rootFrameId: string;
index: ObservationNodeIndex;
url: string;
}
export interface RecordingDocumentScope {
frameId: string;
target: CdpTarget;
}
function nodeKey(frameId: string, backendNodeId: number): string {
return `${frameId}:${backendNodeId}`;
}
function frameTagKey(frameId: string, tag: string): string {
return `${frameId}:${tag.toLowerCase()}`;
}
export class ObservationNodeIndex {
readonly #nodesByFrameTag = new Map<string, IndexedObservationNode[]>();
readonly #refById = new Map<string, RenderedRef>();
readonly #refsByFrame = new Map<string, RenderedRef[]>();
readonly #scopeByProducer = new Map<string, RecordingDocumentScope | null>();
constructor(
input: Pick<CaptureVomObservationResult, "rootFrameId" | "matchNodes" | "refs"> &
Partial<Pick<CaptureVomObservationResult, "frames">>,
) {
const refByNode = new Map<string, RenderedRef>();
for (const ref of input.refs) {
const frameId = ref.frameId ?? input.rootFrameId;
refByNode.set(nodeKey(frameId, ref.backendNodeId), ref);
this.#refById.set(ref.ref, ref);
const frameRefs = this.#refsByFrame.get(frameId) ?? [];
frameRefs.push(ref);
this.#refsByFrame.set(frameId, frameRefs);
}
for (const frame of input.frames ?? []) {
const documentId = frame.recordingDocumentId;
if (!documentId) continue;
this.#scopeByProducer.set(
documentId,
this.#scopeByProducer.has(documentId)
? null
: { frameId: frame.frameId, target: frame.target },
);
}
for (const geometry of input.matchNodes) {
const { frameId } = geometry;
const entry = {
frameId,
geometry,
ref: refByNode.get(nodeKey(frameId, geometry.backendNodeId)),
};
const key = frameTagKey(frameId, geometry.tag);
const bucket = this.#nodesByFrameTag.get(key) ?? [];
bucket.push(entry);
this.#nodesByFrameTag.set(key, bucket);
}
}
candidates(frameId: string, tag: string): readonly IndexedObservationNode[] {
return this.#nodesByFrameTag.get(frameTagKey(frameId, tag)) ?? [];
}
ref(refId: string): RenderedRef | undefined {
return this.#refById.get(refId);
}
refs(frameId: string): readonly RenderedRef[] {
return this.#refsByFrame.get(frameId) ?? [];
}
documentScope(producerId: string): RecordingDocumentScope | undefined {
return this.#scopeByProducer.get(producerId) ?? undefined;
}
}
async function readTabMeta(
tabsApi: ChromeTabsApi,
tabId: number,
): Promise<{ url: string; title?: string }> {
try {
const tab = await tabsApi.get(tabId);
return { url: tab.url ?? "about:blank", title: tab.title };
} catch {
return { url: "about:blank" };
}
}
export async function captureRecordingObservation(input: {
cdp: CdpRunner;
tabsApi: ChromeTabsApi;
tabId: number;
maxTokens: number;
redactValues: boolean;
signal?: AbortSignal;
}): Promise<CapturedRecordingObservation> {
const { url, title } = await readTabMeta(input.tabsApi, input.tabId);
const captured = await captureVomObservation(input.cdp, input.tabId, url, {
maxTokens: input.maxTokens,
redactValues: input.redactValues,
conditionalSurfaceProbe: false,
signal: input.signal,
});
return {
rootFrameId: captured.rootFrameId,
index: new ObservationNodeIndex(captured),
url,
title,
vomText: captured.text,
truncated: captured.truncated,
};
}
@@ -1,128 +0,0 @@
import type { CdpRunner, ChromeTabsApi } from "@/tools/shared";
import { captureRecordingObservation, type RegisteredObservation } from "./observation-capture";
import { RecordingStateRegistry } from "./state-registry";
import { matchObservationTarget, unmatchedTarget } from "./target-matcher";
import type { RecordingDraftStep, StepAnnotation, TargetedRecordingDraft } from "./types";
const DEFAULT_MAX_PAGE_TOKENS = 3_000;
const MIN_CAPTURE_INTERVAL_MS = 200;
export interface TabObservationCursor {
lastSettled: RegisteredObservation | null;
lastCaptureAt: number;
}
function abortableDelay(ms: number, signal?: AbortSignal): Promise<void> {
return new Promise((resolve) => {
if (signal?.aborted) return resolve();
const timer = setTimeout(resolve, ms);
signal?.addEventListener(
"abort",
() => {
clearTimeout(timer);
resolve();
},
{ once: true },
);
});
}
function isTargeted(draft: RecordingDraftStep): draft is TargetedRecordingDraft {
return (
draft.op === "click" ||
draft.op === "hover" ||
draft.op === "fill" ||
draft.op === "press" ||
draft.op === "select"
);
}
export class RecordingObservationSession {
readonly registry: RecordingStateRegistry;
readonly cursor: TabObservationCursor;
readonly annotations: StepAnnotation[];
readonly #maxTokens: number;
readonly #redactValues: boolean;
constructor(
options: {
registry?: RecordingStateRegistry;
cursor?: TabObservationCursor;
annotations?: StepAnnotation[];
maxTokens?: number;
redactValues?: boolean;
} = {},
) {
this.registry = options.registry ?? new RecordingStateRegistry();
this.cursor = options.cursor ?? { lastSettled: null, lastCaptureAt: 0 };
this.annotations = options.annotations ?? [];
this.#maxTokens = options.maxTokens ?? DEFAULT_MAX_PAGE_TOKENS;
this.#redactValues = options.redactValues ?? false;
}
async capture(
cdp: CdpRunner,
tabsApi: ChromeTabsApi,
tabId: number,
signal?: AbortSignal,
): Promise<RegisteredObservation> {
const waitMs = Math.max(0, MIN_CAPTURE_INTERVAL_MS - (Date.now() - this.cursor.lastCaptureAt));
if (waitMs > 0) await abortableDelay(waitMs, signal);
if (signal?.aborted) throw new DOMException("observation aborted", "AbortError");
const captured = await captureRecordingObservation({
cdp,
tabsApi,
tabId,
maxTokens: this.#maxTokens,
redactValues: this.#redactValues,
signal,
});
const state = this.registry.register({
url: captured.url,
title: captured.title,
vomText: captured.vomText,
truncated: captured.truncated,
});
const observation: RegisteredObservation = {
stateId: state.id,
rootFrameId: captured.rootFrameId,
index: captured.index,
url: captured.url,
};
this.cursor.lastSettled = observation;
this.cursor.lastCaptureAt = Date.now();
return observation;
}
bindDraft(draft: RecordingDraftStep, draftId: number, previousActionPending = false): void {
const observation = this.cursor.lastSettled;
if (isTargeted(draft)) {
draft.matchedTarget = observation
? matchObservationTarget({
observation,
hint: draft.targetHint,
fallback: draft.captureTarget,
})
: unmatchedTarget(draft.captureTarget);
}
if (!observation) return;
const unmatched = isTargeted(draft) && draft.matchedTarget?.unmatched === true;
if (previousActionPending && unmatched) return;
draft.preStateId = observation.stateId;
this.registry.markStep(observation.stateId, draftId);
if (!isTargeted(draft) || !draft.matchedTarget?.ref) return;
const ref = observation.index.ref(draft.matchedTarget.ref);
if (!ref) return;
this.annotations.push({
draftId,
op: draft.op,
line: ref.line,
stateId: observation.stateId,
...(draft.op === "fill" && !this.#redactValues
? { detail: JSON.stringify(draft.value) }
: {}),
});
}
}
@@ -1,277 +0,0 @@
import type { CdpRunner, ChromeTabsApi } from "@/tools/shared";
import type { StopReason, TraceV3 } from "@/transport/types";
import { type DocumentSettleScope, waitForDocumentSettled } from "./document-settle";
import type { RegisteredObservation } from "./observation-capture";
import { RecordingObservationSession } from "./observation-session";
import { inferMissingPostStates, SettleController } from "./settle-controller";
import { RecordingStateRegistry } from "./state-registry";
import { buildTraceV3 } from "./trace-builder-v3";
import type { RecordingDraftStep, StepAnnotation } from "./types";
interface TabRecordingContext {
session: RecordingObservationSession;
settle: SettleController;
pendingCapture: PendingCapture | null;
frameRefresh: Promise<void>;
frameRefreshAbort: AbortController | null;
}
interface PendingCapture {
promise: Promise<RegisteredObservation>;
abort: AbortController;
}
export class RecordingObservationRuntime {
readonly #cdp: CdpRunner;
readonly #tabsApi: ChromeTabsApi;
readonly #registry = new RecordingStateRegistry();
readonly #annotations: StepAnnotation[] = [];
readonly #contexts = new Map<number, TabRecordingContext>();
readonly #maxTokens?: number;
readonly #redactValues: boolean;
constructor(input: {
cdp: CdpRunner;
tabsApi: ChromeTabsApi;
maxTokens?: number;
redactValues?: boolean;
}) {
this.#cdp = input.cdp;
this.#tabsApi = input.tabsApi;
this.#maxTokens = input.maxTokens;
this.#redactValues = input.redactValues ?? false;
}
#context(tabId: number): TabRecordingContext {
const existing = this.#contexts.get(tabId);
if (existing) return existing;
const session = new RecordingObservationSession({
registry: this.#registry,
annotations: this.#annotations,
maxTokens: this.#maxTokens,
redactValues: this.#redactValues,
});
const context: TabRecordingContext = {
session,
settle: new SettleController({
session,
cdp: this.#cdp,
tabsApi: this.#tabsApi,
tabId,
}),
pendingCapture: null,
frameRefresh: Promise.resolve(),
frameRefreshAbort: null,
};
this.#contexts.set(tabId, context);
return context;
}
async #capture(tabId: number): Promise<RegisteredObservation> {
const context = this.#context(tabId);
if (context.pendingCapture) return context.pendingCapture.promise;
const abort = new AbortController();
let pending!: PendingCapture;
const promise = context.session.capture(this.#cdp, this.#tabsApi, tabId, abort.signal);
pending = {
abort,
promise: promise.finally(() => {
if (context.pendingCapture === pending) context.pendingCapture = null;
}),
};
context.pendingCapture = pending;
return pending.promise;
}
async captureInitial(tabId: number): Promise<void> {
const context = this.#context(tabId);
if (context.session.cursor.lastSettled) return;
await this.#capture(tabId);
}
/** Refresh the safe observation after a late child Document becomes usable. */
async refreshDocument(tabId: number, producerId: string): Promise<void> {
const context = this.#context(tabId);
context.frameRefreshAbort?.abort();
const abort = new AbortController();
context.frameRefreshAbort = abort;
const previous = context.frameRefresh;
const refresh = (async () => {
await previous;
if (abort.signal.aborted) return;
if (context.pendingCapture) await Promise.allSettled([context.pendingCapture.promise]);
if (abort.signal.aborted) return;
// The first capture discovers the safe producer -> CDP Document scope.
await this.#capture(tabId);
if (abort.signal.aborted) return;
const scope = context.session.cursor.lastSettled?.index.documentScope(producerId);
if (scope) {
await waitForDocumentSettled(this.#cdp, scope, { signal: abort.signal });
}
if (abort.signal.aborted) return;
// Capture again after the child SPA is quiet so the next action can be
// matched against refs that actually exist in its pre-action state.
await this.#capture(tabId);
})();
const tracked = refresh.catch(() => {});
context.frameRefresh = tracked;
try {
await refresh;
} finally {
if (context.frameRefresh === tracked) context.frameRefreshAbort = null;
}
}
async captureTabTransition(
fromTabId: number,
toTabId: number,
): Promise<{ preStateId?: string; postStateId?: string; targetUrl?: string }> {
const from = this.#context(fromTabId);
await this.#flushContext(from);
if (!from.session.cursor.lastSettled) {
try {
await this.captureInitial(fromTabId);
} catch {
// A target-tab observation can still preserve the forward transition.
}
}
const to = this.#context(toTabId);
let target = to.session.cursor.lastSettled;
try {
target = await this.#capture(toTabId);
} catch {
// Reuse the last settled target state when a refresh races navigation.
}
const source = from.session.cursor.lastSettled;
return {
...(source ? { preStateId: source.stateId } : {}),
...(target ? { postStateId: target.stateId, targetUrl: target.url } : {}),
};
}
bindTabTransition(
draft: Extract<RecordingDraftStep, { op: "switch_tab" }>,
draftId: number,
): void {
if (draft.preStateId) this.#registry.markStep(draft.preStateId, draftId);
}
async processDraft(
tabId: number,
drafts: RecordingDraftStep[],
draftIndex: number,
producerId?: string,
): Promise<void> {
const draft = drafts[draftIndex];
if (!draft) return;
const context = this.#context(tabId);
if (!context.session.cursor.lastSettled) {
try {
await this.captureInitial(tabId);
} catch {
// Post-action settle can still provide a usable state.
}
}
const scope = producerId
? context.session.cursor.lastSettled?.index.documentScope(producerId)
: undefined;
if (
producerId &&
(draft.op === "click" ||
draft.op === "hover" ||
draft.op === "fill" ||
draft.op === "press" ||
draft.op === "select")
) {
draft.targetHint = {
...(draft.targetHint ?? {}),
frameId: scope?.frameId ?? null,
geometrySpace: "local",
};
}
context.session.bindDraft(draft, draftIndex + 1, context.settle.hasPending);
context.settle.schedule(drafts, draftIndex, scope);
}
scheduleSettle(
tabId: number,
drafts: RecordingDraftStep[],
draftIndex: number,
scope?: DocumentSettleScope,
): void {
this.#context(tabId).settle.schedule(drafts, draftIndex, scope);
}
clearRedirect(tabId: number): void {
this.#contexts.get(tabId)?.settle.clearRedirect();
}
scheduleRedirect(tabId: number, drafts: RecordingDraftStep[], url: string): void {
this.#context(tabId).settle.scheduleRedirect(drafts, url);
}
async #flushContext(context: TabRecordingContext): Promise<void> {
await context.frameRefresh;
if (context.pendingCapture) await Promise.allSettled([context.pendingCapture.promise]);
await context.settle.flushRedirects();
await context.settle.flush();
}
async flushRedirects(tabId: number): Promise<void> {
await this.#contexts.get(tabId)?.settle.flushRedirects();
}
async flush(): Promise<void> {
for (const context of this.#contexts.values()) await this.#flushContext(context);
}
async settleTrailing(tabId: number, drafts: RecordingDraftStep[]): Promise<void> {
const context = this.#context(tabId);
if (context.pendingCapture) await Promise.allSettled([context.pendingCapture.promise]);
if (!context.session.cursor.lastSettled) {
try {
await this.captureInitial(tabId);
} catch {
// The trace may remain observation-free when CDP is unavailable.
}
}
await context.settle.settleTrailing(drafts);
inferMissingPostStates(drafts);
}
cancel(): void {
for (const context of this.#contexts.values()) {
context.frameRefreshAbort?.abort();
context.pendingCapture?.abort.abort();
context.settle.cancel();
}
}
buildTrace(input: {
drafts: RecordingDraftStep[];
startedAt: string;
purpose?: string;
startUrl?: string;
stoppedBy: StopReason;
bskVersion: string;
includeTabSwitches?: boolean;
}): TraceV3 {
return buildTraceV3({
registry: this.#registry,
drafts: input.drafts,
annotations: this.#annotations,
startedAt: input.startedAt,
purpose: input.purpose,
startUrl: input.startUrl,
stoppedBy: input.stoppedBy,
bskVersion: input.bskVersion,
redactValues: this.#redactValues,
includeTabSwitches: input.includeTabSwitches,
});
}
}
@@ -1,233 +0,0 @@
import type { CdpRunner, ChromeTabsApi } from "@/tools/shared";
import { type DocumentSettleScope, waitForDocumentSettled } from "./document-settle";
import { RecordingObservationSession } from "./observation-session";
import type { RecordingDraftStep } from "./types";
interface PendingSettle {
abort: AbortController;
scope: DocumentSettleScope;
}
interface PendingRedirect {
url: string;
abort: AbortController;
}
const CAPTURE_RETRY_DELAY_MS = 250;
function delay(ms: number, signal?: AbortSignal): Promise<void> {
return new Promise((resolve) => {
if (signal?.aborted) return resolve();
const timer = setTimeout(resolve, ms);
signal?.addEventListener(
"abort",
() => {
clearTimeout(timer);
resolve();
},
{ once: true },
);
});
}
function isAbortError(error: unknown): boolean {
return (
typeof error === "object" &&
error !== null &&
(error as { name?: string }).name === "AbortError"
);
}
export function inferMissingPostStates(drafts: RecordingDraftStep[]): void {
for (let index = 0; index < drafts.length - 1; index += 1) {
const draft = drafts[index];
const next = drafts[index + 1];
if (draft && next && !draft.postStateId && next.preStateId) {
draft.postStateId = next.preStateId;
}
}
}
export class SettleController {
readonly #session: RecordingObservationSession;
readonly #cdp: CdpRunner;
readonly #tabsApi: ChromeTabsApi;
readonly #tabId: number;
readonly #rootScope: DocumentSettleScope;
readonly #pending = new Map<number, PendingSettle>();
#queue = Promise.resolve();
#pendingRedirect: PendingRedirect | null = null;
#redirectQueue = Promise.resolve();
constructor(input: {
session: RecordingObservationSession;
cdp: CdpRunner;
tabsApi: ChromeTabsApi;
tabId: number;
}) {
this.#session = input.session;
this.#cdp = input.cdp;
this.#tabsApi = input.tabsApi;
this.#tabId = input.tabId;
this.#rootScope = { target: { tabId: input.tabId } };
}
get hasPending(): boolean {
return this.#pending.size > 0 || this.#pendingRedirect !== null;
}
async #captureWithRetry(signal?: AbortSignal) {
try {
return await this.#session.capture(this.#cdp, this.#tabsApi, this.#tabId, signal);
} catch (error) {
if (signal?.aborted) throw error;
await delay(CAPTURE_RETRY_DELAY_MS, signal);
return this.#session.capture(this.#cdp, this.#tabsApi, this.#tabId, signal);
}
}
schedule(
drafts: RecordingDraftStep[],
draftIndex: number,
scope: DocumentSettleScope = this.#rootScope,
): void {
if (scope.target.tabId !== this.#tabId) {
throw new Error(
`settle scope tab ${scope.target.tabId} does not belong to tab ${this.#tabId}`,
);
}
const landing = drafts[draftIndex]?.preStateId;
for (const [index, pending] of this.#pending) {
if (index >= draftIndex) continue;
pending.abort.abort();
this.#pending.delete(index);
if (landing && drafts[index] && !drafts[index].postStateId) {
drafts[index].postStateId = landing;
}
}
this.#pending.get(draftIndex)?.abort.abort();
const pending = { abort: new AbortController(), scope };
this.#pending.set(draftIndex, pending);
const task = async () => {
if (pending.abort.signal.aborted) return;
try {
const outcome = await waitForDocumentSettled(this.#cdp, pending.scope, {
signal: pending.abort.signal,
});
if (outcome === "cancelled") return;
const observation = await this.#captureWithRetry(pending.abort.signal);
if (!pending.abort.signal.aborted && drafts[draftIndex]) {
drafts[draftIndex].postStateId = observation.stateId;
}
} catch (error) {
if (!isAbortError(error)) {
console.warn(
`[bsk record] post-action observation failed for step ${draftIndex + 1}`,
error,
);
}
} finally {
if (this.#pending.get(draftIndex) === pending) this.#pending.delete(draftIndex);
}
};
this.#queue = this.#queue.then(task, task).catch(() => {});
}
cancel(): void {
for (const pending of this.#pending.values()) pending.abort.abort();
this.#pending.clear();
this.clearRedirect();
}
async flush(): Promise<void> {
for (let round = 0; round < 10; round += 1) {
const current = this.#queue;
await current;
if (current === this.#queue) return;
}
console.warn("[bsk record] settle queue kept growing; using completed observations");
}
async settleTrailing(drafts: RecordingDraftStep[]): Promise<void> {
const trailing: RecordingDraftStep[] = [];
for (let index = drafts.length - 1; index >= 0; index -= 1) {
const draft = drafts[index];
if (!draft || draft.postStateId) break;
trailing.push(draft);
}
if (trailing.length === 0) return;
try {
const observation = await this.#captureWithRetry();
for (const draft of trailing) draft.postStateId = observation.stateId;
} catch (error) {
console.warn("[bsk record] final observation at stop failed", error);
}
}
clearRedirect(): void {
this.#pendingRedirect?.abort.abort();
this.#pendingRedirect = null;
}
scheduleRedirect(drafts: RecordingDraftStep[], url: string): void {
this.#pendingRedirect?.abort.abort();
const pending: PendingRedirect = { url, abort: new AbortController() };
this.#pendingRedirect = pending;
const task = () => this.#settleRedirect(drafts, pending);
this.#redirectQueue = this.#redirectQueue.then(task, task).catch(() => {});
}
async #settleRedirect(drafts: RecordingDraftStep[], pending: PendingRedirect): Promise<void> {
const outcome = await waitForDocumentSettled(this.#cdp, this.#rootScope, {
signal: pending.abort.signal,
});
if (outcome === "cancelled" || this.#pendingRedirect !== pending) return;
let finalUrl = pending.url;
try {
finalUrl = (await this.#tabsApi.get(this.#tabId)).url || finalUrl;
} catch {
// The navigation event URL remains the best available destination.
}
if (this.#pendingRedirect !== pending) return;
this.#pendingRedirect = null;
if (
!finalUrl ||
finalUrl === "about:blank" ||
this.#session.cursor.lastSettled?.url === finalUrl
) {
return;
}
const last = drafts[drafts.length - 1];
if (last?.op === "navigate" && last.url === finalUrl) {
if (!last.postStateId) this.schedule(drafts, drafts.length - 1);
await this.flush();
return;
}
const draft: RecordingDraftStep = {
op: "navigate",
url: finalUrl,
pageUrl: finalUrl,
cause: "browser",
transitionQualifiers: ["server_redirect"],
preStateId: this.#session.cursor.lastSettled?.stateId,
};
drafts.push(draft);
const draftIndex = drafts.length - 1;
if (draft.preStateId) this.#session.registry.markStep(draft.preStateId, draftIndex + 1);
this.schedule(drafts, draftIndex);
await this.flush();
}
async flushRedirects(): Promise<void> {
for (let round = 0; round < 10; round += 1) {
const current = this.#redirectQueue;
await current;
if (current === this.#redirectQueue) return;
}
console.warn("[bsk record] redirect queue kept growing; using the final completed landing");
}
}
@@ -1,57 +0,0 @@
export interface RecordedStateEntry {
id: string;
url: string;
title?: string;
/** Rendered VOM text; capture indexes and source DOM/AX data never enter the registry. */
vomText: string;
truncated: boolean;
stepsHere: number[];
}
function stateIdentity(url: string, body: string): string {
return `${url}\0${body}`;
}
export class RecordingStateRegistry {
readonly #entriesById = new Map<string, RecordedStateEntry>();
readonly #idByIdentity = new Map<string, string>();
#nextId = 1;
register(input: {
url: string;
title?: string;
vomText: string;
truncated?: boolean;
}): RecordedStateEntry {
const identity = stateIdentity(input.url, input.vomText);
const existingId = this.#idByIdentity.get(identity);
if (existingId) {
const existing = this.#entriesById.get(existingId)!;
if (!existing.title && input.title) existing.title = input.title;
if (input.truncated) existing.truncated = true;
return existing;
}
const entry: RecordedStateEntry = {
id: `s${this.#nextId}`,
url: input.url,
...(input.title ? { title: input.title } : {}),
vomText: input.vomText,
truncated: input.truncated ?? false,
stepsHere: [],
};
this.#nextId += 1;
this.#entriesById.set(entry.id, entry);
this.#idByIdentity.set(identity, entry.id);
return entry;
}
values(): RecordedStateEntry[] {
return [...this.#entriesById.values()];
}
markStep(stateId: string, draftId: number): void {
const entry = this.#entriesById.get(stateId);
if (entry && !entry.stepsHere.includes(draftId)) entry.stepsHere.push(draftId);
}
}
@@ -1,155 +0,0 @@
import type { RecordStepPayload } from "../record-bridge";
import { hasRedirectQualifier } from "./navigation-policy";
import type { RecordingDraftStep, TargetMatchHint } from "./types";
export interface RecordingStepBuffer {
steps: RecordingDraftStep[];
navigation: RecordingNavigationCursor;
}
export interface RecordingNavigationCursor {
currentUrl?: string;
pendingNavigation: boolean;
pendingNavigationDeadline?: number;
}
const NAVIGATION_TRIGGER_WINDOW_MS = 3_000;
function toDraftStep(
payload: RecordStepPayload,
targetHint?: TargetMatchHint,
): RecordingDraftStep | null {
const pageUrl = payload.page_url;
const common = {
...(pageUrl ? { pageUrl } : {}),
...(targetHint ? { targetHint } : {}),
};
switch (payload.op) {
case "click":
return payload.target ? { op: "click", captureTarget: payload.target, ...common } : null;
case "hover":
return payload.target ? { op: "hover", captureTarget: payload.target, ...common } : null;
case "fill":
return payload.target
? {
op: "fill",
captureTarget: payload.target,
value: payload.value ?? "",
...(payload.commit ? { commit: payload.commit } : {}),
...(payload.redacted ? { redacted: true } : {}),
...common,
}
: null;
case "press":
return payload.key
? {
op: "press",
key: payload.key,
...(payload.target ? { captureTarget: payload.target } : {}),
...(payload.modifiers?.length ? { modifiers: payload.modifiers } : {}),
...common,
}
: null;
case "select":
return payload.target && payload.values
? {
op: "select",
captureTarget: payload.target,
values: payload.values,
...(payload.labels?.length ? { labels: payload.labels } : {}),
...common,
}
: null;
case "navigate":
return null;
}
}
function annotateLastStepNavigation(buffer: RecordingStepBuffer, url: string): number {
for (let index = buffer.steps.length - 1; index >= 0; index -= 1) {
const step = buffer.steps[index];
if (!step) continue;
if (step.op === "click" || step.op === "press" || step.op === "select" || step.op === "fill") {
step.navigatedTo = url;
return index;
}
break;
}
return -1;
}
export type NavigationObserveResult =
| { kind: "noop" }
| { kind: "annotated"; index: number }
| { kind: "appended"; index: number }
| { kind: "coalesce_redirect"; url: string };
export function observeRecordedNavigation(
buffer: RecordingStepBuffer,
url: string,
causedByAction?: boolean,
transitionType?: string,
transitionQualifiers?: string[],
): NavigationObserveResult {
const navigation = buffer.navigation;
if (!url || url === navigation.currentUrl) return { kind: "noop" };
navigation.currentUrl = url;
const pendingIsCurrent =
navigation.pendingNavigation &&
(navigation.pendingNavigationDeadline === undefined ||
navigation.pendingNavigationDeadline >= Date.now());
if (causedByAction === true || (causedByAction === undefined && pendingIsCurrent)) {
navigation.pendingNavigation = false;
navigation.pendingNavigationDeadline = undefined;
const annotatedIndex = annotateLastStepNavigation(buffer, url);
if (annotatedIndex >= 0) return { kind: "annotated", index: annotatedIndex };
} else {
navigation.pendingNavigation = false;
navigation.pendingNavigationDeadline = undefined;
}
if (hasRedirectQualifier(transitionQualifiers)) {
return { kind: "coalesce_redirect", url };
}
buffer.steps.push({
op: "navigate",
url,
pageUrl: url,
transitionType,
transitionQualifiers,
});
return { kind: "appended", index: buffer.steps.length - 1 };
}
export function appendRecordedPayload(
buffer: RecordingStepBuffer,
payload: RecordStepPayload,
targetHint?: TargetMatchHint,
): number | null {
if (payload.op === "navigate") {
if (!payload.url) return null;
const result = observeRecordedNavigation(
buffer,
payload.url,
payload.navigation_caused_by_action,
payload.transitionType,
payload.transitionQualifiers,
);
return result.kind === "appended" ? result.index : null;
}
const step = toDraftStep(
{ ...payload, page_url: payload.page_url ?? buffer.navigation.currentUrl },
targetHint,
);
if (!step) return null;
buffer.steps.push(step);
if (step.op === "click" || step.op === "press" || step.op === "select" || step.op === "fill") {
buffer.navigation.pendingNavigation = payload.expects_navigation === true;
buffer.navigation.pendingNavigationDeadline = buffer.navigation.pendingNavigation
? Date.now() + NAVIGATION_TRIGGER_WINDOW_MS
: undefined;
}
return buffer.steps.length - 1;
}
@@ -1,61 +0,0 @@
import type { RecordingNavigationCursor } from "./step-buffer";
export interface TabActivation {
tabId: number;
revision: number;
}
export class RecordingTabCoordinator {
readonly #navigationByTab = new Map<number, RecordingNavigationCursor>();
#activeTabId: number;
#currentTabId: number;
#activationRevision = 0;
constructor(initialTabId: number, initialUrl?: string) {
this.#activeTabId = initialTabId;
this.#currentTabId = initialTabId;
this.#navigationByTab.set(initialTabId, {
currentUrl: initialUrl,
pendingNavigation: false,
});
}
get activeTabId(): number {
return this.#activeTabId;
}
get currentTabId(): number {
return this.#currentTabId;
}
noteActivation(tabId: number): TabActivation {
this.#activeTabId = tabId;
this.#activationRevision += 1;
return { tabId, revision: this.#activationRevision };
}
isLatest(activation: TabActivation): boolean {
return (
activation.tabId === this.#activeTabId && activation.revision === this.#activationRevision
);
}
commit(tabId: number, currentUrl?: string): void {
if (currentUrl !== undefined) this.navigation(tabId).currentUrl = currentUrl;
this.#currentTabId = tabId;
}
navigation(tabId: number, fallbackUrl?: string): RecordingNavigationCursor {
const existing = this.#navigationByTab.get(tabId);
if (existing) {
if (!existing.currentUrl && fallbackUrl) existing.currentUrl = fallbackUrl;
return existing;
}
const created: RecordingNavigationCursor = {
currentUrl: fallbackUrl,
pendingNavigation: false,
};
this.#navigationByTab.set(tabId, created);
return created;
}
}
@@ -1,86 +0,0 @@
import type { RenderedRef } from "@browser-skill/vom";
import type { TargetDescriptorV3 } from "@/transport/types";
import type { CaptureTargetDescriptor } from "../describe-target";
import type { IndexedObservationNode, RegisteredObservation } from "./observation-capture";
import type { TargetGeometry, TargetMatchHint } from "./types";
const MATCH_TOLERANCE_PX = 2;
function close(a: number, b: number): boolean {
return Math.abs(a - b) <= MATCH_TOLERANCE_PX;
}
function rectMatches(a: TargetGeometry["rect"], b: TargetGeometry["rect"]): boolean {
return close(a.x, b.x) && close(a.y, b.y) && close(a.w, b.w) && close(a.h, b.h);
}
function candidateMatches(
candidate: IndexedObservationNode,
geometry: TargetGeometry,
geometrySpace: "top" | "local",
): boolean {
const rect = geometrySpace === "local" ? candidate.geometry.localRect : candidate.geometry.rect;
return rect != null && rectMatches(geometry.rect, rect);
}
export function unmatchedTarget(fallback?: CaptureTargetDescriptor): TargetDescriptorV3 {
return {
...(fallback?.role ? { role: fallback.role } : {}),
...(fallback?.name ? { name: fallback.name } : {}),
unmatched: true,
};
}
function normalized(value: string | undefined): string {
return value?.replace(/\s+/g, " ").trim().toLowerCase() ?? "";
}
function matchesSemantics(ref: RenderedRef, fallback?: CaptureTargetDescriptor): boolean {
const role = normalized(fallback?.role);
const name = normalized(fallback?.name);
if (!role && !name) return false;
if (role && normalized(ref.role) !== role) return false;
if (name && normalized(ref.name) !== name) return false;
return true;
}
function descriptor(ref: RenderedRef): TargetDescriptorV3 {
return {
ref: ref.ref,
...(ref.role ? { role: ref.role } : {}),
...(ref.name ? { name: ref.name } : {}),
...(ref.ctx ? { ctx: ref.ctx } : {}),
};
}
export function matchObservationTarget(input: {
observation: RegisteredObservation;
hint?: TargetMatchHint;
fallback?: CaptureTargetDescriptor;
}): TargetDescriptorV3 {
if (input.hint?.frameId === null) return unmatchedTarget(input.fallback);
const frameId = input.hint?.frameId ?? input.observation.rootFrameId;
const geometry = input.hint?.geometry;
if (geometry) {
const matches = input.observation.index
.candidates(frameId, geometry.tag)
.filter(
(candidate) =>
candidate.ref &&
candidateMatches(candidate, geometry, input.hint?.geometrySpace ?? "top"),
);
if (matches.length === 1) return descriptor(matches[0]!.ref!);
const semanticMatches = matches.filter(
(candidate) => candidate.ref && matchesSemantics(candidate.ref, input.fallback),
);
if (semanticMatches.length === 1) return descriptor(semanticMatches[0]!.ref!);
return unmatchedTarget(input.fallback);
}
const semanticMatches = input.observation.index
.refs(frameId)
.filter((ref) => matchesSemantics(ref, input.fallback));
return semanticMatches.length === 1
? descriptor(semanticMatches[0]!)
: unmatchedTarget(input.fallback);
}
@@ -1,92 +0,0 @@
import {
type StepV3,
type StopReason,
TRACE_VERSION_V3,
type TraceStateV3,
type TraceV3,
VOM_FORMAT_VERSION,
} from "@/transport/types";
import { resolveDraftStartUrl } from "./draft-policy";
import type { RecordedStateEntry, RecordingStateRegistry } from "./state-registry";
import { reduceTraceStepsV3 } from "./trace-reducer-v3";
import { formatTraceStateBody } from "./trace-state-body";
import type { RecordingDraftStep, StepAnnotation } from "./types";
function publishedEntries(registry: RecordingStateRegistry, steps: StepV3[]): RecordedStateEntry[] {
const entries = registry.values();
if (steps.length === 0) return entries.slice(0, 1);
const referenced = new Set(steps.flatMap((step) => [step.state, step.result.state]));
return entries.filter((entry) => referenced.has(entry.id));
}
function remapDraftIds(draftIds: number[], stepIdByDraftId: Map<number, number>): number[] {
return [
...new Set(
draftIds.flatMap((id) => {
const stepId = stepIdByDraftId.get(id);
return stepId === undefined ? [] : [stepId];
}),
),
].sort((a, b) => a - b);
}
export function buildTraceV3(input: {
registry: RecordingStateRegistry;
drafts: RecordingDraftStep[];
annotations?: StepAnnotation[];
startedAt: string;
purpose?: string;
startUrl?: string;
stoppedBy: StopReason;
bskVersion: string;
redactValues?: boolean;
includeTabSwitches?: boolean;
}): TraceV3 {
const reduced = reduceTraceStepsV3(input.drafts, {
includeTabSwitches: input.includeTabSwitches,
redactValues: input.redactValues,
});
const entries = publishedEntries(input.registry, reduced.steps);
const publishedId = new Map(entries.map((entry, index) => [entry.id, `s${index + 1}`]));
const annotationsByState = new Map<string, StepAnnotation[]>();
for (const annotation of input.annotations ?? []) {
const bucket = annotationsByState.get(annotation.stateId) ?? [];
bucket.push(annotation);
annotationsByState.set(annotation.stateId, bucket);
}
const steps = reduced.steps.map((step) => ({
...step,
state: publishedId.get(step.state) ?? step.state,
result: { state: publishedId.get(step.result.state) ?? step.result.state },
}));
const states: TraceStateV3[] = entries.map((entry) => {
const id = publishedId.get(entry.id) ?? entry.id;
return {
id,
url: entry.url,
...(entry.title ? { title: entry.title } : {}),
body: formatTraceStateBody({
stateId: id,
url: entry.url,
title: entry.title,
stepIds: remapDraftIds(entry.stepsHere, reduced.stepIdByDraftId),
vomText: entry.vomText,
annotations: annotationsByState.get(entry.id) ?? [],
stepIdByDraftId: reduced.stepIdByDraftId,
}),
...(entry.truncated ? { truncated: true } : {}),
};
});
return {
version: TRACE_VERSION_V3,
...(input.purpose ? { purpose: input.purpose } : {}),
recorded_at: new Date().toISOString(),
started_at: input.startedAt,
stopped_by: input.stoppedBy,
entry: { start_url: resolveDraftStartUrl(input.drafts, input.startUrl, states[0]?.url) },
recorder: { bsk: input.bskVersion, vom: VOM_FORMAT_VERSION },
states,
steps,
};
}
@@ -1,215 +0,0 @@
import type { PageRefV2, SelectedOptionV2, StepV2, TraceV2 } from "@/transport/types";
import { resolveDraftStartUrl, shouldIncludeDraft } from "./draft-policy";
import type { RecordingDraftStep } from "./types";
/** Collapse consecutive navigations to the last hop. */
function collapseNavigations(steps: RecordingDraftStep[]): RecordingDraftStep[] {
const out: RecordingDraftStep[] = [];
for (const step of steps) {
const prev = out[out.length - 1];
if (step.op === "navigate" && prev?.op === "navigate") {
out[out.length - 1] = step;
continue;
}
out.push(step);
}
return out;
}
function collectUrls(steps: RecordingDraftStep[], startUrl?: string): string[] {
const urls: string[] = [];
if (startUrl) urls.push(startUrl);
for (const step of steps) {
if (step.op === "navigate") {
urls.push(step.url);
continue;
}
if (step.pageUrl) urls.push(step.pageUrl);
if ("navigatedTo" in step && step.navigatedTo) urls.push(step.navigatedTo);
}
const seen = new Set<string>();
const unique: string[] = [];
for (const url of urls) {
if (!url || seen.has(url)) continue;
seen.add(url);
unique.push(url);
}
return unique;
}
function buildPageRegistry(
steps: RecordingDraftStep[],
startUrl?: string,
): { pages: PageRefV2[]; urlToId: Map<string, string> } {
const urls = collectUrls(steps, startUrl);
const urlToId = new Map<string, string>();
const pages = urls.map((url, index) => {
const id = `p${index + 1}`;
urlToId.set(url, id);
return { id, url };
});
return { pages, urlToId };
}
function pageIdFor(
url: string | undefined,
urlToId: Map<string, string>,
fallbackUrl?: string,
): string {
if (url && urlToId.has(url)) return urlToId.get(url)!;
if (fallbackUrl && urlToId.has(fallbackUrl)) return urlToId.get(fallbackUrl)!;
return urlToId.values().next().value ?? "p1";
}
function pageUrlForDraft(step: RecordingDraftStep, fallbackUrl?: string): string | undefined {
if (step.op === "navigate") return step.pageUrl ?? step.url;
if (step.pageUrl) return step.pageUrl;
return fallbackUrl;
}
function effectForNavigation(
navigatedTo: string | undefined,
urlToId: Map<string, string>,
): StepV2["effect"] {
if (!navigatedTo) return undefined;
const pageId = urlToId.get(navigatedTo);
if (!pageId) return undefined;
return { navigated_to: pageId };
}
function withEffect(step: StepV2, effect: StepV2["effect"]): StepV2 {
if (!effect) return step;
return { ...step, effect };
}
function toSelection(values: string[], labels?: string[]): SelectedOptionV2[] {
return values.map((value, index) => ({
value,
...(labels?.[index] ? { label: labels[index] } : {}),
}));
}
function toV2Step(
step: RecordingDraftStep,
id: number,
urlToId: Map<string, string>,
fallbackUrl?: string,
): StepV2 | null {
if (!shouldIncludeDraft(step)) return null;
const pageUrl = pageUrlForDraft(step, fallbackUrl);
const page = pageIdFor(pageUrl, urlToId, fallbackUrl);
switch (step.op) {
case "navigate":
return {
op: "navigate",
id,
page: pageIdFor(step.url, urlToId, fallbackUrl),
to: step.url,
};
case "click":
if (!step.captureTarget) return null;
return withEffect(
{
op: "click",
id,
page,
target: step.captureTarget,
},
effectForNavigation(step.navigatedTo, urlToId),
);
case "fill":
if (!step.captureTarget) return null;
return {
op: "fill",
id,
page,
target: step.captureTarget,
value: step.value,
...(step.redacted ? { redacted: true } : {}),
};
case "press":
return withEffect(
{
op: "press",
id,
page,
key: step.key,
...(step.captureTarget ? { target: step.captureTarget } : {}),
...(step.modifiers?.length ? { modifiers: step.modifiers } : {}),
},
effectForNavigation(step.navigatedTo, urlToId),
);
case "select":
if (!step.captureTarget) return null;
return withEffect(
{
op: "select",
id,
page,
target: step.captureTarget,
selection: toSelection(step.values, step.labels),
},
effectForNavigation(step.navigatedTo, urlToId),
);
// `hover` only exists in Trace v3. Peers that negotiate v2 predate the
// step variant and fail to decode the whole result if we emit it.
case "hover":
case "scroll":
case "switch_tab":
return null;
}
}
interface ReducedTrace {
pages: PageRefV2[];
steps: StepV2[];
}
/**
* Compile capture drafts into record-only trace v2 steps.
* Variable inputs are NOT classified here — executing agents infer that at run time.
*/
function reduceTraceSteps(steps: RecordingDraftStep[], startUrl?: string): ReducedTrace {
const collapsed = collapseNavigations(steps);
const { pages, urlToId } = buildPageRegistry(collapsed, startUrl);
const out: StepV2[] = [];
let id = 1;
let lastUrl = startUrl;
for (const draft of collapsed) {
if (draft.op === "navigate") lastUrl = draft.url;
else if ("navigatedTo" in draft && draft.navigatedTo) lastUrl = draft.navigatedTo;
else if (draft.pageUrl) lastUrl = draft.pageUrl;
const step = toV2Step(draft, id, urlToId, lastUrl);
if (!step) continue;
out.push(step);
id += 1;
}
return { pages, steps: out };
}
function resolveTraceStartUrl(
drafts: RecordingDraftStep[],
startUrl?: string,
pages?: PageRefV2[],
): string {
return resolveDraftStartUrl(drafts, startUrl, pages?.[0]?.url);
}
export function buildTraceV2(input: {
steps: RecordingDraftStep[];
startedAt: string;
startUrl?: string;
purpose?: string;
}): TraceV2 {
const { pages, steps } = reduceTraceSteps(input.steps, input.startUrl);
return {
recorded_at: new Date().toISOString(),
started_at: input.startedAt,
...(input.purpose ? { purpose: input.purpose } : {}),
entry: { start_url: resolveTraceStartUrl(input.steps, input.startUrl, pages) },
pages,
steps,
};
}
@@ -1,154 +0,0 @@
import type { NavigationCause, StepV3 } from "@/transport/types";
import { shouldIncludeDraft } from "./draft-policy";
import { hasRedirectQualifier } from "./navigation-policy";
import { unmatchedTarget } from "./target-matcher";
import type { RecordingDraftStep } from "./types";
interface CollapsedDraft {
draft: RecordingDraftStep;
draftIds: number[];
}
const TRANSITION_CAUSES: Record<string, NavigationCause> = {
typed: "user_typed",
generated: "user_typed",
keyword: "user_typed",
keyword_generated: "user_typed",
link: "link",
form_submit: "form_submit",
reload: "reload",
auto_bookmark: "browser",
start_page: "browser",
};
function isRedirect(step: Extract<RecordingDraftStep, { op: "navigate" }>): boolean {
return hasRedirectQualifier(step.transitionQualifiers);
}
function collapseRedirects(steps: RecordingDraftStep[]): CollapsedDraft[] {
const output: CollapsedDraft[] = [];
steps.forEach((step, index) => {
const previous = output[output.length - 1];
if (step.op === "navigate" && previous?.draft.op === "navigate" && isRedirect(step)) {
previous.draft = {
...previous.draft,
url: step.url,
postStateId: step.postStateId ?? previous.draft.postStateId,
};
previous.draftIds.push(index + 1);
return;
}
output.push({ draft: { ...step }, draftIds: [index + 1] });
});
return output;
}
function navigationCause(step: Extract<RecordingDraftStep, { op: "navigate" }>): NavigationCause {
if (step.cause) return step.cause;
const qualifiers = step.transitionQualifiers ?? [];
if (qualifiers.includes("forward_back")) return "history";
if (qualifiers.includes("from_address_bar")) return "user_typed";
return TRANSITION_CAUSES[step.transitionType ?? ""] ?? "browser";
}
function selection(values: string[], labels?: string[]): Array<{ value: string; label?: string }> {
return values.map((value, index) => ({
value,
...(labels?.[index] ? { label: labels[index] } : {}),
}));
}
interface ReduceDraftOptions {
includeTabSwitches: boolean;
redactValues: boolean;
}
function reduceDraft(
draft: RecordingDraftStep,
id: number,
options: ReduceDraftOptions,
): StepV3 | null {
if (!shouldIncludeDraft(draft)) return null;
if (draft.op === "switch_tab") {
if (!options.includeTabSwitches || !draft.preStateId || !draft.postStateId) return null;
return {
op: "switch_tab",
id,
state: draft.preStateId,
result: { state: draft.postStateId },
};
}
const state = draft.preStateId ?? draft.postStateId;
const resultState = draft.postStateId ?? draft.preStateId;
if (!state || !resultState) return null;
const common = { id, state, result: { state: resultState } };
switch (draft.op) {
case "navigate":
return { op: "navigate", ...common, to: draft.url, cause: navigationCause(draft) };
case "click":
return {
op: "click",
...common,
target: draft.matchedTarget ?? unmatchedTarget(draft.captureTarget),
};
case "hover":
return {
op: "hover",
...common,
target: draft.matchedTarget ?? unmatchedTarget(draft.captureTarget),
};
case "fill":
const fillIsRedacted = options.redactValues || draft.redacted === true;
return {
op: "fill",
...common,
target: draft.matchedTarget ?? unmatchedTarget(draft.captureTarget),
value: fillIsRedacted ? "***" : draft.value,
commit: draft.commit ?? "blur",
...(fillIsRedacted ? { redacted: true } : {}),
};
case "press":
return {
op: "press",
...common,
key: draft.key,
...(draft.captureTarget || draft.matchedTarget
? { target: draft.matchedTarget ?? unmatchedTarget(draft.captureTarget) }
: {}),
...(draft.modifiers?.length ? { modifiers: draft.modifiers } : {}),
};
case "select":
return {
op: "select",
...common,
target: draft.matchedTarget ?? unmatchedTarget(draft.captureTarget),
...(!options.redactValues ? { selection: selection(draft.values, draft.labels) } : {}),
};
case "scroll":
return { op: "scroll", ...common };
}
}
export interface ReducedTraceV3 {
steps: StepV3[];
stepIdByDraftId: Map<number, number>;
}
export function reduceTraceStepsV3(
steps: RecordingDraftStep[],
options: { includeTabSwitches?: boolean; redactValues?: boolean } = {},
): ReducedTraceV3 {
const output: StepV3[] = [];
const stepIdByDraftId = new Map<number, number>();
for (const { draft, draftIds } of collapseRedirects(steps)) {
const step = reduceDraft(draft, output.length + 1, {
includeTabSwitches: options.includeTabSwitches === true,
redactValues: options.redactValues === true,
});
if (!step) continue;
output.push(step);
for (const draftId of draftIds) stepIdByDraftId.set(draftId, step.id);
}
return { steps: output, stepIdByDraftId };
}
@@ -1,39 +0,0 @@
import type { StepAnnotation } from "./types";
function annotationText(annotation: StepAnnotation, stepId: number): string {
return ` ⟵ step ${stepId}: ${annotation.op}${annotation.detail ? `: ${annotation.detail}` : ""}`;
}
export function formatTraceStateBody(input: {
stateId: string;
url: string;
title?: string;
stepIds: number[];
vomText: string;
annotations: StepAnnotation[];
stepIdByDraftId: Map<number, number>;
}): string {
const lines = ["# bsk-observation 1", `state: ${JSON.stringify(input.stateId)}`];
lines.push(`url: ${JSON.stringify(input.url)}`);
if (input.title) lines.push(`title: ${JSON.stringify(input.title)}`);
if (input.stepIds.length > 0) lines.push(`steps_here: [${input.stepIds.join(", ")}]`);
lines.push("---");
const byLine = new Map<number, Array<{ annotation: StepAnnotation; stepId: number }>>();
for (const annotation of input.annotations) {
const stepId = input.stepIdByDraftId.get(annotation.draftId);
if (stepId === undefined) continue;
const bucket = byLine.get(annotation.line) ?? [];
bucket.push({ annotation, stepId });
byLine.set(annotation.line, bucket);
}
input.vomText.split("\n").forEach((bodyLine, lineIndex) => {
let line = bodyLine;
for (const item of byLine.get(lineIndex) ?? []) {
line += annotationText(item.annotation, item.stepId);
}
lines.push(line);
});
return `${lines.join("\n")}\n`;
}
-85
View File
@@ -1,85 +0,0 @@
import type { CaptureTargetDescriptor } from "@/lib/describe-target";
import type {
FillCommit,
KeyModifier,
NavigationCause,
StepV3,
TargetDescriptorV3,
} from "@/transport/types";
export interface TargetGeometry {
/** Top-level viewport-relative CSS pixels, as defined by the geometry module. */
rect: { x: number; y: number; w: number; h: number };
tag: string;
}
export interface TargetMatchHint {
geometry?: TargetGeometry;
/** Missing means top frame; null means the source Document could not be resolved. */
frameId?: string | null;
geometrySpace?: "top" | "local";
}
export interface StepAnnotation {
draftId: number;
op: StepV3["op"];
line: number;
stateId: string;
detail?: string;
}
interface DraftStateLink {
pageUrl?: string;
preStateId?: string;
postStateId?: string;
}
interface DraftTarget {
captureTarget?: CaptureTargetDescriptor;
targetHint?: TargetMatchHint;
matchedTarget?: TargetDescriptorV3;
}
interface DraftNavigationEffect {
navigatedTo?: string;
}
export type RecordingDraftStep =
| ({ op: "click" } & DraftStateLink & DraftTarget & DraftNavigationEffect)
| ({ op: "hover" } & DraftStateLink & DraftTarget)
| ({
op: "fill";
value: string;
commit?: FillCommit;
redacted?: boolean;
} & DraftStateLink &
DraftTarget &
DraftNavigationEffect)
| ({
op: "press";
key: string;
modifiers?: KeyModifier[];
} & DraftStateLink &
DraftTarget &
DraftNavigationEffect)
| ({
op: "select";
values: string[];
labels?: string[];
} & DraftStateLink &
DraftTarget &
DraftNavigationEffect)
| ({ op: "scroll" } & DraftStateLink)
| ({ op: "switch_tab" } & DraftStateLink)
| ({
op: "navigate";
url: string;
cause?: NavigationCause;
transitionType?: string;
transitionQualifiers?: string[];
} & DraftStateLink);
export type TargetedRecordingDraft = Extract<
RecordingDraftStep,
{ op: "click" | "hover" | "fill" | "press" | "select" }
>;
+236
View File
@@ -0,0 +1,236 @@
import type {
DraftTraceStep,
FillCommit,
NavigationCause,
Step,
TraceState,
} from "@/transport/types";
import {
DEFAULT_FILL_COMMIT,
fnv1a64,
mapNavigationCause,
nextStateId,
resetStateIdCounterForTests,
} from "./record-constants";
const CLIPBOARD_KEYS = new Set(["a", "c", "v", "x", "A", "C", "V", "X"]);
const MODIFIER_ONLY_KEYS = new Set(["Meta", "Control", "Alt", "Shift", "OS", "Hyper", "Super"]);
export function shouldRecordPress(
key: string,
modifiers?: Array<"alt" | "ctrl" | "meta" | "shift">,
): boolean {
if (MODIFIER_ONLY_KEYS.has(key)) return false;
const mods = modifiers ?? [];
const hasCtrlOrMeta = mods.includes("ctrl") || mods.includes("meta");
if (hasCtrlOrMeta && CLIPBOARD_KEYS.has(key)) return false;
if (key === "Enter" || key === "Escape") return true;
if (key.length === 1 && !hasCtrlOrMeta && !mods.includes("alt")) return false;
return false;
}
function shouldIncludeDraft(step: DraftTraceStep): boolean {
if (step.op === "press" && !shouldRecordPress(step.key, step.modifiers)) return false;
return true;
}
/** A reduced draft plus the capture-order ids of every draft folded into it. */
interface CollapsedDraft {
draft: DraftTraceStep;
draftIds: number[];
}
/**
* Collapse a redirect chain into a single hop.
*
* The surviving step keeps the *first* hop's origin state and cause — that is
* where the user was and why they left — and the *last* hop's destination, so
* the intermediate URL the browser only passed through never becomes the
* step's `state` or `to`.
*/
function collapseNavigations(steps: DraftTraceStep[]): CollapsedDraft[] {
const out: CollapsedDraft[] = [];
steps.forEach((step, index) => {
const draftId = index + 1;
const prev = out[out.length - 1];
if (step.op === "navigate" && prev?.draft.op === "navigate") {
prev.draft = {
...prev.draft,
url: step.url,
postStateId: step.postStateId ?? prev.draft.postStateId,
};
prev.draftIds.push(draftId);
return;
}
out.push({ draft: step, draftIds: [draftId] });
});
return out;
}
export interface StateRegistryEntry extends TraceState {
contentHash: string;
rawVomText: string;
stepsHere: number[];
}
export function stateDedupKey(body: string, url: string): string {
return `${fnv1a64(body)}:${url}`;
}
/** Register or reuse a page observation in the states dictionary. */
export function registerObservation(
registry: Map<string, StateRegistryEntry>,
input: {
url: string;
title?: string;
rawVomText: string;
truncated?: boolean;
},
): string {
const key = stateDedupKey(input.rawVomText, input.url);
for (const entry of registry.values()) {
if (entry.contentHash === key) return entry.id;
}
const id = nextStateId();
registry.set(id, {
id,
url: input.url,
...(input.title ? { title: input.title } : {}),
truncated: input.truncated ?? false,
contentHash: key,
rawVomText: input.rawVomText,
stepsHere: [],
});
return id;
}
function toSelection(
values: string[],
labels?: string[],
): Array<{ value: string; label?: string }> {
return values.map((value, index) => ({
value,
...(labels?.[index] ? { label: labels[index] } : {}),
}));
}
function navigateCauseForDraft(
draft: Extract<DraftTraceStep, { op: "navigate" }>,
): NavigationCause {
if (draft.cause) return draft.cause;
const mapped = mapNavigationCause({
transitionType: draft.transitionType,
transitionQualifiers: draft.transitionQualifiers,
});
return mapped ?? "browser";
}
function toV3Step(draft: DraftTraceStep, id: number): Step | null {
if (!shouldIncludeDraft(draft)) return null;
// An action the user really performed must not disappear because one of its
// observations is missing — a capture racing a document swap is routine, and
// the last step of a recording is the most exposed to it. Fall back to the
// endpoint we do know; only a step with no observation at all has nothing to
// point at.
const preState = draft.preStateId ?? draft.postStateId;
const postState = draft.postStateId ?? draft.preStateId;
if (!preState || !postState) return null;
const common = { id, state: preState, result: { state: postState } };
switch (draft.op) {
case "navigate":
return {
op: "navigate",
...common,
to: draft.url,
cause: navigateCauseForDraft(draft),
};
case "click":
return { op: "click", ...common, target: draft.target };
case "hover":
return { op: "hover", ...common, target: draft.target };
case "fill":
return {
op: "fill",
...common,
target: draft.target,
value: draft.value,
commit: draft.commit ?? DEFAULT_FILL_COMMIT,
...(draft.redacted ? { redacted: true } : {}),
};
case "press":
return {
op: "press",
...common,
key: draft.key,
...(draft.target ? { target: draft.target } : {}),
...(draft.modifiers?.length ? { modifiers: draft.modifiers } : {}),
};
case "select":
return {
op: "select",
...common,
target: draft.target,
selection: toSelection(draft.values, draft.labels),
};
case "scroll":
return { op: "scroll", ...common };
}
}
export interface ReducedTrace {
states: TraceState[];
steps: Step[];
/**
* Capture-order draft id (`draftIndex + 1`) → published step id. Collapsed
* and dropped drafts make the two diverge, so anything the recorder tagged
* with a draft id (`steps_here`, inline annotations) must be remapped.
*/
stepIdByDraftId: Map<number, number>;
}
/**
* Compile capture drafts into record-only trace v3 steps.
* Drafts must already carry `preStateId` / `postStateId` from the recorder.
*/
export function reduceTraceSteps(
steps: DraftTraceStep[],
registry: Map<string, StateRegistryEntry>,
): ReducedTrace {
const collapsed = collapseNavigations(steps);
const out: Step[] = [];
const stepIdByDraftId = new Map<number, number>();
let id = 1;
for (const { draft, draftIds } of collapsed) {
const step = toV3Step(draft, id);
if (!step) continue;
out.push(step);
for (const draftId of draftIds) stepIdByDraftId.set(draftId, id);
id += 1;
}
const states = [...registry.values()].map(
({ contentHash: _hash, rawVomText: _body, stepsHere: _steps, ...state }) => state,
);
return { states, steps: out, stepIdByDraftId };
}
export function resolveTraceStartUrl(
drafts: DraftTraceStep[],
startUrl?: string,
states?: TraceState[],
): string {
if (startUrl) return startUrl;
const navigate = drafts.find((step): step is Extract<DraftTraceStep, { op: "navigate" }> => {
return step.op === "navigate";
});
if (navigate) return navigate.url;
for (const draft of drafts) {
if ("page_url" in draft && draft.page_url) return draft.page_url;
}
return states?.[0]?.url ?? "about:blank";
}
export type { FillCommit, NavigationCause };
/** Test seam */
export { resetStateIdCounterForTests };
@@ -75,52 +75,6 @@ describe("SessionManager", () => {
await expect(sm.start("aa11")).rejects.toThrow(/already exists/);
});
it("removes a newly created Agent Window when startup is aborted", async () => {
const aw = fakeAgentWindow();
let resolveCreate: (windowId: number) => void = () => {};
aw.createMock.mockImplementationOnce(
() =>
new Promise<number>((resolve) => {
resolveCreate = resolve;
}),
);
const sm = new SessionManager({ agentWindow: aw });
const controller = new AbortController();
const pending = sm.start("aa11", { signal: controller.signal });
controller.abort();
resolveCreate(777);
await expect(pending).rejects.toMatchObject({ name: "AbortError" });
expect(aw.removeMock).toHaveBeenCalledWith(777);
expect(sm.has("aa11")).toBe(false);
});
it("removes an incomplete Agent Window when active-tab setup fails", async () => {
const aw = fakeAgentWindow();
aw.ensureActiveTabMock.mockRejectedValueOnce(new Error("tab setup failed"));
const sm = new SessionManager({ agentWindow: aw });
await expect(sm.start("aa11")).rejects.toThrow("tab setup failed");
expect(aw.removeMock).toHaveBeenCalledWith(100);
expect(sm.has("aa11")).toBe(false);
});
it("surfaces the orphan Agent Window id when startup cleanup fails", async () => {
const aw = fakeAgentWindow();
aw.ensureActiveTabMock.mockRejectedValueOnce(new Error("tab setup failed"));
aw.removeMock.mockRejectedValueOnce(new Error("window removal denied"));
const sm = new SessionManager({ agentWindow: aw });
await expect(sm.start("aa11")).rejects.toMatchObject({
name: "SessionStartCleanupError",
windowId: 100,
message: expect.stringMatching(/cleanup of Agent Window 100 failed.*window removal denied/),
});
expect(sm.has("aa11")).toBe(false);
});
it("stop() closes the Agent Window and forgets the session", async () => {
const aw = fakeAgentWindow();
const sm = new SessionManager({ agentWindow: aw });
@@ -33,19 +33,4 @@ describe("RefStore", () => {
expect(s.resolve("@e11")).toBe(11);
expect(s.size()).toBe(2);
});
it("preserves the child CDP session as part of ref identity", () => {
const s = new RefStore();
s.set("e1", 42, {
tabId: 7,
frameId: "child-frame",
cdpSessionId: "child-session",
});
expect(s.resolveEntry("e1")).toMatchObject({
backendNodeId: 42,
tabId: 7,
frameId: "child-frame",
cdpSessionId: "child-session",
});
});
});
@@ -43,11 +43,12 @@ export const chromeAgentWindowApi: AgentWindowApi = {
return win.id;
},
async remove(windowId: number): Promise<void> {
// Callers decide whether a missing/failed removal is benign. In
// particular, transactional session-start cleanup must be able to
// surface a window it could not remove instead of reporting a false
// cancellation success while the Agent Window remains open.
await chrome.windows.remove(windowId);
try {
await chrome.windows.remove(windowId);
} catch (err) {
// Window may have been closed by the user already; ignore.
console.debug("[bh] chrome.windows.remove failed", err);
}
},
async ensureActiveTab(windowId: number, url: string): Promise<void> {
const tabs = await chrome.tabs.query({ windowId });
+12 -62
View File
@@ -31,38 +31,6 @@ export interface SessionStartOptions {
size?: { width: number; height: number };
/** Defaults to true so existing clients keep visible Agent Windows. */
focused?: boolean;
/** Cancellation for the transactional Agent Window startup sequence. */
signal?: AbortSignal;
}
export class SessionStartCleanupError extends Error {
readonly windowId: number;
readonly startupError: unknown;
readonly cleanupError: unknown;
constructor(windowId: number, startupError: unknown, cleanupError: unknown) {
const startupMessage =
startupError instanceof Error ? startupError.message : String(startupError);
const cleanupMessage =
cleanupError instanceof Error ? cleanupError.message : String(cleanupError);
super(
`session_start failed (${startupMessage}) and cleanup of Agent Window ${windowId} failed: ${cleanupMessage}`,
);
this.name = "SessionStartCleanupError";
this.windowId = windowId;
this.startupError = startupError;
this.cleanupError = cleanupError;
}
}
function sessionStartAbortError(): Error {
const error = new Error("session_start aborted");
error.name = "AbortError";
return error;
}
function throwIfSessionStartAborted(signal: AbortSignal | undefined): void {
if (signal?.aborted) throw sessionStartAbortError();
}
/**
@@ -172,36 +140,18 @@ export class SessionManager {
if (this.sessions.has(sessionId)) {
throw new Error(`[bh] session ${sessionId} already exists`);
}
throwIfSessionStartAborted(opts.signal);
let windowId: number | null = null;
try {
const { signal: _signal, ...createOptions } = opts;
windowId = await this.agentWindow.create(AGENT_WINDOW_HOME, createOptions);
throwIfSessionStartAborted(opts.signal);
await this.agentWindow.ensureActiveTab(windowId, AGENT_WINDOW_HOME);
throwIfSessionStartAborted(opts.signal);
const ctx: SessionContext = {
sessionId,
agentWindowId: windowId,
refStore: new RefStore(),
borrowedTabs: new Map(),
createdAtMs: this.now(),
};
this.sessions.set(sessionId, ctx);
this.windowIndex.set(windowId, sessionId);
return ctx;
} catch (startupError) {
if (windowId !== null) {
try {
await this.agentWindow.remove(windowId);
} catch (cleanupError) {
throw new SessionStartCleanupError(windowId, startupError, cleanupError);
}
}
throw startupError;
}
const windowId = await this.agentWindow.create(AGENT_WINDOW_HOME, opts);
await this.agentWindow.ensureActiveTab(windowId, AGENT_WINDOW_HOME);
const ctx: SessionContext = {
sessionId,
agentWindowId: windowId,
refStore: new RefStore(),
borrowedTabs: new Map(),
createdAtMs: this.now(),
};
this.sessions.set(sessionId, ctx);
this.windowIndex.set(windowId, sessionId);
return ctx;
}
/**
@@ -1,10 +1,9 @@
/**
* Per-session map from `@e<N>` snapshot refs to a CDP node address.
* Per-session map from `@e<N>` snapshot refs to CDP `backendNodeId`.
*
* Each fresh `tool.snapshot` resets the store: M6 will call
* `replace(...)` with the new ref → node address pairs. A node address
* includes the owning flat CDP session/frame when the element lives in
* an OOPIF; tools resolve live geometry from that identity at call time.
* `replace(...)` with the new ref → backendNodeId pairs. Tools like
* `tool.click` consume the store via `resolve("@e1")`.
*
* Refs are session-scoped (§7): looking up a ref in the wrong session
* returns `null`, never silently leaks. Storing values in different
@@ -16,19 +15,10 @@ export type BackendNodeId = number;
export interface RefEntry {
backendNodeId: BackendNodeId;
tabId: number | null;
frameId?: string;
cdpSessionId?: string;
generation: number;
}
export type RefInput =
| BackendNodeId
| {
backendNodeId: BackendNodeId;
tabId: number;
frameId?: string;
cdpSessionId?: string;
};
type RefInput = BackendNodeId | { backendNodeId: BackendNodeId; tabId: number };
export class RefStore {
private readonly map = new Map<string, RefEntry>();
@@ -54,7 +44,7 @@ export class RefStore {
}
/**
* Replace the entire store with a new ref → CDP node identity mapping.
* Replace the entire store with a new ref → backendNodeId mapping.
* Used after every fresh `tool.snapshot`.
*/
replace(entries: Iterable<readonly [string, RefInput]>): void {
@@ -63,20 +53,10 @@ export class RefStore {
for (const [ref, input] of entries) this.map.set(normaliseRef(ref), this.entry(input));
}
set(
ref: string,
id: BackendNodeId,
opts: {
tabId?: number;
frameId?: string;
cdpSessionId?: string;
} = {},
): void {
set(ref: string, id: BackendNodeId, opts: { tabId?: number } = {}): void {
this.map.set(normaliseRef(ref), {
backendNodeId: id,
tabId: opts.tabId ?? null,
...(opts.frameId ? { frameId: opts.frameId } : {}),
...(opts.cdpSessionId ? { cdpSessionId: opts.cdpSessionId } : {}),
generation: this.generation,
});
}
@@ -100,8 +80,6 @@ export class RefStore {
return {
backendNodeId: input.backendNodeId,
tabId: input.tabId,
...(input.frameId ? { frameId: input.frameId } : {}),
...(input.cdpSessionId ? { cdpSessionId: input.cdpSessionId } : {}),
generation: this.generation,
};
}
@@ -1,22 +0,0 @@
export const RECORD_DOCUMENT_ATTRIBUTE = "data-bsk-record-document";
const RECORDING_DOCUMENT_ID_PATTERN =
/^[0-9a-f]{8}-[0-9a-f]{4}-4[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$/i;
const RECORDING_DOCUMENT_MARKER_PREFIX = "bsk:";
export function recordingDocumentMarkerValue(identity: string): string {
if (!RECORDING_DOCUMENT_ID_PATTERN.test(identity)) {
throw new TypeError("recording Document identity must be a random UUID");
}
return `${RECORDING_DOCUMENT_MARKER_PREFIX}${identity}`;
}
/** Read BrowserSkill's opaque per-Document recording identity from captured attributes. */
export function readRecordingDocumentIdentity(
attrs: Readonly<Record<string, string>>,
): string | undefined {
const marker = attrs[RECORD_DOCUMENT_ATTRIBUTE];
if (!marker?.startsWith(RECORDING_DOCUMENT_MARKER_PREFIX)) return undefined;
const identity = marker.slice(RECORDING_DOCUMENT_MARKER_PREFIX.length);
return identity && RECORDING_DOCUMENT_ID_PATTERN.test(identity) ? identity : undefined;
}
@@ -612,14 +612,4 @@ describe("isInjectableContentScriptUrl", () => {
).toBe(false);
expect(isInjectableContentScriptUrl("https://chromewebstore.google.com/")).toBe(false);
});
it("rejects the Edge Add-ons store", () => {
expect(
isInjectableContentScriptUrl(
"https://microsoftedge.microsoft.com/addons/detail/browserskill/emacgiaaaiojkkpkddmmdfhmokgmnikg",
),
).toBe(false);
// Non-store paths on the same host stay injectable.
expect(isInjectableContentScriptUrl("https://microsoftedge.microsoft.com/")).toBe(true);
});
});
@@ -0,0 +1,86 @@
import { describe, expect, it } from "vitest";
import { RECORD_DOCUMENT_TOKEN_ATTR } from "@/lib/record-document-token";
import type { CapturedNode } from "@/tools/vom/capture";
import { collectDocumentTokenOwners } from "../capture-vom-observation";
function htmlNode(
backendNodeId: number,
token: string,
ownerFrameBackendNodeId: number | null = null,
): CapturedNode {
return {
backendNodeId,
parentBackendNodeId: null,
tag: "html",
attrs: { [RECORD_DOCUMENT_TOKEN_ATTR]: token },
rect: { x: 0, y: 0, w: 1280, h: 720 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
...(ownerFrameBackendNodeId === null ? {} : { ownerFrameBackendNodeId }),
};
}
describe("collectDocumentTokenOwners", () => {
it("maps document tokens to their immediate iframe owner backend node", () => {
const topToken = "top-doc-token";
const childToken = "child-doc-token";
const owners = collectDocumentTokenOwners({
viewport: { width: 1280, height: 720 },
nodes: [htmlNode(1, topToken, null)],
iframeNodes: new Map([
[
13,
[
htmlNode(101, childToken, 13),
{
backendNodeId: 102,
parentBackendNodeId: 101,
tag: "input",
attrs: {},
rect: { x: 10, y: 20, w: 200, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
ownerFrameBackendNodeId: 13,
},
],
],
]),
excludedBackendNodeIds: new Set(),
});
expect(owners.get(topToken)).toBeNull();
expect(owners.get(childToken)).toBe(13);
});
it("maps nested iframe documents to their direct owner, not the outer iframe", () => {
const nestedToken = "nested-doc-token";
const owners = collectDocumentTokenOwners({
viewport: { width: 1280, height: 720 },
nodes: [htmlNode(1, "top-token", null)],
iframeNodes: new Map([
[
13,
[
{
backendNodeId: 23,
parentBackendNodeId: 101,
tag: "iframe",
attrs: {},
rect: { x: 0, y: 0, w: 400, h: 300 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
ownerFrameBackendNodeId: 13,
},
],
],
[23, [htmlNode(201, nestedToken, 23)]],
]),
excludedBackendNodeIds: new Set(),
});
expect(owners.get(nestedToken)).toBe(23);
});
});
@@ -8,7 +8,6 @@ import type {
RequestFrame,
} from "@/transport/types";
import { ToolDispatcher } from "../dispatcher";
import { resetBrowserObservationForTests, setBrowserObservationAttachForTests } from "../record";
type TestDispatcherCdp = NonNullable<ConstructorParameters<typeof ToolDispatcher>[0]["cdp"]>;
@@ -45,72 +44,9 @@ function makeRequest(method: string, params: unknown): RequestFrame {
describe("ToolDispatcher", () => {
afterEach(() => {
resetBrowserObservationForTests();
vi.unstubAllGlobals();
});
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 () => {}),
},
});
await sessions.start("aa11");
const tab = {
id: 7,
windowId: 4242,
active: true,
status: "complete",
url: "https://example.com/start",
} as chrome.tabs.Tab;
const frameCoordinator = {
begin: vi.fn(),
armTab: vi.fn(async () => true),
sourceFor: vi.fn(() => null),
stop: vi.fn(async () => true),
cancel: vi.fn(),
};
const sendToTab = vi.fn(async () => ({ ok: true }));
setBrowserObservationAttachForTests(
() => () => {},
() => () => {},
);
const dispatcher = new ToolDispatcher({
transport,
sessions,
recording: {
tabsApi: {
get: vi.fn(async () => tab),
query: vi.fn(async () => [tab]),
},
frameCoordinator,
sendToTab,
},
});
dispatcher.start();
deliver(
makeRequest("tool.record_start", {
session_id: "aa11",
url: "https://example.com/start",
}),
);
await vi.waitFor(() => expect(sent).toHaveLength(1));
expect(sent[0]).toMatchObject({ result: { tab_id: 7, recording: true } });
expect(frameCoordinator.begin).toHaveBeenCalledOnce();
expect(frameCoordinator.armTab).toHaveBeenCalledWith(expect.any(String), 7);
deliver({ id: "r-2", method: "tool.record_stop", params: { session_id: "aa11" } });
await vi.waitFor(() => expect(sent).toHaveLength(2));
expect(frameCoordinator.stop).toHaveBeenCalledOnce();
expect(sent[1]).toMatchObject({ id: "r-2", result: { trace: { steps: [] } } });
});
it("routes tool.session_start to the SessionManager and replies with the window id", async () => {
const { transport, sent, deliver } = fakeTransport();
const sessions = new SessionManager({
@@ -267,55 +203,6 @@ describe("ToolDispatcher", () => {
expect(sent[0]).toEqual({ id: "r-1", result: {} });
});
it("forwards daemon cancellation into an in-flight session stop", async () => {
const { transport, sent, deliver } = fakeTransport();
const remove = vi.fn(async () => {});
const sessions = new SessionManager({
agentWindow: {
create: vi.fn(async () => 4242),
remove,
ensureActiveTab: vi.fn(async () => {}),
},
});
await sessions.start("aa11");
let finishDetach: () => void = () => {};
const detach = new Promise<void>((resolve) => {
finishDetach = resolve;
});
const cdp = {
send: vi.fn(),
detachSession: vi.fn(() => detach),
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.session_stop", { session_id: "aa11" }));
await vi.waitFor(() => expect(cdp.detachSession).toHaveBeenCalledWith("aa11"));
deliver({ id: "cancel-stop", method: "cancel", params: { rpc_id: "r-1" } });
await flushMicrotasks();
finishDetach();
await flushMicrotasks();
expect(sent).toContainEqual({ id: "cancel-stop", result: { cancelled: true } });
expect(sent).toContainEqual({
id: "r-1",
error: expect.objectContaining({ code: "cancelled" }),
});
expect(sessions.has("aa11")).toBe(true);
expect(remove).not.toHaveBeenCalled();
});
it("returns not_found when stopping an unknown session", async () => {
const { transport, sent, deliver } = fakeTransport();
const sessions = new SessionManager({
@@ -790,31 +677,23 @@ describe("ToolDispatcher", () => {
await flushMicrotasks();
expect(ac?.signal.aborted).toBe(true);
// Cancel ack arrives synchronously, but the original RPC must not reply
// until the in-progress window creation has completed and been rolled back.
// Cancel ack arrived synchronously; the slow tool replies with
// `cancelled` once the dispatcher's race observes the abort.
const ack = sent.find(
(m) =>
typeof (m as { id?: string }).id === "string" && (m as { id: string }).id === "cancel-1",
);
expect(ack).toEqual({ id: "cancel-1", result: { cancelled: true } });
expect(
sent.find(
(m) => typeof (m as { id?: string }).id === "string" && (m as { id: string }).id === "r-1",
),
).toBeUndefined();
expect(dispatcher.inflightAbortControllers.has("r-1")).toBe(true);
resolveCreate(9999);
await flushMicrotasks();
const slow = sent.find(
(m) => typeof (m as { id?: string }).id === "string" && (m as { id: string }).id === "r-1",
);
expect(slow).toMatchObject({ id: "r-1", error: { code: "cancelled" } });
expect(dispatcher.inflightAbortControllers.has("r-1")).toBe(false);
expect(sessions.has("aa44")).toBe(false);
expect(sessions.list()).toEqual([]);
// Drain the dangling create promise so vitest does not warn.
resolveCreate(9999);
await flushMicrotasks();
});
it("cancel for an unknown rpc_id replies with cancelled=false", async () => {
@@ -1,54 +1,24 @@
import { describe, expect, it } from "vitest";
import { nodeContentRegion } from "../element-geometry";
import { nodeBoundingRect, quadBoundingRect } from "../element-geometry";
import type { CdpRunner } from "../shared";
describe("nodeContentRegion", () => {
it("rejects invalid content quads before using the box model fallback", async () => {
const send = async (_tabId: number, method: string) => {
if (method === "DOM.getContentQuads") return { quads: [[0, 0, 0, 0, 0, 0, 0, 0]] };
if (method === "DOM.getBoxModel") {
return { model: { content: [5, 10, 25, 10, 25, 30, 5, 30] } };
}
throw new Error(`unexpected CDP call ${method}`);
};
await expect(nodeContentRegion({ send: send as CdpRunner["send"] }, 7, 555)).resolves.toEqual([
[
{ x: 5, y: 10 },
{ x: 25, y: 10 },
{ x: 25, y: 30 },
{ x: 5, y: 30 },
],
]);
});
it("preserves every visible content fragment", async () => {
const send = async () => ({
quads: [
[10, 20, 60, 20, 60, 40, 10, 40],
[15, 50, 90, 50, 90, 80, 15, 80],
],
describe("quadBoundingRect", () => {
it("computes axis-aligned bounds from an 8-double quad", () => {
expect(quadBoundingRect([10, 20, 110, 20, 110, 60, 10, 60])).toEqual({
x: 10,
y: 20,
width: 100,
height: 40,
});
const cdp: CdpRunner = {
send: send as CdpRunner["send"],
};
await expect(nodeContentRegion(cdp, 7, 555)).resolves.toEqual([
[
{ x: 10, y: 20 },
{ x: 60, y: 20 },
{ x: 60, y: 40 },
{ x: 10, y: 40 },
],
[
{ x: 15, y: 50 },
{ x: 90, y: 50 },
{ x: 90, y: 80 },
{ x: 15, y: 80 },
],
]);
});
it("returns null for degenerate quads", () => {
expect(quadBoundingRect([0, 0, 0, 0, 0, 0, 0, 0])).toBeNull();
expect(quadBoundingRect([1, 2, 3])).toBeNull();
});
});
describe("nodeBoundingRect", () => {
it("falls back to visible descendant bounds for zero-size containers", async () => {
const calls: Array<{ method: string; params?: object }> = [];
const send = async (_tabId: number, method: string, params?: object) => {
@@ -68,14 +38,12 @@ describe("nodeContentRegion", () => {
};
const cdp = { send: send as CdpRunner["send"] };
await expect(nodeContentRegion(cdp, 7, 555)).resolves.toEqual([
[
{ x: 242, y: 468 },
{ x: 1011, y: 468 },
{ x: 1011, y: 648 },
{ x: 242, y: 648 },
],
]);
await expect(nodeBoundingRect(cdp, 7, 555)).resolves.toEqual({
x: 242,
y: 468,
width: 769,
height: 180,
});
expect(calls.map((c) => c.method)).toEqual([
"DOM.getContentQuads",
"DOM.getBoxModel",
@@ -1,286 +0,0 @@
import { describe, expect, it, vi } from "vitest";
import { resolveFrameProjection, resolveNodeGeometry } from "../frame-geometry";
import {
clipPolygon,
polygonArea,
polygonBounds,
projectAndClipRegion,
projectUnitPoint,
type Quad,
rectPolygon,
regionBounds,
} from "../geometry";
import type { CdpRunner } from "../shared";
describe("frame geometry projection", () => {
it("keeps region bounds separate from polygon area", () => {
const region = [
rectPolygon({ x: 0, y: 0, w: 10, h: 10 }),
rectPolygon({ x: 20, y: 5, w: 5, h: 5 }),
];
expect(regionBounds(region)).toEqual({ x: 0, y: 0, width: 25, height: 10 });
expect(polygonArea(region[0])).toBe(100);
});
it("maps through the iframe content box instead of its border box", () => {
const contentQuad: Quad = [
{ x: 204, y: 306 },
{ x: 604, y: 306 },
{ x: 604, y: 506 },
{ x: 204, y: 506 },
];
const projected = projectAndClipRegion(
[rectPolygon({ x: 10, y: 20, w: 100, h: 40 })],
[{ sourceViewport: { width: 200, height: 100 }, destinationQuad: contentQuad }],
{ width: 1000, height: 800 },
);
expect(polygonBounds(projected.flat())).toEqual({ x: 224, y: 346, width: 200, height: 80 });
});
it("uses a projective mapping for perspective-transformed iframe quads", () => {
const quad: Quad = [
{ x: 0, y: 0 },
{ x: 200, y: 20 },
{ x: 180, y: 140 },
{ x: 20, y: 100 },
];
expect(projectUnitPoint({ x: 0, y: 0 }, quad)).toEqual(quad[0]);
expect(projectUnitPoint({ x: 1, y: 0 }, quad)).toEqual(quad[1]);
expect(projectUnitPoint({ x: 1, y: 1 }, quad)).toEqual(quad[2]);
expect(projectUnitPoint({ x: 0, y: 1 }, quad)).toEqual(quad[3]);
});
it("clips against the iframe polygon rather than its bounding box", () => {
const frameQuad: Quad = [
{ x: 50, y: 0 },
{ x: 100, y: 50 },
{ x: 50, y: 100 },
{ x: 0, y: 50 },
];
expect(clipPolygon(rectPolygon({ x: 0, y: 0, w: 10, h: 10 }), frameQuad)).toEqual([]);
});
it("does not reapply same-target frame transforms around an OOPIF", async () => {
const send = vi.fn(async (_tabId, method, params) => {
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 800, clientHeight: 600 } };
}
if (method === "DOM.getBoxModel") {
const backendNodeId = (params as { backendNodeId?: number }).backendNodeId;
return backendNodeId === 20
? { model: { content: [110, 70, 310, 70, 310, 170, 110, 170] } }
: { model: { content: [100, 50, 400, 50, 400, 250, 100, 250] } };
}
throw new Error(`unexpected root command ${method}`);
});
const cdp: CdpRunner = {
send: send as CdpRunner["send"],
sendToTarget: vi.fn(async (_target, method) => {
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 200, clientHeight: 100 } };
}
throw new Error(`unexpected child command ${method}`);
}) as CdpRunner["sendToTarget"],
};
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([
{
sourceViewport: { width: 200, height: 100 },
destinationQuad: [
{ x: 110, y: 70 },
{ x: 310, y: 70 },
{ x: 310, y: 170 },
{ x: 110, y: 170 },
],
destinationClips: [
[
{ x: 100, y: 50 },
{ x: 400, y: 50 },
{ x: 400, y: 250 },
{ x: 100, y: 250 },
],
],
},
]);
});
it("clips live OOPIF geometry at every frame boundary", async () => {
const cdp: CdpRunner = {
send: vi.fn(async (_tabId, method) => {
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 800, clientHeight: 600 } };
}
if (method === "DOM.getBoxModel") {
return { model: { content: [100, 100, 300, 100, 300, 200, 100, 200] } };
}
throw new Error(`unexpected root command ${method}`);
}) as CdpRunner["send"],
sendToTarget: vi.fn(async (_target, method) => {
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 200, clientHeight: 100 } };
}
if (method === "DOM.getContentQuads") {
return { quads: [[-50, -20, 250, -20, 250, 120, -50, 120]] };
}
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 geometry = await resolveNodeGeometry(cdp, 4, {
target: { tabId: 4, sessionId: "child-session" },
frameId: "child",
backendNodeId: 101,
});
expect(geometry).toMatchObject({
topBounds: { x: 100, y: 100, width: 200, height: 100 },
actionPoint: { x: 200, y: 150 },
});
});
it("reuses one frame graph while scrolling and projecting live geometry", async () => {
const 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 cdp: CdpRunner = {
send: vi.fn(async (_tabId, method) => {
if (method === "DOM.scrollIntoViewIfNeeded") return {};
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 800, clientHeight: 600 } };
}
if (method === "DOM.getBoxModel") {
return { model: { content: [100, 100, 300, 100, 300, 200, 100, 200] } };
}
throw new Error(`unexpected root command ${method}`);
}) as CdpRunner["send"],
sendToTarget: vi.fn(async (_target, method) => {
if (method === "DOM.scrollIntoViewIfNeeded") return {};
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 200, clientHeight: 100 } };
}
if (method === "DOM.getContentQuads") {
return { quads: [[0, 0, 20, 0, 20, 20, 0, 20]] };
}
throw new Error(`unexpected child command ${method}`);
}) as CdpRunner["sendToTarget"],
getFrameGraph,
};
await expect(
resolveNodeGeometry(
cdp,
4,
{
target: { tabId: 4, sessionId: "child-session" },
frameId: "child",
backendNodeId: 101,
},
{ scrollIntoView: true },
),
).resolves.not.toMatchObject({ code: expect.any(String) });
expect(getFrameGraph).toHaveBeenCalledOnce();
});
it("clips live geometry to same-target iframe ancestors", async () => {
const cdp: CdpRunner = {
send: vi.fn(async (_tabId, method) => {
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 800, clientHeight: 600 } };
}
if (method === "DOM.getBoxModel") {
return { model: { content: [100, 100, 300, 100, 300, 200, 100, 200] } };
}
if (method === "DOM.getContentQuads") {
return { quads: [[50, 50, 350, 50, 350, 250, 50, 250]] };
}
throw new Error(`unexpected ${method}`);
}) as CdpRunner["send"],
getFrameGraph: vi.fn(async () => ({
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 4 } },
{
frameId: "child",
parentFrameId: "main",
ownerBackendNodeId: 10,
target: { tabId: 4 },
},
],
})),
};
const geometry = await resolveNodeGeometry(cdp, 4, {
target: { tabId: 4 },
frameId: "child",
backendNodeId: 101,
});
expect(geometry).toMatchObject({
topBounds: { x: 100, y: 100, width: 200, height: 100 },
actionPoint: { x: 200, y: 150 },
});
});
it("fails closed when an OOPIF frame graph is unavailable", async () => {
const cdp: CdpRunner = {
send: vi.fn(),
sendToTarget: vi.fn(async (_target, method) => {
if (method === "DOM.getContentQuads") {
return { quads: [[0, 0, 20, 0, 20, 20, 0, 20]] };
}
throw new Error(`unexpected ${method}`);
}) as CdpRunner["sendToTarget"],
};
await expect(
resolveNodeGeometry(cdp, 4, {
target: { tabId: 4, sessionId: "child-session" },
frameId: "child",
backendNodeId: 101,
}),
).resolves.toMatchObject({ code: "cdp_failed" });
});
});
@@ -1,6 +1,5 @@
import { afterEach, describe, expect, it, vi } from "vitest";
import { SessionManager } from "@/session-manager/manager";
import { RefStore } from "@/session-manager/ref-store";
import type { RequestHelpParams } from "@/transport/types";
import { handleRequestHelp, type RequestHelpDeps, resetHelpLifecycleForTests } from "../human-loop";
@@ -51,10 +50,11 @@ function installHelpLifecycleChrome() {
}
function fakeManager(sessionId: string, agentWindowId: number, tabId: number) {
const refStore = new RefStore();
const mgr = {
get: (id: string) =>
id === sessionId ? { sessionId, agentWindowId, refStore, borrowedTabs: new Map() } : null,
id === sessionId
? { sessionId, agentWindowId, refStore: { resolve: () => null }, borrowedTabs: new Map() }
: null,
findByWindowId: (wid: number) => (wid === agentWindowId ? { sessionId } : null),
} as unknown as SessionManager;
return mgr;
@@ -339,23 +339,26 @@ describe("handleRequestHelp", () => {
ac.abort();
await expect(pending).resolves.toMatchObject({ code: "cancelled" });
expect(cdpSend).not.toHaveBeenCalledWith(
expect.anything(),
"DOM.removeAttribute",
expect.anything(),
expect(cdpSend).toHaveBeenCalledWith(
5,
"DOM.querySelectorAll",
expect.objectContaining({ selector: "[data-bsk-help]" }),
);
expect(cdpSend).toHaveBeenCalledWith(
6,
"DOM.querySelectorAll",
expect.objectContaining({ selector: "[data-bsk-help]" }),
);
});
it("resolves ref targets to explicit viewport rectangles without mutating the page", async () => {
const refStore = new RefStore();
refStore.set("e1", 42, { tabId: 5 });
it("tags ref targets via CDP and reports them matched", async () => {
const mgr = {
get: (id: string) =>
id === "abcd"
? {
sessionId: "abcd",
agentWindowId: 99,
refStore,
refStore: { resolve: () => 42 },
borrowedTabs: new Map(),
}
: null,
@@ -363,17 +366,7 @@ describe("handleRequestHelp", () => {
} as unknown as SessionManager;
const deps = baseDeps({
cdp: {
send: vi.fn(async (_tabId, method) => {
if (method === "DOM.getDocument") return { root: { nodeId: 1 } };
if (method === "DOM.scrollIntoViewIfNeeded") return {};
if (method === "DOM.getContentQuads") {
return { quads: [[10, 20, 110, 20, 110, 60, 10, 60]] };
}
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 1280, clientHeight: 720 } };
}
throw new Error(`unexpected ${method}`);
}),
send: vi.fn(async () => ({ object: { objectId: "obj-1" } })),
} as unknown as RequestHelpDeps["cdp"],
});
const res = await handleRequestHelp(
@@ -382,97 +375,14 @@ describe("handleRequestHelp", () => {
deps,
);
const sentMsg = (deps.sendToTab as ReturnType<typeof vi.fn>).mock.calls[0][1];
expect(sentMsg.selectors).toEqual([]);
expect(sentMsg.rects).toEqual([{ top: 20, left: 10, width: 100, height: 40 }]);
expect(sentMsg.selectors).toContain('[data-bsk-help="0"]');
expect(res).toMatchObject({
outcome: "continued",
tab_id: 5,
resolved_targets: [
{
matched: true,
ref: "@e1",
},
],
resolved_targets: [{ matched: true, ref: "@e1" }],
});
});
it("projects an OOPIF ref through its live content quad for the help overlay", async () => {
const mgr = {
get: (id: string) =>
id === "abcd"
? {
sessionId: "abcd",
agentWindowId: 99,
refStore: {
resolveEntry: () => ({
backendNodeId: 42,
tabId: 5,
frameId: "child",
cdpSessionId: "child-session",
generation: 1,
}),
},
borrowedTabs: new Map(),
}
: null,
findByWindowId: (wid: number) => (wid === 99 ? { sessionId: "abcd" } : null),
} as unknown as SessionManager;
const send = vi.fn(async (_tabId, method) => {
if (method === "DOM.getDocument") return { root: { nodeId: 1 } };
if (method === "DOM.scrollIntoViewIfNeeded") return {};
if (method === "DOM.getBoxModel") {
return { model: { content: [204, 306, 604, 306, 604, 506, 204, 506] } };
}
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 1280, clientHeight: 720 } };
}
throw new Error(`unexpected root ${method}`);
});
const sendToTarget = vi.fn(async (_target, method) => {
if (method === "DOM.scrollIntoViewIfNeeded") return {};
if (method === "DOM.getContentQuads") {
return { quads: [[10, 20, 110, 20, 110, 60, 10, 60]] };
}
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 200, clientHeight: 100 } };
}
throw new Error(`unexpected child ${method}`);
});
const deps = baseDeps({
cdp: {
send,
sendToTarget,
getFrameGraph: vi.fn(async () => ({
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 5 } },
{
frameId: "child",
parentFrameId: "main",
ownerBackendNodeId: 99,
target: { tabId: 5, sessionId: "child-session" },
},
],
})),
} as unknown as NonNullable<RequestHelpDeps["cdp"]>,
});
const res = await handleRequestHelp(
mgr,
baseParams({ tab_id: 5, targets: [{ ref: "@e1" }] }),
deps,
);
const sentMsg = (deps.sendToTab as ReturnType<typeof vi.fn>).mock.calls[0][1];
expect(sentMsg.rects).toEqual([{ top: 346, left: 224, width: 200, height: 80 }]);
expect(res).toMatchObject({ resolved_targets: [{ matched: true, ref: "@e1" }] });
expect(sendToTarget).toHaveBeenCalledWith(
{ tabId: 5, sessionId: "child-session" },
"DOM.getContentQuads",
{ backendNodeId: 42 },
);
});
it("reports ref target unmatched when ref does not resolve", async () => {
const deps = baseDeps();
const res = await handleRequestHelp(
@@ -488,15 +398,16 @@ describe("handleRequestHelp", () => {
});
it("reports ref target unmatched when ref is for another tab", async () => {
const refStore = new RefStore();
refStore.set("e1", 42, { tabId: 4 });
const mgr = {
get: (id: string) =>
id === "abcd"
? {
sessionId: "abcd",
agentWindowId: 99,
refStore,
refStore: {
resolve: (ref: string, opts: { tabId?: number }) =>
ref === "e1" && opts.tabId === 4 ? 42 : null,
},
borrowedTabs: new Map(),
}
: null,
@@ -30,9 +30,6 @@ function makeFakeCdp(handlers: Record<string, (params: unknown) => unknown>) {
const sendImpl = async (tabId: number, method: string, params?: object) => {
sent.push({ tabId, method, params });
const h = handlers[method];
if (!h && method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 1280, clientHeight: 720 } };
}
if (!h) throw new Error(`unexpected CDP call ${method}`);
return h(params);
};
@@ -167,63 +164,6 @@ describe("handleClick", () => {
});
});
it("resolves frame refs in their CDP session and dispatches input in top coordinates", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e3", 1234, {
tabId: 4,
frameId: "child-frame",
cdpSessionId: "child-session",
});
const fake = makeFakeCdp({
"Input.dispatchMouseEvent": () => ({}),
"DOM.scrollIntoViewIfNeeded": () => ({}),
"DOM.getBoxModel": () => ({
model: { content: [204, 306, 604, 306, 604, 506, 204, 506] },
}),
});
fake.cdp.getFrameGraph = vi.fn(async () => ({
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 4 } },
{
frameId: "child-frame",
parentFrameId: "main",
ownerBackendNodeId: 99,
target: { tabId: 4, sessionId: "child-session" },
},
],
}));
const targetCalls: Array<{ sessionId?: string; method: string }> = [];
fake.cdp.sendToTarget = vi.fn(async (target, method) => {
targetCalls.push({ sessionId: target.sessionId, method });
if (method === "DOM.scrollIntoViewIfNeeded") return {};
if (method === "DOM.getContentQuads") {
return { quads: [[10, 20, 110, 20, 110, 60, 10, 60]] };
}
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 200, clientHeight: 100 } };
}
throw new Error(`unexpected child CDP call ${method}`);
}) as CdpRunner["sendToTarget"];
const res = await handleClick(
sm,
{ session_id: "aa11", ref: "@e3" },
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
// The iframe content box starts at (204, 306) after its border and is scaled 2x.
expect(res).toMatchObject({ x: 324, y: 386 });
expect(targetCalls).toEqual([
{ sessionId: "child-session", method: "DOM.scrollIntoViewIfNeeded" },
{ sessionId: "child-session", method: "DOM.getContentQuads" },
{ sessionId: "child-session", method: "Page.getLayoutMetrics" },
]);
expect(fake.sent.filter((call) => call.method === "Input.dispatchMouseEvent")).toHaveLength(3);
});
it("enables overlay bypass before mouse events when overlay blocks the click point", async () => {
const order: string[] = [];
const bypassOverlay = vi.fn(async (_tabId: number, enabled: boolean) => {
@@ -5,10 +5,8 @@ import { OVERLAY_HOST_MARKER_ATTR, OVERLAY_HOST_NAME } from "@/lib/overlay-bridg
import { SessionManager } from "@/session-manager/manager";
import type { CdpRunner } from "@/tools/shared";
import {
buildFrameVomScene,
buildVomScene,
type CdpAxNode,
captureVomObservation,
handleGetHtml,
handleObserve,
handleScreenshot,
@@ -64,9 +62,6 @@ function makeFakeCdp(handlers: Record<string, (params?: object) => unknown>) {
const send = vi.fn(async (_tabId: number, method: string, params?: object) => {
sent.push({ method, params });
const handler = handlers[method];
if (!handler && method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 1280, clientHeight: 720 } };
}
if (!handler) throw new Error(`unexpected CDP call ${method}`);
return handler(params);
});
@@ -513,292 +508,6 @@ describe("handleScreenshot overlay suppression", () => {
// ---------------------------------------------------------------------------
describe("buildVomScene", () => {
it("merges multiple sibling and nested frames without mixing their targets", () => {
const node = (
backendNodeId: number,
parentBackendNodeId: number | null,
frameId: string,
tag: string,
attrs: Record<string, string> = {},
): CapturedNode => ({
backendNodeId,
parentBackendNodeId,
frameId,
tag,
attrs,
rect: { x: 0, y: 0, w: 100, h: 30 },
localRect: { x: 0, y: 0, w: 100, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
});
const mainNodes = [
node(1, null, "main", "body"),
node(10, 1, "main", "iframe", { title: "First" }),
node(20, 1, "main", "iframe", { title: "Second" }),
];
const firstNodes = [
node(100, null, "first", "body"),
node(101, 100, "first", "button", { "aria-label": "First action" }),
];
const secondNodes = [
node(200, null, "second", "body"),
node(201, 200, "second", "h2"),
node(210, 200, "second", "iframe", { title: "Nested" }),
];
const nestedNodes = [
node(300, null, "nested", "body"),
node(301, 300, "nested", "input", { placeholder: "Nested field" }),
];
const captured: CapturedViewModel = {
viewport: { width: 1200, height: 800 },
nodes: mainNodes,
iframeNodes: new Map([
[10, firstNodes],
[20, secondNodes],
[210, nestedNodes],
]),
frameNodes: new Map([
["main", mainNodes],
["first", firstNodes],
["second", secondNodes],
["nested", nestedNodes],
]),
frameOwnerBackendNodeIds: new Map([
["first", 10],
["second", 20],
["nested", 210],
]),
rootFrameId: "main",
excludedBackendNodeIds: new Set(),
};
const axNode = (
nodeId: string,
backendDOMNodeId: number,
role: string,
parentId?: string,
name?: string,
): CdpAxNode => ({
nodeId,
backendDOMNodeId,
role: { type: "role", value: role },
...(parentId ? { parentId } : {}),
...(name ? { name: { type: "computedString", value: name } } : {}),
});
const result = buildFrameVomScene(
[
{
frameId: "main",
contextScopeId: "main",
target: { tabId: 7 },
domNodes: mainNodes,
axNodes: [
axNode("root", 1, "RootWebArea"),
axNode("frame-1", 10, "Iframe", "root", "First"),
axNode("frame-2", 20, "Iframe", "root", "Second"),
],
},
{
frameId: "first",
contextScopeId: "first",
parentFrameId: "main",
ownerBackendNodeId: 10,
target: { tabId: 7, sessionId: "session-first" },
domNodes: firstNodes,
axNodes: [
axNode("root", 100, "RootWebArea"),
axNode("button", 101, "button", "root", "First action"),
],
},
{
frameId: "second",
contextScopeId: "second",
parentFrameId: "main",
ownerBackendNodeId: 20,
target: { tabId: 7, sessionId: "session-second" },
domNodes: secondNodes,
axNodes: [
axNode("root", 200, "RootWebArea"),
axNode("heading", 201, "heading", "root", "Second heading"),
axNode("nested-frame", 210, "Iframe", "root", "Nested"),
],
},
{
frameId: "nested",
contextScopeId: "nested",
parentFrameId: "second",
ownerBackendNodeId: 210,
target: { tabId: 7, sessionId: "session-nested" },
domNodes: nestedNodes,
axNodes: [
axNode("root", 300, "RootWebArea"),
axNode("input", 301, "textbox", "root", "Nested field"),
],
},
],
captured,
);
const rendered = renderVom(result);
expect(rendered.text).toContain('Iframe "First"');
expect(rendered.text).toContain('@e1 button "First action"');
expect(rendered.text).toContain('heading "Second heading"');
expect(rendered.text).toContain('Iframe "Nested"');
expect(rendered.text).toContain('textbox "Nested field"');
expect(rendered.refs.find((ref) => ref.backendNodeId === 101)?.frameId).toBe("first");
expect(rendered.refs.find((ref) => ref.backendNodeId === 301)?.frameId).toBe("nested");
const firstAction = result.nodes.find((item) => item.backendNodeId === 101);
const nestedInput = result.nodes.find((item) => item.backendNodeId === 301);
expect(firstAction).toMatchObject({ frameId: "first", contextScopeId: "first" });
expect(nestedInput).toMatchObject({ frameId: "nested", contextScopeId: "nested" });
expect(nestedInput?.parentId).toBe(result.nodes.find((item) => item.backendNodeId === 210)?.id);
});
it("does not place a child document at the page root when its frame boundary is unresolved", () => {
const childNode: CapturedNode = {
backendNodeId: 101,
parentBackendNodeId: null,
frameId: "child",
tag: "button",
attrs: {},
rect: { x: 0, y: 0, w: 100, h: 30 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
};
const captured: CapturedViewModel = {
viewport: { width: 800, height: 600 },
nodes: [],
iframeNodes: new Map(),
frameNodes: new Map([["child", [childNode]]]),
rootFrameId: "main",
excludedBackendNodeIds: new Set(),
};
const result = buildFrameVomScene(
[
{
frameId: "main",
contextScopeId: "main",
target: { tabId: 7 },
domNodes: [],
axNodes: [],
},
{
frameId: "child",
contextScopeId: "child",
parentFrameId: "main",
target: { tabId: 7 },
domNodes: [childNode],
axNodes: [
{
nodeId: "button",
frameId: "child",
backendDOMNodeId: 101,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "Child action" },
},
],
},
],
captured,
);
expect(result.nodes).toEqual([]);
});
it("keeps AX-only frame content attached to its iframe boundary", () => {
const mainNodes: CapturedNode[] = [
{
backendNodeId: 1,
parentBackendNodeId: null,
frameId: "main",
tag: "body",
attrs: {},
rect: { x: 0, y: 0, w: 800, h: 600 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
},
{
backendNodeId: 10,
parentBackendNodeId: 1,
frameId: "main",
tag: "iframe",
attrs: { title: "Remote" },
rect: { x: 100, y: 100, w: 400, h: 300 },
paintOrder: 1,
position: "static",
pointerEvents: "auto",
},
];
const captured: CapturedViewModel = {
viewport: { width: 800, height: 600 },
nodes: mainNodes,
iframeNodes: new Map(),
frameNodes: new Map([
["main", mainNodes],
["child", []],
]),
rootFrameId: "main",
excludedBackendNodeIds: new Set(),
};
const result = buildFrameVomScene(
[
{
frameId: "main",
contextScopeId: "main",
target: { tabId: 7 },
domNodes: mainNodes,
axNodes: [
{
nodeId: "main-root",
backendDOMNodeId: 1,
role: { type: "role", value: "RootWebArea" },
},
{
nodeId: "frame-owner",
parentId: "main-root",
backendDOMNodeId: 10,
role: { type: "role", value: "Iframe" },
name: { type: "computedString", value: "Remote" },
},
],
},
{
frameId: "child",
contextScopeId: "child",
parentFrameId: "main",
ownerBackendNodeId: 10,
target: { tabId: 7, sessionId: "child-session" },
domNodes: [],
axNodes: [
{
nodeId: "child-root",
backendDOMNodeId: 100,
role: { type: "role", value: "RootWebArea" },
},
{
nodeId: "child-button",
parentId: "child-root",
backendDOMNodeId: 101,
role: { type: "role", value: "button" },
name: { type: "computedString", value: "AX fallback action" },
},
],
},
],
captured,
);
const childButton = result.nodes.find((node) => node.backendNodeId === 101);
expect(childButton).toMatchObject({ frameId: "child", contextScopeId: "child" });
expect(childButton?.parentId).toBe(result.nodes.find((node) => node.backendNodeId === 10)?.id);
expect(renderVom(result).text).toContain('@e1 button "AX fallback action"');
});
it("joins AX semantics with captured geometry by backendDOMNodeId", () => {
const axNodes: CdpAxNode[] = [
{
@@ -1107,7 +816,6 @@ describe("buildVomScene", () => {
parentId: "2",
role: { type: "role", value: "textbox" },
name: { type: "x", value: "输入密码" },
value: { value: "iframe-secret" },
backendDOMNodeId: 202,
properties: [{ name: "inputType", value: { value: "password" } }],
},
@@ -1162,10 +870,6 @@ describe("buildVomScene", () => {
expect(passwordNodes).toHaveLength(1);
expect(passwordNodes[0]).toEqual(expect.objectContaining({ id: 202, sensitive: true }));
expect(passwordNodes[0].value).toBeUndefined();
const rendered = renderVom(buildVomScene(axNodes, captured)).text;
expect(rendered).toContain('textbox "输入密码" [filled] ="•••"');
expect(rendered).not.toContain("iframe-secret");
});
it("keeps unnamed iframe controls but skips unnamed iframe links", () => {
@@ -1656,7 +1360,7 @@ describe("buildVomScene", () => {
const scene = buildVomScene(axNodes, captured);
expect(scene.nodes.find((n) => n.id === 20)).toEqual(
expect.objectContaining({ id: 20, role: "button", name: "close", cursor: "pointer" }),
expect.objectContaining({ id: 20, role: "generic", cursor: "pointer" }),
);
const rendered = renderVom(scene);
expect(rendered.text).toContain('@e1 button "close"');
@@ -1732,7 +1436,7 @@ describe("buildVomScene", () => {
};
const scene = buildVomScene(axNodes, captured);
expect(scene.nodes.find((n) => n.id === 20)).toBeUndefined();
expect(scene.nodes.find((n) => n.id === 20)?.role).toBe("generic");
expect(scene.nodes.find((n) => n.id === 30)?.role).toBe("link");
});
@@ -1801,9 +1505,9 @@ describe("buildVomScene", () => {
const scene = buildVomScene(axNodes, captured);
expect(scene.nodes.find((n) => n.id === 20)).toEqual(
expect.objectContaining({ id: 20, role: "button", attrs: { "aria-label": "收藏" } }),
expect.objectContaining({ id: 20, role: "generic", attrs: { "aria-label": "收藏" } }),
);
expect(scene.nodes.find((n) => n.id === 30)).toBeUndefined();
expect(scene.nodes.find((n) => n.id === 30)?.role).toBe("generic");
const rendered = renderVom(scene);
expect(rendered.text).toContain('@e1 button "收藏"');
expect(rendered.refs.map(({ ref, backendNodeId }) => ({ ref, backendNodeId }))).toEqual([
@@ -2131,7 +1835,7 @@ describe("buildVomScene", () => {
});
expect(scene.surfaces).toEqual([
{ triggerId: 20, triggerAction: "hover", subItems: ["My profile", "Sign out"] },
{ triggerId: 21, triggerAction: "hover", subItems: ["My profile", "Sign out"] },
]);
expect(renderVom(scene).text).toContain(
'@e1 button "image" [hover first: My profile | Sign out]',
@@ -2757,64 +2461,6 @@ describe("handleSnapshot", () => {
expect(ctx.refStore.resolve("e1")).toBeNull();
});
it("keeps the previous RefStore when cancellation lands during DOM capture", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e1", 999, { tabId: 4 });
const controller = new AbortController();
let resolveCapture: (value: unknown) => void = () => {};
const send = vi.fn(async (_tabId: number, method: string) => {
if (method === "Accessibility.enable") return {};
if (method === "Accessibility.getFullAXTree") {
return {
nodes: [
{
nodeId: "new",
role: { type: "role", value: "button" },
name: { type: "computedString", value: "New" },
backendDOMNodeId: 123,
},
],
};
}
if (method === "Page.getLayoutMetrics") {
return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
}
if (method === "DOMSnapshot.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") {
return new Promise((resolve) => {
resolveCapture = resolve;
});
}
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(),
query: vi.fn(async () => [{ id: 4, windowId: 100, active: true } as chrome.tabs.Tab]),
},
};
const pending = handleSnapshot(sm, { session_id: "aa11" }, deps, controller.signal);
await vi.waitFor(() =>
expect(send).toHaveBeenCalledWith(4, "DOMSnapshot.captureSnapshot", expect.any(Object)),
);
controller.abort();
resolveCapture({ strings: [], documents: [] });
await expect(pending).resolves.toMatchObject({ code: "cancelled" });
expect(ctx.refStore.resolve("e1", { tabId: 4 })).toBe(999);
expect(ctx.refStore.resolve("e2")).toBeNull();
});
it("surfaces CDP failures as cdp_failed", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
await sm.start("aa11");
@@ -2909,452 +2555,10 @@ describe("handleSnapshot", () => {
],
};
}
function secretsSnapshotReply(secrets: {
email: string;
password: string;
otp: string;
card: string;
}) {
const S = [
"html",
"body",
"input",
"position",
"static",
"pointer-events",
"auto",
"type",
"text",
"password",
"autocomplete",
"one-time-code",
"cc-number",
"value",
secrets.email,
secrets.password,
secrets.otp,
secrets.card,
];
const i = (s: string) => S.indexOf(s);
const style = [i("static"), i("auto"), i("auto")];
return {
strings: S,
documents: [
{
nodes: {
parentIndex: [-1, 0, 1, 1, 1, 1],
nodeName: [i("html"), i("body"), i("input"), i("input"), i("input"), i("input")],
backendNodeId: [10, 11, 12, 13, 14, 15],
attributes: [
[],
[],
[i("type"), i("text"), i("value"), i(secrets.email)],
[i("type"), i("password"), i("value"), i(secrets.password)],
[
i("type"),
i("text"),
i("autocomplete"),
i("one-time-code"),
i("value"),
i(secrets.otp),
],
[
i("type"),
i("text"),
i("autocomplete"),
i("cc-number"),
i("value"),
i(secrets.card),
],
],
inputValue: {
index: [2, 3, 4, 5],
value: [i(secrets.email), i(secrets.password), i(secrets.otp), i(secrets.card)],
},
},
layout: {
nodeIndex: [1, 2, 3, 4, 5],
styles: [style, style, style, style, style],
bounds: [
[0, 0, 1000, 800],
[10, 10, 200, 32],
[10, 50, 200, 32],
[10, 90, 200, 32],
[10, 130, 200, 32],
],
paintOrders: [0, 1, 2, 3, 4],
},
},
],
};
}
const VP_METRICS = {
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
};
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")];
const snapshot = {
strings,
documents: [
{
frameId: "main",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i("iframe")],
backendNodeId: [10, 11, 12],
attributes: [[], [], [i("title"), i("Remote")]],
contentDocumentIndex: { index: [2], value: [1] },
},
layout: {
nodeIndex: [0, 1, 2],
styles: [styles, styles, styles],
bounds: [
[0, 0, 1000, 800],
[0, 0, 1000, 800],
[100, 100, 400, 300],
],
paintOrders: [0, 0, 1],
},
},
{
frameId: "child",
nodes: {
parentIndex: [-1, 0, 1],
nodeName: [i("html"), i("body"), i("button")],
backendNodeId: [20, 21, 22],
attributes: [[], [], []],
},
layout: {
nodeIndex: [0, 1, 2],
styles: [styles, styles, styles],
bounds: [
[0, 0, 400, 300],
[0, 0, 400, 300],
[20, 30, 120, 40],
],
paintOrders: [0, 0, 1],
},
},
],
};
const mainAx: CdpAxNode[] = [
{
nodeId: "main-root",
role: { type: "role", value: "RootWebArea" },
backendDOMNodeId: 11,
childIds: ["frame-owner"],
},
{
nodeId: "frame-owner",
parentId: "main-root",
role: { type: "role", value: "Iframe" },
name: { type: "computedString", value: "Remote" },
backendDOMNodeId: 12,
},
];
const childAx: CdpAxNode[] = [
{
nodeId: "child-root",
role: { type: "role", value: "RootWebArea" },
backendDOMNodeId: 21,
childIds: ["child-button"],
},
{
nodeId: "child-button",
parentId: "child-root",
role: { type: "role", value: "button" },
name: { type: "computedString", value: "Frame action" },
backendDOMNodeId: 22,
},
];
const send = vi.fn(async (_tabId: number, method: string) => {
if (method === "Page.getLayoutMetrics") return VP_METRICS;
if (method === "DOMSnapshot.enable" || method === "Accessibility.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
if (method === "Accessibility.getFullAXTree") return { nodes: mainAx };
throw new Error(`unexpected root CDP method ${method}`);
});
const sendToTarget = vi.fn(async (_target, method: string) => {
if (method === "Accessibility.enable") return {};
if (method === "Accessibility.getFullAXTree") return { nodes: childAx };
throw new Error(`unexpected child CDP method ${method}`);
});
const cdp = {
send: send as unknown as CdpRunner["send"],
sendToTarget: sendToTarget as unknown as NonNullable<CdpRunner["sendToTarget"]>,
getFrameGraph: vi.fn(async () => ({
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 4 } },
{
frameId: "child",
parentFrameId: "main",
ownerBackendNodeId: 12,
target: { tabId: 4, sessionId: "child-session" },
},
],
})),
trackSessionTab: vi.fn(),
} satisfies CdpRunner;
return {
cdp,
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]),
},
};
}
it("exposes the frame-aware observation result for recording", async () => {
const ax: CdpAxNode[] = [
{
nodeId: "root",
role: { type: "role", value: "RootWebArea" },
backendDOMNodeId: 11,
childIds: ["password"],
},
{
nodeId: "password",
parentId: "root",
role: { type: "role", value: "textbox" },
name: { type: "computedString", value: "Password" },
value: { value: "hunter2" },
backendDOMNodeId: 13,
},
];
const deps = makeOverlayDeps(ax, loginSnapshotReply(), VP_METRICS);
const result = await captureVomObservation(deps.cdp, 4, "https://example.com", {
redactValues: true,
});
expect(result.text).not.toContain("hunter2");
expect(result.text).toContain("•••");
expect(result.refs[0]).toMatchObject({
backendNodeId: 13,
role: "textbox",
name: "Password",
line: expect.any(Number),
});
expect(result.rootFrameId).toBe("root");
expect(result).not.toHaveProperty("frameDocuments");
expect(result.frames).toEqual([{ frameId: "root", target: { tabId: 4 } }]);
expect(result.matchNodes.find((node) => node.backendNodeId === 13)).toMatchObject({
frameId: "root",
backendNodeId: 13,
tag: "input",
rect: { x: 400, y: 300, w: 200, h: 40 },
localRect: { x: 400, y: 300, w: 200, h: 40 },
});
});
it("decorates live observations with active controlled content", async () => {
const strings = [
"html",
"body",
"button",
"div",
"#text",
"role",
"tab",
"aria-selected",
"true",
"aria-controls",
"reviews-panel",
"id",
"static",
"auto",
"visible",
"1",
"A detailed review",
];
const index = (value: string) => strings.indexOf(value);
const style = [index("static"), index("auto"), index("auto"), index("visible"), index("1")];
const snapshot = {
strings,
documents: [
{
nodes: {
parentIndex: [-1, 0, 1, 1, 3],
nodeName: [index("html"), index("body"), index("button"), index("div"), index("#text")],
backendNodeId: [10, 11, 12, 13, 14],
attributes: [
[],
[],
[
index("role"),
index("tab"),
index("aria-selected"),
index("true"),
index("aria-controls"),
index("reviews-panel"),
],
[index("id"), index("reviews-panel")],
[],
],
nodeValue: [-1, -1, -1, -1, index("A detailed review")],
},
layout: {
nodeIndex: [0, 1, 2, 3, 4],
styles: [style, style, style, style, style],
bounds: [
[0, 0, 1000, 800],
[0, 0, 1000, 800],
[20, 20, 120, 40],
[20, 80, 500, 200],
[20, 80, 200, 20],
],
paintOrders: [0, 0, 1, 1, 1],
},
},
],
};
const ax: CdpAxNode[] = [
{
nodeId: "root",
backendDOMNodeId: 11,
role: { type: "role", value: "RootWebArea" },
childIds: ["reviews"],
},
{
nodeId: "reviews",
parentId: "root",
backendDOMNodeId: 12,
role: { type: "role", value: "tab" },
name: { type: "computedString", value: "Reviews" },
properties: [
{ name: "selected", value: { value: true } },
{ name: "controls", value: { value: "reviews-panel" } },
],
},
];
const result = await captureVomObservation(
makeOverlayDeps(ax, snapshot, VP_METRICS).cdp,
4,
"https://example.com",
);
expect(result.text).toContain('@e1 tab "Reviews"');
expect(result.text).toContain("[§ active: Reviews]");
expect(result.text).toContain("A detailed review");
});
it("does not leak form secrets through the record-safe observation payload", async () => {
const secrets = {
email: "user@example.com",
password: "hunter2",
otp: "847291",
card: "4111111111111111",
};
const ax: CdpAxNode[] = [
{
nodeId: "root",
role: { type: "role", value: "RootWebArea" },
backendDOMNodeId: 11,
childIds: ["email", "password", "otp", "card"],
},
{
nodeId: "email",
parentId: "root",
role: { type: "role", value: "textbox" },
name: { type: "computedString", value: "Email" },
value: { value: secrets.email },
backendDOMNodeId: 12,
},
{
nodeId: "password",
parentId: "root",
role: { type: "role", value: "textbox" },
name: { type: "computedString", value: "Password" },
value: { value: secrets.password },
backendDOMNodeId: 13,
},
{
nodeId: "otp",
parentId: "root",
role: { type: "role", value: "textbox" },
name: { type: "computedString", value: "Code" },
value: { value: secrets.otp },
backendDOMNodeId: 14,
},
{
nodeId: "card",
parentId: "root",
role: { type: "role", value: "textbox" },
name: { type: "computedString", value: "Card" },
value: { value: secrets.card },
backendDOMNodeId: 15,
},
];
const deps = makeOverlayDeps(ax, secretsSnapshotReply(secrets), VP_METRICS);
const result = await captureVomObservation(deps.cdp, 4, "https://example.com", {
redactValues: true,
});
const dumped = JSON.stringify(result);
expect(result).not.toHaveProperty("frameDocuments");
expect(dumped).not.toContain(secrets.email);
expect(dumped).not.toContain(secrets.password);
expect(dumped).not.toContain(secrets.otp);
expect(dumped).not.toContain(secrets.card);
expect(dumped).not.toContain("formValue");
expect(dumped).not.toContain("formDefaultValue");
expect(dumped).not.toContain("axNodes");
expect(dumped).not.toContain("domNodes");
expect(dumped).not.toContain("attrs");
expect(result.text).toContain("•••");
});
it("keeps frames and rendered refs on the same frame identity", async () => {
const deps = makeFrameAwareDeps();
const result = await captureVomObservation(deps.cdp, 4, "https://example.com");
expect(result.rootFrameId).toBe("main");
expect(result.frames).toHaveLength(2);
expect(result.frames.find((frame) => frame.frameId === "child")).toEqual({
frameId: "child",
parentFrameId: "main",
ownerBackendNodeId: 12,
target: { tabId: 4, sessionId: "child-session" },
});
expect(result.matchNodes.find((node) => node.backendNodeId === 22)).toMatchObject({
frameId: "child",
tag: "button",
localRect: { x: 20, y: 30, w: 120, h: 40 },
});
expect(result.refs.find((ref) => ref.backendNodeId === 22)).toMatchObject({
frameId: "child",
name: "Frame action",
});
});
it("stores iframe refs with their owning CDP session", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
const deps = makeFrameAwareDeps();
const result = await handleSnapshot(sm, { session_id: "aa11" }, deps);
if ("code" in result) throw new Error(`unexpected error: ${JSON.stringify(result)}`);
expect(result.text).toContain('@e1 button "Frame action"');
const frameRef = [...ctx.refStore.entries()].find(([, entry]) => entry.backendNodeId === 22);
expect(frameRef?.[1]).toMatchObject({
tabId: 4,
frameId: "child",
cdpSessionId: "child-session",
});
});
it("renders a blocking login overlay as the focused top layer", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
await sm.start("aa11");
@@ -3865,32 +3069,6 @@ describe("handleGetHtml", () => {
expect(deps.send).toHaveBeenCalledTimes(1);
});
it("reads a frame ref through its child CDP session", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e7", 4242, {
tabId: 4,
frameId: "child-frame",
cdpSessionId: "child-session",
});
const deps = makeDeps({});
const sendToTarget = vi.fn(async (target, method, params) => {
expect(target).toEqual({ tabId: 4, sessionId: "child-session" });
expect(method).toBe("DOM.getOuterHTML");
expect(params).toEqual({ backendNodeId: 4242 });
return { outerHTML: "<button>frame</button>" };
});
(deps.cdp as CdpRunner).sendToTarget = sendToTarget as unknown as NonNullable<
CdpRunner["sendToTarget"]
>;
const res = await handleGetHtml(sm, { session_id: "aa11", ref: "@e7" }, deps);
if ("code" in res) throw new Error(`unexpected error: ${JSON.stringify(res)}`);
expect(res.html).toBe("<button>frame</button>");
expect(deps.send).not.toHaveBeenCalled();
});
it("returns not_found when a ref belongs to another tab", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
File diff suppressed because it is too large Load Diff
@@ -60,58 +60,11 @@ function makeApis(
}),
getLastFocused: vi.fn(async () => ({ id: 500 }) as chrome.windows.Window),
create: vi.fn(async () => ({ id: 999 }) as chrome.windows.Window),
remove: vi.fn(async () => {}),
};
return { tabs, windows };
}
describe("handleSessionStop with auto-return", () => {
it("leaves the session untouched when cancellation arrived before teardown", async () => {
const aw = fakeAgentWindow([100]);
const sm = new SessionManager({ agentWindow: aw });
await sm.start("aa11");
const cdp = { detachSession: vi.fn(async () => {}) };
const controller = new AbortController();
controller.abort();
const res = await handleSessionStop(
sm,
{ session_id: "aa11" },
{ cdp, signal: controller.signal },
);
expect(res).toMatchObject({ code: "cancelled" });
expect(sm.has("aa11")).toBe(true);
expect(cdp.detachSession).not.toHaveBeenCalled();
expect(aw.remove).not.toHaveBeenCalled();
});
it("does not close the Agent Window when cancellation lands during CDP detach", async () => {
const aw = fakeAgentWindow([100]);
const sm = new SessionManager({ agentWindow: aw });
await sm.start("aa11");
const controller = new AbortController();
let finishDetach: () => void = () => {};
const detach = new Promise<void>((resolve) => {
finishDetach = resolve;
});
const cdp = { detachSession: vi.fn(() => detach) };
const stopping = handleSessionStop(
sm,
{ session_id: "aa11" },
{ cdp, signal: controller.signal },
);
await vi.waitFor(() => expect(cdp.detachSession).toHaveBeenCalledWith("aa11"));
controller.abort();
finishDetach();
const res = await stopping;
expect(res).toMatchObject({ code: "cancelled" });
expect(sm.has("aa11")).toBe(true);
expect(aw.remove).not.toHaveBeenCalled();
});
it("returns every borrowed tab and closes the Agent Window in the right order", async () => {
const aw = fakeAgentWindow([100]);
const sm = new SessionManager({ agentWindow: aw });
@@ -46,25 +46,6 @@ describe("lookupSnapshotRef", () => {
});
describe("resolveSnapshotRef", () => {
it("preserves the frame and child session needed to route iframe refs", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e3", 1234, {
tabId: 4,
frameId: "child-frame",
cdpSessionId: "child-session",
});
const expected = {
backendNodeId: 1234,
refKey: "e3",
frameId: "child-frame",
cdpSessionId: "child-session",
};
expect(lookupSnapshotRef(ctx, "@e3", 4)).toEqual(expected);
expect(resolveSnapshotRef(ctx, "@e3", 4)).toEqual(expected);
});
it("returns not_found for unknown ref", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
@@ -179,7 +179,6 @@ function makeWindowsApi(
get: ReturnType<typeof vi.fn>;
lastFocused: ReturnType<typeof vi.fn>;
create: ReturnType<typeof vi.fn>;
remove: ReturnType<typeof vi.fn>;
};
} {
const get = vi.fn(async (windowId: number) => {
@@ -198,13 +197,7 @@ function makeWindowsApi(
const id = opts?.createWindowId ?? 999;
return { id } as chrome.windows.Window;
});
const remove = vi.fn(async (windowId: number) => {
state.windowsClosed.add(windowId);
});
return {
api: { get, getLastFocused: lastFocused, create, remove },
spies: { get, lastFocused, create, remove },
};
return { api: { get, getLastFocused: lastFocused, create }, spies: { get, lastFocused, create } };
}
describe("handleTabCreate", () => {
@@ -608,86 +601,6 @@ describe("handleTabReturn", () => {
expect(winSpies.create).toHaveBeenCalledOnce();
});
it("closes a newly created fallback window when cancellation wins before the move", 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([200]),
};
const { api, spies } = makeTabMutationApi(state);
const { api: windowsApi, spies: winSpies } = makeWindowsApi(state, {
lastFocused: 100,
createWindowId: 777,
});
let resolveCreate: (window: chrome.windows.Window) => void = () => {};
winSpies.create.mockImplementationOnce(
() =>
new Promise((resolve) => {
resolveCreate = resolve;
}),
);
const controller = new AbortController();
const pending = handleTabReturn(
sm,
{ session_id: "aa11", tab_id: 7 },
{ tabs: api, windows: windowsApi, signal: controller.signal },
);
await vi.waitFor(() => expect(winSpies.create).toHaveBeenCalledOnce());
controller.abort();
resolveCreate({ id: 777 } as chrome.windows.Window);
await expect(pending).resolves.toMatchObject({ code: "cancelled" });
expect(winSpies.remove).toHaveBeenCalledWith(777);
expect(spies.move).not.toHaveBeenCalled();
expect(ctx.borrowedTabs.has(7)).toBe(true);
});
it("surfaces the fallback window id when cancellation cleanup fails", 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([200]),
};
const { api, spies } = makeTabMutationApi(state);
const { api: windowsApi, spies: winSpies } = makeWindowsApi(state, {
lastFocused: 100,
createWindowId: 777,
});
let resolveCreate: (window: chrome.windows.Window) => void = () => {};
winSpies.create.mockImplementationOnce(
() =>
new Promise((resolve) => {
resolveCreate = resolve;
}),
);
winSpies.remove.mockRejectedValueOnce(new Error("window removal denied"));
const controller = new AbortController();
const pending = handleTabReturn(
sm,
{ session_id: "aa11", tab_id: 7 },
{ tabs: api, windows: windowsApi, signal: controller.signal },
);
await vi.waitFor(() => expect(winSpies.create).toHaveBeenCalledOnce());
controller.abort();
resolveCreate({ id: 777 } as chrome.windows.Window);
await expect(pending).resolves.toMatchObject({
code: "protocol_error",
data: { reason: "cleanup_failed", resource_type: "window", resource_id: 777 },
message: expect.stringMatching(/fallback window 777.*window removal denied/),
});
expect(spies.move).not.toHaveBeenCalled();
expect(ctx.borrowedTabs.has(7)).toBe(true);
});
it("falls back to a new window when getLastFocused only returns the Agent Window", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
@@ -250,10 +250,9 @@ const DEFAULT_NOTIFICATION_COPY: BorrowNotificationCopy = {
// URL injection-eligibility test
// ---------------------------------------------------------------------------
const EXTENSION_STORE_RES = [
const CHROME_WEB_STORE_RES = [
/^https:\/\/chrome\.google\.com\/webstore/i,
/^https:\/\/chromewebstore\.google\.com/i,
/^https:\/\/microsoftedge\.microsoft\.com\/addons/i,
];
/**
@@ -265,15 +264,14 @@ const EXTENSION_STORE_RES = [
* - `ftp://` no longer hosts content scripts reliably in modern Chrome.
* - `about:` / `chrome:` / `chrome-extension:` / `edge:` / `devtools:` /
* `view-source:` / `data:` / `blob:` are blocked by the platform.
* - Extension storefronts are blocked by their own browser: the Chrome Web
* Store (legacy and new domains) under Chrome, and Edge Add-ons under Edge.
* - The Chrome Web Store (both legacy and new domains) is also blocked.
*
* Mirrors the implicit scheme list documented in
* https://developer.chrome.com/docs/extensions/develop/concepts/match-patterns.
*/
export function isInjectableContentScriptUrl(url: string | undefined): boolean {
if (!url) return false;
for (const re of EXTENSION_STORE_RES) {
for (const re of CHROME_WEB_STORE_RES) {
if (re.test(url)) return false;
}
return /^https?:\/\//i.test(url);
@@ -1,9 +1,124 @@
export {
type CaptureVomObservationOptions,
captureVomObservation,
} from "./observation";
export {
type CaptureVomFrame,
type CaptureVomMatchNode,
type CaptureVomObservationResult,
} from "./vom/record-safe-observation";
import { type RenderedRef, renderVom, type VomOptions } from "@browser-skill/vom";
import { readRecordDocumentTokenFromAttrs } from "@/lib/record-document-token";
import type { CdpAxNode } from "./observation";
import { buildVomScene } from "./observation";
import type { CdpRunner } from "./shared";
import {
type CapturedNode,
type CapturedSurfaceProbe,
type CapturedViewModel,
captureViewModel,
collectOverlayExcludedBackendIds,
} from "./vom/capture";
export interface CaptureVomObservationOptions extends VomOptions {
conditionalSurfaceProbe?: boolean;
hoverProbeBypassOverlay?: (tabId: number, enabled: boolean) => Promise<void>;
}
export interface CaptureVomObservationResult {
text: string;
refs: RenderedRef[];
truncated: boolean;
captured: CapturedNode[];
/** All nodes including iframe sub-documents, for geometric target matching. */
matchNodes: CapturedNode[];
/** Maps ephemeral record document tokens to immediate iframe owner backend ids. */
documentTokenOwners: Map<string, number | null>;
surfaceProbes?: CapturedSurfaceProbe[];
}
export function flattenCapturedNodes(vm: CapturedViewModel): CapturedNode[] {
return [...vm.nodes, ...[...vm.iframeNodes.values()].flat()];
}
export function collectDocumentTokenOwners(vm: CapturedViewModel): Map<string, number | null> {
const owners = new Map<string, number | null>();
for (const node of flattenCapturedNodes(vm)) {
if (node.tag !== "html") continue;
const token = readRecordDocumentTokenFromAttrs(node.attrs);
if (!token) continue;
owners.set(token, node.ownerFrameBackendNodeId ?? null);
}
return owners;
}
function emptyCapturedViewModel(viewport = { width: 0, height: 0 }): CapturedViewModel {
return { viewport, nodes: [], iframeNodes: new Map(), excludedBackendNodeIds: new Set() };
}
interface LayoutMetricsViewportReply {
cssLayoutViewport?: { clientWidth?: number; clientHeight?: number };
layoutViewport?: { clientWidth?: number; clientHeight?: number };
}
async function fallbackCapturedViewModel(
cdp: CdpRunner,
tabId: number,
): Promise<CapturedViewModel> {
let viewport = { width: 0, height: 0 };
try {
const metrics = await cdp.send<LayoutMetricsViewportReply>(tabId, "Page.getLayoutMetrics", {});
const vpSrc = metrics.cssLayoutViewport ?? metrics.layoutViewport ?? {};
viewport = {
width: vpSrc.clientWidth ?? 0,
height: vpSrc.clientHeight ?? 0,
};
} catch {
// viewport stays zero-sized
}
const excludedBackendNodeIds = await collectOverlayExcludedBackendIds(cdp, tabId);
return { ...emptyCapturedViewModel(viewport), excludedBackendNodeIds };
}
async function captureForVom(
cdp: CdpRunner,
tabId: number,
conditionalSurfaceProbe: boolean,
hoverProbeBypassOverlay?: (tabId: number, enabled: boolean) => Promise<void>,
): Promise<CapturedViewModel> {
try {
return await captureViewModel(cdp, tabId, {
conditionalSurfaceProbe,
hoverProbeBypassOverlay,
});
} catch {
return fallbackCapturedViewModel(cdp, tabId);
}
}
/** Pure VOM capture pipeline shared by snapshot, observe, and recording. */
export async function captureVomObservation(
cdp: CdpRunner,
tabId: number,
url: string | undefined,
opts: CaptureVomObservationOptions = {},
): Promise<CaptureVomObservationResult> {
await cdp.ensureAttachedToUrl?.(tabId, url);
await cdp.send<unknown>(tabId, "Accessibility.enable", {});
const result = await cdp.send<{ nodes: CdpAxNode[] }>(tabId, "Accessibility.getFullAXTree", {});
const axNodes = result.nodes ?? [];
const captured = await captureForVom(
cdp,
tabId,
opts.conditionalSurfaceProbe ?? false,
opts.hoverProbeBypassOverlay,
);
const scene = buildVomScene(axNodes, captured, { pageUrl: url });
const rendered = renderVom(scene, {
maxDepth: opts.maxDepth,
maxTokens: opts.maxTokens,
redactValues: opts.redactValues,
activeRegionPolicy: opts.activeRegionPolicy ?? true,
});
const matchNodes = flattenCapturedNodes(captured);
return {
text: rendered.text,
refs: rendered.refs,
truncated: rendered.truncated,
captured: captured.nodes,
matchNodes,
documentTokenOwners: collectDocumentTokenOwners(captured),
surfaceProbes: captured.surfaceProbes,
};
}
-4
View File
@@ -27,23 +27,19 @@ export async function handleConsole(
manager: SessionManager,
params: ConsoleParams,
deps: ConsoleDeps = defaultConsoleDeps(),
signal?: AbortSignal,
): Promise<ConsoleResult | RpcError> {
if (signal?.aborted) return { code: "cancelled", message: "console aborted" };
const ctxOrErr = lookupSession(manager, params, "console");
if (isRpcError(ctxOrErr)) return ctxOrErr;
const bounds = parseBufferedReadBounds(params);
if (isRpcError(bounds)) return bounds;
const target = await resolveTargetTab(manager, ctxOrErr, params.tab_id, deps.tabsApi);
if (isRpcError(target)) return target;
if (signal?.aborted) return { code: "cancelled", message: "console aborted" };
if (!deps.cdp.ensureConsoleCapture || !deps.cdp.consoleEntriesSince) {
return { code: "cdp_failed", message: "console capture requires CDP console support" };
}
try {
await deps.cdp.ensureConsoleCapture(target.tabId);
if (signal?.aborted) return { code: "cancelled", message: "console aborted" };
deps.cdp.trackSessionTab?.(ctxOrErr.sessionId, target.tabId);
return deps.cdp.consoleEntriesSince(
target.tabId,

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