Compare commits

..
Author SHA1 Message Date
Ljy-0827 64bbbbf4f8 perf(observation): reduce document processing scheduling overhead 2026-09-09 13:20:22 +08:00
Ljy-0827 e2b5acc904 refactor(observation): isolate document processing from capture orchestration 2026-09-09 13:20:22 +08:00
Ljy-0827 361f4603fe fix(observation): preserve snapshot document provenance and URL metadata 2026-09-09 13:20:22 +08:00
Ljy-0827 3e2725bb40 refactor(observation): defer visual facts until visual discovery 2026-09-09 13:20:22 +08:00
Ljy-0827 0ebb4a4283 fix(observation): await capture task cleanup before propagating cancellation 2026-09-09 13:20:22 +08:00
Ljy-0827 cda20d979b refactor(observation): organize capture around document facts 2026-09-09 13:20:22 +08:00
Ljy-0827 2d2636030d perf(geometry): batch iframe owner size measurements 2026-09-09 13:20:21 +08:00
Ljy-0827 a28b9d55e7 fix(vom): surface incomplete iframe geometry in observations 2026-09-09 13:20:21 +08:00
Ljy-0827 c39874591f perf(observation): measure sibling iframe geometry with bounded concurrency 2026-09-09 13:20:21 +08:00
Ljy-0827 1485addfd5 fix(geometry): unify frame projection and screenshot coordinates 2026-09-09 13:20:21 +08:00
Zhang GH 90b0ff301b Merge pull request #204 from Tencent/release/0.2.1
Release/0.2.1
2026-09-09 11:35:05 +08:00
drakezhang e74f354e90 fix(release): support changelogs without unreleased section 2026-09-08 20:38:17 +08:00
drakezhang 05c036518a chore(release): 0.2.1 2026-09-08 20:35:14 +08:00
Zhang GH 020fb3212e Merge pull request #201 from Tencent/fix/windows-install-and-cancellation
fix(windows): harden installation and parent cancellation
2026-09-08 20:15:12 +08:00
Zhang GH 0822c53c65 fix(windows): preserve transfer cleanup after cancellation 2026-09-08 20:04:24 +08:00
Zhang GH 4450fbe28c Merge pull request #196 from Tencent/codex/dsh-plugin-docs
docs(dsh-plugin): clarify installation, configuration, and releases
2026-09-08 19:43:24 +08:00
drakezhang a3bb81bfab docs(dsh-plugin): clarify patch editing and reload behavior 2026-09-08 19:34:25 +08:00
Zhang GH caea98cd52 fix(windows): harden installation and parent cancellation 2026-09-08 19:21:54 +08:00
drakezhang 187b088013 docs(dsh-plugin): restore configuration guidance and simplify releases 2026-09-08 19:03:40 +08:00
drakezhang 5046b5ab44 docs(dsh-plugin): clarify setup and verify npm publishing 2026-09-08 18:44:20 +08:00
Zhang GH e8137b42cc Merge pull request #194 from Tencent/fix/dsh-runtime-peer-dependency
fix(dsh-plugin): remove obsolete client runtime host dependency
2026-09-08 17:34:33 +08:00
Zhang GH cb5dc148d5 fix(dsh-plugin): remove obsolete client runtime host dependency
Keep dsh-client-runtime as a development-only type dependency. Remove its peer metadata, client injection entry, and runtime external allowance so newer hosts do not preflight a package they no longer ship.

Fixes #193
2026-09-08 16:58:20 +08:00
Zhang GH 3c5f838c56 Merge pull request #192 from Tencent/fix/windows-update-reliability
fix(update): make Windows self-updates reliable
2026-09-07 20:37:32 +08:00
46 changed files with 3626 additions and 1167 deletions
+11 -3
View File
@@ -38,7 +38,7 @@ jobs:
run: cargo test --workspace --locked
windows-daemon:
name: Windows daemon and update regression tests
name: Windows daemon, installer and cancellation regression tests
runs-on: windows-latest
steps:
@@ -55,8 +55,16 @@ jobs:
- name: Run Windows update tests
run: cargo test -p bsk --lib --locked cli::update::tests
- name: Run Windows update process tests
run: cargo test -p bsk --test windows_update --locked
- name: Run Windows update and cancellation process tests
run: cargo test -p bsk --test windows_update --test windows_parent_cancel --locked
- name: Run installer tests (Windows PowerShell 5.1)
shell: powershell
run: ./scripts/install-windows.test.ps1
- name: Run installer tests (PowerShell 7)
shell: pwsh
run: ./scripts/install-windows.test.ps1
frontend:
name: Frontend lint, typecheck, tests, build
+18 -1
View File
@@ -5,7 +5,24 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/).
Starting from 0.2.0, CLI / Extension / DSH Plugin share the same version number.
## [Unreleased]
## [0.2.1] - 2026-09-09
### Changed
- DSH Plugin: clarified installation, configuration, profile restart, and upgrade instructions
### Fixed
- CLI: reliable Windows self-updates, including executable replacement and daemon restart
- CLI: Windows named-pipe connection continuity and stale daemon process detection
- Windows installer: PowerShell 5.1 compatibility, path quoting, and staged executable replacement
- CLI / DSH Plugin: cancellation propagation and upload/download cleanup when the parent process exits
- Extension: tab ownership and session cleanup when agent tabs fail to open or borrowed tabs are returned or closed
- Extension: navigation recovery when other extensions restrict Chrome DevTools Protocol access
- Extension: background input filling, automatic append behavior, and verification of field values before reporting success
- Extension: match observed form state to the correct element after page changes
- Extension: UUID generation fallback for recording and overlays on insecure origins
- Browser locale matching for regional language variants
- DSH Plugin: observation state synchronization, thumbnail capture lifecycle, and stale preview cleanup
- DSH Plugin: removed the obsolete client runtime host dependency
## [0.2.0] - 2026-09-02
Generated
+2 -2
View File
@@ -134,7 +134,7 @@ dependencies = [
[[package]]
name = "bsk"
version = "0.2.0"
version = "0.2.1"
dependencies = [
"anyhow",
"base64",
@@ -169,7 +169,7 @@ dependencies = [
[[package]]
name = "bsk-protocol"
version = "0.2.0"
version = "0.2.1"
dependencies = [
"schemars",
"semver",
+2 -2
View File
@@ -7,7 +7,7 @@ members = [
default-members = ["crates/bsk-cli"]
[workspace.package]
version = "0.2.0"
version = "0.2.1"
edition = "2024"
rust-version = "1.85"
license = "MIT"
@@ -43,7 +43,7 @@ rand = "0.8"
uuid = { version = "1", features = ["v4", "serde"] }
# Workspace crates (version required for `cargo publish` of dependents)
bsk-protocol = { version = "0.2.0", path = "crates/bsk-protocol" }
bsk-protocol = { version = "0.2.1", path = "crates/bsk-protocol" }
[profile.release]
strip = "symbols"
+13 -7
View File
@@ -147,20 +147,26 @@ Start a new Agent session and write a prompt that needs the browser, for example
Using [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) (`dsh`)?
BrowserSkill ships a first-class dsh plugin on npm as
[`@wxg-prc-cpg/browser-skill-dsh-plugin`](https://www.npmjs.com/package/@wxg-prc-cpg/browser-skill-dsh-plugin).
It injects native `browser_*` tools (no shelling out to `bsk`) and a live Web UI
overlay of each Agent Window.
It gives the agent native `browser_*` tools and a live view of its browser sessions
in the Web UI. The plugin runs `bsk` on the agent's behalf.
Add it to a dsh profile, then start that profile:
Install the `bsk` CLI and connect the browser extension first. Then add the plugin
to a dsh profile and start it (replace `web` with your profile name):
```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.
The plugin includes the `browser-skill` skill, so `bsk install-skill` is not needed
for dsh. Installed plugins do not update automatically. To upgrade this plugin:
```sh
dsh plugin --profile web update @wxg-prc-cpg/browser-skill-dsh-plugin --latest
```
Restart the profile after upgrading. See the
[plugin README](packages/dsh-plugin-browserskill/README.md) for usage and configuration.
## How It Works
+9 -3
View File
@@ -125,16 +125,22 @@ bsk install-skill
## DeepSeek Harness 插件
在用 [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness)(`dsh`)?BrowserSkill 提供了官方 dsh 插件,已发布到 npm:[`@wxg-prc-cpg/browser-skill-dsh-plugin`](https://www.npmjs.com/package/@wxg-prc-cpg/browser-skill-dsh-plugin)。它会注入原生 `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。
在用 [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness)(`dsh`)?BrowserSkill 提供了官方 dsh 插件,已发布到 npm:[`@wxg-prc-cpg/browser-skill-dsh-plugin`](https://www.npmjs.com/package/@wxg-prc-cpg/browser-skill-dsh-plugin)。它为 Agent 提供原生 `browser_*` 工具,由插件代为调用 `bsk`,并在 Web UI 中实时展示浏览器会话。
把它装进某个 dsh profile,然后启动该 profile:
先安装 `bsk` CLI 并连接浏览器扩展,再将插件装进 dsh profile 并启动(将 `web` 替换为你的 profile 名称):
```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)。
插件自带 `browser-skill` skill,所以在 dsh 下无需执行 `bsk install-skill`。已安装的插件不会自动更新;升级此插件请运行:
```sh
dsh plugin --profile web update @wxg-prc-cpg/browser-skill-dsh-plugin --latest
```
升级后重启该 profile。用法与配置见[插件 README](packages/dsh-plugin-browserskill/README.md)。
## 工作原理
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@browser-skill/extension",
"version": "0.2.0",
"version": "0.2.1",
"private": true,
"type": "module",
"scripts": {
@@ -1,5 +1,5 @@
import { describe, expect, it, vi } from "vitest";
import { resolveFrameProjection, resolveNodeGeometry } from "../frame-geometry";
import { resolveNodeGeometry } from "../frame-geometry";
import {
clipPolygon,
polygonArea,
@@ -10,6 +10,7 @@ import {
rectPolygon,
regionBounds,
} from "../geometry";
import { GeometryContext } from "../geometry/frame-context";
import type { CdpRunner } from "../shared";
describe("frame geometry projection", () => {
@@ -82,28 +83,24 @@ describe("frame geometry projection", () => {
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",
);
const projection = await new GeometryContext(cdp, 4, {
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 4 } },
{
frameId: "same-process-parent",
parentFrameId: "main",
ownerBackendNodeId: 10,
target: { tabId: 4 },
},
{
frameId: "oopif",
parentFrameId: "same-process-parent",
ownerBackendNodeId: 20,
target: { tabId: 4, sessionId: "oopif-session" },
},
],
}).targetProjection("oopif");
expect(projection?.edges).toEqual([
{
@@ -0,0 +1,380 @@
import { describe, expect, it, vi } from "vitest";
import type { CdpFrameGraph } from "@/browser-driver/frame-graph";
import { resolveNodeGeometry } from "../frame-geometry";
import { rectPolygon } from "../geometry";
import {
projectSnapshotRect,
screenshotPageRect,
snapshotViewportRect,
} from "../geometry/coordinate-types";
import { GeometryContext } from "../geometry/frame-context";
import type { CdpRunner } from "../shared";
const target = { tabId: 4 };
const graph: CdpFrameGraph = {
rootFrameId: "main",
frames: [
{ frameId: "main", target },
{ frameId: "child", parentFrameId: "main", ownerBackendNodeId: 10, target },
],
};
function driver() {
const send = vi.fn(async (_tab: number, method: string): Promise<object> => {
if (method === "Page.getLayoutMetrics")
return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 1000 } };
if (method === "DOM.getBoxModel")
return { model: { content: [52.5, 612.5, 427.5, 612.5, 427.5, 862.5, 52.5, 862.5] } };
if (method === "DOM.resolveNode") return { object: { objectId: "owner" } };
if (method === "Runtime.callFunctionOn")
return { result: { value: { width: 300, height: 200 } } };
if (method === "Runtime.releaseObject") return {};
throw new Error(method);
});
return { send: send as CdpRunner["send"], getFrameGraph: vi.fn(async () => graph), calls: send };
}
describe("measurement geometry context", () => {
it("shares in-flight frame measurements, but never shares them with the next context", async () => {
const cdp = driver();
const context = new GeometryContext(cdp, 4);
const results = await Promise.all(
Array.from({ length: 20 }, () => context.targetProjection("child")),
);
expect(results.every((value) => value === results[0])).toBe(true);
expect(cdp.getFrameGraph).toHaveBeenCalledTimes(1);
expect(cdp.calls.mock.calls.map(([, method]) => method)).toEqual([
"Page.getLayoutMetrics",
"DOM.getBoxModel",
]);
await new GeometryContext(cdp, 4).targetProjection("child");
expect(cdp.getFrameGraph).toHaveBeenCalledTimes(2);
expect(cdp.calls.mock.calls).toHaveLength(4);
});
it("projects frame-local snapshot CSS bounds through the scaled owner content quad", async () => {
const cdp = driver();
const context = new GeometryContext(cdp, 4);
const source = { target, frameId: "child" };
const projection = await context.snapshotProjection(source, 10, [], {
width: 1000,
height: 1000,
});
if (projection.status !== "available") throw new Error("expected available projection");
const input = snapshotViewportRect([17, 23, 120, 40], source, { x: 0, y: 0 });
expect(projectSnapshotRect(input!, projection.projection)).toEqual({
x: 73.75,
y: 641.25,
width: 150,
height: 50,
});
const scrolled = snapshotViewportRect([17, 23, 120, 40], source, { x: 0, y: 10 });
expect(projectSnapshotRect(scrolled!, projection.projection)?.y).toBe(628.75);
await context.snapshotProjection(source, 10, [], { width: 1000, height: 1000 });
expect(cdp.calls.mock.calls.filter(([, method]) => method === "DOM.resolveNode")).toHaveLength(
1,
);
expect(
cdp.calls.mock.calls.filter(([, method]) => method === "Runtime.releaseObject"),
).toHaveLength(1);
});
it("falls back only for missing or invalid batch entries and does not reuse sizes across contexts", async () => {
const cdp = driver();
const original = cdp.send;
const calls: string[] = [];
cdp.send = async (tabId, method, params) => {
calls.push(method);
if (method === "Runtime.evaluate")
return {
result: {
deepSerializedValue: {
type: "array",
value: [
{
type: "array",
value: [
{ type: "node", value: { backendNodeId: 10 } },
{ type: "string", value: '{"width":300,"height":200}' },
],
},
{
type: "array",
value: [
{ type: "node", value: { backendNodeId: 11 } },
{ type: "string", value: '{"width":0,"height":200}' },
],
},
],
},
},
} as never;
if (method === "Runtime.releaseObjectGroup") return {} as never;
return original(tabId, method, params);
};
const context = new GeometryContext(cdp, 4);
context.registerSnapshotOwners(target, new Set([10, 11]));
const values = await Promise.all(
[10, 11].map((id) =>
context.snapshotProjection({ target, frameId: String(id) }, id, [], {
width: 1000,
height: 1000,
}),
),
);
expect(values.every((value) => value.status === "available")).toBe(true);
expect(calls.filter((method) => method === "DOM.resolveNode")).toHaveLength(1);
expect(calls.filter((method) => method === "Runtime.evaluate")).toHaveLength(1);
await new GeometryContext(cdp, 4).snapshotProjection({ target, frameId: "child" }, 10, [], {
width: 1000,
height: 1000,
});
expect(calls.filter((method) => method === "DOM.resolveNode")).toHaveLength(2);
});
it("waits for batch object cleanup and propagates cancellation", async () => {
const cdp = driver();
const original = cdp.send;
const controller = new AbortController();
let release!: () => void;
let cleanup!: () => void;
const started = new Promise<void>((resolve) => {
cleanup = resolve;
});
cdp.send = async (tabId, method, params) => {
if (method === "Runtime.evaluate") return {} as never;
if (method === "Runtime.releaseObjectGroup") {
cleanup();
await new Promise<void>((resolve) => {
release = resolve;
});
return {} as never;
}
return original(tabId, method, params);
};
const context = new GeometryContext(cdp, 4, undefined, controller.signal);
context.registerSnapshotOwners(target, new Set([10, 11]));
let settled = false;
const operation = context
.snapshotProjection({ target, frameId: "child" }, 10, [], { width: 1000, height: 1000 })
.finally(() => {
settled = true;
});
const rejected = expect(operation).rejects.toMatchObject({ name: "AbortError" });
await started;
controller.abort();
expect(settled).toBe(false);
release();
await rejected;
expect(cdp.calls.mock.calls.some(([, method]) => method === "DOM.resolveNode")).toBe(false);
});
it("rejects owner mismatches and invalid numeric bounds", () => {
const input = snapshotViewportRect(
[30, 50, 120, 40],
{ target, frameId: "main" },
{ x: 10, y: 20 },
)!;
const projection = {
source: { target, frameId: "main" },
geometry: { sourceClips: [], edges: [], topViewport: { width: 800, height: 600 } },
};
expect(projectSnapshotRect(input, projection)).toEqual({
x: 20,
y: 30,
width: 120,
height: 40,
});
expect(
projectSnapshotRect(input, { ...projection, source: { target, frameId: "other" } }),
).toBeNull();
expect(
projectSnapshotRect(input, {
...projection,
source: { target: { tabId: 5 }, frameId: "main" },
}),
).toBeNull();
expect(snapshotViewportRect([0, 0, NaN, 40], { target }, { x: 0, y: 0 })).toBeNull();
expect(snapshotViewportRect([0, 0, 10, 40], { target }, { x: Infinity, y: 0 })).toBeNull();
});
it("does not turn a border quad or a failed owner read into a content projection", async () => {
const cdp: CdpRunner = {
send: vi.fn(async () => ({
model: { border: [0, 0, 100, 0, 100, 100, 0, 100] },
})) as CdpRunner["send"],
};
expect(
await new GeometryContext(cdp, 4).snapshotProjection({ target, frameId: "child" }, 10, [], {
width: 100,
height: 100,
}),
).toEqual({
status: "unavailable",
source: { target, frameId: "child" },
ownerBackendNodeId: 10,
});
});
it("keeps ancestor clips in target coordinates instead of applying nested offsets twice", async () => {
const cdp = driver();
const projection = await new GeometryContext(cdp, 4).snapshotProjection(
{ target, frameId: "nested" },
10,
[rectPolygon({ x: 60, y: 620, w: 100, h: 100 })],
{ width: 1000, height: 1000 },
);
if (projection.status !== "available") throw new Error("expected available projection");
const input = snapshotViewportRect(
[0, 0, 300, 200],
{ target, frameId: "nested" },
{ x: 0, y: 0 },
);
expect(projectSnapshotRect(input!, projection.projection)).toEqual({
x: 60,
y: 620,
width: 100,
height: 100,
});
});
it("rejects malformed frame ancestry without looping", async () => {
const cdp = driver();
const cycle: CdpFrameGraph = {
rootFrameId: "a",
frames: [
{ frameId: "a", parentFrameId: "b", target },
{ frameId: "b", parentFrameId: "a", target },
],
};
expect(await new GeometryContext(cdp, 4, cycle).targetProjection("a")).toBeNull();
expect(cdp.calls).not.toHaveBeenCalled();
const orphan: CdpFrameGraph = {
rootFrameId: "a",
frames: [{ frameId: "a", parentFrameId: "missing", target }],
};
expect(await new GeometryContext(cdp, 4, orphan).targetProjection("a")).toBeNull();
});
it("rejects a live node whose frame belongs to another target before any DOM input", async () => {
const cdp = driver();
expect(
await resolveNodeGeometry(
cdp,
4,
{ target: { tabId: 4, sessionId: "wrong" }, frameId: "child", backendNodeId: 20 },
{ scrollIntoView: true },
),
).toMatchObject({ code: "cdp_failed" });
expect(cdp.calls).not.toHaveBeenCalled();
});
it("bounds concurrent measurements and does not dispatch queued reads after cancellation", async () => {
let active = 0;
let peak = 0;
const release: Array<() => void> = [];
const send = vi.fn(async () => {
active++;
peak = Math.max(peak, active);
await new Promise<void>((resolve) => release.push(resolve));
active--;
return { cssLayoutViewport: { clientWidth: 100, clientHeight: 100 } };
});
const controller = new AbortController();
const context = new GeometryContext(
{ send: send as CdpRunner["send"] },
4,
undefined,
controller.signal,
);
const tasks = Array.from({ length: 8 }, (_, index) =>
context.viewport({ tabId: 4, sessionId: String(index) }),
);
const settled = Promise.allSettled(tasks);
expect(send).toHaveBeenCalledTimes(4);
controller.abort();
for (const done of release) done();
const results = await settled;
expect(peak).toBe(4);
expect(send).toHaveBeenCalledTimes(4);
expect(results.filter((item) => item.status === "rejected")).toHaveLength(4);
});
it("releases an owner object even when cancellation arrives before its viewport read", async () => {
const controller = new AbortController();
const cdp = driver();
const original = cdp.calls.getMockImplementation()!;
cdp.calls.mockImplementation(async (tab, method) => {
const result = await original(tab, method);
if (method === "DOM.resolveNode") controller.abort();
return result;
});
const context = new GeometryContext(cdp, 4, undefined, controller.signal);
await expect(
context.snapshotProjection({ target, frameId: "child" }, 10, [], {
width: 1000,
height: 1000,
}),
).rejects.toMatchObject({ name: "AbortError" });
expect(cdp.calls.mock.calls.map(([, method]) => method)).toEqual([
"DOM.getBoxModel",
"DOM.resolveNode",
"Runtime.releaseObject",
]);
});
it("reads live owner geometry only after scrolling", async () => {
const cdp = driver();
const original = cdp.calls.getMockImplementation()!;
let scrolled = false;
cdp.calls.mockImplementation(async (tab, method) => {
if (method === "DOM.scrollIntoViewIfNeeded") {
scrolled = true;
return {};
}
if (method === "DOM.getContentQuads") {
expect(scrolled).toBe(true);
return { quads: [[60, 620, 100, 620, 100, 640, 60, 640]] };
}
if (method === "DOM.getBoxModel") expect(scrolled).toBe(true);
return original(tab, method);
});
expect(
await resolveNodeGeometry(
cdp,
4,
{ target, frameId: "child", backendNodeId: 20 },
{ scrollIntoView: true },
),
).toMatchObject({ topBounds: { x: 60, y: 620, width: 40, height: 20 } });
expect(cdp.getFrameGraph).toHaveBeenCalledTimes(1);
expect(cdp.calls.mock.calls.filter(([, method]) => method === "DOM.getBoxModel")).toHaveLength(
1,
);
});
it("adapts viewport CSS bounds to page DIP with scroll and browser zoom, never raster DPR", () => {
const viewport = { width: 1600, height: 1000, scrollX: 10, scrollY: 100, cssToDip: 0.9 };
const clip = screenshotPageRect({ x: 20, y: 30, width: 120, height: 40 }, viewport);
expect(clip).toEqual({ space: "page-dip", rect: { x: 27, y: 117, width: 108, height: 36 } });
expect(
screenshotPageRect({ x: 20, y: 30, width: 120, height: 40 }, { ...viewport, cssToDip: NaN }),
).toBeNull();
expect(
screenshotPageRect({ x: 20, y: 30, width: 120, height: 40 }, { ...viewport, cssToDip: 0 }),
).toBeNull();
});
it("retries a rejected measurement only in a new operation", async () => {
const cdp = driver();
cdp.calls.mockRejectedValueOnce(new Error("unavailable"));
const context = new GeometryContext(cdp, 4);
await expect(context.viewport(target)).rejects.toThrow("unavailable");
await expect(context.viewport(target)).rejects.toThrow("unavailable");
expect(cdp.calls).toHaveBeenCalledTimes(1);
expect(await new GeometryContext(cdp, 4).viewport(target)).toEqual({
width: 1000,
height: 1000,
});
});
});
@@ -266,7 +266,15 @@ describe("handleScreenshot", () => {
expect(sent.find((c) => c.method === "Page.captureScreenshot")).toBeUndefined();
});
it("captures a clipped PNG when ref is given", async () => {
it.each([
{ zoom: 1, scroll: 0, expected: { x: 10, y: 20, width: 100, height: 40 } },
{ zoom: 0.9, scroll: 100, expected: { x: 9, y: 108, width: 90, height: 36 } },
{ zoom: 1.25, scroll: 100, expected: { x: 12.5, y: 150, width: 125, height: 50 } },
])("captures a ref in page DIP at zoom $zoom and scroll $scroll", async ({
zoom,
scroll,
expected,
}) => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e5", 999, { tabId: 7 });
@@ -274,6 +282,10 @@ describe("handleScreenshot", () => {
"DOM.scrollIntoViewIfNeeded": () => ({}),
"DOM.getContentQuads": () => ({ quads: [[10, 20, 110, 20, 110, 60, 10, 60]] }),
"Page.captureScreenshot": () => ({ data: TINY_PNG }),
"Page.getLayoutMetrics": () => ({
cssLayoutViewport: { clientWidth: 1280, clientHeight: 720, pageX: 0, pageY: scroll },
cssVisualViewport: { zoom },
}),
});
const captureVisibleTab = vi.fn();
const res = await handleScreenshot(
@@ -297,7 +309,8 @@ describe("handleScreenshot", () => {
clip?: { x: number; y: number; width: number; height: number };
}
)?.clip;
expect(clip).toMatchObject({ x: 10, y: 20, width: 100, height: 40 });
expect(clip).toMatchObject(expected);
expect(sent.filter((c) => c.method === "Page.getLayoutMetrics")).toHaveLength(1);
});
it("returns not_found for unknown ref", async () => {
@@ -655,6 +668,60 @@ describe("buildVomScene", () => {
expect(nestedInput?.parentId).toBe(result.nodes.find((item) => item.backendNodeId === 210)?.id);
});
it("excludes an overlay only in its owning document when target backend ids collide", () => {
const owner = (id: number): CapturedNode => ({
backendNodeId: id,
parentBackendNodeId: null,
frameId: "main",
tag: "iframe",
attrs: {},
rect: { x: id * 10, y: 0, w: 200, h: 100 },
paintOrder: 0,
position: "static",
pointerEvents: "auto",
});
const owners = [owner(10), owner(20)];
const result = buildFrameVomScene(
[
{
frameId: "main",
contextScopeId: "main",
target: { tabId: 7 },
domNodes: owners,
axNodes: [],
},
...["left", "right"].map((frameId, i) => ({
frameId,
contextScopeId: frameId,
parentFrameId: "main",
ownerBackendNodeId: owners[i].backendNodeId,
target: { tabId: 7, sessionId: frameId },
excludedBackendNodeIds: new Set(i === 0 ? [7] : []),
domNodes: [],
axNodes: [
{
nodeId: "button",
frameId,
backendDOMNodeId: 7,
role: { type: "role", value: "button" },
name: { type: "computedString", value: frameId + " action" },
},
],
})),
],
{
nodes: owners,
viewport: { width: 800, height: 600 },
iframeNodes: new Map(),
excludedBackendNodeIds: new Set(),
},
);
const rendered = renderVom(result);
expect(rendered.text).not.toContain("left action");
expect(rendered.text).toContain("right action");
expect(rendered.refs.find((ref) => ref.backendNodeId === 7)?.frameId).toBe("right");
});
it("does not place a child document at the page root when its frame boundary is unresolved", () => {
const childNode: CapturedNode = {
backendNodeId: 101,
@@ -3134,7 +3201,9 @@ describe("handleSnapshot", () => {
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
};
function makeFrameAwareDeps() {
function makeFrameAwareDeps(
ownerGeometry: "unavailable" | "available" | "clipped" = "unavailable",
) {
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")];
@@ -3214,6 +3283,16 @@ describe("handleSnapshot", () => {
];
const send = vi.fn(async (_tabId: number, method: string) => {
if (method === "Page.getLayoutMetrics") return VP_METRICS;
if (ownerGeometry !== "unavailable") {
if (method === "DOM.getBoxModel") {
const x = ownerGeometry === "clipped" ? 10000 : 100;
return { model: { content: [x, 100, x + 400, 100, x + 400, 400, x, 400] } };
}
if (method === "DOM.resolveNode") return { object: { objectId: "owner" } };
if (method === "Runtime.callFunctionOn")
return { result: { value: { width: 400, height: 300 } } };
if (method === "Runtime.releaseObject") return {};
}
if (method === "DOMSnapshot.enable" || method === "Accessibility.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
if (method === "Accessibility.getFullAXTree") return { nodes: mainAx };
@@ -3454,6 +3533,43 @@ describe("handleSnapshot", () => {
expect(result.text).toContain("•••");
});
it.each([
undefined,
100,
0,
])("reports unavailable iframe geometry within the observation budget %s", async (maxTokens) => {
const result = await captureVomObservation(makeFrameAwareDeps().cdp, 4, "https://example.com", {
maxTokens,
});
expect(result.text.match(/@warning/g)).toHaveLength(1);
expect(result.text).toContain("iframe geometry incomplete");
expect(result.text.startsWith("@vom 1\n")).toBe(true);
if (maxTokens === undefined) {
expect(result.truncated).toBe(false);
expect(result.text).toContain("Frame action");
expect(result.matchNodes.find((node) => node.backendNodeId === 22)).toMatchObject({
rect: null,
localRect: { x: 20, y: 30, w: 120, h: 40 },
});
}
if (maxTokens === 100) expect(Math.ceil(result.text.length / 4)).toBeLessThanOrEqual(maxTokens);
});
it.each([
"available",
"clipped",
] as const)("does not report successful %s geometry as an observation failure", async (ownerGeometry) => {
const result = await captureVomObservation(
makeFrameAwareDeps(ownerGeometry).cdp,
4,
"https://example.com",
);
expect(result.text).not.toContain("@warning");
const node = result.matchNodes.find((item) => item.backendNodeId === 22);
if (ownerGeometry === "clipped") expect(node?.rect).toBeNull();
else expect(node?.rect).toEqual({ x: 120, y: 130, w: 120, h: 40 });
});
it("keeps frames and rendered refs on the same frame identity", async () => {
const deps = makeFrameAwareDeps();
+46 -151
View File
@@ -1,24 +1,21 @@
import { type CdpFrame, type CdpFrameGraph, type CdpTarget } from "@/browser-driver/frame-graph";
import { type CdpTarget, cdpTargetKey } from "@/browser-driver/frame-graph";
import type { RpcError } from "@/transport/types";
import { nodeContentRegion, scrollNodeIntoView } from "./element-geometry";
import {
clipPolygon,
type GeometryProjection,
type Point,
type Polygon,
type ProjectiveEdge,
parseCdpQuad,
polygonArea,
polygonCentroid,
projectRegionToViewport,
type Quad,
type Region,
rectPolygon,
regionBounds,
type Size,
type ViewportRect,
} from "./geometry";
import { type CdpRunner, cdpRunnerForTarget, isRpcError, sendToCdpTarget } from "./shared";
import type { CssViewport } from "./geometry/coordinate-types";
import { cssViewport, GeometryContext } from "./geometry/frame-context";
import { type CdpRunner, cdpRunnerForTarget, isRpcError } from "./shared";
export interface NodeAddress {
target: CdpTarget;
@@ -27,6 +24,8 @@ export interface NodeAddress {
}
export interface ResolvedNodeGeometry {
/** The same top-level measurement used by projection, for screenshot coordinate adaptation. */
topViewport: CssViewport;
topVisibleRegions: Region;
topBounds: ViewportRect;
/** Point in the top-level tab viewport, used by root-target input events. */
@@ -39,145 +38,16 @@ function geometryError(message: string): RpcError {
return { code: "cdp_failed", message };
}
function frameMap(graph: CdpFrameGraph): Map<string, CdpFrame> {
return new Map(graph.frames.map((frame) => [frame.frameId, frame]));
}
function targetRootFrame(byId: Map<string, CdpFrame>, frame: CdpFrame): CdpFrame | null {
const seen = new Set<string>();
let current = frame;
while (current.parentFrameId) {
if (seen.has(current.frameId)) return null;
seen.add(current.frameId);
const parent = byId.get(current.parentFrameId);
if (!parent || parent.target.sessionId !== current.target.sessionId) break;
current = parent;
}
return current;
}
function frameAncestry(graph: CdpFrameGraph, frameId: string): CdpFrame[] | null {
const byId = frameMap(graph);
const path: CdpFrame[] = [];
const seen = new Set<string>();
let current = byId.get(frameId);
if (!current) return null;
while (current.parentFrameId) {
if (seen.has(current.frameId)) return null;
seen.add(current.frameId);
path.push(current);
const parent = byId.get(current.parentFrameId);
if (!parent) return null;
current = parent;
}
return path;
}
async function targetViewport(cdp: CdpRunner, target: CdpTarget): Promise<Size | null> {
const metrics = await sendToCdpTarget<{
cssLayoutViewport?: { clientWidth?: number; clientHeight?: number };
layoutViewport?: { clientWidth?: number; clientHeight?: number };
}>(cdp, target, "Page.getLayoutMetrics", {});
const viewport = metrics.cssLayoutViewport ?? metrics.layoutViewport ?? {};
const width = viewport.clientWidth ?? 0;
const height = viewport.clientHeight ?? 0;
return width > 0 && height > 0 ? { width, height } : null;
}
async function ownerContentQuad(
cdp: CdpRunner,
parent: CdpFrame,
ownerBackendNodeId: number,
): Promise<Quad | null> {
const result = await sendToCdpTarget<{ model?: { content?: number[] } }>(
cdp,
parent.target,
"DOM.getBoxModel",
{ backendNodeId: ownerBackendNodeId },
);
return parseCdpQuad(result.model?.content);
}
async function sameTargetFrameClips(
cdp: CdpRunner,
byId: Map<string, CdpFrame>,
frame: CdpFrame,
targetRoot: CdpFrame,
): Promise<Polygon[] | null> {
const clips: Polygon[] = [];
let current = frame;
const seen = new Set<string>();
while (current.frameId !== targetRoot.frameId) {
if (seen.has(current.frameId) || !current.parentFrameId) return null;
seen.add(current.frameId);
const parent = byId.get(current.parentFrameId);
if (!parent || current.ownerBackendNodeId === undefined) return null;
const clip = await ownerContentQuad(cdp, parent, current.ownerBackendNodeId);
if (!clip) return null;
clips.push(clip);
current = parent;
}
return clips;
}
export async function resolveFrameProjection(
cdp: CdpRunner,
graph: CdpFrameGraph,
frameId: string,
): Promise<GeometryProjection | null> {
const byId = frameMap(graph);
const frame = byId.get(frameId);
if (!frame) return null;
let targetRoot = targetRootFrame(byId, frame);
if (!targetRoot) return null;
const sourceViewport = await targetViewport(cdp, targetRoot.target);
if (!sourceViewport) return null;
const sourceClips = await sameTargetFrameClips(cdp, byId, frame, targetRoot);
if (!sourceClips) return null;
const edges: ProjectiveEdge[] = [];
while (targetRoot.parentFrameId) {
const parent = byId.get(targetRoot.parentFrameId);
if (!parent || targetRoot.ownerBackendNodeId === undefined) return null;
const destinationQuad = await ownerContentQuad(cdp, parent, targetRoot.ownerBackendNodeId);
if (!destinationQuad) return null;
const source =
edges.length === 0 ? sourceViewport : await targetViewport(cdp, targetRoot.target);
if (!source) return null;
const parentTargetRoot = targetRootFrame(byId, parent);
if (!parentTargetRoot) return null;
const destinationClips = await sameTargetFrameClips(cdp, byId, parent, parentTargetRoot);
if (!destinationClips) return null;
edges.push({ sourceViewport: source, destinationQuad, destinationClips });
targetRoot = parentTargetRoot;
}
const topViewport =
edges.length === 0 ? sourceViewport : await targetViewport(cdp, targetRoot.target);
return topViewport ? { sourceClips, edges, topViewport } : null;
}
async function loadFrameGraph(cdp: CdpRunner, tabId: number): Promise<CdpFrameGraph | null> {
if (!cdp.getFrameGraph) return null;
try {
return await cdp.getFrameGraph(tabId);
} catch (error) {
console.debug("[bsk frame-geometry] frame graph resolution failed", error);
return null;
}
}
async function scrollFrameOwners(
cdp: CdpRunner,
tabId: number,
graph: CdpFrameGraph,
context: GeometryContext,
frameId: string,
): Promise<RpcError | null> {
const byId = frameMap(graph);
const ancestry = frameAncestry(graph, frameId);
const ancestry = await context.ancestry(frameId);
if (!ancestry) return geometryError(`could not resolve frame ancestry for ${frameId}`);
for (const child of [...ancestry].reverse()) {
const parent = child.parentFrameId ? byId.get(child.parentFrameId) : undefined;
const parent = child.parentFrameId ? await context.frame(child.parentFrameId) : undefined;
if (!parent || child.ownerBackendNodeId === undefined) {
return geometryError(`could not resolve frame owner for ${child.frameId}`);
}
@@ -191,17 +61,20 @@ async function scrollFrameOwners(
return null;
}
async function scrollElementWithFrameGraph(
async function scrollElementWithContext(
cdp: CdpRunner,
tabId: number,
target: CdpTarget,
backendNodeId: number,
frameId: string | undefined,
graph: CdpFrameGraph | null,
context: GeometryContext,
): Promise<RpcError | null> {
if (frameId) {
if (!graph) return geometryError(`could not resolve frame graph for ${frameId}`);
const error = await scrollFrameOwners(cdp, tabId, graph, frameId);
const frame = await context.frame(frameId);
if (!frame || cdpTargetKey(frame.target) !== cdpTargetKey(target)) {
return geometryError("node frame does not belong to its target");
}
const error = await scrollFrameOwners(cdp, tabId, context, frameId);
if (error) return error;
} else if (target.sessionId) {
return geometryError("an OOPIF node address requires frameId");
@@ -216,8 +89,15 @@ export async function scrollElementAndFramesIntoView(
backendNodeId: number,
frameId?: string,
): Promise<RpcError | null> {
const graph = frameId ? await loadFrameGraph(cdp, tabId) : null;
return scrollElementWithFrameGraph(cdp, tabId, target, backendNodeId, frameId, graph);
if (target.tabId !== tabId) return geometryError("node target belongs to another tab");
return scrollElementWithContext(
cdp,
tabId,
target,
backendNodeId,
frameId,
new GeometryContext(cdp, tabId),
);
}
function largestRegion(regions: Region): Polygon | null {
@@ -240,23 +120,32 @@ export async function resolveNodeGeometry(
if (address.target.sessionId && !address.frameId) {
return geometryError("an OOPIF node address requires frameId");
}
const graph = address.frameId ? await loadFrameGraph(cdp, tabId) : null;
if (address.target.tabId !== tabId) return geometryError("node target belongs to another tab");
const context = new GeometryContext(cdp, tabId);
const graph = address.frameId ? await context.graph() : null;
if (address.frameId && graph) {
const frame = await context.frame(address.frameId);
if (!frame || cdpTargetKey(frame.target) !== cdpTargetKey(address.target)) {
return geometryError("node frame does not belong to its target");
}
}
if (address.frameId && !graph) {
return geometryError(`could not resolve frame graph for ${address.frameId}`);
}
if (options.scrollIntoView) {
const scrollError = await scrollElementWithFrameGraph(
const scrollError = await scrollElementWithContext(
cdp,
tabId,
address.target,
address.backendNodeId,
address.frameId,
graph,
context,
);
if (scrollError) return scrollError;
}
// Only topology was read above. Begin live measurements after scrolling.
const localRegion = await nodeContentRegion(
cdpRunnerForTarget(cdp, address.target),
tabId,
@@ -267,7 +156,7 @@ export async function resolveNodeGeometry(
let topVisibleRegions: Region;
let targetActionPoint: Point | null = null;
if (address.frameId && graph) {
const projection = await resolveFrameProjection(cdp, graph, address.frameId);
const projection = await context.targetProjection(address.frameId);
if (!projection)
return geometryError(`could not resolve frame geometry for ${address.frameId}`);
topVisibleRegions = projectRegionToViewport(localRegion, projection);
@@ -290,7 +179,7 @@ export async function resolveNodeGeometry(
targetActionPoint = localActionRegion ? polygonCentroid(localActionRegion) : null;
}
} else {
const viewport = await targetViewport(cdp, address.target);
const viewport = await context.viewport(address.target);
if (!viewport) return geometryError("could not resolve top viewport geometry");
topVisibleRegions = localRegion
.map((polygon) =>
@@ -309,7 +198,13 @@ export async function resolveNodeGeometry(
return { code: "permission_denied", message: "element not visible in its target" };
}
targetActionPoint ??= actionPoint;
return { topVisibleRegions, topBounds, actionPoint, targetActionPoint };
return {
topVisibleRegions,
topBounds,
actionPoint,
targetActionPoint,
topViewport: cssViewport(await context.layoutMetrics({ tabId })),
};
} catch (error) {
return geometryError(error instanceof Error ? error.message : String(error));
}
-19
View File
@@ -245,22 +245,3 @@ export function projectRectToViewport(
if (!rect) return null;
return regionBounds(projectRegionToViewport([rectPolygon(rect)], projection));
}
export function childFrameProjection(
parent: GeometryProjection,
ownerRectInParent: { x: number; y: number; w: number; h: number },
): GeometryProjection {
const destinationQuad = rectPolygon(ownerRectInParent);
return {
sourceClips: [],
edges: [
{
sourceViewport: { width: ownerRectInParent.w, height: ownerRectInParent.h },
destinationQuad,
destinationClips: parent.sourceClips,
},
...parent.edges,
],
topViewport: parent.topViewport,
};
}
@@ -0,0 +1,102 @@
import { type CdpTarget, cdpTargetKey } from "@/browser-driver/frame-graph";
import type { GeometryProjection, ViewportRect } from "../geometry";
import { projectRectToViewport } from "../geometry";
export interface CoordinateOwner {
target: CdpTarget;
frameId?: string;
}
export interface FrameViewportRect {
space: "frame-viewport-css";
owner: CoordinateOwner;
rect: ViewportRect;
}
export interface SnapshotProjection {
source: CoordinateOwner;
geometry: GeometryProjection;
}
/** A failed owner read is different from a successfully projected, clipped-out rect. */
export interface UnavailableFrameProjection {
status: "unavailable";
source: CoordinateOwner;
ownerBackendNodeId: number;
}
export type SnapshotProjectionResult =
| { status: "available"; projection: SnapshotProjection }
| UnavailableFrameProjection;
/** Descendants inherit the failed boundary without attempting another owner read. */
export type FrameProjectionIssue =
| UnavailableFrameProjection
| { status: "blocked"; source: CoordinateOwner; cause: UnavailableFrameProjection };
export type FrameProjectionState = SnapshotProjectionResult | FrameProjectionIssue;
/** DOMSnapshot bounds are document-relative CSS pixels, independent of raster DPR. */
export function snapshotViewportRect(
bounds: number[],
owner: CoordinateOwner,
scroll: { x: number; y: number },
): FrameViewportRect | null {
if (bounds.length < 4 || !bounds.slice(0, 4).every(Number.isFinite)) return null;
const [x, y, width, height] = bounds;
if (width <= 0 || height <= 0 || !Number.isFinite(scroll.x) || !Number.isFinite(scroll.y)) {
return null;
}
return {
space: "frame-viewport-css",
owner,
rect: { x: x - scroll.x, y: y - scroll.y, width, height },
};
}
export function projectSnapshotRect(
input: FrameViewportRect,
projection: SnapshotProjection,
): ViewportRect | null {
if (
input.owner.frameId !== projection.source.frameId ||
cdpTargetKey(input.owner.target) !== cdpTargetKey(projection.source.target)
) {
return null;
}
const { x, y, width: w, height: h } = input.rect;
return projectRectToViewport({ x, y, w, h }, projection.geometry);
}
/** CSS viewport metadata; browser zoom is distinct from raster devicePixelRatio. */
export interface CssViewport {
width: number;
height: number;
scrollX: number;
scrollY: number;
cssToDip: number;
}
/** Page.captureScreenshot takes page-relative DIP, not viewport-relative CSS pixels. */
export function screenshotPageRect(
rect: ViewportRect,
viewport: CssViewport,
): { space: "page-dip"; rect: ViewportRect } | null {
const { cssToDip, scrollX, scrollY } = viewport;
if (
![rect.x, rect.y, rect.width, rect.height, cssToDip, scrollX, scrollY].every(Number.isFinite) ||
cssToDip <= 0 ||
rect.width <= 0 ||
rect.height <= 0
)
return null;
return {
space: "page-dip",
rect: {
x: (rect.x + scrollX) * cssToDip,
y: (rect.y + scrollY) * cssToDip,
width: rect.width * cssToDip,
height: rect.height * cssToDip,
},
};
}
@@ -0,0 +1,333 @@
import {
type CdpFrame,
type CdpFrameGraph,
type CdpTarget,
cdpTargetKey,
} from "@/browser-driver/frame-graph";
import {
type GeometryProjection,
type Polygon,
type ProjectiveEdge,
parseCdpQuad,
type Quad,
type Size,
} from "../geometry";
import { type CdpRunner, sendToCdpTarget } from "../shared";
import type { CoordinateOwner, CssViewport, SnapshotProjectionResult } from "./coordinate-types";
import { readSnapshotOwnerSizes } from "./snapshot-owner-sizes";
export interface LayoutMetrics {
cssVisualViewport?: { zoom?: number };
visualViewport?: { zoom?: number };
cssLayoutViewport?: {
clientWidth?: number;
clientHeight?: number;
pageX?: number;
pageY?: number;
};
layoutViewport?: { clientWidth?: number; clientHeight?: number; pageX?: number; pageY?: number };
}
/** The legacy field is a compatibility fallback, never a source of raster DPR. */
export function cssViewport(metrics: LayoutMetrics): CssViewport {
const value = metrics.cssLayoutViewport ?? metrics.layoutViewport;
return {
width: value?.clientWidth ?? 0,
height: value?.clientHeight ?? 0,
scrollX: value?.pageX ?? 0,
scrollY: value?.pageY ?? 0,
cssToDip: metrics.cssVisualViewport?.zoom ?? metrics.visualViewport?.zoom ?? 1,
};
}
/** One read-only measurement phase. Discard after scrolling or any later operation. */
export class GeometryContext {
private readonly metrics = new Map<string, Promise<LayoutMetrics>>();
private readonly owners = new Map<string, Promise<Quad | null>>();
private readonly projections = new Map<string, Promise<GeometryProjection | null>>();
private readonly snapshotOwners = new Map<string, Promise<{ quad: Quad; size: Size } | null>>();
private readonly sizeBatches = new Map<string, () => Promise<Map<number, Size>>>();
private active = 0;
private readonly waiting: Array<() => void> = [];
private graphPromise?: Promise<CdpFrameGraph | null>;
private framesPromise?: Promise<Map<string, CdpFrame>>;
constructor(
private readonly cdp: CdpRunner,
private readonly tabId: number,
graph?: CdpFrameGraph,
private readonly signal?: AbortSignal,
) {
if (graph) this.graphPromise = Promise.resolve(graph);
}
private async request<T>(
target: CdpTarget,
method: string,
params: object,
cleanup = false,
): Promise<T> {
if (!cleanup && this.signal?.aborted) throw new DOMException("geometry aborted", "AbortError");
if (this.active >= 4) await new Promise<void>((resolve) => this.waiting.push(resolve));
else this.active++;
try {
if (!cleanup && this.signal?.aborted)
throw new DOMException("geometry aborted", "AbortError");
return await sendToCdpTarget<T>(this.cdp, target, method, params);
} finally {
const next = this.waiting.shift();
if (next) next();
else this.active--;
}
}
graph(): Promise<CdpFrameGraph | null> {
this.graphPromise ??=
this.cdp.getFrameGraph?.(this.tabId).catch(() => null) ?? Promise.resolve(null);
return this.graphPromise;
}
private frames(): Promise<Map<string, CdpFrame>> {
this.framesPromise ??= this.graph().then(
(graph) => new Map(graph?.frames.map((frame) => [frame.frameId, frame]) ?? []),
);
return this.framesPromise;
}
async frame(frameId: string): Promise<CdpFrame | undefined> {
return (await this.frames()).get(frameId);
}
/** Topology only: safe to resolve before the caller scrolls frame owners. */
async ancestry(frameId: string): Promise<CdpFrame[] | null> {
const frames = await this.frames();
const path: CdpFrame[] = [];
const seen = new Set<string>();
let current = frames.get(frameId);
if (!current) return null;
while (current.parentFrameId) {
if (seen.has(current.frameId)) return null;
seen.add(current.frameId);
path.push(current);
const parent = frames.get(current.parentFrameId);
if (!parent) return null;
current = parent;
}
return path;
}
layoutMetrics(target: CdpTarget): Promise<LayoutMetrics> {
const key = cdpTargetKey(target);
let promise = this.metrics.get(key);
if (!promise) {
promise = this.request<LayoutMetrics>(target, "Page.getLayoutMetrics", {});
this.metrics.set(key, promise);
}
return promise;
}
async viewport(target: CdpTarget): Promise<Size | null> {
const { width, height } = cssViewport(await this.layoutMetrics(target));
return Number.isFinite(width) && Number.isFinite(height) && width > 0 && height > 0
? { width, height }
: null;
}
ownerContent(target: CdpTarget, backendNodeId: number): Promise<Quad | null> {
const key = `${cdpTargetKey(target)}:${backendNodeId}`;
let promise = this.owners.get(key);
if (!promise) {
promise = this.request<{ model?: { content?: number[] } }>(target, "DOM.getBoxModel", {
backendNodeId,
}).then((reply) => parseCdpQuad(reply.model?.content));
this.owners.set(key, promise);
}
return promise;
}
/** Same-target owner quads are already target-relative, including nested owners. */
async snapshotProjection(
source: CoordinateOwner,
ownerBackendNodeId: number,
ancestorClips: Polygon[],
viewport: Size,
): Promise<SnapshotProjectionResult> {
const key = `${cdpTargetKey(source.target)}:${ownerBackendNodeId}`;
let promise = this.snapshotOwners.get(key);
if (!promise) {
promise = this.snapshotOwner(source.target, ownerBackendNodeId);
this.snapshotOwners.set(key, promise);
}
let owner: { quad: Quad; size: Size } | null;
try {
owner = await promise;
} catch (error) {
if (error && typeof error === "object" && "name" in error && error.name === "AbortError")
throw error;
console.debug("[bsk geometry] frame owner unavailable", error);
owner = null;
}
return owner
? {
status: "available",
projection: {
source,
geometry: {
sourceClips: [],
edges: [
{
sourceViewport: owner.size,
destinationQuad: owner.quad,
destinationClips: ancestorClips,
},
],
topViewport: viewport,
},
},
}
: { status: "unavailable", source, ownerBackendNodeId };
}
/** Register one target's snapshot owners; the batch starts only when a
* projection actually needs a size. Single owners keep the cheaper old path. */
registerSnapshotOwners(target: CdpTarget, owners: ReadonlySet<number>): void {
const key = cdpTargetKey(target);
if (owners.size < 2 || this.sizeBatches.has(key)) return;
let pending: Promise<Map<number, Size>> | undefined;
this.sizeBatches.set(key, () => {
pending ??= readSnapshotOwnerSizes(
(method, params, cleanup) => this.request(target, method, params, cleanup),
owners,
).catch((error) => {
if (error && typeof error === "object" && "name" in error && error.name === "AbortError")
throw error;
return new Map<number, Size>();
});
return pending;
});
}
private async snapshotOwner(
target: CdpTarget,
backendNodeId: number,
): Promise<{ quad: Quad; size: Size } | null> {
const quad = await this.ownerContent(target, backendNodeId);
if (!quad) return null;
const batchSize = (await this.sizeBatches.get(cdpTargetKey(target))?.())?.get(backendNodeId);
if (this.signal?.aborted) throw new DOMException("geometry aborted", "AbortError");
if (batchSize) return { quad, size: batchSize };
const resolved = await this.request<{ object?: { objectId?: string } }>(
target,
"DOM.resolveNode",
{ backendNodeId },
);
const objectId = resolved.object?.objectId;
if (!objectId) return null;
try {
const reply = await this.request<{ result?: { value?: Size }; exceptionDetails?: unknown }>(
target,
"Runtime.callFunctionOn",
{
objectId,
functionDeclaration: `function() {
if (!this.isConnected) return null;
const style = getComputedStyle(this);
return {
width: this.clientWidth - parseFloat(style.paddingLeft) - parseFloat(style.paddingRight),
height: this.clientHeight - parseFloat(style.paddingTop) - parseFloat(style.paddingBottom)
};
}`,
returnByValue: true,
},
);
const size = reply.result?.value;
return !reply.exceptionDetails &&
size &&
Number.isFinite(size.width) &&
Number.isFinite(size.height) &&
size.width > 0 &&
size.height > 0
? { quad, size }
: null;
} finally {
// Cleanup must still run if cancellation arrived after resolving the object.
await this.request(target, "Runtime.releaseObject", { objectId }, true).catch(() => {});
}
}
private targetRoot(frames: Map<string, CdpFrame>, frame: CdpFrame): CdpFrame | null {
const seen = new Set<string>();
let current = frame;
while (current.parentFrameId) {
if (seen.has(current.frameId)) return null;
seen.add(current.frameId);
const parent = frames.get(current.parentFrameId);
if (!parent) return null;
if (cdpTargetKey(parent.target) !== cdpTargetKey(current.target)) break;
current = parent;
}
return current;
}
private async clips(
frames: Map<string, CdpFrame>,
frame: CdpFrame,
root: CdpFrame,
): Promise<Polygon[] | null> {
const clips: Polygon[] = [];
let current = frame;
const seen = new Set<string>();
while (current.frameId !== root.frameId) {
if (seen.has(current.frameId) || !current.parentFrameId) return null;
seen.add(current.frameId);
const parent = frames.get(current.parentFrameId);
if (!parent || current.ownerBackendNodeId === undefined) return null;
const quad = await this.ownerContent(parent.target, current.ownerBackendNodeId);
if (!quad) return null;
clips.push(quad);
current = parent;
}
return clips;
}
/** Input is already in the frame's CDP target viewport, not its local viewport. */
targetProjection(frameId: string): Promise<GeometryProjection | null> {
let promise = this.projections.get(frameId);
if (!promise) {
promise = this.buildTargetProjection(frameId);
this.projections.set(frameId, promise);
}
return promise;
}
private async buildTargetProjection(frameId: string): Promise<GeometryProjection | null> {
const frames = await this.frames();
const frame = frames.get(frameId);
if (!frame) return null;
let root = this.targetRoot(frames, frame);
if (!root) return null;
const sourceViewport = await this.viewport(root.target);
if (!sourceViewport) return null;
const sourceClips = await this.clips(frames, frame, root);
if (!sourceClips) return null;
const edges: ProjectiveEdge[] = [];
const seen = new Set<string>();
while (root.parentFrameId) {
if (seen.has(root.frameId)) return null;
seen.add(root.frameId);
const parent = frames.get(root.parentFrameId);
if (!parent || root.ownerBackendNodeId === undefined) return null;
const destinationQuad = await this.ownerContent(parent.target, root.ownerBackendNodeId);
const source = await this.viewport(root.target);
const parentRoot = this.targetRoot(frames, parent);
if (!destinationQuad || !source || !parentRoot) return null;
const destinationClips = await this.clips(frames, parent, parentRoot);
if (!destinationClips) return null;
edges.push({ sourceViewport: source, destinationQuad, destinationClips });
root = parentRoot;
}
const topViewport = await this.viewport(root.target);
return topViewport ? { sourceClips, edges, topViewport } : null;
}
}
@@ -0,0 +1,74 @@
import type { Size } from "../geometry";
interface SerializedValue {
type: string;
value?: unknown;
}
type Send = <T>(method: string, params: object, cleanup?: boolean) => Promise<T>;
/** Batch only accessible frame owners. Missing/shadow/cross-origin owners keep
* the existing node-scoped read; no page-wide style columns are requested. */
export async function readSnapshotOwnerSizes(
send: Send,
owners: ReadonlySet<number>,
): Promise<Map<number, Size>> {
const sizes = new Map<number, Size>();
const objectGroup = `bsk-frame-sizes-${crypto.randomUUID()}`;
try {
const reply = await send<{ result?: { deepSerializedValue?: SerializedValue } }>(
"Runtime.evaluate",
{
expression: `(() => {
const result = [];
const documents = [document];
for (let i = 0; i < documents.length && result.length < ${owners.size}; i++) {
for (const owner of documents[i].querySelectorAll('iframe,frame')) {
if (result.length >= ${owners.size}) break;
if (!owner.isConnected) continue;
const style = getComputedStyle(owner);
result.push([owner, JSON.stringify({
width: owner.clientWidth - parseFloat(style.paddingLeft) - parseFloat(style.paddingRight),
height: owner.clientHeight - parseFloat(style.paddingTop) - parseFloat(style.paddingBottom)
})]);
try { if (owner.contentDocument) documents.push(owner.contentDocument); } catch {}
}
}
return result;
})()`,
objectGroup,
serializationOptions: {
serialization: "deep",
maxDepth: 3,
additionalParameters: { maxNodeDepth: 0, includeShadowTree: "none" },
},
},
);
const result = reply.result?.deepSerializedValue;
if (result?.type !== "array" || !Array.isArray(result.value)) return sizes;
for (const entry of result.value as SerializedValue[]) {
if (entry.type !== "array" || !Array.isArray(entry.value)) continue;
const [node, data] = entry.value as SerializedValue[];
if (node?.type !== "node" || data?.type !== "string" || typeof data.value !== "string")
continue;
const id = (node.value as { backendNodeId?: number } | undefined)?.backendNodeId;
if (id === undefined || !owners.has(id)) continue;
try {
const size = JSON.parse(data.value) as Size;
if (
size &&
Number.isFinite(size.width) &&
Number.isFinite(size.height) &&
size.width > 0 &&
size.height > 0
)
sizes.set(id, size);
} catch {
/* An invalid entry uses the existing individual read. */
}
}
} finally {
await send("Runtime.releaseObjectGroup", { objectGroup }, true).catch(() => {});
}
return sizes;
}
+33 -20
View File
@@ -34,6 +34,8 @@ import type {
import { attachDialogs, markDialogCursor } from "./dialogs";
import { rpcError } from "./errors";
import { resolveNodeGeometry } from "./frame-geometry";
import { screenshotPageRect } from "./geometry/coordinate-types";
import { cssViewport, GeometryContext } from "./geometry/frame-context";
import {
type ChromeTabsApi,
enforceToolTargetScope,
@@ -197,15 +199,14 @@ async function captureElementScreenshot(
if (isRpcError(geometry)) return geometry;
if (signal?.aborted) return cancelled("screenshot");
const rect = geometry.topBounds;
const clip = screenshotPageRect(rect, geometry.topViewport);
if (!clip) return { code: "cdp_failed", message: "invalid screenshot coordinate space" };
try {
const shot = await cdp.send<{ data?: string }>(tabId, "Page.captureScreenshot", {
format: "png",
clip: {
x: rect.x,
y: rect.y,
width: rect.width,
height: rect.height,
...clip.rect,
scale: 1,
},
});
@@ -675,6 +676,7 @@ function legacyFrameDocuments(
...(pageUrl ? { url: pageUrl } : {}),
axNodes: [],
domNodes: captured.nodes.map((node) => ({ ...node, frameId: node.frameId ?? rootFrameId })),
excludedBackendNodeIds: captured.frameExcludedBackendNodeIds?.get(rootFrameId),
},
];
const pending = [...captured.iframeNodes.entries()];
@@ -698,6 +700,7 @@ function legacyFrameDocuments(
target: parent.target,
axNodes: [],
domNodes: domNodes.map((node) => ({ ...node, frameId: node.frameId ?? frameId })),
excludedBackendNodeIds: captured.frameExcludedBackendNodeIds?.get(frameId),
});
pending.splice(index, 1);
progress = true;
@@ -984,26 +987,19 @@ function emptyCapturedViewModel(viewport = { width: 0, height: 0 }): CapturedVie
return { viewport, nodes: [], iframeNodes: new Map(), excludedBackendNodeIds: new Set() };
}
interface LayoutMetricsViewportReply {
cssLayoutViewport?: { clientWidth?: number; clientHeight?: number };
layoutViewport?: { clientWidth?: number; clientHeight?: number };
}
async function fallbackCapturedViewModel(
cdp: CdpRunner,
tabId: number,
geometry: GeometryContext,
signal?: AbortSignal,
): Promise<CapturedViewModel> {
throwIfAborted(signal, "observation");
let viewport = { width: 0, height: 0 };
try {
const metrics = await cdp.send<LayoutMetricsViewportReply>(tabId, "Page.getLayoutMetrics", {});
const metrics = await geometry.layoutMetrics({ tabId });
throwIfAborted(signal, "observation");
const source = metrics.cssLayoutViewport ?? metrics.layoutViewport ?? {};
viewport = {
width: source.clientWidth ?? 0,
height: source.clientHeight ?? 0,
};
const source = cssViewport(metrics);
viewport = { width: source.width, height: source.height };
} catch (error) {
if (isAbortError(error)) throw error;
}
@@ -1016,12 +1012,13 @@ async function captureForVom(
cdp: CdpRunner,
tabId: number,
options: CaptureVomObservationOptions,
geometry: GeometryContext,
): Promise<CapturedViewModel> {
try {
return await captureViewModel(cdp, tabId, { signal: options.signal });
return await captureViewModel(cdp, tabId, { signal: options.signal, geometry });
} catch (error) {
if (isAbortError(error)) throw error;
return fallbackCapturedViewModel(cdp, tabId, options.signal);
return fallbackCapturedViewModel(cdp, tabId, geometry, options.signal);
}
}
@@ -1096,9 +1093,16 @@ export async function captureVomObservation(
throwIfAborted(options.signal, "observation");
await cdp.ensureAttachedToUrl?.(tabId, url);
throwIfAborted(options.signal, "observation");
const captured = await captureForVom(cdp, tabId, options);
const geometry = new GeometryContext(cdp, tabId, undefined, options.signal);
const captured = await captureForVom(cdp, tabId, options, geometry);
throwIfAborted(options.signal, "observation");
const documents = await captureFrameData<CdpAxNode>(cdp, tabId, captured, options.signal);
const documents = await captureFrameData<CdpAxNode>(
cdp,
tabId,
captured,
options.signal,
geometry,
);
throwIfAborted(options.signal, "observation");
const normalizedDocuments =
documents.length === 1 && captured.iframeNodes.size > 0
@@ -1131,12 +1135,21 @@ export async function captureVomObservation(
captured,
hoverProbes.surfaceProbes,
);
// Reserve space using the renderer's character-based token estimate. Like VOM
// headers, this integrity notice remains visible even under a tiny token budget.
const geometryNotice = captured.frameGeometryIssues?.length
? "@warning iframe geometry incomplete: some frame content has no top-level coordinates.\n"
: "";
const rendered = renderVom(decoratedScene, {
maxDepth: options.maxDepth,
maxTokens: options.maxTokens,
maxTokens:
!geometryNotice || options.maxTokens === undefined
? options.maxTokens
: Math.max(0, options.maxTokens - Math.ceil(geometryNotice.length / 4)),
redactValues: options.redactValues,
activeRegionPolicy: options.activeRegionPolicy,
});
if (geometryNotice) rendered.text += `\n${geometryNotice.trimEnd()}`;
throwIfAborted(options.signal, "observation");
return projectRecordSafeObservation({
rootFrameId: captured.rootFrameId ?? normalizedDocuments[0]?.frameId ?? "root",
@@ -1,5 +1,6 @@
import { describe, expect, it, vi } from "vitest";
import { OVERLAY_HOST_MARKER_ATTR, OVERLAY_HOST_NAME } from "../../../lib/overlay-bridge";
import type { CdpRunner } from "../../shared";
import { captureViewModel, collectOverlayExcludedBackendIds, probeHoverSurfaces } from "../capture";
// Minimal but format-accurate captureSnapshot reply: a body with one
@@ -527,6 +528,7 @@ describe("captureViewModel", () => {
strings: S,
documents: [
{
frameId: "main",
nodes: {
parentIndex: [-1, 0, 1, 0, 3, 4],
nodeName: [i("html"), i("body"), i("div"), i(OVERLAY_HOST_NAME), i("div"), i("button")],
@@ -557,8 +559,12 @@ describe("captureViewModel", () => {
],
};
const { excludedBackendNodeIds } = await captureViewModel(makeCdp(snapshot), 4);
const { excludedBackendNodeIds, frameExcludedBackendNodeIds } = await captureViewModel(
makeCdp(snapshot),
4,
);
expect(excludedBackendNodeIds).toEqual(new Set([13, 14, 15]));
expect(frameExcludedBackendNodeIds?.get("main")).toEqual(excludedBackendNodeIds);
});
it("excludes overlay host matched by tag name only", async () => {
@@ -754,7 +760,7 @@ describe("captureViewModel", () => {
expect(div?.rect).toMatchObject({ y: 0, h: 600 });
});
it("normalizes device-pixel bounds by devicePixelRatio", async () => {
it("keeps CSS snapshot bounds independent of legacy metrics ratio", async () => {
const S = ["html", "body", "div", "position", "fixed", "static", "pointer-events", "auto"];
const i = (s: string) => S.indexOf(s);
const snapshot = {
@@ -802,6 +808,12 @@ describe("captureViewModel", () => {
w: 1000,
h: 800,
});
expect(nodes.find((n) => n.backendNodeId === 12)?.localRect).toEqual({
x: 0,
y: 0,
w: 2000,
h: 1600,
});
});
it("extracts textContent from #text child nodes via nodeValue", async () => {
@@ -950,6 +962,12 @@ describe("captureViewModel", () => {
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
};
}
if (method === "DOM.getBoxModel")
return { model: { content: [100, 300, 900, 300, 900, 700, 100, 700] } };
if (method === "DOM.resolveNode") return { object: { objectId: "owner" } };
if (method === "Runtime.callFunctionOn")
return { result: { value: { width: 800, height: 400 } } };
if (method === "Runtime.releaseObject") return {};
throw new Error(method);
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
@@ -979,7 +997,7 @@ describe("captureViewModel", () => {
expect(frameParentIds?.get("child-frame")).toBe("main-frame");
});
it("captures iframe documents without requiring owner-frame geometry", async () => {
it("projects iframe documents independently of owner snapshot geometry", async () => {
const S = [
"html",
"body",
@@ -1040,6 +1058,12 @@ describe("captureViewModel", () => {
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
};
}
if (method === "DOM.getBoxModel")
return { model: { content: [100, 300, 900, 300, 900, 700, 100, 700] } };
if (method === "DOM.resolveNode") return { object: { objectId: "owner" } };
if (method === "Runtime.callFunctionOn")
return { result: { value: { width: 800, height: 400 } } };
if (method === "Runtime.releaseObject") return {};
throw new Error(method);
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
@@ -1048,7 +1072,7 @@ describe("captureViewModel", () => {
const input = iframeNodes.get(13)?.find((n) => n.backendNodeId === 101);
expect(input?.localRect).toEqual({ x: 20, y: 20, w: 120, h: 60 });
expect(input?.rect).toBeNull();
expect(input?.rect).toEqual({ x: 120, y: 320, w: 120, h: 60 });
});
it("recursively normalizes nested iframe sub-documents", async () => {
@@ -1127,16 +1151,43 @@ describe("captureViewModel", () => {
],
};
const cdp = {
send: vi.fn(async (_t: number, method: string) => {
if (method === "DOMSnapshot.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
if (method === "Page.getLayoutMetrics") {
return {
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
};
}
throw new Error(method);
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
send: vi.fn(
async (
_t: number,
method: string,
params?: { backendNodeId?: number; objectId?: string },
) => {
if (method === "DOMSnapshot.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
if (method === "Page.getLayoutMetrics") {
return {
cssLayoutViewport: { clientWidth: 1000, clientHeight: 800, pageX: 0, pageY: 0 },
};
}
if (method === "DOM.getBoxModel")
return {
model: {
content:
params?.backendNodeId === 13
? [10, 20, 310, 20, 310, 220, 10, 220]
: [15, 26, 115, 26, 115, 106, 15, 106],
},
};
if (method === "DOM.resolveNode")
return { object: { objectId: String(params?.backendNodeId) } };
if (method === "Runtime.callFunctionOn")
return {
result: {
value:
params?.objectId === "13"
? { width: 300, height: 200 }
: { width: 100, height: 80 },
},
};
if (method === "Runtime.releaseObject") return {};
throw new Error(method);
},
) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const { iframeNodes } = await captureViewModel(cdp, 4);
@@ -1150,7 +1201,7 @@ describe("captureViewModel", () => {
expect(input?.rect).toEqual({ x: 16, y: 28, w: 40, h: 20 });
});
it("normalizes bounds then subtracts CSS scroll at dpr>1", async () => {
it("subtracts CSS scroll once without dividing snapshot bounds by a metrics ratio", async () => {
const S = ["html", "body", "div", "position", "fixed", "static", "pointer-events", "auto"];
const i = (s: string) => S.indexOf(s);
const snapshot = {
@@ -1192,7 +1243,7 @@ describe("captureViewModel", () => {
}) as unknown as <T>(tabId: number, method: string, params?: object) => Promise<T>,
};
const { nodes } = await captureViewModel(cdp, 4);
expect(nodes.find((n) => n.backendNodeId === 12)?.rect?.y).toBe(400 / 2 - 100);
expect(nodes.find((n) => n.backendNodeId === 12)?.rect?.y).toBe(400 - 100);
});
it("collectOverlayExcludedBackendIds walks the pierced overlay host subtree", async () => {
@@ -1217,3 +1268,194 @@ describe("captureViewModel", () => {
expect(excluded).toEqual(new Set([200, 201, 202]));
});
});
// Six sibling frames and one nested frame exercise scheduling through the real capture entry.
function siblingCaptureFixture(
beforeReply: (method: string, params: Record<string, unknown>) => Promise<void> = async () => {},
) {
const document = (id: number, owners: number[], childIndexes: number[]) => ({
frameId: `frame-${id}`,
nodes: {
parentIndex: [-1, ...owners.map(() => 0)],
nodeName: [0, ...owners.map(() => 1)],
backendNodeId: [1000 + id, ...owners],
attributes: [[], ...owners.map(() => [])],
contentDocumentIndex: { index: owners.map((_, i) => i + 1), value: childIndexes },
},
layout: {
nodeIndex: [0, ...owners.map((_, i) => i + 1)],
bounds: [[0, 0, 200, 100], ...owners.map(() => [0, 0, 200, 100])],
},
});
const snapshot = {
strings: ["body", "iframe"],
documents: [
document(0, [100, 101, 102, 103, 104, 105], [1, 2, 3, 4, 5, 6]),
document(1, [200], [7]),
...Array.from({ length: 6 }, (_, i) => document(i + 2, [], [])),
],
};
let active = 0;
let peak = 0;
const send = vi.fn(async (_tabId: number, method: string, params: object = {}) => {
const args = params as Record<string, unknown>;
active++;
peak = Math.max(peak, active);
try {
await beforeReply(method, args);
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
if (method === "Page.getLayoutMetrics")
return { cssLayoutViewport: { clientWidth: 1000, clientHeight: 800 } };
if (method === "DOM.getBoxModel")
return { model: { content: [0, 0, 200, 0, 200, 100, 0, 100] } };
if (method === "DOM.resolveNode") return { object: { objectId: String(args.backendNodeId) } };
if (method === "Runtime.callFunctionOn")
return { result: { value: { width: 200, height: 100 } } };
return {};
} finally {
active--;
}
});
return {
cdp: { send: send as CdpRunner["send"] },
send,
peak: () => peak,
active: () => active,
measured: () =>
send.mock.calls
.filter(([, method]) => method === "DOM.getBoxModel")
.map(([, , params]) => (params as { backendNodeId: number }).backendNodeId),
};
}
describe("sibling frame measurement scheduling", () => {
it("batches same-target owner sizes without changing projected results", async () => {
const fixture = siblingCaptureFixture();
const original = fixture.cdp.send;
const methods: string[] = [];
fixture.cdp.send = async (tabId, method, params) => {
methods.push(method);
if (method === "Runtime.evaluate")
return {
result: {
deepSerializedValue: {
type: "array",
value: [100, 101, 102, 103, 104, 105, 200].map((backendNodeId) => ({
type: "array",
value: [
{ type: "node", value: { backendNodeId } },
{ type: "string", value: JSON.stringify({ width: 200, height: 100 }) },
],
})),
},
},
} as never;
return original(tabId, method, params);
};
const captured = await captureViewModel(fixture.cdp, 4);
expect(captured.frameGeometryIssues).toEqual([]);
expect([...captured.iframeNodes.keys()]).toEqual([100, 200, 101, 102, 103, 104, 105]);
expect(captured.iframeNodes.get(200)?.[0].rect).toEqual({ x: 0, y: 0, w: 200, h: 100 });
expect(methods.filter((method) => method === "DOM.getBoxModel")).toHaveLength(7);
expect(methods.filter((method) => method === "Runtime.evaluate")).toHaveLength(1);
expect(methods.filter((method) => method === "Runtime.releaseObjectGroup")).toHaveLength(1);
expect(methods).not.toContain("DOM.resolveNode");
expect(methods).not.toContain("Runtime.callFunctionOn");
});
it("bounds concurrent reads, fills free slots and preserves depth-first output despite reordered replies", async () => {
const pending = new Map<number, () => void>();
const fixture = siblingCaptureFixture(async (method, params) => {
if (method === "DOM.getBoxModel" && Number(params.backendNodeId) < 200)
await new Promise<void>((resolve) => pending.set(Number(params.backendNodeId), resolve));
});
const capture = captureViewModel(fixture.cdp, 4);
await vi.waitFor(() => expect(pending.size).toBe(4));
expect(fixture.measured()).toEqual([100, 101, 102, 103]);
pending.get(103)!();
await vi.waitFor(() => expect(pending.has(104)).toBe(true));
pending.get(104)!();
await vi.waitFor(() => expect(pending.has(105)).toBe(true));
expect(fixture.measured()).not.toContain(200);
for (const id of [105, 102, 101, 100]) pending.get(id)!();
const captured = await capture;
expect(captured.frameGeometryIssues).toEqual([]);
expect(fixture.peak()).toBe(4);
expect(fixture.active()).toBe(0);
expect(fixture.measured()).toEqual([100, 101, 102, 103, 104, 105, 200]);
expect([...captured.iframeNodes.keys()]).toEqual([100, 200, 101, 102, 103, 104, 105]);
expect(captured.iframeNodes.get(200)?.[0].rect).toEqual({ x: 0, y: 0, w: 200, h: 100 });
for (const method of [
"DOM.getBoxModel",
"DOM.resolveNode",
"Runtime.callFunctionOn",
"Runtime.releaseObject",
])
expect(fixture.send.mock.calls.filter(([, name]) => name === method)).toHaveLength(7);
});
it("does not measure descendants of a failed owner and retains sibling geometry and local nodes", async () => {
const fixture = siblingCaptureFixture(async (method, params) => {
if (method === "DOM.resolveNode" && params.backendNodeId === 100)
throw new Error("owner replaced");
});
const captured = await captureViewModel(fixture.cdp, 4);
expect(captured.frameGeometryIssues).toEqual([
{
status: "unavailable",
source: { target: { tabId: 4 }, frameId: "frame-1" },
ownerBackendNodeId: 100,
},
{
status: "blocked",
source: { target: { tabId: 4 }, frameId: "frame-7" },
cause: captured.frameGeometryIssues?.[0],
},
]);
expect(fixture.measured()).not.toContain(200);
expect(captured.iframeNodes.get(200)?.[0]).toMatchObject({
tag: "body",
rect: null,
localRect: { x: 0, y: 0, w: 200, h: 100 },
});
expect(captured.iframeNodes.get(101)?.[0].rect).toEqual({ x: 0, y: 0, w: 200, h: 100 });
expect([...captured.iframeNodes.keys()]).toEqual([100, 200, 101, 102, 103, 104, 105]);
});
it("stops scheduling on cancellation and waits for resolved objects to be released", async () => {
const controller = new AbortController();
const resolutions = new Map<string, () => void>();
const releases = new Map<string, () => void>();
const fixture = siblingCaptureFixture(async (method, params) => {
if (method === "DOM.resolveNode")
await new Promise<void>((resolve) =>
resolutions.set(String(params.backendNodeId), resolve),
);
if (method === "Runtime.releaseObject")
await new Promise<void>((resolve) => releases.set(String(params.objectId), resolve));
});
let settled = false;
const capture = captureViewModel(fixture.cdp, 4, { signal: controller.signal });
const rejected = expect(capture).rejects.toMatchObject({ name: "AbortError" });
void capture.then(
() => {
settled = true;
},
() => {
settled = true;
},
);
await vi.waitFor(() => expect(resolutions.size).toBe(4));
controller.abort();
for (const resolve of resolutions.values()) resolve();
await vi.waitFor(() => expect(releases.size).toBe(4));
expect(settled).toBe(false);
expect(fixture.measured()).toEqual([100, 101, 102, 103]);
for (const release of releases.values()) release();
await rejected;
expect(fixture.active()).toBe(0);
expect(fixture.send.mock.calls.some(([, method]) => method === "Runtime.callFunctionOn")).toBe(
false,
);
});
});
@@ -0,0 +1,127 @@
import { describe, expect, it, vi } from "vitest";
import { OVERLAY_HOST_MARKER_ATTR } from "@/lib/overlay-bridge";
import { createCaptureCheckpoint } from "../capture-abort";
import { buildDocumentIndex, type DecodedNode } from "../facts";
import { decodeDocument, REQUESTED_STYLES } from "../snapshot";
function node(id: number, parent: number | null): DecodedNode {
return {
backendNodeId: id,
parentBackendNodeId: parent,
tag: "div",
attrs: {},
paintOrder: 0,
position: "static",
pointerEvents: "auto",
};
}
describe("document facts", () => {
it.each([
1_000, 10_000, 100_000,
])("indexes deep and wide inputs of %i without copying ancestors", async (count) => {
for (const wide of [false, true]) {
let reads = 0;
const input = Array.from({ length: count }, (_, i) => {
const item = node(i, i ? (wide ? 0 : i - 1) : null);
if (i === 0) item.attrs[OVERLAY_HOST_MARKER_ATTR] = "";
Object.defineProperty(item, "parentBackendNodeId", {
get: () => {
reads++;
return i ? (wide ? 0 : i - 1) : null;
},
});
return item;
}).reverse(); // parent need not precede child
const index = await buildDocumentIndex(input);
expect(index.nodes.size).toBe(count);
expect(index.excludedBackendNodeIds.size).toBe(count);
expect(reads).toBeLessThanOrEqual(count * 8);
expect(index.nodes.get(count - 1)).toBe(input[0]);
}
});
it("handles cycles and orphans and propagates overlay through shadow roots", async () => {
const host = { ...node(1, null), attrs: { [OVERLAY_HOST_MARKER_ATTR]: "" } };
const input = [
node(3, 2),
{ ...node(2, 1), tag: "#document-fragment" },
host,
node(4, 99),
node(5, 6),
node(6, 5),
node(7, 6),
];
const index = await buildDocumentIndex(input);
expect([...index.excludedBackendNodeIds].sort()).toEqual([1, 2, 3]);
expect(index.nodes.size).toBe(input.length);
});
it("does not propagate a descendant overlay backwards into a cycle", async () => {
const overlay = { ...node(3, 1), attrs: { [OVERLAY_HOST_MARKER_ATTR]: "" } };
const index = await buildDocumentIndex([overlay, node(1, 2), node(2, 1)]);
expect([...index.excludedBackendNodeIds]).toEqual([3]);
});
it("decodes current observation bounds, styles and attributes without projecting coordinates", async () => {
const strings = ["div", "aria-hidden", "true", "inert", "", "visible", "0", "static", "auto"];
const styles = REQUESTED_STYLES.map((style) =>
style === "visibility" ? 5 : style === "opacity" ? 6 : style === "position" ? 7 : 8,
);
const { nodes } = await decodeDocument(
{
nodes: { backendNodeId: [1], parentIndex: [-1], nodeName: [0], attributes: [[1, 2, 3, 4]] },
layout: { nodeIndex: [0], bounds: [[10, 20, 120, 40]], styles: [styles] },
},
strings,
);
expect(nodes[0].attrs).toEqual({ "aria-hidden": "true", inert: "" });
expect(nodes[0].layout).toEqual({
boundsSpace: "snapshot-document-css",
bounds: [10, 20, 120, 40],
styles: {
position: "static",
"pointer-events": "auto",
cursor: "auto",
visibility: "visible",
opacity: "0",
},
});
expect(nodes[0]).not.toHaveProperty("rect");
expect(nodes[0]).not.toHaveProperty("excluded");
});
it("keeps short blocks synchronous and checks cancellation after yielding", async () => {
const clock = vi.spyOn(performance, "now").mockReturnValue(0);
try {
const controller = new AbortController();
const checkpoint = createCaptureCheckpoint(controller.signal);
for (let i = 0; i < 20; i++) expect(checkpoint()).toBeUndefined();
clock.mockReturnValue(9);
const pending = checkpoint();
expect(pending).toBeInstanceOf(Promise);
controller.abort();
await expect(pending).rejects.toMatchObject({ name: "AbortError" });
} finally {
clock.mockRestore();
}
});
it("checks cancellation at bounded indexing blocks", async () => {
const controller = new AbortController();
const input = Array.from({ length: 100_000 }, (_, i) => node(i, i ? i - 1 : null));
let reads = 0;
for (const item of input)
Object.defineProperty(item, "attrs", {
get: () => {
reads++;
if (reads === 100) controller.abort();
return {};
},
});
await expect(buildDocumentIndex(input, controller.signal)).rejects.toMatchObject({
name: "AbortError",
});
expect(reads).toBeLessThanOrEqual(356);
});
});
@@ -1,6 +1,7 @@
import { describe, expect, it, vi } from "vitest";
import { type CdpRunner, cdpRunnerForTarget } from "../../shared";
import { captureViewModel } from "../capture";
import { enrichFormControlStates } from "../form-capture";
import { decodeDocument } from "../snapshot";
interface Control {
id: number;
@@ -77,21 +78,32 @@ function reply(entries: Array<[number, unknown]>) {
};
}
function fakeCdp(groups: Control[][], evaluate: (params: Record<string, unknown>) => unknown) {
async function fakeCdp(
groups: Control[][],
evaluate: (params: Record<string, unknown>) => unknown,
) {
const snap = snapshot(groups);
const send = vi.fn(async (_tabId: number, method: string, params?: object) => {
if (method === "DOMSnapshot.captureSnapshot") return snap;
if (method === "Runtime.evaluate") return evaluate(params as Record<string, unknown>);
return {};
});
return { send, cdp: { send: send as CdpRunner["send"] } };
const nodes = await decodeControls(snap);
return { send, cdp: { send: send as CdpRunner["send"] }, nodes };
}
async function decodeControls(snap: ReturnType<typeof snapshot>) {
return Promise.all(
snap.documents.map(async (doc) =>
(await decodeDocument(doc, snap.strings)).nodes.map((node) => ({ ...node, rect: null })),
),
);
}
describe("form state identity", () => {
it("matches reordered controls by identity and preserves controls missing from the batch", async () => {
// The snapshot includes a shadow input. The runtime query skips it,
// encounters a new input, and sees the remaining inputs in a new order.
const { cdp } = fakeCdp(
const { cdp, nodes } = await fakeCdp(
[
[
{ id: 10, value: "" },
@@ -106,21 +118,21 @@ describe("form state identity", () => {
[11, state("alice@example.com")],
]),
);
const captured = await captureViewModel(cdp, 7);
expect(captured.nodes.find((n) => n.backendNodeId === 10)).toMatchObject({
await enrichFormControlStates(cdp, 7, nodes);
expect(nodes[0].find((n) => n.backendNodeId === 10)).toMatchObject({
formValue: "",
formState: "empty",
formPlaceholder: "snapshot placeholder",
});
expect(captured.nodes.find((n) => n.backendNodeId === 11)).toMatchObject({
expect(nodes[0].find((n) => n.backendNodeId === 11)).toMatchObject({
formValue: "alice@example.com",
});
expect(captured.nodes.find((n) => n.backendNodeId === 12)).toMatchObject({ formValue: "上海" });
expect(captured.nodes.some((n) => n.backendNodeId === 99)).toBe(false);
expect(nodes[0].find((n) => n.backendNodeId === 12)).toMatchObject({ formValue: "上海" });
expect(nodes[0].some((n) => n.backendNodeId === 99)).toBe(false);
});
it("does not shift state between frames when one frame is absent from the runtime batch", async () => {
const { cdp } = fakeCdp(
const { cdp, nodes } = await fakeCdp(
[
[],
[{ id: 11, value: "inaccessible frame" }],
@@ -133,8 +145,8 @@ describe("form state identity", () => {
[21, state("second frame")],
]),
);
const captured = await captureViewModel(cdp, 7);
const controls = [...captured.iframeNodes.values()].flat();
await enrichFormControlStates(cdp, 7, nodes);
const controls = nodes.slice(1).flat();
expect(controls.find((n) => n.backendNodeId === 11)?.formValue).toBe("inaccessible frame");
expect(controls.find((n) => n.backendNodeId === 21)?.formValue).toBe("second frame");
expect(controls.find((n) => n.backendNodeId === 31)?.formValue).toBe("third frame");
@@ -142,7 +154,6 @@ describe("form state identity", () => {
it("keeps identical backend ids in different OOPIF targets separate", async () => {
const sendToTarget = vi.fn(async (target, method) => {
if (method === "DOMSnapshot.captureSnapshot") return snapshot([[{ id: 11, value: "old" }]]);
if (method === "Runtime.evaluate") return reply([[11, state(target.sessionId)]]);
return {};
});
@@ -151,8 +162,9 @@ describe("form state identity", () => {
});
const cdp = { send, sendToTarget } as unknown as CdpRunner;
for (const sessionId of ["left-frame", "right-frame"]) {
const captured = await captureViewModel(cdpRunnerForTarget(cdp, { tabId: 7, sessionId }), 7);
expect(captured.nodes.find((n) => n.backendNodeId === 11)?.formValue).toBe(sessionId);
const nodes = await decodeControls(snapshot([[{ id: 11, value: "old" }]]));
await enrichFormControlStates(cdpRunnerForTarget(cdp, { tabId: 7, sessionId }), 7, nodes);
expect(nodes[0].find((n) => n.backendNodeId === 11)?.formValue).toBe(sessionId);
expect(sendToTarget).toHaveBeenCalledWith(
{ tabId: 7, sessionId },
"Runtime.releaseObjectGroup",
@@ -168,7 +180,7 @@ describe("form state identity", () => {
"malformed",
"invalid-state",
])("preserves snapshot data when enrichment is %s", async (mode) => {
const { cdp, send } = fakeCdp([[{ id: 11, value: "snapshot value" }]], () => {
const { cdp, send, nodes } = await fakeCdp([[{ id: 11, value: "snapshot value" }]], () => {
if (mode === "unsupported") throw new Error("serialization unsupported");
if (mode === "legacy") return { result: { value: { controls: [state("wrong value")] } } };
const result = reply([
@@ -178,8 +190,8 @@ describe("form state identity", () => {
result.result.deepSerializedValue.value[0].value[1].value = "not json";
return result;
});
const captured = await captureViewModel(cdp, 7);
expect(captured.nodes.find((n) => n.backendNodeId === 11)).toMatchObject({
expect(await enrichFormControlStates(cdp, 7, nodes)).toBe(mode !== "unsupported");
expect(nodes[0].find((n) => n.backendNodeId === 11)).toMatchObject({
formValue: "snapshot value",
formPlaceholder: "snapshot placeholder",
});
@@ -188,18 +200,34 @@ describe("form state identity", () => {
it("releases the batch's remote objects when capture is cancelled", async () => {
const controller = new AbortController();
const { cdp, send } = fakeCdp([[{ id: 11, value: "old" }]], () => {
const { cdp, send, nodes } = await fakeCdp([[{ id: 11, value: "old" }]], () => {
controller.abort();
return reply([[11, state("new")]]);
});
await expect(captureViewModel(cdp, 7, { signal: controller.signal })).rejects.toMatchObject({
await expect(enrichFormControlStates(cdp, 7, nodes, controller.signal)).rejects.toMatchObject({
name: "AbortError",
});
expect(send).toHaveBeenCalledWith(7, "Runtime.releaseObjectGroup", expect.anything());
});
it("does not report success when cancelled during object cleanup", async () => {
const controller = new AbortController();
const nodes = await decodeControls(snapshot([[{ id: 11, value: "old" }]]));
const cdp: CdpRunner = {
send: vi.fn(async (_tabId, method) => {
if (method === "Runtime.evaluate") return reply([[11, state("new")]]);
if (method === "Runtime.releaseObjectGroup") controller.abort();
return {};
}) as CdpRunner["send"],
};
await expect(enrichFormControlStates(cdp, 7, nodes, controller.signal)).rejects.toMatchObject({
name: "AbortError",
});
expect(cdp.send).toHaveBeenCalledWith(7, "Runtime.releaseObjectGroup", expect.anything());
});
it("skips entries without node identity while still applying valid entries", async () => {
const { cdp } = fakeCdp(
const { cdp, nodes } = await fakeCdp(
[
[
{ id: 11, value: "snapshot value" },
@@ -216,20 +244,20 @@ describe("form state identity", () => {
return result;
},
);
const captured = await captureViewModel(cdp, 7);
expect(captured.nodes.find((n) => n.backendNodeId === 11)?.formValue).toBe("snapshot value");
expect(captured.nodes.find((n) => n.backendNodeId === 12)?.formValue).toBe("live value");
await enrichFormControlStates(cdp, 7, nodes);
expect(nodes[0].find((n) => n.backendNodeId === 11)?.formValue).toBe("snapshot value");
expect(nodes[0].find((n) => n.backendNodeId === 12)?.formValue).toBe("live value");
});
it.each([
"password",
"text",
])("redacts a sensitive %s control after identity matching", async (type) => {
const { cdp } = fakeCdp([[{ id: 11, value: "secret", type }]], () =>
const { cdp, nodes } = await fakeCdp([[{ id: 11, value: "secret", type }]], () =>
reply([[11, { ...state("secret"), sensitive: true }]]),
);
const captured = await captureViewModel(cdp, 7);
const control = captured.nodes.find((n) => n.backendNodeId === 11);
await enrichFormControlStates(cdp, 7, nodes);
const control = nodes[0].find((n) => n.backendNodeId === 11);
expect(control?.formState).toBe("filled");
expect(control?.formValue).toBeUndefined();
expect(control?.formDefaultValue).toBeUndefined();
@@ -246,7 +274,7 @@ describe("form state identity", () => {
defaultValue: "",
placeholder: "",
}));
const { cdp, send } = fakeCdp([controls], (params) => {
const { cdp, send, nodes } = await fakeCdp([controls], (params) => {
const doc = {
querySelectorAll: (selector: string) =>
selector === "input,textarea,select" ? elements : [],
@@ -257,9 +285,9 @@ describe("form state identity", () => {
expect(entries).toHaveLength(250);
return reply(entries.map(([element, json]) => [element.backendNodeId, JSON.parse(json)]));
});
const captured = await captureViewModel(cdp, 7);
expect(captured.nodes.find((n) => n.backendNodeId === 250)?.formValue).toBe("live 250");
expect(captured.nodes.find((n) => n.backendNodeId === 251)?.formValue).toBe("old");
await enrichFormControlStates(cdp, 7, nodes);
expect(nodes[0].find((n) => n.backendNodeId === 250)?.formValue).toBe("live 250");
expect(nodes[0].find((n) => n.backendNodeId === 251)?.formValue).toBe("old");
expect(send.mock.calls.filter(([, method]) => method === "Runtime.evaluate")).toHaveLength(1);
expect(
send.mock.calls.filter(([, method]) => method === "Runtime.releaseObjectGroup"),
@@ -1,4 +1,5 @@
import { describe, expect, it, vi } from "vitest";
import { OVERLAY_HOST_MARKER_ATTR } from "@/lib/overlay-bridge";
import type { CdpRunner } from "../../shared";
import type { CapturedNode, CapturedViewModel } from "../capture";
import { captureFrameData } from "../frame-capture";
@@ -30,7 +31,7 @@ function childSnapshot(frameId: string, backendNodeId: number) {
parentIndex: [-1, 0],
nodeName: [1, 2],
backendNodeId: [backendNodeId - 1, backendNodeId],
attributes: [[], []],
attributes: [[], []] as number[][],
},
layout: {
nodeIndex: [0, 1],
@@ -50,6 +51,68 @@ function childSnapshot(frameId: string, backendNodeId: number) {
}
describe("captureFrameData", () => {
it("retains nested owner failures when merging a captured OOPIF", async () => {
const owner = ownerNode(10, 50);
const captured: CapturedViewModel = {
nodes: [owner],
viewport: { width: 1000, height: 800 },
iframeNodes: new Map(),
frameNodes: new Map([["main", [owner]]]),
rootFrameId: "main",
excludedBackendNodeIds: new Set(),
};
const child = childSnapshot("child", 101);
const nested = childSnapshot("nested", 201);
const document = child.documents[0];
const snapshot = {
strings: child.strings,
documents: [
{
...document,
nodes: { ...document.nodes, contentDocumentIndex: { index: [1], value: [1] } },
},
nested.documents[0],
],
};
const reply = async (_target: unknown, method: string) => {
if (method === "Page.getLayoutMetrics")
return { cssLayoutViewport: { clientWidth: 300, clientHeight: 200 } };
if (method === "DOMSnapshot.captureSnapshot") return snapshot;
if (method === "DOM.getBoxModel")
return { model: { content: [50, 100, 350, 100, 350, 300, 50, 300] } };
if (method === "DOM.resolveNode") throw new Error("nested owner replaced");
return {};
};
const cdp: CdpRunner = {
send: vi.fn(reply) as CdpRunner["send"],
sendToTarget: vi.fn(reply) as NonNullable<CdpRunner["sendToTarget"]>,
getFrameGraph: vi.fn(async () => ({
rootFrameId: "main",
frames: [
{ frameId: "main", target: { tabId: 4 } },
{
frameId: "child",
parentFrameId: "main",
ownerBackendNodeId: 10,
target: { tabId: 4, sessionId: "child-session" },
},
],
})),
};
await captureFrameData(cdp, 4, captured);
expect(captured.frameGeometryIssues).toEqual([
{
status: "unavailable",
source: { target: { tabId: 4, sessionId: "child-session" }, frameId: "nested" },
ownerBackendNodeId: 101,
},
]);
expect(captured.frameNodes?.get("nested")?.[1]).toMatchObject({
rect: null,
localRect: { x: 10, y: 20, w: 100, h: 40 },
});
});
it("captures and positions multiple OOPIF documents missing from the root snapshot", async () => {
const leftOwner = ownerNode(10, 50);
const rightOwner = ownerNode(20, 500);
@@ -68,9 +131,15 @@ describe("captureFrameData", () => {
}
if (method === "DOMSnapshot.enable" || method === "Accessibility.enable") return {};
if (method === "DOMSnapshot.captureSnapshot") {
return target.sessionId === "left-session"
? childSnapshot("left", 101)
: childSnapshot("right", 201);
if (target.sessionId !== "left-session") return childSnapshot("right", 201);
const snapshot = childSnapshot("left", 101);
const marker = snapshot.strings.push(OVERLAY_HOST_MARKER_ATTR) - 1;
const nodes = snapshot.documents[0].nodes;
nodes.backendNodeId.push(201); // Same id as a real button in the other target.
nodes.parentIndex.push(0);
nodes.nodeName.push(2);
nodes.attributes.push([marker, -1]);
return snapshot;
}
if (method === "Accessibility.getFullAXTree") return { nodes: [] };
throw new Error(`unexpected ${method}`);
@@ -112,6 +181,10 @@ describe("captureFrameData", () => {
const trees = await captureFrameData(cdp, 4, captured);
expect(trees.find((tree) => tree.frameId === "left")?.excludedBackendNodeIds).toEqual(
new Set([201]),
);
expect(trees.find((tree) => tree.frameId === "right")?.excludedBackendNodeIds?.size).toBe(0);
expect(trees.map((tree) => tree.frameId)).toEqual(["main", "left", "right"]);
expect(
captured.frameNodes?.get("left")?.find((node) => node.backendNodeId === 101)?.rect,
@@ -29,7 +29,7 @@ function captured(frameNodes: Map<string, CapturedNode[]>): CapturedViewModel {
}
describe("buildFrameDocuments", () => {
it("partitions mixed AX results by node ownership and cuts cross-frame parent edges", () => {
it("partitions mixed AX results by node ownership and cuts cross-frame parent edges", async () => {
const graph: CdpFrameGraph = {
rootFrameId: "main",
frames: [
@@ -54,7 +54,7 @@ describe("buildFrameDocuments", () => {
},
];
const documents = buildFrameDocuments(
const documents = await buildFrameDocuments(
graph,
batches,
captured(
@@ -72,7 +72,7 @@ describe("buildFrameDocuments", () => {
expect(childNodes.find((node) => node.nodeId === "virtual")?.frameId).toBe("child");
});
it("deduplicates overlapping same-target AX results using the strongest ownership", () => {
it("deduplicates overlapping same-target AX results using the strongest ownership", async () => {
const graph: CdpFrameGraph = {
rootFrameId: "main",
frames: [
@@ -92,7 +92,7 @@ describe("buildFrameDocuments", () => {
},
];
const documents = buildFrameDocuments(
const documents = await buildFrameDocuments(
graph,
batches,
captured(
@@ -107,7 +107,7 @@ describe("buildFrameDocuments", () => {
expect(documents.find((document) => document.frameId === "child")?.axNodes).toHaveLength(1);
});
it("uses target-scoped backend ownership when OOPIF backend ids collide", () => {
it("uses target-scoped backend ownership when OOPIF backend ids collide", async () => {
const graph: CdpFrameGraph = {
rootFrameId: "main",
frames: [
@@ -129,7 +129,7 @@ describe("buildFrameDocuments", () => {
nodes: [{ nodeId: `${frame.frameId}-node`, backendDOMNodeId: 7 }],
}));
const documents = buildFrameDocuments(
const documents = await buildFrameDocuments(
graph,
batches,
captured(
@@ -149,7 +149,7 @@ describe("buildFrameDocuments", () => {
);
});
it("uses captured frame parent identity instead of guessing from backend ids", () => {
it("uses captured frame parent identity instead of guessing from backend ids", async () => {
const frameNodes = new Map([
["main", [domNode("main", 1)]],
["left", [domNode("left", 7)]],
@@ -164,11 +164,25 @@ describe("buildFrameDocuments", () => {
nodes: [],
}));
const documents = buildFrameDocuments(null, frames, capture);
const documents = await buildFrameDocuments(null, frames, capture);
expect(documents.find((document) => document.frameId === "child")).toMatchObject({
parentFrameId: "left",
ownerBackendNodeId: 7,
});
});
it("resolves a reverse-ordered deep AX parent chain without recursion", async () => {
const frame = { frameId: "main", target: { tabId: 4 } };
const nodes: FrameOwnedAxNode[] = Array.from({ length: 10000 }, (_, i) => ({
nodeId: String(i),
...(i ? { parentId: String(i - 1) } : { frameId: "main" }),
})).reverse();
const documents = await buildFrameDocuments(
{ rootFrameId: "main", frames: [frame] },
[{ frame, nodes }],
captured(new Map()),
);
expect(documents[0].axNodes).toHaveLength(10000);
expect(documents[0].axNodes[0].frameId).toBe("main");
});
});
@@ -0,0 +1,40 @@
function captureAbortError(): Error {
const error = new Error("observation aborted");
error.name = "AbortError";
return error;
}
export function isAbortError(error: unknown): boolean {
return (
typeof error === "object" &&
error !== null &&
(error as { name?: string }).name === "AbortError"
);
}
export function throwIfAborted(signal: AbortSignal | undefined): void {
if (signal?.aborted) throw captureAbortError();
}
/** Check at bounded work blocks; yield only after a processing slice is spent.
* Each caller owns its deadline, so unrelated captures do not share state. */
export function createCaptureCheckpoint(signal?: AbortSignal): () => Promise<void> | undefined {
throwIfAborted(signal);
let deadline = performance.now() + 8;
return () => {
throwIfAborted(signal);
if (performance.now() < deadline) return;
return new Promise<void>((resolve) => {
const channel = new MessageChannel();
channel.port1.onmessage = () => {
channel.port1.close();
channel.port2.close();
resolve();
};
channel.port2.postMessage(null);
}).then(() => {
throwIfAborted(signal);
deadline = performance.now() + 8;
});
};
}
@@ -0,0 +1,37 @@
import type { Rect } from "@browser-skill/vom";
export interface CapturedNode {
backendNodeId: number;
parentBackendNodeId: number | null;
frameId?: string;
/** Owning iframe backend node id; `null` for the top-level document. */
ownerFrameBackendNodeId?: number | null;
tag: string;
attrs: Record<string, string>;
/** Top-level viewport-relative CSS px, clipped to the owning frame viewport. */
rect: Rect | null;
/** Frame-local viewport-relative CSS px before top-level projection. */
localRect?: Rect | null;
paintOrder: number;
position: string;
pointerEvents: string;
/**
* computed `cursor`. `cursor: pointer` is the strongest CDP-free signal
* that a non-semantic element (a `<div>`/`<span>` with a click handler)
* is actually an interactive control — used by the adapter to surface
* custom buttons/checkboxes the AX tree drops as `generic`. Optional like
* `textContent`: the live parser always sets it, hand-built fixtures may not.
*/
cursor?: string;
/**
* Whether the live DOM snapshot provides a painted, non-hidden box for this
* node. Semantic resolution uses this only for DOM fallback nodes; AX-backed
* nodes remain authoritative even when they are outside the viewport.
*/
rendered?: boolean;
textContent?: string;
formState?: "empty" | "filled" | "default";
formValue?: string;
formDefaultValue?: string;
formPlaceholder?: string;
}
+155 -550
View File
@@ -1,56 +1,27 @@
// CDP capture adapter: DOMSnapshot.captureSnapshot + Page.getLayoutMetrics
// → CapturedNode[] + Viewport. This is the ONLY VOM module that touches
// raw CDP. The captureSnapshot reply is columnar (parallel arrays + a
// shared string table); requested computed styles are decoded through
// STYLE_COL so capture and visibility policy share one explicit contract.
// Coordinate DOMSnapshot acquisition, frame geometry and hover probes.
// Snapshot decoding and form enrichment live in their own modules.
import type { Rect, Viewport } from "@browser-skill/vom";
import type { Viewport } from "@browser-skill/vom";
import type { CdpTarget } from "@/browser-driver/frame-graph";
import { evaluateHoverTrigger } from "@/lib/hover-trigger-policy";
import { isOverlayHostNode, OVERLAY_HOST_SELECTOR } from "../../lib/overlay-bridge";
import { childFrameProjection, type GeometryProjection, projectRectToViewport } from "../geometry";
import { OVERLAY_HOST_SELECTOR } from "../../lib/overlay-bridge";
import { type FrameProjectionIssue, type FrameProjectionState } from "../geometry/coordinate-types";
import { cssViewport, GeometryContext, type LayoutMetrics } from "../geometry/frame-context";
import type { CdpRunner } from "../shared";
import { isAbortError, throwIfAborted } from "./capture-abort";
import type { CapturedNode } from "./capture-types";
import { enrichFormControlStates } from "./form-capture";
import { clearHover, ProbeBudget, waitForHover } from "./hover-perception";
import { type FrameContext, normalizeDocument } from "./normalize";
import {
REQUESTED_STYLES,
type SnapshotDocument,
type SnapshotReply,
snapshotFrameId,
sparseIndexMap,
} from "./snapshot";
const REQUESTED_STYLES = ["position", "pointer-events", "cursor", "visibility", "opacity"] as const;
const STYLE_COL = Object.fromEntries(
REQUESTED_STYLES.map((name, index) => [name, index]),
) as Record<(typeof REQUESTED_STYLES)[number], number>;
export interface CapturedNode {
backendNodeId: number;
parentBackendNodeId: number | null;
frameId?: string;
/** Owning iframe backend node id; `null` for the top-level document. */
ownerFrameBackendNodeId?: number | null;
tag: string;
attrs: Record<string, string>;
/** Top-level viewport-relative CSS px, clipped to the owning frame viewport. */
rect: Rect | null;
/** Frame-local viewport-relative CSS px before top-level projection. */
localRect?: Rect | null;
paintOrder: number;
position: string;
pointerEvents: string;
/**
* computed `cursor`. `cursor: pointer` is the strongest CDP-free signal
* that a non-semantic element (a `<div>`/`<span>` with a click handler)
* is actually an interactive control — used by the adapter to surface
* custom buttons/checkboxes the AX tree drops as `generic`. Optional like
* `textContent`: the live parser always sets it, hand-built fixtures may not.
*/
cursor?: string;
/**
* Whether the live DOM snapshot provides a painted, non-hidden box for this
* node. Semantic resolution uses this only for DOM fallback nodes; AX-backed
* nodes remain authoritative even when they are outside the viewport.
*/
rendered?: boolean;
textContent?: string;
formState?: "empty" | "filled" | "default";
formValue?: string;
formDefaultValue?: string;
formPlaceholder?: string;
}
export type { CapturedNode } from "./capture-types";
export type CapturedIframeNodes = Map<number, CapturedNode[]>;
@@ -67,266 +38,26 @@ export interface CapturedViewModel {
viewport: Viewport;
iframeNodes: CapturedIframeNodes;
frameNodes?: Map<string, CapturedNode[]>;
frameExcludedBackendNodeIds?: Map<string, ReadonlySet<number>>;
frameOwnerBackendNodeIds?: Map<string, number>;
/** Explicit DOMSnapshot frame ancestry; never inferred from backend node ids. */
frameParentIds?: Map<string, string>;
rootFrameId?: string;
/** Failed boundaries and descendants blocked by them; clipping is not a failure. */
frameGeometryIssues?: FrameProjectionIssue[];
/** Backend node ids belonging to the agent overlay host + its shadow subtree. */
excludedBackendNodeIds: Set<number>;
}
export interface CaptureViewModelOptions {
signal?: AbortSignal;
}
function captureAbortError(): Error {
const error = new Error("observation aborted");
error.name = "AbortError";
return error;
}
function isAbortError(error: unknown): boolean {
return (
typeof error === "object" &&
error !== null &&
(error as { name?: string }).name === "AbortError"
);
}
function throwIfAborted(signal: AbortSignal | undefined): void {
if (signal?.aborted) throw captureAbortError();
}
/** Sparse array format Chrome uses for infrequently-set per-node fields. */
interface SparseArray {
index: number[];
value: number[];
}
interface RareBooleanData {
index: number[];
}
interface SnapshotDocument {
frameId?: string | number;
scrollOffsetX?: number;
scrollOffsetY?: number;
nodes?: {
parentIndex?: number[];
nodeName?: number[];
backendNodeId?: number[];
attributes?: number[][];
/**
* Per-node text value (index into strings), set for `#text` / CDATA nodes.
* Element nodes carry -1. Same length as `backendNodeId`.
*/
nodeValue?: number[];
/** Maps node array index → index into `documents[]` for frame content. */
contentDocumentIndex?: SparseArray;
inputValue?: SparseArray;
textValue?: SparseArray;
inputChecked?: RareBooleanData;
optionSelected?: RareBooleanData;
};
layout?: {
nodeIndex?: number[];
styles?: number[][];
bounds?: number[][];
paintOrders?: number[];
};
}
function snapshotFrameId(document: SnapshotDocument, strings: string[]): string | undefined {
if (typeof document.frameId === "string") return document.frameId || undefined;
if (typeof document.frameId === "number") return str(strings, document.frameId) || undefined;
return undefined;
}
interface SnapshotReply {
strings?: string[];
documents?: SnapshotDocument[];
}
interface LayoutMetricsReply {
cssLayoutViewport?: {
clientWidth?: number;
clientHeight?: number;
pageX?: number;
pageY?: number;
};
layoutViewport?: { clientWidth?: number; clientHeight?: number; pageX?: number; pageY?: number };
}
function isFormControlTag(tag: string): boolean {
return tag === "input" || tag === "textarea" || tag === "select";
}
function isSensitiveFormControl(node: Pick<CapturedNode, "tag" | "attrs">): boolean {
return node.tag === "input" && (node.attrs.type ?? "").toLowerCase() === "password";
}
function snapshotFormState(
value: string | undefined,
defaultValue: string,
hasDefaultValue: boolean,
sensitive: boolean,
): CapturedNode["formState"] {
if (sensitive) {
if (value === undefined && !hasDefaultValue) return undefined;
return (value ?? defaultValue) === "" ? "empty" : "filled";
}
if (value === undefined) return undefined;
if (value === "") return "empty";
return value === defaultValue ? "default" : "filled";
}
const MAX_FORM_ENRICH_CONTROLS = 250;
interface CapturedFormState {
value?: string;
defaultValue?: string;
placeholder?: string;
state?: "empty" | "filled" | "default";
sensitive?: boolean;
}
interface DeepSerializedValue {
type: string;
value?: unknown;
}
function formStateBatchExpression(maxControls: number): string {
return `(() => {
const maxControls = ${JSON.stringify(maxControls)};
let remaining = maxControls;
const controlSelector = "input,textarea,select";
const controlState = (el) => {
const tag = el.tagName.toLowerCase();
const type = tag === "input" ? String(el.type || "text").toLowerCase() : tag;
const sensitive = type === "password" || type === "credit-card";
const rawValue = typeof el.value === "string" ? el.value : "";
const defaultValue = typeof el.defaultValue === "string" ? el.defaultValue : "";
const placeholder = typeof el.placeholder === "string" ? el.placeholder : "";
const state = rawValue === "" ? "empty" : rawValue === defaultValue ? "default" : "filled";
return {
state,
sensitive,
placeholder,
...(sensitive ? {} : { value: rawValue, defaultValue }),
};
};
const controls = [];
const collect = (doc) => {
for (const el of Array.from(doc.querySelectorAll(controlSelector))) {
if (remaining <= 0) break;
// Deep serialization supplies the node's backend id. Keep the
// state as JSON so decoding needs no general-purpose V8 deserializer.
controls.push([el, JSON.stringify(controlState(el))]);
remaining -= 1;
}
for (const frame of Array.from(doc.querySelectorAll("iframe"))) {
if (remaining <= 0) break;
let childDoc = null;
try { childDoc = frame.contentDocument; } catch { childDoc = null; }
if (childDoc) collect(childDoc);
}
};
collect(document);
return controls;
})()`;
}
function formStatesByBackendId(result: RuntimeEvaluateReply): Map<number, CapturedFormState> {
const states = new Map<number, CapturedFormState>();
const serialized = result.result?.deepSerializedValue;
if (serialized?.type !== "array" || !Array.isArray(serialized.value)) return states;
for (const entry of serialized.value as DeepSerializedValue[]) {
if (entry?.type !== "array" || !Array.isArray(entry.value)) continue;
const [element, json] = entry.value as DeepSerializedValue[];
if (element?.type !== "node" || json?.type !== "string" || typeof json.value !== "string") {
continue;
}
const backendNodeId = (element.value as { backendNodeId?: number } | undefined)?.backendNodeId;
if (typeof backendNodeId !== "number" || !Number.isSafeInteger(backendNodeId)) continue;
try {
const state = JSON.parse(json.value) as CapturedFormState | null;
if (
!state ||
!["empty", "filled", "default"].includes(state.state ?? "") ||
typeof state.sensitive !== "boolean" ||
typeof state.placeholder !== "string" ||
(!state.sensitive &&
(typeof state.value !== "string" || typeof state.defaultValue !== "string"))
) {
continue;
}
states.set(backendNodeId, state);
} catch {
// A malformed entry must not overwrite the snapshot's own state.
}
}
return states;
}
function applyFormStates(nodes: CapturedNode[], states: Map<number, CapturedFormState>): void {
for (const node of nodes) {
if (!isFormControlTag(node.tag)) continue;
const state = states.get(node.backendNodeId);
if (!state) continue;
node.formState = state.state;
node.formPlaceholder = state.placeholder ?? "";
if (state.sensitive || isSensitiveFormControl(node)) {
delete node.formValue;
delete node.formDefaultValue;
delete node.attrs.value;
} else {
node.formDefaultValue = state.defaultValue ?? "";
if (state.value !== undefined) node.formValue = state.value;
}
}
}
async function enrichFormControlStates(
cdp: CdpRunner,
tabId: number,
frameNodeGroups: CapturedNode[][],
signal?: AbortSignal,
): Promise<void> {
const hasControls = frameNodeGroups.some((nodes) =>
nodes.some((node) => isFormControlTag(node.tag)),
);
if (!hasControls) return;
const objectGroup = `bsk-vom-forms-${crypto.randomUUID()}`;
try {
throwIfAborted(signal);
const result = await cdp.send<RuntimeEvaluateReply>(tabId, "Runtime.evaluate", {
expression: formStateBatchExpression(MAX_FORM_ENRICH_CONTROLS),
objectGroup,
serializationOptions: {
serialization: "deep",
maxDepth: 3,
additionalParameters: { maxNodeDepth: 0, includeShadowTree: "none" },
},
});
throwIfAborted(signal);
// Backend ids are scoped to this capture's CDP target. OOPIF targets
// use their own captureViewModel call and never share this lookup.
const states = formStatesByBackendId(result);
for (const nodes of frameNodeGroups) {
applyFormStates(nodes, states);
}
} catch (error) {
if (isAbortError(error)) throw error;
// Best-effort enrichment. DOMSnapshot/AX data still carries the nodes.
} finally {
await cdp.send(tabId, "Runtime.releaseObjectGroup", { objectGroup }).catch(() => undefined);
}
geometry?: GeometryContext;
target?: CdpTarget;
}
interface RuntimeEvaluateReply {
result?: {
value?: unknown;
deepSerializedValue?: DeepSerializedValue;
};
}
@@ -345,44 +76,6 @@ interface CdpDomNode {
shadowRoots?: CdpDomNode[];
}
interface ParseDocumentResult {
nodes: CapturedNode[];
excludedBackendNodeIds: Set<number>;
}
interface FrameContext {
frameId?: string;
ownerFrameBackendNodeId: number | null;
projection: GeometryProjection | null;
scrollX: number;
scrollY: number;
}
function str(strings: string[], idx: number | undefined): string {
if (idx === undefined || idx < 0) return "";
return strings[idx] ?? "";
}
function devicePixelRatio(metrics: LayoutMetricsReply): number {
const layoutW = metrics.layoutViewport?.clientWidth ?? 0;
const cssW = metrics.cssLayoutViewport?.clientWidth ?? 0;
if (!layoutW || !cssW) return 1;
const dpr = layoutW / cssW;
if (!Number.isFinite(dpr) || dpr <= 0) return 1;
return dpr >= 1 ? dpr : 1;
}
function sparseIndexMap(sparse: SparseArray | undefined): Map<number, number> {
const out = new Map<number, number>();
if (!sparse?.index || !sparse.value) return out;
for (let i = 0; i < sparse.index.length; i++) {
const nodeIndex = sparse.index[i];
const docIndex = sparse.value[i];
if (nodeIndex !== undefined && docIndex !== undefined) out.set(nodeIndex, docIndex);
}
return out;
}
function collectBackendIdsFromDomNode(node: CdpDomNode | undefined, out: Set<number>): void {
if (!node) return;
if (typeof node.backendNodeId === "number") {
@@ -792,230 +485,108 @@ export async function collectOverlayExcludedBackendIds(
return excluded;
}
/**
* Parse one DOMSnapshot document into CapturedNode[].
*
* @param doc - the raw DOMSnapshot document object
* @param strings - the shared string table for the whole snapshot
* @param dpr - device-pixel-ratio from Page.getLayoutMetrics
* @param context - frame coordinate context; output rects are top viewport-relative
*/
function parseDocumentNodes(
doc: SnapshotDocument,
strings: string[],
dpr: number,
context: FrameContext,
): ParseDocumentResult {
const dn = doc.nodes;
const dl = doc.layout;
if (!dn?.backendNodeId) {
return { nodes: [], excludedBackendNodeIds: new Set() };
}
const count = dn.backendNodeId.length;
const layoutByNode = new Map<number, number>();
(dl?.nodeIndex ?? []).forEach((nodeIdx, layoutIdx) => layoutByNode.set(nodeIdx, layoutIdx));
// The agent's own overlay (WXT shadow host, marked with OVERLAY_HOST_MARKER_ATTR)
// is injected into the page and its open shadow root
// is inlined by DOMSnapshot as descendants of the host. Its fixed
// full-viewport click-blocker would otherwise dominate occlusion detection
// and hide the real page, so mark the host + its whole subtree excluded.
// parentIndex always references an earlier node, so one forward pass suffices.
const excluded = new Array<boolean>(count).fill(false);
const excludedBackendNodeIds = new Set<number>();
for (let n = 0; n < count; n++) {
const parentIdx = dn.parentIndex?.[n] ?? -1;
const inherited = parentIdx >= 0 && excluded[parentIdx];
let isOverlayHost = inherited;
if (!isOverlayHost) {
const pairs = dn.attributes?.[n] ?? [];
const attrNames: string[] = [];
for (let a = 0; a + 1 < pairs.length; a += 2) {
attrNames.push(str(strings, pairs[a]));
}
isOverlayHost = isOverlayHostNode(str(strings, dn.nodeName?.[n]), attrNames);
}
if (!isOverlayHost) continue;
excluded[n] = true;
const backendNodeId = dn.backendNodeId[n];
if (backendNodeId !== undefined) {
excludedBackendNodeIds.add(backendNodeId);
}
}
const posCol = STYLE_COL.position;
const peCol = STYLE_COL["pointer-events"];
const cursorCol = STYLE_COL.cursor;
const visibilityCol = STYLE_COL.visibility;
const opacityCol = STYLE_COL.opacity;
const inputValues = sparseIndexMap(dn.inputValue);
const textValues = sparseIndexMap(dn.textValue);
const checkedInputs = new Set(dn.inputChecked?.index ?? []);
const selectedOptions = new Set(dn.optionSelected?.index ?? []);
// Collect visible text from #text child nodes so element CapturedNodes
// carry a textContent value usable as a button/link label fallback.
// nodeValue is a parallel array: string index for text nodes, -1 otherwise.
const nodeTextContent = new Map<number, string>();
if (dn.nodeValue) {
for (let n = 0; n < count; n++) {
const nvIdx = dn.nodeValue[n] ?? -1;
if (nvIdx < 0) continue;
const text = str(strings, nvIdx).trim();
if (!text) continue;
const parentIdx = dn.parentIndex?.[n] ?? -1;
if (parentIdx >= 0) {
const existing = nodeTextContent.get(parentIdx);
nodeTextContent.set(parentIdx, existing ? `${existing} ${text}` : text);
}
}
}
// Build CapturedNodes.
const nodes: CapturedNode[] = [];
for (let n = 0; n < count; n++) {
if (excluded[n]) continue;
const backendNodeId = dn.backendNodeId[n];
const parentIdx = dn.parentIndex?.[n] ?? -1;
const parentBackendNodeId = parentIdx >= 0 ? (dn.backendNodeId[parentIdx] ?? null) : null;
const tag = str(strings, dn.nodeName?.[n]).toLowerCase();
const attrs: Record<string, string> = {};
const pairs = dn.attributes?.[n] ?? [];
for (let a = 0; a + 1 < pairs.length; a += 2) {
attrs[str(strings, pairs[a]).toLowerCase()] = str(strings, pairs[a + 1]);
}
let rect: Rect | null = null;
let localRect: Rect | null = null;
let paintOrder = 0;
let position = "static";
let pointerEvents = "auto";
let cursor = "auto";
let rendered = false;
const li = layoutByNode.get(n);
if (li !== undefined) {
const b = dl?.bounds?.[li];
if (b && b.length >= 4 && b[2] > 0 && b[3] > 0) {
localRect = {
x: b[0] / dpr - context.scrollX,
y: b[1] / dpr - context.scrollY,
w: b[2] / dpr,
h: b[3] / dpr,
};
const bounds = context.projection
? projectRectToViewport(localRect, context.projection)
: null;
rect = bounds ? { x: bounds.x, y: bounds.y, w: bounds.width, h: bounds.height } : null;
}
paintOrder = dl?.paintOrders?.[li] ?? 0;
const styleRow = dl?.styles?.[li] ?? [];
position = str(strings, styleRow[posCol]) || "static";
pointerEvents = str(strings, styleRow[peCol]) || "auto";
cursor = str(strings, styleRow[cursorCol]) || "auto";
const visibility = str(strings, styleRow[visibilityCol]) || "visible";
const opacity = str(strings, styleRow[opacityCol]) || "1";
rendered =
localRect !== null &&
visibility !== "hidden" &&
visibility !== "collapse" &&
(Number.parseFloat(opacity) || 0) > 0;
}
// Skip non-element nodes (#text, #cdata-section, etc.) — they carry no
// geometry and are never queried by callers.
if (tag.startsWith("#")) continue;
const textContent = nodeTextContent.get(n);
const rawFormValueIndex = tag === "textarea" ? textValues.get(n) : inputValues.get(n);
const rawFormValue =
rawFormValueIndex !== undefined ? str(strings, rawFormValueIndex) : undefined;
const sensitive = isSensitiveFormControl({ tag, attrs });
const formDefaultValue = attrs.value ?? "";
const formValue = sensitive ? undefined : rawFormValue;
const formState = snapshotFormState(
rawFormValue,
formDefaultValue,
Object.prototype.hasOwnProperty.call(attrs, "value"),
sensitive,
);
if (sensitive) delete attrs.value;
nodes.push({
backendNodeId,
parentBackendNodeId,
...(context.frameId ? { frameId: context.frameId } : {}),
ownerFrameBackendNodeId: context.ownerFrameBackendNodeId,
tag,
attrs,
rect,
localRect,
paintOrder,
position,
pointerEvents,
cursor,
rendered,
textContent,
...(formValue !== undefined ? { formValue } : {}),
...(tag === "input" || tag === "textarea"
? {
formPlaceholder: attrs.placeholder ?? "",
...(!sensitive ? { formDefaultValue } : {}),
...(formState ? { formState } : {}),
}
: {}),
...(checkedInputs.has(n) ? { formValue: "true", formState: "filled" } : {}),
...(selectedOptions.has(n) ? { formValue: attrs.value ?? textContent ?? "" } : {}),
});
}
return { nodes, excludedBackendNodeIds };
}
interface ParseFrameDocumentsResult {
frameGeometryIssues: FrameProjectionIssue[];
iframeNodes: CapturedIframeNodes;
frameOwnerBackendNodeIds: Map<string, number>;
frameParentIds: Map<string, string>;
frameExcludedBackendNodeIds: Map<string, ReadonlySet<number>>;
excludedBackendNodeIds: Set<number>;
}
function parseChildFrameDocuments(
async function parseChildFrameDocuments(
documents: SnapshotDocument[],
strings: string[],
dpr: number,
parentDocIndex: number,
parentNodes: CapturedNode[],
parentContext: FrameContext,
geometry: GeometryContext,
signal?: AbortSignal,
visited = new Set<number>(),
): ParseFrameDocumentsResult {
): Promise<ParseFrameDocumentsResult> {
const frameGeometryIssues: FrameProjectionIssue[] = [];
const iframeNodes: CapturedIframeNodes = new Map();
const frameOwnerBackendNodeIds = new Map<string, number>();
const frameParentIds = new Map<string, string>();
const frameExcludedBackendNodeIds = new Map<string, ReadonlySet<number>>();
const excludedBackendNodeIds = new Set<number>();
const parentDoc = documents[parentDocIndex];
const cdi = sparseIndexMap(parentDoc?.nodes?.contentDocumentIndex);
if (cdi.size === 0) {
return { iframeNodes, frameOwnerBackendNodeIds, frameParentIds, excludedBackendNodeIds };
return {
iframeNodes,
frameOwnerBackendNodeIds,
frameParentIds,
frameExcludedBackendNodeIds,
excludedBackendNodeIds,
frameGeometryIssues,
};
}
const parentBackendIds = parentDoc?.nodes?.backendNodeId ?? [];
const parentNodeByBackendId = new Map(parentNodes.map((node) => [node.backendNodeId, node]));
for (const [nodeArrayIdx, childDocIndex] of cdi) {
if (visited.has(childDocIndex)) continue;
const children = [...cdi].flatMap(([nodeArrayIdx, childDocIndex]) => {
const childDoc = documents[childDocIndex];
if (!childDoc) continue;
const iframeBackendId = parentBackendIds[nodeArrayIdx];
if (iframeBackendId === undefined) continue;
const iframeNode = parentNodeByBackendId.get(iframeBackendId);
const projection =
parentContext.projection && iframeNode?.localRect
? childFrameProjection(parentContext.projection, iframeNode.localRect)
: null;
if (visited.has(childDocIndex) || !childDoc || iframeBackendId === undefined) return [];
const source = { target: parentContext.target, frameId: snapshotFrameId(childDoc, strings) };
const parent = parentContext.projection;
const projection: FrameProjectionState =
parent.status === "available"
? { status: "unavailable", source, ownerBackendNodeId: iframeBackendId }
: { status: "blocked", source, cause: parent.status === "blocked" ? parent.cause : parent };
return [
{
childDocIndex,
childDoc,
iframeBackendId,
source,
projection: projection as FrameProjectionState,
},
];
});
const parentProjection =
parentContext.projection.status === "available"
? parentContext.projection.projection.geometry
: null;
if (parentProjection) {
// Measure only direct siblings. Recursion starts after these workers finish,
// so descendants never hold or recursively acquire a measurement slot.
const edge = parentProjection.edges[0];
const clips = edge
? [edge.destinationQuad, ...(edge.destinationClips ?? [])]
: parentProjection.sourceClips;
let cursor = 0;
let failure: unknown;
await Promise.all(
Array.from({ length: Math.min(4, children.length) }, async () => {
while (cursor < children.length && !signal?.aborted && !failure) {
const child = children[cursor++];
try {
// Owner quads are target-relative; do not apply the parent transform twice.
child.projection = await geometry.snapshotProjection(
child.source,
child.iframeBackendId,
clips,
parentProjection.topViewport,
);
} catch (error) {
failure ??= error;
}
}
}),
);
// Join all active reads, including object cleanup, before propagating abort.
if (failure) throw failure;
}
throwIfAborted(signal);
// Completion order must not change document traversal or result insertion order.
for (const { childDocIndex, childDoc, iframeBackendId, source, projection } of children) {
throwIfAborted(signal);
if (projection.status !== "available") frameGeometryIssues.push(projection);
const childContext: FrameContext = {
frameId: snapshotFrameId(childDoc, strings),
frameId: source.frameId,
target: source.target,
ownerFrameBackendNodeId: iframeBackendId,
projection,
scrollX: childDoc.scrollOffsetX ?? 0,
@@ -1023,23 +594,25 @@ function parseChildFrameDocuments(
};
const nextVisited = new Set(visited);
nextVisited.add(childDocIndex);
const parsed = parseDocumentNodes(childDoc, strings, dpr, childContext);
const parsed = await normalizeDocument(childDoc, strings, childContext, signal);
iframeNodes.set(iframeBackendId, parsed.nodes);
if (childContext.frameId) {
frameOwnerBackendNodeIds.set(childContext.frameId, iframeBackendId);
frameExcludedBackendNodeIds.set(childContext.frameId, parsed.index.excludedBackendNodeIds);
if (parentContext.frameId) frameParentIds.set(childContext.frameId, parentContext.frameId);
}
for (const id of parsed.excludedBackendNodeIds) excludedBackendNodeIds.add(id);
for (const id of parsed.index.excludedBackendNodeIds) excludedBackendNodeIds.add(id);
const nested = parseChildFrameDocuments(
const nested = await parseChildFrameDocuments(
documents,
strings,
dpr,
childDocIndex,
parsed.nodes,
childContext,
geometry,
signal,
nextVisited,
);
frameGeometryIssues.push(...nested.frameGeometryIssues);
for (const [nestedFrameId, nestedNodes] of nested.iframeNodes) {
iframeNodes.set(nestedFrameId, nestedNodes);
}
@@ -1049,10 +622,19 @@ function parseChildFrameDocuments(
for (const [frameId, parentFrameId] of nested.frameParentIds) {
frameParentIds.set(frameId, parentFrameId);
}
for (const [frameId, excluded] of nested.frameExcludedBackendNodeIds)
frameExcludedBackendNodeIds.set(frameId, excluded);
for (const id of nested.excludedBackendNodeIds) excludedBackendNodeIds.add(id);
}
return { iframeNodes, frameOwnerBackendNodeIds, frameParentIds, excludedBackendNodeIds };
return {
iframeNodes,
frameOwnerBackendNodeIds,
frameParentIds,
frameExcludedBackendNodeIds,
excludedBackendNodeIds,
frameGeometryIssues,
};
}
export async function captureViewModel(
@@ -1061,22 +643,20 @@ export async function captureViewModel(
options: CaptureViewModelOptions = {},
): Promise<CapturedViewModel> {
throwIfAborted(options.signal);
let metrics: LayoutMetricsReply = {};
const target = options.target ?? { tabId };
const geometry = options.geometry ?? new GeometryContext(cdp, tabId, undefined, options.signal);
let metrics: LayoutMetrics = {};
try {
metrics = await cdp.send<LayoutMetricsReply>(tabId, "Page.getLayoutMetrics", {});
metrics = await geometry.layoutMetrics(target);
} catch (error) {
if (isAbortError(error)) throw error;
console.debug("[bsk capture] layout metrics unavailable", error);
}
throwIfAborted(options.signal);
const dpr = devicePixelRatio(metrics);
const vpSrc = metrics.cssLayoutViewport ?? metrics.layoutViewport ?? {};
const viewport: Viewport = {
width: vpSrc.clientWidth ?? 0,
height: vpSrc.clientHeight ?? 0,
};
const scrollX = vpSrc.pageX ?? 0;
const scrollY = vpSrc.pageY ?? 0;
const measured = cssViewport(metrics);
const viewport: Viewport = { width: measured.width, height: measured.height };
const scrollX = measured.scrollX;
const scrollY = measured.scrollY;
await cdp.send(tabId, "DOMSnapshot.enable", {});
throwIfAborted(options.signal);
@@ -1102,20 +682,43 @@ export async function captureViewModel(
const topContext: FrameContext = {
frameId: snapshotFrameId(doc0, strings),
ownerFrameBackendNodeId: null,
target,
projection: {
sourceClips: [],
edges: [],
topViewport: viewport,
status: "available",
projection: {
source: { target, frameId: snapshotFrameId(doc0, strings) },
geometry: { sourceClips: [], edges: [], topViewport: viewport },
},
},
scrollX,
scrollY,
};
const mainParsed = parseDocumentNodes(doc0, strings, dpr, topContext);
const mainParsed = await normalizeDocument(doc0, strings, topContext, options.signal);
const nodes = mainParsed.nodes;
const excludedBackendNodeIds = new Set(mainParsed.excludedBackendNodeIds);
const excludedBackendNodeIds = new Set(mainParsed.index.excludedBackendNodeIds);
const frameParsed = parseChildFrameDocuments(documents, strings, dpr, 0, nodes, topContext);
const ownerIds = new Set<number>();
for (const document of documents) {
for (const index of document.nodes?.contentDocumentIndex?.index ?? []) {
const id = document.nodes?.backendNodeId?.[index];
if (id !== undefined) ownerIds.add(id);
}
}
geometry.registerSnapshotOwners(target, ownerIds);
const frameParsed = await parseChildFrameDocuments(
documents,
strings,
0,
topContext,
geometry,
options.signal,
);
const iframeNodes = frameParsed.iframeNodes;
if (topContext.frameId)
frameParsed.frameExcludedBackendNodeIds.set(
topContext.frameId,
mainParsed.index.excludedBackendNodeIds,
);
for (const id of frameParsed.excludedBackendNodeIds) {
excludedBackendNodeIds.add(id);
}
@@ -1140,7 +743,9 @@ export async function captureViewModel(
viewport,
iframeNodes,
frameNodes,
frameGeometryIssues: frameParsed.frameGeometryIssues,
frameOwnerBackendNodeIds: frameParsed.frameOwnerBackendNodeIds,
frameExcludedBackendNodeIds: frameParsed.frameExcludedBackendNodeIds,
frameParentIds: frameParsed.frameParentIds,
...(topContext.frameId ? { rootFrameId: topContext.frameId } : {}),
excludedBackendNodeIds,
+94
View File
@@ -0,0 +1,94 @@
import { isOverlayHostNode } from "@/lib/overlay-bridge";
import { createCaptureCheckpoint } from "./capture-abort";
import type { CapturedNode } from "./capture-types";
/** Bounds retain their snapshot document CSS units until normalization. */
export interface SnapshotLayout {
readonly boundsSpace: "snapshot-document-css";
bounds?: number[];
styles: Readonly<Record<string, string>>;
}
export interface DecodedNode extends Omit<CapturedNode, "rect" | "localRect" | "rendered"> {
nodeType?: number;
layout?: SnapshotLayout;
}
export interface NodeFacts extends CapturedNode {
nodeType?: number;
layout?: SnapshotLayout;
}
export interface DocumentIndex<T extends DecodedNode = NodeFacts> {
readonly nodes: ReadonlyMap<number, T>;
readonly excludedBackendNodeIds: ReadonlySet<number>;
}
export interface DecodedDocument {
nodes: DecodedNode[];
}
/** All snapshot nodes participate, including document and shadow roots. This
* preserves overlay propagation when the semantic adapter omits those nodes. */
export async function buildDocumentIndex<T extends DecodedNode>(
input: readonly T[],
signal?: AbortSignal,
): Promise<DocumentIndex<T>> {
const checkpoint = createCaptureCheckpoint(signal);
const nodes = new Map<number, T>();
const overlayByNode = new Map<number, boolean>();
const excludedBackendNodeIds = new Set<number>();
for (let i = 0; i < input.length; i++) {
if (i % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
const node = input[i];
nodes.set(node.backendNodeId, node);
}
let work = 0;
for (const node of input) {
if (work++ % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
if (overlayByNode.has(node.backendNodeId)) continue;
const path: DecodedNode[] = [];
const visiting = new Set<number>();
let current: DecodedNode | undefined = node;
let overlay = false;
while (current && !overlayByNode.has(current.backendNodeId)) {
if (work++ % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
if (visiting.has(current.backendNodeId)) {
// Only an overlay inside the cycle may mark the cycle and its descendants.
overlay = path
.slice(path.findIndex((item) => item.backendNodeId === current!.backendNodeId))
.some((item) => isOverlayHostNode(item.tag, Object.keys(item.attrs)));
break;
}
visiting.add(current.backendNodeId);
path.push(current);
if (current.parentBackendNodeId === null) {
current = undefined;
break;
}
current = nodes.get(current.parentBackendNodeId);
}
if (current && overlayByNode.has(current.backendNodeId))
overlay = overlayByNode.get(current.backendNodeId)!;
for (let i = path.length - 1; i >= 0; i--) {
if (work++ % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
const item = path[i];
overlay = overlay || isOverlayHostNode(item.tag, Object.keys(item.attrs));
overlayByNode.set(item.backendNodeId, overlay);
if (overlay) excludedBackendNodeIds.add(item.backendNodeId);
}
}
return { nodes, excludedBackendNodeIds };
}
@@ -0,0 +1,155 @@
import type { CdpRunner } from "../shared";
import { isAbortError, throwIfAborted } from "./capture-abort";
import type { CapturedNode } from "./capture-types";
interface RuntimeEvaluateReply {
result?: { deepSerializedValue?: DeepSerializedValue };
}
const MAX_FORM_ENRICH_CONTROLS = 250;
interface CapturedFormState {
value?: string;
defaultValue?: string;
placeholder?: string;
state?: "empty" | "filled" | "default";
sensitive?: boolean;
}
interface DeepSerializedValue {
type: string;
value?: unknown;
}
function formStateBatchExpression(maxControls: number): string {
return `(() => {
const maxControls = ${JSON.stringify(maxControls)};
let remaining = maxControls;
const controlSelector = "input,textarea,select";
const controlState = (el) => {
const tag = el.tagName.toLowerCase();
const type = tag === "input" ? String(el.type || "text").toLowerCase() : tag;
const sensitive = type === "password" || type === "credit-card";
const rawValue = typeof el.value === "string" ? el.value : "";
const defaultValue = typeof el.defaultValue === "string" ? el.defaultValue : "";
const placeholder = typeof el.placeholder === "string" ? el.placeholder : "";
const state = rawValue === "" ? "empty" : rawValue === defaultValue ? "default" : "filled";
return {
state,
sensitive,
placeholder,
...(sensitive ? {} : { value: rawValue, defaultValue }),
};
};
const controls = [];
const collect = (doc) => {
for (const el of Array.from(doc.querySelectorAll(controlSelector))) {
if (remaining <= 0) break;
// Deep serialization supplies the node's backend id. Keep the
// state as JSON so decoding needs no general-purpose V8 deserializer.
controls.push([el, JSON.stringify(controlState(el))]);
remaining -= 1;
}
for (const frame of Array.from(doc.querySelectorAll("iframe"))) {
if (remaining <= 0) break;
let childDoc = null;
try { childDoc = frame.contentDocument; } catch { childDoc = null; }
if (childDoc) collect(childDoc);
}
};
collect(document);
return controls;
})()`;
}
function formStatesByBackendId(result: RuntimeEvaluateReply): Map<number, CapturedFormState> {
const states = new Map<number, CapturedFormState>();
const serialized = result.result?.deepSerializedValue;
if (serialized?.type !== "array" || !Array.isArray(serialized.value)) return states;
for (const entry of serialized.value as DeepSerializedValue[]) {
if (entry?.type !== "array" || !Array.isArray(entry.value)) continue;
const [element, json] = entry.value as DeepSerializedValue[];
if (element?.type !== "node" || json?.type !== "string" || typeof json.value !== "string") {
continue;
}
const backendNodeId = (element.value as { backendNodeId?: number } | undefined)?.backendNodeId;
if (typeof backendNodeId !== "number" || !Number.isSafeInteger(backendNodeId)) continue;
try {
const state = JSON.parse(json.value) as CapturedFormState | null;
if (
!state ||
!["empty", "filled", "default"].includes(state.state ?? "") ||
typeof state.sensitive !== "boolean" ||
typeof state.placeholder !== "string" ||
(!state.sensitive &&
(typeof state.value !== "string" || typeof state.defaultValue !== "string"))
) {
continue;
}
states.set(backendNodeId, state);
} catch {
// A malformed entry must not overwrite the snapshot's own state.
}
}
return states;
}
function applyFormStates(nodes: CapturedNode[], states: Map<number, CapturedFormState>): void {
for (const node of nodes) {
if (!["input", "textarea", "select"].includes(node.tag)) continue;
const state = states.get(node.backendNodeId);
if (!state) continue;
node.formState = state.state;
node.formPlaceholder = state.placeholder ?? "";
if (
state.sensitive ||
(node.tag === "input" && (node.attrs.type ?? "").toLowerCase() === "password")
) {
delete node.formValue;
delete node.formDefaultValue;
delete node.attrs.value;
} else {
node.formDefaultValue = state.defaultValue ?? "";
if (state.value !== undefined) node.formValue = state.value;
}
}
}
export async function enrichFormControlStates(
cdp: CdpRunner,
tabId: number,
frameNodeGroups: CapturedNode[][],
signal?: AbortSignal,
): Promise<boolean> {
const hasControls = frameNodeGroups.some((nodes) =>
nodes.some((node) => ["input", "textarea", "select"].includes(node.tag)),
);
if (!hasControls) return true;
const objectGroup = `bsk-vom-forms-${crypto.randomUUID()}`;
try {
throwIfAborted(signal);
const result = await cdp.send<RuntimeEvaluateReply>(tabId, "Runtime.evaluate", {
expression: formStateBatchExpression(MAX_FORM_ENRICH_CONTROLS),
objectGroup,
serializationOptions: {
serialization: "deep",
maxDepth: 3,
additionalParameters: { maxNodeDepth: 0, includeShadowTree: "none" },
},
});
throwIfAborted(signal);
// Backend ids are scoped to this capture's CDP target. OOPIF targets
// have separate enrichment calls and never share this lookup.
const states = formStatesByBackendId(result);
for (const nodes of frameNodeGroups) {
applyFormStates(nodes, states);
}
return true;
} catch (error) {
if (isAbortError(error)) throw error;
// Best-effort enrichment. DOMSnapshot/AX data still carries the nodes.
return false;
} finally {
await cdp.send(tabId, "Runtime.releaseObjectGroup", { objectGroup }).catch(() => undefined);
throwIfAborted(signal);
}
}
+17 -15
View File
@@ -1,6 +1,6 @@
import type { CdpFrame, CdpFrameGraph } from "@/browser-driver/frame-graph";
import { resolveFrameProjection } from "../frame-geometry";
import { type GeometryProjection, projectRectToViewport } from "../geometry";
import { GeometryContext } from "../geometry/frame-context";
import { type CdpRunner, cdpRunnerForTarget, sendToCdpTarget } from "../shared";
import { type CapturedNode, type CapturedViewModel, captureViewModel } from "./capture";
import {
@@ -21,16 +21,6 @@ function isAbortError(err: unknown): boolean {
return err instanceof Error && err.name === "AbortError";
}
async function discoverFrameGraph(cdp: CdpRunner, tabId: number): Promise<CdpFrameGraph | null> {
if (!cdp.getFrameGraph) return null;
try {
return await cdp.getFrameGraph(tabId);
} catch (err) {
console.debug("[bsk observation] frame graph capture failed", err);
return null;
}
}
function transformFrameNodes(
nodes: CapturedNode[],
projection: GeometryProjection | null,
@@ -51,6 +41,7 @@ async function captureMissingFrameDocuments(
tabId: number,
graph: CdpFrameGraph,
captured: CapturedViewModel,
geometry: GeometryContext,
signal?: AbortSignal,
): Promise<void> {
if (!captured.frameNodes) captured.frameNodes = new Map();
@@ -62,10 +53,20 @@ async function captureMissingFrameDocuments(
try {
const child = await captureViewModel(cdpRunnerForTarget(cdp, frame.target), tabId, {
signal,
geometry,
target: frame.target,
});
if (child.frameExcludedBackendNodeIds?.size) {
captured.frameExcludedBackendNodeIds ??= new Map();
for (const [id, excluded] of child.frameExcludedBackendNodeIds)
captured.frameExcludedBackendNodeIds.set(id, excluded);
}
if (child.frameGeometryIssues?.length) {
(captured.frameGeometryIssues ??= []).push(...child.frameGeometryIssues);
}
let projection: GeometryProjection | null = null;
try {
projection = await resolveFrameProjection(cdp, graph, frame.frameId);
projection = await geometry.targetProjection(frame.frameId);
} catch (err) {
if (isAbortError(err)) throw err;
console.debug("[bsk observation] child frame geometry projection failed", {
@@ -171,11 +172,12 @@ export async function captureFrameData<T extends FrameAxNode>(
tabId: number,
captured: CapturedViewModel,
signal?: AbortSignal,
geometry = new GeometryContext(cdp, tabId, undefined, signal),
): Promise<CapturedFrameDocument<T>[]> {
const graph = await discoverFrameGraph(cdp, tabId);
const graph = await geometry.graph();
const frames = graph?.frames ?? [];
if (graph) await captureMissingFrameDocuments(cdp, tabId, graph, captured, signal);
if (graph) await captureMissingFrameDocuments(cdp, tabId, graph, captured, geometry, signal);
throwIfAborted(signal);
const batches = await captureAxTrees<T>(cdp, tabId, frames, captured, signal);
return buildFrameDocuments(graph, batches, captured);
return buildFrameDocuments(graph, batches, captured, signal);
}
+80 -46
View File
@@ -4,7 +4,8 @@ import {
type CdpTarget,
cdpTargetKey,
} from "@/browser-driver/frame-graph";
import type { CapturedNode, CapturedViewModel } from "./capture";
import { createCaptureCheckpoint } from "./capture-abort";
import type { CapturedNode } from "./capture-types";
export interface FrameOwnedAxNode {
nodeId: string;
@@ -23,6 +24,17 @@ export interface FrameDocument<T extends FrameOwnedAxNode> extends CdpFrame {
contextScopeId: string;
axNodes: T[];
domNodes: CapturedNode[];
excludedBackendNodeIds?: ReadonlySet<number>;
}
/** Explicit snapshot document data used to join DOM and AX ownership. */
export interface FrameDomInput {
nodes: CapturedNode[];
rootFrameId?: string;
frameNodes?: ReadonlyMap<string, CapturedNode[]>;
frameOwnerBackendNodeIds?: ReadonlyMap<string, number>;
frameParentIds?: ReadonlyMap<string, string>;
frameExcludedBackendNodeIds?: ReadonlyMap<string, ReadonlySet<number>>;
}
interface Ownership {
@@ -47,7 +59,7 @@ function targetBackendKey(target: CdpTarget, backendNodeId: number): string {
function frameList<T extends FrameOwnedAxNode>(
graph: CdpFrameGraph | null,
batches: FrameAxBatch<T>[],
captured: CapturedViewModel,
captured: FrameDomInput,
): CdpFrame[] {
const frames = new Map<string, CdpFrame>();
for (const frame of graph?.frames ?? []) frames.set(frame.frameId, frame);
@@ -70,11 +82,14 @@ function frameList<T extends FrameOwnedAxNode>(
});
}
export function buildFrameDocuments<T extends FrameOwnedAxNode>(
export async function buildFrameDocuments<T extends FrameOwnedAxNode>(
graph: CdpFrameGraph | null,
batches: FrameAxBatch<T>[],
captured: CapturedViewModel,
): FrameDocument<T>[] {
captured: FrameDomInput,
signal?: AbortSignal,
): Promise<FrameDocument<T>[]> {
const checkpoint = createCaptureCheckpoint(signal);
let work = 0;
const frames = frameList(graph, batches, captured);
const frameById = new Map(frames.map((frame) => [frame.frameId, frame]));
const rootFrameId = graph?.rootFrameId ?? captured.rootFrameId ?? frames[0]?.frameId;
@@ -83,54 +98,68 @@ export function buildFrameDocuments<T extends FrameOwnedAxNode>(
const backendOwner = new Map<string, string>();
for (const frame of frames) {
for (const node of domNodesForFrame(frame.frameId)) {
if (work++ % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
backendOwner.set(targetBackendKey(frame.target, node.backendNodeId), frame.frameId);
}
}
const candidates = new Map<string, OwnedCandidate<T>>();
for (const batch of batches) {
const nodeById = new Map(batch.nodes.map((node) => [node.nodeId, node]));
const ownershipByNodeId = new Map<string, Ownership>();
const resolving = new Set<string>();
const resolveOwnership = (node: T): Ownership => {
const cached = ownershipByNodeId.get(node.nodeId);
if (cached) return cached;
if (node.frameId && frameById.has(node.frameId)) {
const ownership = { frameId: node.frameId, strength: 4 };
ownershipByNodeId.set(node.nodeId, ownership);
return ownership;
}
if (typeof node.backendDOMNodeId === "number") {
const frameId = backendOwner.get(
targetBackendKey(batch.frame.target, node.backendDOMNodeId),
);
if (frameId) {
const ownership = { frameId, strength: 3 };
ownershipByNodeId.set(node.nodeId, ownership);
return ownership;
}
}
if (node.parentId && !resolving.has(node.nodeId)) {
const parent = nodeById.get(node.parentId);
if (parent) {
resolving.add(node.nodeId);
const inherited = resolveOwnership(parent);
resolving.delete(node.nodeId);
const ownership = {
frameId: inherited.frameId,
strength: Math.min(2, inherited.strength),
};
ownershipByNodeId.set(node.nodeId, ownership);
return ownership;
}
}
const ownership = { frameId: batch.frame.frameId, strength: 1 };
ownershipByNodeId.set(node.nodeId, ownership);
return ownership;
};
const nodeById = new Map<string, T>();
for (const node of batch.nodes) {
const ownership = resolveOwnership(node);
if (work++ % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
nodeById.set(node.nodeId, node);
}
const ownershipByNodeId = new Map<string, Ownership>();
for (const node of batch.nodes) {
const path: T[] = [];
const visiting = new Set<string>();
let current: T | undefined = node;
let ownership: Ownership = { frameId: batch.frame.frameId, strength: 1 };
while (current) {
if (work++ % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
const cached = ownershipByNodeId.get(current.nodeId);
if (cached) {
ownership = cached;
break;
}
if (visiting.has(current.nodeId)) break;
visiting.add(current.nodeId);
if (current.frameId && frameById.has(current.frameId)) {
ownership = { frameId: current.frameId, strength: 4 };
ownershipByNodeId.set(current.nodeId, ownership);
break;
}
const frameId =
typeof current.backendDOMNodeId === "number"
? backendOwner.get(targetBackendKey(batch.frame.target, current.backendDOMNodeId))
: undefined;
if (frameId) {
ownership = { frameId, strength: 3 };
ownershipByNodeId.set(current.nodeId, ownership);
break;
}
path.push(current);
current = current.parentId ? nodeById.get(current.parentId) : undefined;
}
for (let i = path.length - 1; i >= 0; i--) {
if (work++ % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
ownership = { frameId: ownership.frameId, strength: Math.min(2, ownership.strength) };
ownershipByNodeId.set(path[i].nodeId, ownership);
}
if (!ownershipByNodeId.has(node.nodeId)) ownershipByNodeId.set(node.nodeId, ownership);
const key = targetNodeKey(batch.frame.target, node.nodeId);
const existing = candidates.get(key);
if (!existing || ownership.strength > existing.ownership.strength) {
@@ -144,6 +173,10 @@ export function buildFrameDocuments<T extends FrameOwnedAxNode>(
);
const axNodesByFrame = new Map<string, T[]>();
for (const candidate of candidates.values()) {
if (work++ % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
const { node, target, ownership } = candidate;
const parentFrameId = node.parentId
? ownershipByTargetNode.get(targetNodeKey(target, node.parentId))
@@ -169,5 +202,6 @@ export function buildFrameDocuments<T extends FrameOwnedAxNode>(
contextScopeId: frame.frameId,
axNodes: axNodesByFrame.get(frame.frameId) ?? [],
domNodes: domNodesForFrame(frame.frameId),
excludedBackendNodeIds: captured.frameExcludedBackendNodeIds?.get(frame.frameId),
}));
}
+73
View File
@@ -0,0 +1,73 @@
import type { CdpTarget } from "@/browser-driver/frame-graph";
import {
type FrameProjectionState,
projectSnapshotRect,
snapshotViewportRect,
} from "../geometry/coordinate-types";
import { createCaptureCheckpoint } from "./capture-abort";
import { buildDocumentIndex, type DocumentIndex, type NodeFacts } from "./facts";
import { decodeDocument, type SnapshotDocument } from "./snapshot";
export interface FrameContext {
frameId?: string;
ownerFrameBackendNodeId: number | null;
projection: FrameProjectionState;
target: CdpTarget;
scrollX: number;
scrollY: number;
}
export interface NormalizedDocument {
nodes: NodeFacts[];
index: DocumentIndex;
}
/** Interpret one document using a supplied projection. No live reads or frame scheduling. */
export async function normalizeDocument(
doc: SnapshotDocument,
strings: string[],
context: FrameContext,
signal?: AbortSignal,
): Promise<NormalizedDocument> {
const decoded = await decodeDocument(doc, strings, signal);
const checkpoint = createCaptureCheckpoint(signal);
const nodes: NodeFacts[] = [];
for (let i = 0; i < decoded.nodes.length; i++) {
if (i % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
const node = decoded.nodes[i];
const input = snapshotViewportRect(
node.layout?.bounds ?? [],
{ target: context.target, frameId: context.frameId },
{ x: context.scrollX, y: context.scrollY },
);
const local = input?.rect;
const rect =
input && context.projection.status === "available"
? projectSnapshotRect(input, context.projection.projection)
: null;
const visibility = node.layout?.styles.visibility || "visible";
const opacity = node.layout?.styles.opacity || "1";
nodes.push({
...node,
...(context.frameId ? { frameId: context.frameId } : {}),
ownerFrameBackendNodeId: context.ownerFrameBackendNodeId,
localRect: local ? { x: local.x, y: local.y, w: local.width, h: local.height } : null,
rect: rect ? { x: rect.x, y: rect.y, w: rect.width, h: rect.height } : null,
rendered:
!!local &&
visibility !== "hidden" &&
visibility !== "collapse" &&
(Number.parseFloat(opacity) || 0) > 0,
});
}
const index = await buildDocumentIndex(nodes, signal);
return {
nodes: nodes.filter(
(node) => !node.tag.startsWith("#") && !index.excludedBackendNodeIds.has(node.backendNodeId),
),
index,
};
}
@@ -2,7 +2,10 @@ import type { Rect, RenderedRef, VomResult } from "@browser-skill/vom";
import type { CdpTarget } from "@/browser-driver/frame-graph";
import { readRecordingDocumentIdentity } from "@/shared/recording-document-identity";
import type { CapturedSurfaceProbe } from "./capture";
import type { CapturedFrameDocument, FrameAxNode } from "./frame-capture";
import type {
FrameDocument as CapturedFrameDocument,
FrameOwnedAxNode as FrameAxNode,
} from "./frame-document";
/** Frame identity needed to resolve an `@eN` that lives in an iframe. */
export interface CaptureVomFrame {
@@ -61,8 +61,9 @@ export function buildSemanticGraph(input: BuildSemanticGraphInput): SemanticGrap
dom,
sourceOrder: index,
excluded:
document.frameId === rootFrameId &&
input.excludedBackendNodeIds?.has(dom.backendNodeId) === true,
document.excludedBackendNodeIds?.has(dom.backendNodeId) === true ||
(document.frameId === rootFrameId &&
input.excludedBackendNodeIds?.has(dom.backendNodeId) === true),
};
nodes.set(id, node);
frameNodeIds.push(id);
@@ -90,9 +91,10 @@ export function buildSemanticGraph(input: BuildSemanticGraphInput): SemanticGrap
ax,
sourceOrder: document.domNodes.length + index,
excluded:
document.frameId === rootFrameId &&
typeof ax.backendDOMNodeId === "number" &&
input.excludedBackendNodeIds?.has(ax.backendDOMNodeId) === true,
(document.excludedBackendNodeIds?.has(ax.backendDOMNodeId) === true ||
(document.frameId === rootFrameId &&
input.excludedBackendNodeIds?.has(ax.backendDOMNodeId) === true)),
});
frameNodeIds.push(id);
}
+224
View File
@@ -0,0 +1,224 @@
import { createCaptureCheckpoint } from "./capture-abort";
import type { CapturedNode } from "./capture-types";
import type { DecodedDocument, DecodedNode } from "./facts";
export const REQUESTED_STYLES = [
"position",
"pointer-events",
"cursor",
"visibility",
"opacity",
] as const;
const STYLE_COL = Object.fromEntries(
REQUESTED_STYLES.map((name, index) => [name, index]),
) as Record<(typeof REQUESTED_STYLES)[number], number>;
/** Sparse array format Chrome uses for infrequently-set per-node fields. */
interface SparseArray {
index: number[];
value: number[];
}
interface RareBooleanData {
index: number[];
}
export interface SnapshotDocument {
frameId?: string | number;
scrollOffsetX?: number;
scrollOffsetY?: number;
nodes?: {
parentIndex?: number[];
nodeName?: number[];
nodeType?: number[];
backendNodeId?: number[];
attributes?: number[][];
/**
* Per-node text value (index into strings), set for `#text` / CDATA nodes.
* Element nodes carry -1. Same length as `backendNodeId`.
*/
nodeValue?: number[];
/** Maps node array index → index into `documents[]` for frame content. */
contentDocumentIndex?: SparseArray;
inputValue?: SparseArray;
textValue?: SparseArray;
inputChecked?: RareBooleanData;
optionSelected?: RareBooleanData;
};
layout?: {
nodeIndex?: number[];
styles?: number[][];
bounds?: number[][];
paintOrders?: number[];
};
}
export function snapshotFrameId(document: SnapshotDocument, strings: string[]): string | undefined {
if (typeof document.frameId === "string") return document.frameId || undefined;
if (typeof document.frameId === "number") return str(strings, document.frameId) || undefined;
return undefined;
}
export interface SnapshotReply {
strings?: string[];
documents?: SnapshotDocument[];
}
function isSensitiveFormControl(node: Pick<CapturedNode, "tag" | "attrs">): boolean {
return node.tag === "input" && (node.attrs.type ?? "").toLowerCase() === "password";
}
function snapshotFormState(
value: string | undefined,
defaultValue: string,
hasDefaultValue: boolean,
sensitive: boolean,
): CapturedNode["formState"] {
if (sensitive) {
if (value === undefined && !hasDefaultValue) return undefined;
return (value ?? defaultValue) === "" ? "empty" : "filled";
}
if (value === undefined) return undefined;
if (value === "") return "empty";
return value === defaultValue ? "default" : "filled";
}
function str(strings: string[], idx: number | undefined): string {
if (idx === undefined || idx < 0) return "";
return strings[idx] ?? "";
}
export function sparseIndexMap(sparse: SparseArray | undefined): Map<number, number> {
const out = new Map<number, number>();
if (!sparse?.index || !sparse.value) return out;
for (let i = 0; i < sparse.index.length; i++) {
const nodeIndex = sparse.index[i];
const docIndex = sparse.value[i];
if (nodeIndex !== undefined && docIndex !== undefined) out.set(nodeIndex, docIndex);
}
return out;
}
export async function decodeDocument(
doc: SnapshotDocument,
strings: string[],
signal?: AbortSignal,
): Promise<DecodedDocument> {
const checkpoint = createCaptureCheckpoint(signal);
const dn = doc.nodes;
const dl = doc.layout;
if (!dn?.backendNodeId) {
return { nodes: [] };
}
const count = dn.backendNodeId.length;
const layoutByNode = new Map<number, number>();
for (let i = 0; i < (dl?.nodeIndex?.length ?? 0); i++) {
if (i % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
layoutByNode.set(dl!.nodeIndex![i], i);
}
const inputValues = sparseIndexMap(dn.inputValue);
const textValues = sparseIndexMap(dn.textValue);
const checkedInputs = new Set(dn.inputChecked?.index ?? []);
const selectedOptions = new Set(dn.optionSelected?.index ?? []);
// Collect visible text from #text child nodes so element CapturedNodes
// carry a textContent value usable as a button/link label fallback.
// nodeValue is a parallel array: string index for text nodes, -1 otherwise.
const nodeTextContent = new Map<number, string[]>();
if (dn.nodeValue) {
for (let n = 0; n < count; n++) {
if (n % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
const nvIdx = dn.nodeValue[n] ?? -1;
if (nvIdx < 0) continue;
const text = str(strings, nvIdx).trim();
if (!text) continue;
const parentIdx = dn.parentIndex?.[n] ?? -1;
if (parentIdx >= 0) {
const existing = nodeTextContent.get(parentIdx);
if (existing) existing.push(text);
else nodeTextContent.set(parentIdx, [text]);
}
}
}
// Decode fields without assigning a coordinate projection or semantic policy.
const nodes: DecodedNode[] = [];
for (let n = 0; n < count; n++) {
if (n % 256 === 0) {
const pending = checkpoint();
if (pending) await pending;
}
const backendNodeId = dn.backendNodeId[n];
const parentIdx = dn.parentIndex?.[n] ?? -1;
const parentBackendNodeId = parentIdx >= 0 ? (dn.backendNodeId[parentIdx] ?? null) : null;
const tag = str(strings, dn.nodeName?.[n]).toLowerCase();
const attrs: Record<string, string> = {};
const pairs = dn.attributes?.[n] ?? [];
for (let a = 0; a + 1 < pairs.length; a += 2) {
attrs[str(strings, pairs[a]).toLowerCase()] = str(strings, pairs[a + 1]);
}
const li = layoutByNode.get(n);
const styleRow = li === undefined ? [] : (dl?.styles?.[li] ?? []);
const styles: Record<string, string> = {};
for (const name of REQUESTED_STYLES) styles[name] = str(strings, styleRow[STYLE_COL[name]]);
const layout =
li === undefined
? undefined
: {
boundsSpace: "snapshot-document-css" as const,
bounds: dl?.bounds?.[li],
styles,
};
const textContent = nodeTextContent.get(n)?.join(" ");
const rawFormValueIndex = tag === "textarea" ? textValues.get(n) : inputValues.get(n);
const rawFormValue =
rawFormValueIndex !== undefined ? str(strings, rawFormValueIndex) : undefined;
const sensitive = isSensitiveFormControl({ tag, attrs });
const formDefaultValue = attrs.value ?? "";
const formValue = sensitive ? undefined : rawFormValue;
const formState = snapshotFormState(
rawFormValue,
formDefaultValue,
Object.prototype.hasOwnProperty.call(attrs, "value"),
sensitive,
);
if (sensitive) delete attrs.value;
nodes.push({
backendNodeId,
nodeType: dn.nodeType?.[n],
parentBackendNodeId,
tag,
attrs,
layout,
paintOrder: li === undefined ? 0 : (dl?.paintOrders?.[li] ?? 0),
position: styles.position || "static",
pointerEvents: styles["pointer-events"] || "auto",
cursor: styles.cursor || "auto",
textContent,
...(formValue !== undefined ? { formValue } : {}),
...(tag === "input" || tag === "textarea"
? {
formPlaceholder: attrs.placeholder ?? "",
...(!sensitive ? { formDefaultValue } : {}),
...(formState ? { formState } : {}),
}
: {}),
...(checkedInputs.has(n) ? { formValue: "true", formState: "filled" } : {}),
...(selectedOptions.has(n) ? { formValue: attrs.value ?? textContent ?? "" } : {}),
});
}
return { nodes };
}
+103 -6
View File
@@ -73,6 +73,14 @@ where
P: Serialize + Send + 'static,
R: DeserializeOwned + Send + 'static,
{
let parent_cancel = stdin_cancellation();
if parent_cancel.as_ref().is_some_and(|rx| *rx.borrow()) {
return Err(CliError::from_rpc(RpcError {
code: ErrorCode::Cancelled,
message: "parent closed the cancellation pipe".into(),
data: Some(serde_json::json!({"reason": "cancelled_before_dispatch"})),
}));
}
let rpc_id: RpcId = format!("{}-{}", rpc_id_prefix, random_short_id());
let mut client = IpcClient::connect(sock.clone()).await?;
let rpc_id_for_call = rpc_id.clone();
@@ -88,16 +96,16 @@ where
let outcome = tokio::select! {
biased;
res = &mut main_fut => res?,
sig = wait_for_sigint() => {
sig.context("install SIGINT handler").map_err(CliError::Local)?;
debug!(rpc_id = %rpc_id_for_cancel, "SIGINT: forwarding cancel to daemon");
sig = wait_for_cancel(parent_cancel) => {
sig.context("wait for cancellation").map_err(CliError::Local)?;
debug!(rpc_id = %rpc_id_for_cancel, "forwarding cancel to daemon");
let _ = send_cancel(&sock, &rpc_id_for_cancel).await;
match tokio::time::timeout(CANCEL_RESPONSE_GRACE, &mut main_fut).await {
Ok(res) => res?,
Err(_) => {
debug!(
rpc_id = %rpc_id_for_cancel,
"SIGINT: cancel grace elapsed; synthesising cancelled error"
"cancel grace elapsed; synthesising cancelled error"
);
return Err(CliError::from_rpc(RpcError {
code: ErrorCode::Cancelled,
@@ -112,6 +120,46 @@ where
outcome.map_err(CliError::from_rpc)
}
/// Release caller-owned staging even after cancellation. This deliberately
/// exposes only transfer.release, not a general bypass for business RPCs.
/// The entire batch, including connection setup, shares one bounded budget.
pub fn release_transfers<'a>(
sock: &Path,
transfer_ids: impl IntoIterator<Item = &'a str>,
) -> Result<(), CliError> {
use bsk_protocol::tools::{TransferIdParams, TransferReleaseResult};
const CLEANUP_TIMEOUT: Duration = Duration::from_secs(5);
let ids: Vec<_> = transfer_ids.into_iter().collect();
if ids.is_empty() {
return Ok(());
}
let rt = tokio::runtime::Builder::new_current_thread()
.enable_all()
.build()
.context("build runtime for transfer cleanup")?;
rt.block_on(async {
tokio::time::timeout(CLEANUP_TIMEOUT, async {
let mut client = IpcClient::connect(sock).await?;
for id in ids {
client
.call::<_, TransferReleaseResult>(
"transfer-release",
Method::TransferRelease,
Some(TransferIdParams {
transfer_id: id.to_string(),
}),
CLEANUP_TIMEOUT,
)
.await?
.map_err(CliError::from_rpc)?;
}
Ok::<_, CliError>(())
})
.await
.context("transfer cleanup exceeded its total time budget")?
})
}
/// Send a `cancel { rpc_id }` frame over a fresh connection so it
/// lands on the daemon while the original call is still parked.
///
@@ -146,8 +194,57 @@ fn random_short_id() -> String {
bytes.iter().map(|b| format!("{b:02x}")).collect()
}
/// Wait for either Ctrl-C or process SIGTERM. Returning here means
/// the user has asked us to stop.
/// Opt-in control pipe for parent processes that cannot send Ctrl-C (Node on
/// Windows). One reader survives the short-lived runtimes used by multi-RPC
/// commands such as upload. Ordinary CLI stdin and terminal Ctrl-C are unchanged.
fn stdin_cancellation() -> Option<tokio::sync::watch::Receiver<bool>> {
if std::env::var("BSK_CANCEL_ON_STDIN_CLOSE").as_deref() != Ok("1") {
return None;
}
static CANCEL: std::sync::OnceLock<tokio::sync::watch::Receiver<bool>> =
std::sync::OnceLock::new();
Some(
CANCEL
.get_or_init(|| {
let (tx, rx) = tokio::sync::watch::channel(false);
std::thread::spawn(move || {
use std::io::Read;
let mut stdin = std::io::stdin().lock();
let mut buf = [0; 64];
loop {
match stdin.read(&mut buf) {
Ok(0) => break,
Ok(_) => {}
Err(err) if err.kind() == std::io::ErrorKind::Interrupted => continue,
Err(_) => break,
}
}
let _ = tx.send(true);
});
rx
})
.clone(),
)
}
async fn wait_for_cancel(
parent_cancel: Option<tokio::sync::watch::Receiver<bool>>,
) -> anyhow::Result<()> {
let parent_closed = async move {
match parent_cancel {
Some(mut rx) => {
let _ = rx.wait_for(|closed| *closed).await;
}
None => std::future::pending::<()>().await,
}
};
tokio::select! {
result = wait_for_sigint() => result,
_ = parent_closed => Ok(()),
}
}
/// Wait for terminal Ctrl-C.
async fn wait_for_sigint() -> anyhow::Result<()> {
tokio::signal::ctrl_c().await.context("listen for SIGINT")?;
Ok(())
+2 -9
View File
@@ -9,8 +9,7 @@ use anyhow::Context;
use base64::Engine;
use bsk_protocol::Method;
use bsk_protocol::tools::{
DownloadParams, DownloadResult, TransferChunkParams, TransferChunkResult, TransferIdParams,
TransferReleaseResult,
DownloadParams, DownloadResult, TransferChunkParams, TransferChunkResult,
};
use clap::Args;
use uuid::Uuid;
@@ -70,13 +69,7 @@ pub fn dispatch(args: DownloadArgs, format: Format) -> Result<(), CliError> {
CliError::Local(anyhow::anyhow!("daemon returned no download transfer id"))
})?;
let write_result = write_transfer(&info.sock_path, &transfer_id, &args.out, args.overwrite);
let _: Result<TransferReleaseResult, CliError> = crate::cli::business_rpc::call(
info.sock_path,
"transfer-release",
Method::TransferRelease,
Some(TransferIdParams { transfer_id }),
Duration::from_secs(5),
);
let _ = crate::cli::business_rpc::release_transfers(&info.sock_path, [transfer_id.as_str()]);
write_result?;
match format {
Format::Json => {
+48 -51
View File
@@ -10,8 +10,7 @@ use base64::Engine;
use bsk_protocol::Method;
use bsk_protocol::tools::{
TransferBeginParams, TransferBeginResult, TransferChunkParams, TransferChunkResult,
TransferIdParams, TransferReadyResult, TransferReleaseResult, UploadFile, UploadMode,
UploadParams, UploadResult,
TransferIdParams, TransferReadyResult, UploadFile, UploadMode, UploadParams, UploadResult,
};
use clap::{Args, ValueEnum};
@@ -69,14 +68,12 @@ pub fn dispatch(args: UploadArgs, format: Format) -> Result<(), CliError> {
let (ref_, selector) = split_target(args.target, args.ref_, args.selector)?;
let mut staged = Vec::new();
for path in &args.files {
match stage_file(&info.sock_path, &args.session, path) {
Ok(file) => staged.push(file),
Err(err) => {
for (id, _) in &staged {
let _ = release(&info.sock_path, id);
}
return Err(err);
}
if let Err(err) = stage_file(&info.sock_path, &args.session, path, &mut staged) {
let _ = crate::cli::business_rpc::release_transfers(
&info.sock_path,
staged.iter().map(|(id, _)| id.as_str()),
);
return Err(err);
}
}
let params = UploadParams {
@@ -102,6 +99,17 @@ pub fn dispatch(args: UploadArgs, format: Format) -> Result<(), CliError> {
Some(params),
ipc_timeout(args.timeout),
);
// The helper can reject cancellation before handing any request to the
// daemon. In that case staging still belongs to this CLI.
if result.as_ref().is_err_and(|err| {
err.data()
.is_some_and(|data| data["reason"] == "cancelled_before_dispatch")
}) {
let _ = crate::cli::business_rpc::release_transfers(
&info.sock_path,
staged.iter().map(|(id, _)| id.as_str()),
);
}
// Once tool.upload is dispatched, staging ownership belongs to the
// session. A transport timeout cannot prove that Chrome did not attach
// the file, so releasing here could invalidate a late successful attach.
@@ -118,7 +126,12 @@ pub fn dispatch(args: UploadArgs, format: Format) -> Result<(), CliError> {
Ok(())
}
fn stage_file(sock: &Path, session: &str, path: &PathBuf) -> Result<(String, String), CliError> {
fn stage_file(
sock: &Path,
session: &str,
path: &PathBuf,
staged: &mut Vec<(String, String)>,
) -> Result<(), CliError> {
let mut file = File::open(path)
.with_context(|| format!("open upload file {}", path.display()))
.map_err(CliError::Local)?;
@@ -149,55 +162,39 @@ fn stage_file(sock: &Path, session: &str, path: &PathBuf) -> Result<(String, Str
}),
Duration::from_secs(10),
)?;
let staged = (|| {
let mut offset = 0u64;
let mut buf = vec![0u8; begin.chunk_size as usize];
loop {
let n = file.read(&mut buf).map_err(|e| CliError::Local(e.into()))?;
if n == 0 {
break;
}
let reply: TransferChunkResult = crate::cli::business_rpc::call(
sock.to_path_buf(),
"transfer-chunk",
Method::TransferChunk,
Some(TransferChunkParams {
transfer_id: begin.transfer_id.clone(),
offset,
data_base64: base64::engine::general_purpose::STANDARD.encode(&buf[..n]),
}),
Duration::from_secs(30),
)?;
offset = reply.next_offset;
// Record ownership immediately so one error path releases both completed
// files and the current partially staged file.
staged.push((begin.transfer_id.clone(), name));
let mut offset = 0u64;
let mut buf = vec![0u8; begin.chunk_size as usize];
loop {
let n = file.read(&mut buf).map_err(|e| CliError::Local(e.into()))?;
if n == 0 {
break;
}
let _: TransferReadyResult = crate::cli::business_rpc::call(
let reply: TransferChunkResult = crate::cli::business_rpc::call(
sock.to_path_buf(),
"transfer-finish",
Method::TransferFinish,
Some(TransferIdParams {
"transfer-chunk",
Method::TransferChunk,
Some(TransferChunkParams {
transfer_id: begin.transfer_id.clone(),
offset,
data_base64: base64::engine::general_purpose::STANDARD.encode(&buf[..n]),
}),
Duration::from_secs(10),
Duration::from_secs(30),
)?;
Ok::<_, CliError>(())
})();
if let Err(err) = staged {
let _ = release(sock, &begin.transfer_id);
return Err(err);
offset = reply.next_offset;
}
Ok((begin.transfer_id, name))
}
fn release(sock: &Path, id: &str) -> Result<TransferReleaseResult, CliError> {
crate::cli::business_rpc::call(
let _: TransferReadyResult = crate::cli::business_rpc::call(
sock.to_path_buf(),
"transfer-release",
Method::TransferRelease,
"transfer-finish",
Method::TransferFinish,
Some(TransferIdParams {
transfer_id: id.to_string(),
transfer_id: begin.transfer_id.clone(),
}),
Duration::from_secs(5),
)
Duration::from_secs(10),
)?;
Ok(())
}
fn ipc_timeout(timeout_ms: u32) -> Duration {
@@ -0,0 +1,342 @@
//! Real Windows CLI cancellation, including caller-owned transfer cleanup.
#![cfg(windows)]
use std::path::Path;
use std::sync::{Arc, Mutex};
use std::time::{Duration, Instant};
use bsk::daemon::{file_transfer::TransferRegistry, info::DaemonInfo};
use bsk_protocol::tools::{TransferBeginParams, TransferIdParams};
use bsk_protocol::{ErrorCode, Frame, Method, ResponseBody, ResponseFrame, RpcError};
use serde_json::json;
use tokio::io::{AsyncBufReadExt, AsyncWriteExt, BufReader};
use tokio::net::windows::named_pipe::ServerOptions;
use tokio::process::Command;
use tokio::sync::{Notify, watch};
fn response<T: serde::Serialize>(result: Result<T, RpcError>) -> ResponseBody {
match result {
Ok(value) => ResponseBody::Ok(serde_json::to_value(value).unwrap()),
Err(err) => ResponseBody::Err(err),
}
}
#[test]
fn stdin_close_cancels_business_but_releases_resources_with_a_bounded_budget() {
// Resolve the production registry's root before starting any runtime threads.
let registry_home = tempfile::tempdir().unwrap();
let original_home = std::env::var_os("BSK_HOME");
unsafe {
std::env::set_var("BSK_HOME", registry_home.path());
}
let transfers = Arc::new(TransferRegistry::new().unwrap());
unsafe {
match original_home {
Some(value) => std::env::set_var("BSK_HOME", value),
None => std::env::remove_var("BSK_HOME"),
}
}
transfers.initialize().unwrap();
tokio::runtime::Builder::new_current_thread()
.enable_all()
.build()
.unwrap()
.block_on(exercise(
transfers,
&registry_home.path().join("run/transfers"),
));
}
async fn exercise(transfers: Arc<TransferRegistry>, staging_root: &Path) {
for mode in [
"wait",
"upload",
"upload-multi",
"upload-before-dispatch",
"download",
"upload-multi-stall",
"ordinary",
] {
let home = tempfile::tempdir().unwrap();
let pipe_name = format!(r"\\.\pipe\bsk-parent-cancel-{}", uuid::Uuid::new_v4());
let info = DaemonInfo::now(std::process::id(), (&pipe_name).into(), 0, "0.2.0");
std::fs::write(
home.path().join("daemon.json"),
serde_json::to_vec(&info).unwrap(),
)
.unwrap();
let mut pipe = ServerOptions::new()
.first_pipe_instance(true)
.create(&pipe_name)
.unwrap();
let registered = Arc::new(Notify::new());
let pending = Arc::new(Mutex::new(None::<String>));
let ids = Arc::new(Mutex::new(Vec::<String>::new()));
let released = Arc::new(Mutex::new(Vec::<String>::new()));
let received = Arc::new(Mutex::new(Vec::<Method>::new()));
let download_id = if mode == "download" {
let staging = transfers.begin_download("fixture").unwrap();
let browser_dir = home.path().join("BrowserSkill").join(&staging.transfer_id);
std::fs::create_dir_all(&browser_dir).unwrap();
let file = browser_dir.join("download.txt");
std::fs::write(&file, b"download fixture").unwrap();
transfers
.import_download(&staging.transfer_id, &file)
.unwrap();
ids.lock().unwrap().push(staging.transfer_id.clone());
Some(staging.transfer_id)
} else {
None
};
let (cancel, cancelled) = watch::channel(false);
let ready = Arc::clone(&registered);
let name = pipe_name.clone();
let registry = Arc::clone(&transfers);
let server_ids = Arc::clone(&ids);
let server_released = Arc::clone(&released);
let server_received = Arc::clone(&received);
let server = tokio::spawn(async move {
let mut connections = tokio::task::JoinSet::new();
loop {
pipe.connect().await.unwrap();
let next = ServerOptions::new().create(&name).unwrap();
let connection = std::mem::replace(&mut pipe, next);
let ready = Arc::clone(&ready);
let pending = Arc::clone(&pending);
let cancel = cancel.clone();
let mut cancelled = cancelled.clone();
let name = name.clone();
let registry = Arc::clone(&registry);
let ids = Arc::clone(&server_ids);
let released = Arc::clone(&server_released);
let received = Arc::clone(&server_received);
let download_id = download_id.clone();
connections.spawn(async move {
let (read, mut write) = tokio::io::split(connection);
let mut reader = BufReader::new(read);
let mut line = String::new();
while reader.read_line(&mut line).await.unwrap_or(0) > 0 {
let Frame::Request(req) = serde_json::from_str::<Frame>(&line).unwrap()
else {
panic!("expected request");
};
line.clear();
received.lock().unwrap().push(req.method.clone());
let params = req.params.clone().unwrap_or_default();
let body = match req.method {
Method::SystemStatus => ResponseBody::Ok(json!({
"daemon_version": "0.2.0", "protocol_version": "1.1",
"pid": std::process::id(), "uptime_secs": 0,
"ws_port": 0, "sock_path": name,
"browsers": [], "sessions": [], "version_skew_browsers": []
})),
Method::TransferBegin => {
let begin = registry
.begin_upload(serde_json::from_value(params).unwrap())
.unwrap();
ids.lock().unwrap().push(begin.transfer_id.clone());
response(Ok(begin))
}
Method::ToolDownload => ResponseBody::Ok(json!({
"tab_id": 1, "suggested_filename": "download.txt",
"byte_size": 16, "transfer_id": download_id,
})),
Method::ToolWaitMs if mode == "ordinary" => {
ResponseBody::Ok(json!({"waited_ms": 1}))
}
Method::TransferChunk
if mode == "upload-before-dispatch"
|| (mode.contains("multi")
&& ids.lock().unwrap().len() == 1) =>
{
response(
registry.write_chunk(serde_json::from_value(params).unwrap()),
)
}
Method::TransferFinish if mode != "upload-before-dispatch" => response(
registry.finish_upload(serde_json::from_value(params).unwrap()),
),
Method::ToolWaitMs
| Method::TransferChunk
| Method::TransferRead
| Method::TransferFinish => {
*pending.lock().unwrap() = Some(req.id.clone());
ready.notify_one();
cancelled.wait_for(|value| *value).await.unwrap();
if mode == "upload-before-dispatch" {
// Finish won the race with cancellation, but tool.upload must
// not be dispatched and the CLI still owns the staging.
response(
registry
.finish_upload(serde_json::from_value(params).unwrap()),
)
} else {
ResponseBody::Err(RpcError {
code: ErrorCode::Cancelled,
message: "parent cancellation reached daemon".into(),
data: None,
})
}
}
Method::Cancel => {
let target = params["rpc_id"].as_str().unwrap();
assert_eq!(pending.lock().unwrap().as_deref(), Some(target));
cancel.send(true).unwrap();
ResponseBody::Ok(json!({"cancelled": true}))
}
Method::TransferRelease => {
let params: TransferIdParams =
serde_json::from_value(params).unwrap();
released.lock().unwrap().push(params.transfer_id.clone());
if mode.contains("stall") {
std::future::pending::<()>().await;
}
response(Ok(registry.release(params)))
}
other => panic!("unexpected request after cancellation: {other:?}"),
};
let response = Frame::Response(ResponseFrame { id: req.id, body });
let mut bytes = serde_json::to_vec(&response).unwrap();
bytes.push(b'\n');
if write.write_all(&bytes).await.is_err() {
break;
}
}
});
}
});
let mut cmd = Command::new(env!("CARGO_BIN_EXE_bsk"));
cmd.env("BSK_HOME", home.path())
.env("BSK_AUTO_UPDATE", "off")
.env_remove("BSK_CANCEL_ON_STDIN_CLOSE")
.stdout(std::process::Stdio::piped())
.stderr(std::process::Stdio::piped())
.creation_flags(0x0800_0000)
.kill_on_drop(true);
if mode.starts_with("upload") {
let source = home.path().join("upload.txt");
// Declare 300 MiB without allocating or transferring that much data.
std::fs::File::create(&source)
.unwrap()
.set_len(if mode == "upload-before-dispatch" {
16
} else {
300 * 1024 * 1024
})
.unwrap();
cmd.args(["upload", "--session", "fixture", "--selector", "input"]);
if mode.contains("multi") {
let first = home.path().join("first.txt");
std::fs::write(&first, b"first file").unwrap();
cmd.arg("--file").arg(first);
}
cmd.arg("--file").arg(source);
} else if mode == "download" {
let out = home.path().join("out.txt");
std::fs::write(&out, b"existing output").unwrap();
cmd.args([
"download",
"--session",
"fixture",
"--selector",
"a",
"--overwrite",
"--out",
])
.arg(out);
} else {
cmd.args(["wait-ms", if mode == "ordinary" { "1ms" } else { "60s" }]);
}
cmd.arg("--json");
if mode == "ordinary" {
cmd.stdin(std::process::Stdio::null());
} else {
cmd.env("BSK_CANCEL_ON_STDIN_CLOSE", "1")
.stdin(std::process::Stdio::piped());
}
let mut child = cmd.spawn().unwrap();
if mode != "ordinary" {
tokio::time::timeout(Duration::from_secs(10), registered.notified())
.await
.expect("CLI registered business RPC");
child
.stdin
.as_mut()
.unwrap()
.write_all(b"still connected")
.await
.unwrap();
drop(child.stdin.take());
}
let start = Instant::now();
let output = tokio::time::timeout(Duration::from_secs(8), child.wait_with_output())
.await
.expect("CLI must settle promptly, including cleanup")
.unwrap();
server.abort();
let _ = server.await;
assert_eq!(
output.status.code(),
Some(if mode == "ordinary" { 0 } else { 2 }),
"{mode}: stdout={} stderr={}",
String::from_utf8_lossy(&output.stdout),
String::from_utf8_lossy(&output.stderr)
);
if mode != "ordinary" {
let body: serde_json::Value = serde_json::from_slice(&output.stdout).unwrap();
assert_eq!(body["code"], "cancelled");
if mode != "upload-before-dispatch" {
assert_eq!(body["message"], "parent cancellation reached daemon");
}
let received = received.lock().unwrap();
let cancel = received.iter().position(|m| *m == Method::Cancel).unwrap();
assert!(
received[cancel + 1..]
.iter()
.all(|m| *m == Method::TransferRelease),
"only cleanup may follow cancellation: {received:?}"
);
}
let ids = ids.lock().unwrap();
if mode.contains("stall") {
assert_eq!(released.lock().unwrap().len(), 1);
assert!(start.elapsed() >= Duration::from_secs(4));
// The CLI cannot force an unresponsive daemon to clean up.
transfers.release_session("fixture");
} else {
assert_eq!(
*released.lock().unwrap(),
*ids,
"{mode}: every allocation must be released"
);
for id in ids.iter() {
assert!(!staging_root.join(id).exists(), "staging leaked: {id}");
}
if mode.starts_with("upload") {
let retry = transfers
.begin_upload(TransferBeginParams {
session_id: "fixture".into(),
name: "retry.txt".into(),
byte_size: 300 * 1024 * 1024,
})
.expect("same session must have room for another 300 MiB upload");
transfers.release(TransferIdParams {
transfer_id: retry.transfer_id,
});
}
}
if mode == "download" {
assert_eq!(
std::fs::read(home.path().join("out.txt")).unwrap(),
b"existing output"
);
assert!(
!std::fs::read_dir(home.path())
.unwrap()
.flatten()
.any(|entry| entry.file_name().to_string_lossy().ends_with(".part"))
);
}
}
}
+41 -15
View File
@@ -21,6 +21,7 @@ $ErrorActionPreference = "Stop"
$Repo = if ($env:BSK_REPO) { $env:BSK_REPO } else { "Tencent/BrowserSkill" }
$InstallDir = if ($env:BSK_INSTALL_DIR) { $env:BSK_INSTALL_DIR } else { Join-Path $HOME ".local\bin" }
$InstallDir = $ExecutionContext.SessionState.Path.GetUnresolvedProviderPathFromPSPath($InstallDir)
$GitHub = "https://github.com/${Repo}"
function Write-Log {
@@ -64,7 +65,7 @@ function Get-PlatformTriple {
function Add-ToUserPath {
param([string]$Dir)
$currentUserPath = [Environment]::GetEnvironmentVariable("PATH", "User") -split ";" | Where-Object { $_ }
$currentUserPath = @([Environment]::GetEnvironmentVariable("PATH", "User") -split ";" | Where-Object { $_ })
if ($currentUserPath -contains $Dir) {
Write-Log "$Dir is already in your user PATH"
@@ -90,30 +91,59 @@ function Add-ToSessionPath {
# ── Git Bash (bash environment) PATH helper ──────────────────────────────────
function Add-ToBashProfile {
param([string]$Dir)
param([string]$Dir, [string]$BashRc = (Join-Path $HOME ".bashrc"))
# Convert Windows path (e.g. C:\Users\foo\.local\bin) to Git-Bash Unix-style (/c/Users/foo/.local/bin)
$unixPath = $Dir -replace '\\', '/'
if ($unixPath -match '^([A-Z]):(.*)$') {
$unixPath = '/' + $matches[1].ToLower() + $matches[2]
}
$bashRc = Join-Path $HOME ".bashrc"
$exportLine = "export PATH=""${unixPath}:`$PATH"" # bsk CLI"
# Single-quote the literal directory; only the existing PATH is expanded.
$shellQuote = "'" + [char]34 + "'" + [char]34 + "'"
$quotedPath = "'" + $unixPath.Replace("'", $shellQuote) + "'"
$exportLine = "export PATH=${quotedPath}:`"`$PATH`" # bsk CLI"
if (Test-Path $bashRc) {
$content = Get-Content $bashRc -Raw -ErrorAction SilentlyContinue
if ($content -match [regex]::Escape($unixPath)) {
if (Test-Path -LiteralPath $BashRc) {
$content = [System.IO.File]::ReadAllText($BashRc)
if ($content.Contains($exportLine)) {
Write-Log "$unixPath is already in ~/.bashrc"
return
}
}
Add-Content $bashRc "`n$exportLine" -Encoding ASCII
# Explicit BOM-less UTF-8 also works in Windows PowerShell 5.1.
[System.IO.File]::AppendAllText($BashRc, "`n$exportLine`n", (New-Object System.Text.UTF8Encoding($false)))
Write-Log "added ${unixPath} to ~/.bashrc"
}
# ── Main ──────────────────────────────────────────────────────────────────────
# Stage on the destination volume before stopping the daemon. Never truncate
# the installed executable: failed replacement must leave it usable.
function Install-Binary {
param([string]$Source, [string]$Target)
$staged = "$Target.install-$([Guid]::NewGuid().ToString('N'))"
try {
[System.IO.File]::Copy($Source, $staged)
if ([System.IO.File]::Exists($Target)) {
# Use the downloaded CLI: older versions have broken Windows
# liveness checks. Stop verifies daemon identity before terminating it.
& $Source daemon stop
if ($LASTEXITCODE -ne 0) { throw "could not stop bsk daemon; existing installation was not replaced" }
# PowerShell 5.1 converts $null to an empty path for string parameters.
[System.IO.File]::Replace($staged, $Target, [NullString]::Value)
Write-Log "daemon will restart automatically on the next browser command"
}
else {
[System.IO.File]::Move($staged, $Target)
}
}
finally {
if ([System.IO.File]::Exists($staged)) { [System.IO.File]::Delete($staged) }
}
}
function Main {
$platform = Get-PlatformTriple
@@ -184,7 +214,7 @@ function Main {
New-Item -ItemType Directory -Path $InstallDir -Force | Out-Null
}
Copy-Item -Path (Join-Path $tempDir "bsk.exe") -Destination (Join-Path $InstallDir "bsk.exe") -Force
Install-Binary -Source (Join-Path $tempDir "bsk.exe") -Target (Join-Path $InstallDir "bsk.exe")
Write-Log "installed bsk to $InstallDir\bsk.exe"
@@ -199,12 +229,8 @@ function Main {
# Verify
$bskPath = Join-Path $InstallDir "bsk.exe"
if (Get-Command bsk -ErrorAction SilentlyContinue) {
& bsk --version
}
else {
Write-Log "verify install: & ""$bskPath"" --version"
}
& $bskPath --version
if ($LASTEXITCODE -ne 0) { throw "installed bsk failed verification" }
Write-Log "done"
Write-Host ""
+138 -154
View File
@@ -1,13 +1,51 @@
# dsh-plugin-browserskill
# BrowserSkill for DeepSeek Harness
npm: [`@wxg-prc-cpg/browser-skill-dsh-plugin`](https://www.npmjs.com/package/@wxg-prc-cpg/browser-skill-dsh-plugin)
[![npm version](https://img.shields.io/npm/v/@wxg-prc-cpg/browser-skill-dsh-plugin)](https://www.npmjs.com/package/@wxg-prc-cpg/browser-skill-dsh-plugin)
A [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) (dsh) tool plugin that exposes
[BrowserSkill](https://github.com/Tencent/BrowserSkill) (`bsk`) browser automation to the model.
Use [BrowserSkill](https://github.com/Tencent/BrowserSkill) in
[DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) (`dsh`) to browse
websites, fill forms, and capture screenshots through native `browser_*` tools.
Browser tasks run in Agent Windows, with a live view in the dsh Web UI.
Each action maps to one `bsk <cmd> --json` invocation: the plugin spawns the bsk CLI, parses its
structured JSON output, and returns a canonical typed value. The bsk daemon, browser, and browser
extension keep owning the actual browser control — this package is a thin, well-typed bridge.
## Installation
Before installing the plugin:
- Install [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) and
[pnpm](https://pnpm.io/installation), which dsh uses to manage plugins.
- Install the `bsk` CLI and connect the BrowserSkill extension in Chrome or Edge.
Follow the [BrowserSkill setup guide](https://github.com/Tencent/BrowserSkill#quick-start).
- Make sure `bsk` is on the `PATH` used to start dsh, or set `bskPath` in the plugin configuration.
Install the plugin into the `web` profile, then start it:
```sh
dsh plugin --profile web add @wxg-prc-cpg/browser-skill-dsh-plugin
dsh --profile web
```
Replace `web` with your profile name if you use a different profile. The plugin
includes the `browser-skill` skill; no separate `bsk install-skill` step is needed.
In a conversation, try:
```text
/browser-skill open example.com and summarize the page.
```
By default, the browser tools become available when the skill is invoked.
## Updating
Installed plugins do not update automatically. To upgrade this plugin to npm's
`latest` version, including versions outside the profile's saved dependency range:
```sh
dsh plugin --profile web update @wxg-prc-cpg/browser-skill-dsh-plugin --latest
```
Restart that dsh profile after upgrading. This command updates the plugin; update
the `bsk` CLI and browser extension separately when a release requires it.
## Tools
@@ -20,23 +58,7 @@ extension keep owning the actual browser control — this package is a thin, wel
| `browser_tabs` | `list`, `create`, `select`, `close`, `borrow`, `return` | Manage Agent Window tabs and temporarily borrow user tabs. |
| `browser_assist` | `resize`, `emulate`, `request-help` | Resize or emulate the browser and pause for human-only steps. |
`bsk evaluate` and `bsk record` are intentionally not exposed by this plugin: arbitrary page
evaluation is a higher-risk capability, while recording is long-running and needs a dedicated
DeepSeek Harness lifecycle before it can be added safely.
## Agent skill (progressive disclosure)
Beyond the tools, the plugin publishes the **`browser-skill` agent skill** through the harness's
official skill seam (`ctx.skills.register`): the catalog entry (name + routing description) is
resident in `<available_skills>`, and the body is loaded only when the model invokes the `skill`
tool. Its single source is the DSH-specific `skill/SKILL.md`, which documents only structured
`browser_*` calls and their plugin semantics. The repository-root CLI skill is intentionally not
concatenated: its command examples belong to a different execution interface and would bypass
the plugin's ownership, live observation UI, cancellation, and cleanup path if followed directly.
The build rejects internal CLI-name leakage, command-line code blocks, unknown browser tools, and
missing supported browser tools before embedding the Markdown. Registration and every pre-step
catalog snapshot are pure in-memory reads (no disk/process/daemon); compositions without the skill
seam degrade silently.
Arbitrary page-script evaluation and interaction recording are not supported.
## Multi-session model
@@ -55,136 +77,73 @@ an explicit `session` argument naming a foreign or unknown id is rejected, the `
`browser_session` shows plugin-created sessions only (no daemon-wide view), and stop/unload cleanup
can never touch a session owned by another program.
## Installation
The plugin follows the standard dsh bundle layout (`dsh.bundle` manifest + `cordis.patch.yml`):
```sh
dsh plugin --profile <name> add @wxg-prc-cpg/browser-skill-dsh-plugin
dsh --profile <name>
```
Prerequisite: the `bsk` CLI must be installed and on `PATH`, and the BrowserSkill browser extension
(Chrome or Edge) must be connected — see the
[BrowserSkill README](https://github.com/Tencent/BrowserSkill). When bsk is missing, tool calls fail
with install guidance instead of a bare spawn error.
## Configuration
All fields are optional and validated through the plugin's Schemastery `Config`:
After installing the plugin, edit your profile's `cordis.patch.yml`. For the `web`
profile, the default location is `~/.dsh/profiles/web/cordis.patch.yml`. If you set
`DSH_HOME`, use `$DSH_HOME/profiles/web/cordis.patch.yml` instead. Replace `web` with
your profile name as needed.
If the file contains only comments and `[]`, keep the comments and replace `[]`
with the YAML below. If it already contains patch entries, add this entry to the
existing list or edit its existing `id: browserskill` entry. Keep a single
top-level YAML list. This overrides the plugin registered by the installed bundle:
```yaml
# cordis.patch.yml override example
- insert:
- id: browserskill
name: "@wxg-prc-cpg/browser-skill-dsh-plugin"
config:
bskPath: bsk # path to the bsk binary (default: resolve from PATH)
defaultTimeoutMs: 120000
maxSessions: 5
# observationEnabled: true # live PiP/overlay observation (below)
# thumbnailIntervalMs: 1500 # frame cadence while a session is active
# idleIntervalMs: 8000 # idle cadence / recent-activity window
# lazyTools: true # reveal browser_* tools only after the skill is invoked
- id: browserskill
config:
bskPath: bsk
defaultTimeoutMs: 120000
maxSessions: 5
observationEnabled: true
thumbnailIntervalMs: 1500
idleIntervalMs: 8000
lazyTools: true
```
- **`lazyTools` (default `true`)** — the final progressive-disclosure stage: the six
`browser_*` tool schemas stay OUT of the system prompt (zero schema tokens) until the
`browser-skill` skill is actually invoked — the skill catalog entry is the only
advertisement. One successful invocation (model tool call, or a `/browser-skill` user
gesture) registers the whole suite for the rest of the process; repeated invocations are
no-ops, and sessions resumed with a past invocation in their durable log reveal the suite
on entry. Set `false` for the legacy always-on registration.
Change `bskPath` to the full path of your CLI binary if it is not on dsh's `PATH`.
A patch replaces the entry's entire `config` object, so keep all overrides you need
together in that object.
## Observation overlay (PiP mini-window)
Configuration changes follow `dsh.profile.patchReload` in the profile's
`package.json`: `live` (the default for `web`) applies changes when you save the
patch file; `startup` requires restarting the profile. Restart after upgrading
the plugin in either case.
When the plugin runs inside the dsh Web UI, an **observation overlay** floats over the app
(registered into the `shell.overlay` seat): a breathing thumbnail per owned session plus its
current action and elapsed time. The card docks at the top-right of the content area (clear of
the composer and the shell's header controls) and wears the **BrowserSkill product family's own
look**: the overlay reuses `@browser-skill/ui` components (`Button`, `cn`) and its oklch design
tokens (`--card`, `--primary`, `--destructive`, `--ring`, …), status dots spec'd after the
extension popup's connection indicator, and Remix icons. The BSK utility sheet is compiled
scoped under the `.bsk-obs` root class (`scripts/build-client-css.mjs`), so the overlay looks
like the BrowserSkill extension without leaking a single selector into the host shell — and the
shell's theme cannot bleed back in.
All fields are optional; omitted fields use the defaults below:
- **Lifecycle**: hidden while the plugin owns no sessions; appears on the first
`browser_session` start action; disappears when all sessions stop (or the plugin unloads).
- **Focus view**: status row (green/idle/red dot + session + action + mm:ss), the latest page
frame (while viewed, refreshes every ~1.5s while active, ~8s when idle; the last good frame stays on
stage while the next one loads, and is kept on errors so the card does not flash),
and a compact icon toolbar (Interrupt + Pop out, hover for the label).
- **Interrupt**: one click kills the in-flight bsk command of the focus session (same semantics
as the chat Stop button — the current action fails, the agent run may continue). Strip items
carry their own hover interrupt button.
- **Multi-session strip**: every session gets a tile (mini frame + id + status dot); focus
auto-follows the most recently active session; clicking a tile pins focus (pin badge, click
again to release); errored sessions get a red edge without stealing focus; sessions the daemon
lost are greyed out; prolonged daemon/browser outage shows "browser unavailable" and greys
the interrupt button until captures recover.
- **Drag & resize**: drag the header to move the card; drag any of the four
corners to resize (min 240×180, max 80% of the viewport; no visible grip).
Both are remembered for the page lifetime.
- **Pop out (PiP)**: upgrades the card into a native Document PiP window (requires a user
gesture, per browser rules), sized from the current card; closing the PiP falls back to the
in-page card with state intact. Browsers without Document PiP simply hide the button.
- **Screenshot demand**: the client requests periodic screenshots while an observation view is
visible, using the PiP document's visibility when popped out. Hidden or collapsed views can
keep subscribing to state without requesting screenshots. The first screenshot subscriber
starts capture scheduling; the last one's departure cancels timers and skips queued captures.
An already running capture may finish. Demand applies to the service's owned sessions, not just
the selected session.
- **Wire**: `GET /bsk-observation/events` is the live synchronization channel (SSE). Every connection,
including reconnects, starts with `{ type: "snapshot", sessions, available }`, followed by
`upsert`, `remove`, `reset`, and `availability` events on the same stream. Replace local state
with each snapshot before applying subsequent events. Use `?thumbnails=0` for state-only
subscriptions or `?thumbnails=1` to request screenshots; omitting the parameter defaults to
requesting screenshots for compatibility. Closing the stream releases its screenshot demand.
`GET /bsk-observation/state` remains a one-time `{ sessions, available }` read and does not
request screenshots. It has no ordering guarantee relative to a separate SSE connection;
live clients should initialize and resynchronize from the stream's snapshot instead.
The host also serves `POST /bsk-observation/interrupt`, `POST /bsk-observation/stop`, and
`GET /bsk-observation/thumbnail/<attachmentId>` through the dsh `webServer` route seam
(dsh 0.1's Typert Remote pipeline is closed to out-of-tree packages). All commands for one
session — tool calls and frame captures alike — run through a per-session FIFO, because the
daemon accepts only one unfinished command per session.
- **Programmatic subscription**: `ObservationService.subscribe(listener, { thumbnails: false })`
subscribes to state without requesting screenshots. On an active service, the listener receives
the initial `snapshot` synchronously, before `subscribe` returns, then receives subsequent
changes. `thumbnails` defaults to `true`, so callers should choose it explicitly. The returned
unsubscribe function is safe to call repeatedly and releases this subscription's screenshot
demand. Subscribing after service disposal is a no-op.
- **Trust model**: these routes expose live screenshots (and an interrupt write), so they
replicate the browser-trust fence dsh applies to its own `/api` routes: the request Host
must be a loopback authority (`localhost`, `127.0.0.0/8`, `[::1]`), a present Origin must
match the Host, `sec-fetch-site: cross-site` is refused, and POST requires an
`application/json` body (cross-site simple requests can never satisfy that). The channel is
therefore built for **loopback-only serving** — binding the dsh web server to `0.0.0.0` and
reaching it through a LAN address will (deliberately) fail the fence; do not put these
routes behind a non-loopback reverse proxy without adding your own authentication.
- Configure with `observationEnabled` / `thumbnailIntervalMs` / `idleIntervalMs`.
| Option | Default | Purpose |
| --- | --- | --- |
| `bskPath` | `bsk` | Path to the CLI binary. |
| `defaultTimeoutMs` | `120000` | Default command timeout in milliseconds. |
| `maxSessions` | `5` | Maximum concurrent sessions started by this plugin. |
| `observationEnabled` | `true` | Enable live browser observation. |
| `thumbnailIntervalMs` | `1500` | Screenshot interval for active sessions, in milliseconds. |
| `idleIntervalMs` | `8000` | Screenshot interval for idle sessions and the recent-activity window, in milliseconds. |
| `lazyTools` | `true` | Reveal the browser tools when the skill is invoked. Set `false` to register them at startup. |
## Behavior notes
With `lazyTools: true`, only the skill's catalog entry is initially advertised to
the model. The six `browser_*` tool schemas are added to the system prompt after
the `browser-skill` skill is successfully invoked, either by the model or through
`/browser-skill`. Set `lazyTools: false` to make the tools available immediately.
- **Cancellation**: aborting a tool call (`exec.signal`) kills the underlying bsk child process,
matching BrowserSkill's cooperative tool-cancellation model.
- **UI cards**: calls render as terminal cards (command line as title, output as the completed
card). Screenshots additionally attach the image itself when the host mounts an attachment store
and the active model route declares image input; otherwise the PNG path is returned.
- **Web UI toolview (browser half)**: the package is dual-face. `dsh.client` (platform `web`) ships
`lib/client.cjs`, which registers a keyed `tool.call.toolview` view for `browser_inspect`. The
custom view keeps a terminal block for every inspect action and, when a screenshot result carries
an image block, resolves the durable attachment through the client session's authorized
`readAttachment` RPC and renders it with the shared `MessageImage` thumbnail/lightbox atoms.
The other five tools keep the stock terminal card. The bundle follows the dsh client
contract: a CJS closure factory handed to `window.__ModuleLoader__.load`, platform modules
(`react`, `dsh-client-ui-*`) external, everything else inlined, CSS Modules compiled by
lightningcss.
- **Errors**: non-zero bsk exits surface the CLI's JSON error envelope (`code`, `message`, `hint`)
so the model gets the daemon's actionable guidance.
- **Long-running work** (e.g. `bsk record`) is not backgrounded via `ctx.jobs` yet — tracked as a
follow-up.
## Live browser view
The dsh Web UI shows the plugin's browser sessions in a floating panel. If your
profile provides the `dsh-better-sidebar` integration, the view appears in a
**Browser Skill** sidebar tab instead.
- See the current action, elapsed time, and recent screenshot for each session.
- Select a session to focus on it. The sidebar view follows the current conversation.
- Use **Interrupt** to cancel the current browser command. The agent may continue
with another action afterward.
- Drag or resize the floating panel, or use **Pop out** to open a Picture-in-Picture
window in browsers that support it.
- Periodic screenshots are requested while a browser observation view is visible.
Configure the active and idle intervals with the options above.
The observation endpoints require a loopback address such as `localhost` or
`127.0.0.1`. Access through a LAN hostname or non-loopback reverse proxy is not supported.
## Development
@@ -195,22 +154,47 @@ pnpm --filter @wxg-prc-cpg/browser-skill-dsh-plugin test # unit tests mock b
pnpm --filter @wxg-prc-cpg/browser-skill-dsh-plugin build # tsdown -> lib/
```
See the [development notes](https://github.com/Tencent/BrowserSkill/blob/main/packages/dsh-plugin-browserskill/docs/development.md)
for skill registration, tool results, and observation APIs in the current source.
## Publishing
The GitHub Actions workflow **Release dsh plugin** publishes this package to npm
as `@wxg-prc-cpg/browser-skill-dsh-plugin`. The Cordis plugin id, client
bundle registration, and `cordis.patch.yml` name are the same specifier so
dsh can import and materialize the plugin without a ModuleLoader id mismatch.
The [Release dsh plugin workflow](https://github.com/Tencent/BrowserSkill/blob/main/.github/workflows/release-dsh-plugin.yml)
publishes the package and this README to npm. Pushing a `dsh-plugin-vX.Y.Z` tag
triggers it; ordinary commits to `main` do not.
Trigger it by pushing a tag that matches `package.json`'s `version`:
1. Commit this README and any other changes intended for the release.
2. From the repository root, run the
[release script](https://github.com/Tencent/BrowserSkill/blob/main/scripts/release.mjs)
with a new stable version, replacing `<version>` below. The script updates the
CLI, extension, and DSH plugin versions, commits the version changes, and creates
their release tags:
```sh
git tag dsh-plugin-v0.1.2
git push origin dsh-plugin-v0.1.2
```
```sh
node scripts/release.mjs <version>
```
Or run the workflow from the Actions tab (`workflow_dispatch`). The job reads the
`NPM_TOKEN` secret from the `npm-publish` GitHub Environment.
3. Push the version commit to the release branch, then push the DSH plugin tag
created by the script, using the same `<version>`:
```sh
git push origin HEAD
git push origin dsh-plugin-v<version>
```
This publishes the DSH plugin. Push the CLI and extension tags separately when
those components are ready for release.
The workflow checks the version, runs typechecks and tests, builds the package,
and publishes it to npm.
You can also run the workflow manually from GitHub Actions on the intended release
ref. Both triggers require an unpublished version and the `NPM_TOKEN` secret in the
`npm-publish` GitHub Environment.
npm updates the package README only when a new version is published, including
for documentation-only changes. Published versions cannot be overwritten. See
[npm's README update rules](https://docs.npmjs.com/about-package-readme-files/).
## License
@@ -0,0 +1,90 @@
# DSH plugin development notes
For installation, usage, and configuration, see the [plugin README](../README.md).
These notes describe the current source on this branch; a published npm version may
not include later changes.
## Tool execution
The plugin runs the `bsk` CLI and parses its JSON output. The daemon and browser
extension perform the browser operations. The published package name is also the
Cordis plugin id, client bundle registration id, and `cordis.patch.yml` plugin name.
Keep these identifiers aligned so dsh can load both halves of the plugin.
## Agent skill
Beyond the tools, the plugin publishes the **`browser-skill` agent skill** through the harness's
official skill seam (`ctx.skills.register`): the catalog entry (name + routing description) is
resident in `<available_skills>`, and the body is loaded only when the model invokes the `skill`
tool. Its single source is the DSH-specific `skill/SKILL.md`, which documents only structured
`browser_*` calls and their plugin semantics. The repository-root CLI skill is intentionally not
concatenated: its command examples belong to a different execution interface and would bypass
the plugin's ownership, live observation UI, cancellation, and cleanup path if followed directly.
The build rejects internal CLI-name leakage, command-line code blocks, unknown browser tools, and
missing supported browser tools before embedding the Markdown. Registration and every pre-step
catalog snapshot are pure in-memory reads (no disk/process/daemon); compositions without the skill
seam degrade silently.
With `lazyTools: true`, the six tool schemas stay out of the system prompt until
the skill is successfully invoked. Registration happens once and lasts until the
plugin is unloaded. Repeated invocations do not register duplicate tools. Entering
a resumed conversation whose history contains a successful skill invocation also
registers the tools. Setting `lazyTools: false` registers them at plugin startup.
## Observation subscriptions and routes
- **Screenshot demand**: the client requests periodic screenshots while an observation view is
visible, using the PiP document's visibility when popped out. Hidden or collapsed views can
keep subscribing to state without requesting screenshots. The first screenshot subscriber
starts capture scheduling; the last one's departure cancels timers and skips queued captures.
An already running capture may finish. Demand applies to the service's owned sessions, not just
the selected session.
- **Wire**: `GET /bsk-observation/events` is the live synchronization channel (SSE). Every connection,
including reconnects, starts with `{ type: "snapshot", sessions, available }`, followed by
`upsert`, `remove`, `reset`, and `availability` events on the same stream. Replace local state
with each snapshot before applying subsequent events. Use `?thumbnails=0` for state-only
subscriptions or `?thumbnails=1` to request screenshots; omitting the parameter defaults to
requesting screenshots for compatibility. Closing the stream releases its screenshot demand.
`GET /bsk-observation/state` remains a one-time `{ sessions, available }` read and does not
request screenshots. It has no ordering guarantee relative to a separate SSE connection;
live clients should initialize and resynchronize from the stream's snapshot instead.
The host also serves `POST /bsk-observation/interrupt`, `POST /bsk-observation/stop`, and
`GET /bsk-observation/thumbnail/<attachmentId>` through the dsh `webServer` route seam
(dsh 0.1's Typert Remote pipeline is closed to out-of-tree packages). All commands for one
session — tool calls and frame captures alike — run through a per-session FIFO, because the
daemon accepts only one unfinished command per session.
- **Programmatic subscription**: `ObservationService.subscribe(listener, { thumbnails: false })`
subscribes to state without requesting screenshots. On an active service, the listener receives
the initial `snapshot` synchronously, before `subscribe` returns, then receives subsequent
changes. `thumbnails` defaults to `true`, so callers should choose it explicitly. The returned
unsubscribe function is safe to call repeatedly and releases this subscription's screenshot
demand. Subscribing after service disposal is a no-op.
- **Trust model**: these routes expose live screenshots (and an interrupt write), so they
replicate the browser-trust fence dsh applies to its own `/api` routes: the request Host
must be a loopback authority (`localhost`, `127.0.0.0/8`, `[::1]`), a present Origin must
match the Host, `sec-fetch-site: cross-site` is refused, and POST requires an
`application/json` body (cross-site simple requests can never satisfy that). The channel is
therefore built for **loopback-only serving** — binding the dsh web server to `0.0.0.0` and
reaching it through a LAN address will (deliberately) fail the fence; do not put these
routes behind a non-loopback reverse proxy without adding your own authentication.
## Tool results and cancellation
- **Cancellation**: aborting a tool call (`exec.signal`) kills the underlying bsk child process,
matching BrowserSkill's cooperative tool-cancellation model.
- **UI cards**: calls render as terminal cards (command line as title, output as the completed
card). Screenshots additionally attach the image itself when the host mounts an attachment store
and the active model route declares image input; otherwise the PNG path is returned.
- **Web UI toolview (browser half)**: the package is dual-face. `dsh.client` (platform `web`) ships
`lib/client.cjs`, which registers a keyed `tool.call.toolview` view for `browser_inspect`. The
custom view keeps a terminal block for every inspect action and, when a screenshot result carries
an image block, resolves the durable attachment through the client session's authorized
`readAttachment` RPC and renders it with the shared `MessageImage` thumbnail/lightbox atoms.
The other five tools keep the stock terminal card. The bundle follows the dsh client
contract: a CJS closure factory handed to `window.__ModuleLoader__.load`, platform modules
(`react`, `dsh-client-ui-*`) external, everything else inlined, CSS Modules compiled by
lightningcss.
- **Errors**: non-zero bsk exits surface the CLI's JSON error envelope (`code`, `message`, `hint`)
so the model gets the daemon's actionable guidance.
- **Long-running work** (e.g. `bsk record`) is not backgrounded via `ctx.jobs` yet — tracked as a
follow-up.
@@ -1,7 +1,7 @@
{
"name": "@wxg-prc-cpg/browser-skill-dsh-plugin",
"description": "DeepSeek Harness tool plugin that exposes BrowserSkill browser automation (browser_* tools) to the model",
"version": "0.2.0",
"version": "0.2.1",
"license": "MIT",
"publishConfig": {
"access": "public",
@@ -47,7 +47,6 @@
"client": {
"platform": "web",
"inject": [
"@deepseek-ai/dsh-client-runtime",
"@deepseek-ai/dsh-client-ui-tool",
"@deepseek-ai/dsh-client-ui-layout"
],
@@ -69,7 +68,6 @@
"peerDependencies": {
"@deepseek-ai/cordis": "^4.0.1",
"@deepseek-ai/dsh-attachment": "^0.1.0-rc.6",
"@deepseek-ai/dsh-client-runtime": "^0.1.0-rc.6",
"@deepseek-ai/dsh-client-ui-attachment": "^0.1.0-rc.6",
"@deepseek-ai/dsh-client-ui-primitives": "^0.1.0-rc.6",
"@deepseek-ai/dsh-client-ui-tool": "^0.1.0-rc.6",
@@ -82,9 +80,6 @@
"@deepseek-ai/dsh-attachment": {
"optional": true
},
"@deepseek-ai/dsh-client-runtime": {
"optional": true
},
"@deepseek-ai/dsh-client-ui-attachment": {
"optional": true
},
@@ -7,6 +7,7 @@
*/
import type { ImageAttachmentRef } from "@deepseek-ai/dsh-attachment";
// Development-only types for the injected services; newer hosts no longer ship this package.
import type { ClientContext, ISessions, SessionId } from "@deepseek-ai/dsh-client-runtime/client";
// Type-only: pulls the 'shell.overlay' SlotMap merge into scope.
import type {} from "@deepseek-ai/dsh-client-ui-layout/client";
+51 -10
View File
@@ -5,7 +5,7 @@
* map the CLI's JSON error envelope onto a thrown `BskError`.
*/
import { type ChildProcess, spawn } from "node:child_process";
import { type ChildProcess, type SpawnOptionsWithoutStdio, spawn } from "node:child_process";
/** Shape of the JSON error envelope `bsk --json` prints on failure. */
export interface BskErrorBody {
@@ -53,7 +53,11 @@ export interface BskRunOptions {
}
/** Minimal spawn signature so tests can substitute a fake child process. */
export type SpawnImpl = (command: string, args: string[]) => ChildProcess;
export type SpawnImpl = (
command: string,
args: string[],
options?: SpawnOptionsWithoutStdio,
) => ChildProcess;
export interface BskRunner {
/** Run `bsk <args...> --json` and collect its output. */
@@ -64,29 +68,66 @@ export interface BskRunner {
killFor(tag: string): number;
}
// Business RPCs translate SIGINT into the daemon's cancel(rpc_id) protocol.
// Give that bounded reconciliation path time to settle before the hard kill.
// Business RPCs translate Ctrl-C / opt-in stdin EOF into cancel(rpc_id).
// Allow reconciliation before hard-killing an old or unresponsive CLI.
const KILL_GRACE_MS = 3000;
// Windows IPC may spend 5s connecting, 2s cancelling, 2s settling,
// and up to 5s releasing the entire batch of caller-owned transfers.
const WINDOWS_KILL_GRACE_MS = 15_000;
const SESSION_BUSY_RETRY_DELAY_MS = 100;
export function createBskRunner(bskPath: string, spawnImpl: SpawnImpl = spawn): BskRunner {
const live = new Map<ChildProcess, string | undefined>();
const windows = process.platform === "win32";
const cancelling = new Set<ChildProcess>();
function killChild(child: ChildProcess): void {
if (child.exitCode !== null || child.signalCode !== null) return;
child.kill("SIGINT");
const force = setTimeout(() => {
if (child.exitCode === null && child.signalCode === null) child.kill("SIGKILL");
}, KILL_GRACE_MS);
if (child.exitCode !== null || child.signalCode !== null || cancelling.has(child)) return;
cancelling.add(child);
// Node kills Windows children outright for SIGINT. EOF asks the CLI to
// send its existing cancel RPC and wait for browser reconciliation.
if (windows && child.stdin) child.stdin.end();
else child.kill("SIGINT");
const force = setTimeout(
() => {
if (child.exitCode === null && child.signalCode === null) child.kill("SIGKILL");
},
windows ? WINDOWS_KILL_GRACE_MS : KILL_GRACE_MS,
);
force.unref();
child.once("close", () => {
clearTimeout(force);
cancelling.delete(child);
});
}
return {
run(args, options = {}) {
if (options.signal?.aborted) {
return Promise.resolve({
code: null,
stdout: "",
stderr: "",
timedOut: false,
aborted: true,
});
}
return new Promise<BskRunResult>((resolve, reject) => {
let child: ChildProcess;
try {
child = spawnImpl(bskPath, [...args, "--json"]);
child = spawnImpl(
bskPath,
[...args, "--json"],
windows
? {
windowsHide: true,
env: { ...process.env, BSK_CANCEL_ON_STDIN_CLOSE: "1" },
}
: undefined,
);
// A child exiting while cancellation closes stdin may report EPIPE.
// Its close/error event remains the authority for the run result.
child.stdin?.on("error", () => {});
} catch (error) {
reject(error);
return;
@@ -1,6 +1,7 @@
import type { ChildProcess } from "node:child_process";
import { EventEmitter } from "node:events";
import { describe, expect, it } from "vitest";
import { PassThrough } from "node:stream";
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
import {
type BskRunResult,
createBskRunner,
@@ -92,6 +93,77 @@ describe("createBskRunner", () => {
});
});
describe("Windows parent cancellation", () => {
const originalPlatform = Object.getOwnPropertyDescriptor(process, "platform")!;
beforeEach(() => Object.defineProperty(process, "platform", { value: "win32" }));
afterEach(() => {
Object.defineProperty(process, "platform", originalPlatform);
vi.useRealTimers();
});
it("opts in to stdin cancellation and waits for CLI reconciliation", async () => {
const child = Object.assign(new FakeChild(), { stdin: new PassThrough() });
const spawn = vi.fn(() => child as unknown as ChildProcess);
const runner = createBskRunner("bsk", spawn);
const abort = new AbortController();
const result = runner.run(["snapshot"], { signal: abort.signal });
expect(spawn.mock.calls[0]).toEqual([
"bsk",
["snapshot", "--json"],
{
windowsHide: true,
env: { ...process.env, BSK_CANCEL_ON_STDIN_CLOSE: "1" },
},
]);
abort.abort();
expect(child.stdin.writableEnded).toBe(true);
expect(child.killedWith).toEqual([]);
// Closing an already-exited child's pipe must not crash the host.
child.stdin.emit("error", Object.assign(new Error("closed"), { code: "EPIPE" }));
child.finish(2, '{"code":"cancelled"}');
expect(await result).toMatchObject({ code: 2, aborted: true });
});
it("bounds cancellation of an old or unresponsive CLI", async () => {
vi.useFakeTimers();
const child = Object.assign(new FakeChild(), { stdin: new PassThrough() });
const runner = createBskRunner("bsk", fakeSpawn([child]));
const result = runner.run(["snapshot"], { timeoutMs: 5 });
await vi.advanceTimersByTimeAsync(5);
expect(child.stdin.writableEnded).toBe(true);
expect(child.killedWith).toEqual([]);
await vi.advanceTimersByTimeAsync(10_000);
expect(child.killedWith).toEqual([]);
await vi.advanceTimersByTimeAsync(5_000);
expect(child.killedWith).toEqual(["SIGKILL"]);
expect(await result).toMatchObject({ timedOut: true });
});
it("cancels only the requested tag and clears the fallback after exit", async () => {
vi.useFakeTimers();
const a = Object.assign(new FakeChild(), { stdin: new PassThrough() });
const b = Object.assign(new FakeChild(), { stdin: new PassThrough() });
const runner = createBskRunner("bsk", fakeSpawn([a, b]));
const first = runner.run(["snapshot"], { tag: "a" });
const second = runner.run(["snapshot"], { tag: "b" });
expect(runner.killFor("a")).toBe(1);
expect(a.stdin.writableEnded).toBe(true);
expect(b.stdin.writableEnded).toBe(false);
a.finish(2);
b.finish(0);
await Promise.all([first, second]);
expect(vi.getTimerCount()).toBe(0);
});
it("does not start work for an already-aborted call", async () => {
const spawn = vi.fn();
const runner = createBskRunner("bsk", spawn);
const signal = AbortSignal.abort();
expect(await runner.run(["snapshot"], { signal })).toMatchObject({ aborted: true });
expect(spawn).not.toHaveBeenCalled();
});
});
describe("parseBskJson", () => {
const base: BskRunResult = { code: 0, stdout: "", stderr: "", timedOut: false, aborted: false };
@@ -25,7 +25,6 @@ const CLIENT_EXTERNALS: readonly string[] = [
"@deepseek-ai/dsh-client-ui-primitives",
"@deepseek-ai/dsh-client-ui-attachment",
"@deepseek-ai/dsh-client-schema-form",
"@deepseek-ai/dsh-client-runtime/client",
];
/** Wire/type layers with no shared runtime identity: safe to inline. */
+135
View File
@@ -0,0 +1,135 @@
#Requires -Version 5.1
param([string]$BskPath = (Join-Path $PSScriptRoot "../target/debug/bsk.exe"))
$ErrorActionPreference = "Stop"
# Load definitions, never Main: no downloads or changes to the real user PATH.
$installer = Join-Path $PSScriptRoot "../install.ps1"
$tokens = $null
$errors = $null
$ast = [System.Management.Automation.Language.Parser]::ParseFile($installer, [ref]$tokens, [ref]$errors)
if ($errors.Count) { throw ($errors | Out-String) }
foreach ($statement in $ast.EndBlock.Statements) {
if ($statement -is [System.Management.Automation.Language.FunctionDefinitionAst]) {
$definition = $statement.Extent.Text
if ($statement.Name -eq "Add-ToUserPath") {
$definition = $definition.Replace('[Environment]::GetEnvironmentVariable("PATH", "User")', '$script:UserPath')
$definition = $definition.Replace('[Environment]::SetEnvironmentVariable("PATH", $newUserPath, "User")', '$script:UserPath = $newUserPath')
}
Invoke-Expression $definition
}
}
function Assert-Equal($Actual, $Expected) {
if ($Actual -cne $Expected) { throw "expected [$Expected], got [$Actual]" }
}
function Assert-Fails([scriptblock]$Action) {
$failed = $false
try { & $Action } catch { $failed = $true }
if (-not $failed) { throw "expected failure" }
}
$dir = 'C:\Users\Alice\.local\bin'
foreach ($existing in @('', 'C:\WindowsApps', 'C:\A;C:\B')) {
$script:UserPath = $existing
Add-ToUserPath $dir
$expected = if ($existing) { "$existing;$dir" } else { $dir }
Assert-Equal $script:UserPath $expected
Add-ToUserPath $dir
Assert-Equal $script:UserPath $expected
}
$root = Join-Path ([IO.Path]::GetTempPath()) ("bsk-install-test-" + [Guid]::NewGuid().ToString('N'))
[IO.Directory]::CreateDirectory($root) | Out-Null
$oldBskHome = $env:BSK_HOME
$oldAutoUpdate = $env:BSK_AUTO_UPDATE
$daemon = $null
try {
$utf8 = New-Object System.Text.UTF8Encoding($false)
$bashRc = Join-Path $root ".bashrc"
$existing = "# existing 中文 configuration" + [char]10
[IO.File]::WriteAllText($bashRc, $existing, $utf8)
$special = 'C:\Users\张三 space $HOME $(echo unsafe) ! & [x] O''Brien\.local\bin'
Add-ToBashProfile $special $bashRc
$first = [IO.File]::ReadAllText($bashRc)
if (-not $first.StartsWith($existing)) { throw "existing bashrc content changed" }
if (-not $first.Contains('张三')) { throw "Unicode path was lost" }
Add-ToBashProfile $special $bashRc
Assert-Equal ([IO.File]::ReadAllText($bashRc)) $first
$bytes = [IO.File]::ReadAllBytes($bashRc)
if ($bytes[0] -eq 0xEF) { throw "unexpected UTF-8 BOM" }
$bash = [IO.Path]::GetFullPath((Join-Path (Split-Path (Get-Command git).Source -Parent) "../bin/bash.exe"))
if (-not (Test-Path -LiteralPath $bash)) { throw "Git Bash is required for quoting regression" }
$env:BSK_TEST_RC = $bashRc
$probe = Join-Path $root 'probe.sh'
[IO.File]::WriteAllText($probe, 'source "$BSK_TEST_RC"; printf "%s\n" "${PATH%%:*}"', $utf8)
$actual = & $bash --noprofile --norc $probe
if ($LASTEXITCODE -ne 0) { throw "Git Bash failed" }
Assert-Equal $actual ('/c' + $special.Substring(2).Replace('\', '/'))
$env:BSK_HOME = Join-Path $root "home"
$env:BSK_AUTO_UPDATE = "off"
[IO.Directory]::CreateDirectory($env:BSK_HOME) | Out-Null
$sourceDir = Join-Path $root "download"
[IO.Directory]::CreateDirectory($sourceDir) | Out-Null
$source = Join-Path $sourceDir "bsk.exe"
[IO.File]::Copy((Resolve-Path -LiteralPath $BskPath).Path, $source)
$targetDir = Join-Path $root "中文 space [x] & install"
[IO.Directory]::CreateDirectory($targetDir) | Out-Null
$target = Join-Path $targetDir "bsk.exe"
Install-Binary $source $target
Assert-Equal (Get-FileHash -LiteralPath $target).Hash (Get-FileHash -LiteralPath $source).Hash
$daemon = Start-Process -FilePath $target -ArgumentList @('daemon', 'start', '--foreground', '--port', '0') -WindowStyle Hidden -PassThru
$infoPath = Join-Path $env:BSK_HOME "daemon.json"
$deadline = [DateTime]::UtcNow.AddSeconds(15)
while (-not [IO.File]::Exists($infoPath)) {
if ($daemon.HasExited -or [DateTime]::UtcNow -gt $deadline) { throw "daemon failed to start" }
Start-Sleep -Milliseconds 50
}
# PE overlays distinguish old/new executables without another build.
$stream = [IO.File]::OpenWrite($source)
try {
$stream.Seek(0, [IO.SeekOrigin]::End) | Out-Null
$marker = $utf8.GetBytes("installer replacement regression")
$stream.Write($marker, 0, $marker.Length)
} finally { $stream.Dispose() }
Install-Binary $source $target
if (-not $daemon.WaitForExit(5000)) { throw "old daemon still running" }
Assert-Equal (Get-FileHash -LiteralPath $target).Hash (Get-FileHash -LiteralPath $source).Hash
& $target --version
if ($LASTEXITCODE -ne 0) { throw "replacement is not executable" }
# Refuse replacement when daemon identity cannot be verified.
[IO.File]::WriteAllText($infoPath, 'invalid daemon metadata')
$before = (Get-FileHash -LiteralPath $target).Hash
Assert-Fails { Install-Binary $source $target }
Assert-Equal (Get-FileHash -LiteralPath $target).Hash $before
[IO.File]::Delete($infoPath)
# A remaining lock must fail without truncation or staging debris.
$lock = [IO.File]::Open($target, [IO.FileMode]::Open, [IO.FileAccess]::Read, [IO.FileShare]::None)
try { Assert-Fails { Install-Binary $source $target } } finally { $lock.Dispose() }
Assert-Equal (Get-FileHash -LiteralPath $target).Hash $before
if (@(Get-ChildItem -LiteralPath $targetDir -Filter "*.install-*").Count) { throw "staging files leaked" }
Write-Host "Windows installer regressions passed ($($PSVersionTable.PSVersion))"
}
catch {
Write-Host ($_ | Out-String)
Write-Host $_.ScriptStackTrace
throw
}
finally {
if ($daemon -and -not $daemon.HasExited) {
Stop-Process -Id $daemon.Id -Force
$daemon.WaitForExit(5000) | Out-Null
}
$env:BSK_HOME = $oldBskHome
$env:BSK_AUTO_UPDATE = $oldAutoUpdate
Remove-Item Env:BSK_TEST_RC -ErrorAction SilentlyContinue
# Resolve and verify before recursive cleanup; only this fixture is removed.
$resolvedRoot = [IO.Path]::GetFullPath($root)
$tempRoot = [IO.Path]::GetFullPath([IO.Path]::GetTempPath()).TrimEnd('\') + '\'
if (-not $resolvedRoot.StartsWith($tempRoot, [StringComparison]::OrdinalIgnoreCase) -or
-not ([IO.Path]::GetFileName($resolvedRoot)).StartsWith('bsk-install-test-')) { throw "invalid cleanup path" }
Remove-Item -LiteralPath $resolvedRoot -Recurse -Force
}
+9 -3
View File
@@ -174,16 +174,22 @@ function updateChangelog(version) {
const today = new Date().toISOString().slice(0, 10);
const escapedVer = version.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
const versionHeading = new RegExp(`^## \\[${escapedVer}\\](?:\\s|$)`, "m");
// First: fill in any date-placeholder line for this version (e.g. "## [0.2.0] - 2026-09-XX")
const versionPlaceholder = new RegExp(`^## \\[${escapedVer}\\]\\s*-\\s*\\d{4}-\\d{2}-XX`, "m");
if (versionPlaceholder.test(content)) {
content = content.replace(versionPlaceholder, `## [${version}] - ${today}`);
} else {
// Otherwise: insert a new section after [Unreleased]
} else if (!versionHeading.test(content)) {
// Preserve prepared release entries; new versions go before the release history.
const heading = `## [${version}] - ${today}`;
const unreleased = /^## \[Unreleased\]/m;
if (unreleased.test(content)) {
content = content.replace(unreleased, `## [Unreleased]\n\n## [${version}] - ${today}`);
content = content.replace(unreleased, `## [Unreleased]\n\n${heading}`);
} else if (/^## /m.test(content)) {
content = content.replace(/^## /m, `${heading}\n\n## `);
} else {
content = `${content.trimEnd()}\n\n${heading}\n`;
}
}