aboutsummaryrefslogtreecommitdiff
path: root/src/cdp
diff options
context:
space:
mode:
authorAman Kumar <145339995+amankumarsingh77@users.noreply.github.com>2026-07-25 00:23:05 +0530
committerGitHub <noreply@github.com>2026-07-25 00:23:05 +0530
commit6dd79f7c3bafacba54acb2840f8655fcb05318bf (patch)
tree1570768785ae836717d3dbb2ff42fe0a13f19585 /src/cdp
parent0fc1ece6fa4a2f24e87eb4a66eb828a9928e30f7 (diff)
feat: pin the agent to a chosen browser profile (#16)
* feat: pin the agent to a chosen browser profile (#15) Harness tabs were created with a bare Target.createTarget, which places them in Chrome's defaultBrowserContextId — and that value follows window focus. Which profile the agent acted as therefore depended on which browser window the user last clicked, so the same task could run as a work account on one run and a personal account on the next. /browser-profile lists the connected browser's profiles as "Name (email)" and pins one to ~/.pi/agent/browser-harness.json, so the choice outlives the session. The same picker appears on first browser_setup when nothing is pinned; with no interactive UI, or on cancel, setup continues with a note and the previous behavior. Chrome offers no direct route to another profile: Target.createTarget rejects a foreign browserContextId, and openerId does not inherit the opener's context. The window is opened through the browser's own command line (--profile-directory, handed to the running browser by Chromium's ProcessSingleton) and identified by a unique file:// sentinel page, since a bare about:blank#token argument is discarded. Further tabs come from window.open evaluated with userGesture: true — the only CDP-reachable way to place a tab in a non-default browser context — correlated by a unique token so concurrent isolated tabs stay distinct. A failed handshake is reported, never silently redirected to another profile. All four tab-creation sites now funnel through cdp/target-factory, so open_urls and the isolated tabs behind web_search / read_page cannot run with a different profile's cookies than the visible tabs. Also fixed along the way: snap Chromium is discovered, Windows uses %LOCALAPPDATA%, browsers launched with an explicit --user-data-dir are found, the running browser is chosen by ranking candidates against the connected user-data-dir rather than taking the first process found, and an installed-but-closed browser no longer reads as running. CI runs the profile suites and a real-browser end-to-end test on ubuntu, macOS, and Windows — profile discovery is the one part of the harness whose behavior genuinely differs per OS. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: single-flight harness window creation Isolated tabs run concurrently (browser_read_page is registered unserialized), so several could each find "no harness window" and create one — two blank windows before this feature, two LAUNCHED profile windows after it. ensureHarnessWindow now shares one in-flight creation per client. Sharing introduces a second hazard: freshlyCreated is a claim on the seed tab, and if every waiter received it, they would all drive the same tab. Only the caller that started the creation keeps the claim; the rest open their own tab beside it. Covered by test/manual/profile-concurrency-test.ts (five concurrent isolated tabs, pinned and unpinned: distinct targets, one window, correct profile), wired into CI on Linux only — the coordination is pure JS and identical across platforms. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix: tilde expansion differs by purpose on Windows CI on windows-latest caught this: join("~", "x") yields "~\x" there, and expandTilde only handled "~/". The two uses are not the same, so they no longer share a helper. The agent dir stays byte-compatible with pi's own expandTildePath ("~/" only, every platform) — being more lenient would put the pin file somewhere pi never looks. $CHROME_USER_DATA_DIR is ours to interpret, so it accepts "~\" as well, which is what a Windows user would type. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'src/cdp')
-rw-r--r--src/cdp/discovery.ts96
-rw-r--r--src/cdp/session.ts19
-rw-r--r--src/cdp/target-factory.ts223
3 files changed, 282 insertions, 56 deletions
diff --git a/src/cdp/discovery.ts b/src/cdp/discovery.ts
index 1b35418..295df20 100644
--- a/src/cdp/discovery.ts
+++ b/src/cdp/discovery.ts
@@ -1,61 +1,24 @@
import { readFile, stat } from "node:fs/promises";
-import { homedir } from "node:os";
import { join } from "node:path";
import { connect as netConnect } from "node:net";
import { request as httpRequest } from "node:http";
import { type Result, err, ok } from "../util/result";
+import { userDataDirCandidates } from "../profile/paths";
import { type CdpError, cdpError } from "./errors";
const PORT_PROBE_DEADLINE_MS = 30_000;
const PORT_PROBE_INTERVAL_MS = 1_000;
-const profileDirs = (): ReadonlyArray<string> => {
- const home = homedir();
- return [
- // macOS — Chrome (all channels), Chromium, Brave, Edge
- join(home, "Library/Application Support/Google/Chrome"),
- join(home, "Library/Application Support/Google/Chrome Beta"),
- join(home, "Library/Application Support/Google/Chrome Dev"),
- join(home, "Library/Application Support/Google/Chrome Canary"),
- join(home, "Library/Application Support/Chromium"),
- join(home, "Library/Application Support/BraveSoftware/Brave-Browser"),
- join(home, "Library/Application Support/BraveSoftware/Brave-Browser-Beta"),
- join(home, "Library/Application Support/BraveSoftware/Brave-Browser-Nightly"),
- join(home, "Library/Application Support/BraveSoftware/Brave-Browser-Dev"),
- join(home, "Library/Application Support/Microsoft Edge"),
- join(home, "Library/Application Support/Microsoft Edge Beta"),
- join(home, "Library/Application Support/Microsoft Edge Dev"),
- join(home, "Library/Application Support/Microsoft Edge Canary"),
- // Linux — Chrome (all channels), Chromium, Brave, Edge
- join(home, ".config/google-chrome"),
- join(home, ".config/google-chrome-beta"),
- join(home, ".config/google-chrome-unstable"),
- join(home, ".config/chromium"),
- join(home, ".config/chromium-browser"),
- join(home, ".config/BraveSoftware/Brave-Browser"),
- join(home, ".config/BraveSoftware/Brave-Browser-Beta"),
- join(home, ".config/BraveSoftware/Brave-Browser-Nightly"),
- join(home, ".config/microsoft-edge"),
- join(home, ".config/microsoft-edge-beta"),
- join(home, ".config/microsoft-edge-dev"),
- // Linux flatpak
- join(home, ".var/app/org.chromium.Chromium/config/chromium"),
- join(home, ".var/app/com.google.Chrome/config/google-chrome"),
- join(home, ".var/app/com.brave.Browser/config/BraveSoftware/Brave-Browser"),
- join(home, ".var/app/com.microsoft.Edge/config/microsoft-edge"),
- // Windows — Chrome, Chromium, Brave, Edge
- join(home, "AppData/Local/Google/Chrome/User Data"),
- join(home, "AppData/Local/Google/Chrome Beta/User Data"),
- join(home, "AppData/Local/Google/Chrome Dev/User Data"),
- join(home, "AppData/Local/Google/Chrome SxS/User Data"),
- join(home, "AppData/Local/Chromium/User Data"),
- join(home, "AppData/Local/BraveSoftware/Brave-Browser/User Data"),
- join(home, "AppData/Local/BraveSoftware/Brave-Browser-Beta/User Data"),
- join(home, "AppData/Local/Microsoft/Edge/User Data"),
- join(home, "AppData/Local/Microsoft/Edge Beta/User Data"),
- join(home, "AppData/Local/Microsoft/Edge Dev/User Data"),
- join(home, "AppData/Local/Microsoft/Edge SxS/User Data"),
- ];
+/**
+ * A live CDP endpoint plus, when discovery went through a DevToolsActivePort
+ * file, the user-data-dir that file lives in. That directory is the browser's
+ * profile registry (`Local State`) — Chromium writes DevToolsActivePort to
+ * chrome::DIR_USER_DATA — so it is what profile selection enumerates.
+ * Undefined when the endpoint came from BU_CDP_WS or a bare port probe.
+ */
+export type CdpEndpoint = {
+ readonly wsUrl: string;
+ readonly userDataDir?: string;
};
const probePort = (port: number): Promise<Result<void, CdpError>> =>
@@ -144,10 +107,20 @@ const fallbackPorts = (): ReadonlyArray<number> => {
return Array.from(ports);
};
-type Candidate = { readonly port: number; readonly path: string; readonly mtimeMs: number };
+type Candidate = {
+ readonly port: number;
+ readonly path: string;
+ readonly mtimeMs: number;
+ /** The user-data-dir whose DevToolsActivePort produced this candidate. */
+ readonly userDataDir: string;
+};
-export const discoverWsUrl = async (): Promise<Result<string, CdpError>> => {
- const dirs = profileDirs();
+/**
+ * Locate a live CDP endpoint, reporting the user-data-dir it belongs to when
+ * that is knowable. `discoverWsUrl` is the URL-only view of the same walk.
+ */
+export const discoverEndpoint = async (): Promise<Result<CdpEndpoint, CdpError>> => {
+ const dirs = userDataDirCandidates();
// Phase 1: collect every readable DevToolsActivePort candidate up front,
// rather than committing to the first one found. A single browser writes one
@@ -190,7 +163,7 @@ export const discoverWsUrl = async (): Promise<Result<string, CdpError>> => {
// a Result error. Skip such entries.
const portNum = Number(port);
if (!Number.isInteger(portNum) || portNum <= 0 || portNum >= 65536) continue;
- candidates.push({ port: portNum, path, mtimeMs });
+ candidates.push({ port: portNum, path, mtimeMs, userDataDir: base });
}
// Phase 2: no readable candidate — probe well-known ports directly. Covers
@@ -201,7 +174,9 @@ export const discoverWsUrl = async (): Promise<Result<string, CdpError>> => {
for (const port of fallbackPorts()) {
if (!(await isPortLive(port))) continue;
const live = await queryLiveWsUrl(port);
- if (live) return ok(live);
+ // No DevToolsActivePort file was involved, so the user-data-dir behind
+ // this endpoint is unknown — profile selection stays unavailable.
+ if (live) return ok({ wsUrl: live });
}
const permHint = readErrors.length > 0
? `\n\nDevToolsActivePort reads were denied (${readErrors.join(", ")}); if you're running in a sandbox, grant read access to those files or set BU_CDP_WS / BU_CDP_PORTS to bypass file discovery.`
@@ -232,7 +207,7 @@ export const discoverWsUrl = async (): Promise<Result<string, CdpError>> => {
// /json/version. Some browsers disable that HTTP endpoint when remote
// debugging is toggled only via chrome://inspect (rather than a launch flag),
// so fall back to the WS path written in DevToolsActivePort.
- let lastErr: Result<string, CdpError> | null = null;
+ let lastErr: Result<CdpEndpoint, CdpError> | null = null;
for (const c of ordered) {
const ready = await waitForPort(c.port);
if (!ready.success) {
@@ -240,7 +215,7 @@ export const discoverWsUrl = async (): Promise<Result<string, CdpError>> => {
continue;
}
const liveUrl = await queryLiveWsUrl(c.port);
- return ok(liveUrl ?? `ws://127.0.0.1:${c.port}${c.path}`);
+ return ok({ wsUrl: liveUrl ?? `ws://127.0.0.1:${c.port}${c.path}`, userDataDir: c.userDataDir });
}
// Every discovered candidate was stale/unreachable. Before giving up, try the
@@ -250,8 +225,17 @@ export const discoverWsUrl = async (): Promise<Result<string, CdpError>> => {
for (const port of fallbackPorts()) {
if (byPort.has(port) || !(await isPortLive(port))) continue;
const liveUrl = await queryLiveWsUrl(port);
- if (liveUrl) return ok(liveUrl);
+ if (liveUrl) return ok({ wsUrl: liveUrl });
}
return lastErr ?? err(cdpError("discovery_failed", "no live DevTools endpoint among discovered candidates"));
};
+
+/**
+ * URL-only view of {@link discoverEndpoint}, kept as the stable entry point for
+ * callers that don't care which user-data-dir answered.
+ */
+export const discoverWsUrl = async (): Promise<Result<string, CdpError>> => {
+ const endpoint = await discoverEndpoint();
+ return endpoint.success ? ok(endpoint.data.wsUrl) : endpoint;
+};
diff --git a/src/cdp/session.ts b/src/cdp/session.ts
index 03410ba..eeb3802 100644
--- a/src/cdp/session.ts
+++ b/src/cdp/session.ts
@@ -45,9 +45,21 @@ export type CdpSession = {
drainConsoleBuffer(filter: ConsoleFilter): ConsoleDrainResult;
};
+/**
+ * Supplies the seed tab when attachFirstPage finds no owned tab to attach to.
+ * Injected by the client so that seeding goes through the target factory —
+ * which, with a profile pinned, opens the window inside that profile. Without
+ * it, attachFirstPage's own `Target.createTarget` would land in whichever
+ * profile currently has focus.
+ *
+ * The provider is responsible for its own ownership bookkeeping.
+ */
+export type SeedTargetProvider = () => Promise<Result<string, CdpError>>;
+
export const createCdpSession = (
transport: CdpTransport,
ownership?: OwnershipRegistry,
+ createSeedTarget?: SeedTargetProvider,
): CdpSession => {
let sessionId: string | null = null;
let targetId: string | null = null;
@@ -246,6 +258,13 @@ export const createCdpSession = (
const ownedLive = ownership.list().filter((id) => allPages.some((p) => p.targetId === id));
pickTargetId = ownedLive[0];
}
+ if (!pickTargetId && createSeedTarget) {
+ // Delegated seeding (see SeedTargetProvider): the provider creates the
+ // window in the right profile and records ownership itself.
+ const seeded = await createSeedTarget();
+ if (!seeded.success) return seeded;
+ pickTargetId = seeded.data;
+ }
if (!pickTargetId) {
const createParams: Record<string, unknown> = { url: "about:blank" };
if (ownership) createParams["newWindow"] = true;
diff --git a/src/cdp/target-factory.ts b/src/cdp/target-factory.ts
new file mode 100644
index 0000000..25c43a6
--- /dev/null
+++ b/src/cdp/target-factory.ts
@@ -0,0 +1,223 @@
+/**
+ * The single place harness tabs and windows are created.
+ *
+ * Every tab the harness opens must land in the pinned profile, so all creation
+ * paths (client.newTab, browser_open_urls, isolated tabs for web_search /
+ * read_page) funnel through here. A missed call site would silently act in
+ * another profile — with that profile's cookies and logins.
+ *
+ * Two mechanisms, chosen by whether a profile is pinned:
+ *
+ * unpinned — `Target.createTarget`, exactly as before: `newWindow: true` for
+ * a fresh dedicated window, `openerId` for siblings inside it.
+ *
+ * pinned — the window comes from a command-line launch into the profile
+ * (see profile/launch.ts), and further tabs come from
+ * `window.open(..., '_blank')` evaluated in an owned page with
+ * `userGesture: true`. That is the only CDP-reachable way to place
+ * a tab in a non-default browser context: createTarget rejects a
+ * foreign browserContextId outright, and `openerId` does NOT
+ * inherit the opener's context (verified — it lands in the
+ * focus-derived default context, in a different window).
+ * window.open keeps both the context and the window, recursively.
+ *
+ * Correlation: window.open returns no target id, so each spawn carries a unique
+ * `about:blank#pi-<uuid>` token and the new target is found by that token.
+ * Set-difference polling would be wrong here — isolated tabs run concurrently
+ * (browser_read_page is registered unserialized).
+ */
+
+import { randomUUID } from "node:crypto";
+import type { BrowserClient } from "../client";
+import { type Result, err, ok } from "../util/result";
+import { type CdpError, cdpError } from "./errors";
+
+/** How long to wait for a window.open-spawned target to appear. */
+const SPAWN_DEADLINE_MS = 8_000;
+const SPAWN_POLL_MS = 100;
+
+export type HarnessWindow = {
+ /** Target id of the window's seed tab. */
+ readonly targetId: string;
+ /**
+ * True when this call created the window. The seed tab is then a blank tab
+ * the caller may use directly, instead of opening a second one.
+ */
+ readonly freshlyCreated: boolean;
+};
+
+type PageTarget = {
+ readonly targetId: string;
+ readonly type: string;
+ readonly url: string;
+ readonly browserContextId?: string;
+};
+
+const listPageTargets = async (client: BrowserClient): Promise<Result<ReadonlyArray<PageTarget>, CdpError>> => {
+ const r = await client.session().callBrowser("Target.getTargets");
+ if (!r.success) return r;
+ const data = r.data as { targetInfos: ReadonlyArray<PageTarget> };
+ return ok(data.targetInfos.filter((t) => t.type === "page"));
+};
+
+/** A CDP session id for driving `targetId`, reusing the active one when possible. */
+const sessionForTarget = async (client: BrowserClient, targetId: string): Promise<Result<string, CdpError>> => {
+ const current = client.current();
+ if (current?.targetId === targetId) return ok(current.sessionId);
+ const attached = await client.session().callBrowser("Target.attachToTarget", { targetId, flatten: true });
+ if (!attached.success) return attached;
+ return ok((attached.data as { sessionId: string }).sessionId);
+};
+
+/**
+ * Spawn a tab from `openerTargetId` via window.open, so it inherits the
+ * opener's profile and window, and return its target id.
+ */
+const spawnTabViaOpener = async (
+ client: BrowserClient,
+ openerTargetId: string,
+): Promise<Result<string, CdpError>> => {
+ const session = await sessionForTarget(client, openerTargetId);
+ if (!session.success) return session;
+
+ const token = `pi-${randomUUID()}`;
+ // userGesture: true is what gets this past the popup blocker.
+ const opened = await client.session().callOnTarget(
+ "Runtime.evaluate",
+ {
+ expression: `!!window.open('about:blank#${token}', '_blank')`,
+ returnByValue: true,
+ userGesture: true,
+ },
+ session.data,
+ );
+ if (!opened.success) return opened;
+ const result = opened.data as { result?: { value?: unknown } };
+ if (result.result?.value !== true) {
+ return err(cdpError(
+ "invalid_response",
+ "the browser blocked window.open in the pinned profile's window — the page may have navigated away; retry, or run /browser-profile to re-seed",
+ "Runtime.evaluate",
+ ));
+ }
+
+ const deadline = Date.now() + SPAWN_DEADLINE_MS;
+ while (Date.now() < deadline) {
+ const targets = await listPageTargets(client);
+ if (targets.success) {
+ const spawned = targets.data.find((t) => t.url.includes(token));
+ if (spawned) return ok(spawned.targetId);
+ }
+ await new Promise((r) => setTimeout(r, SPAWN_POLL_MS));
+ }
+ return err(cdpError("timeout", `the tab opened in the pinned profile did not report back within ${SPAWN_DEADLINE_MS}ms`));
+};
+
+/**
+ * In-flight window creation, per client. Isolated tabs run concurrently
+ * (browser_read_page is registered unserialized), so two of them starting at
+ * once would otherwise each find "no harness window" and create one — two blank
+ * windows before, and two launched profile windows now. Callers share the first
+ * call's result instead.
+ */
+const inFlight = new WeakMap<BrowserClient, Promise<Result<HarnessWindow, CdpError>>>();
+
+/**
+ * The harness window for this session, creating it when absent.
+ *
+ * Reuses a live owned tab when one exists — including after the user closed the
+ * original seed — so reconnects don't scatter windows.
+ */
+export const ensureHarnessWindow = async (client: BrowserClient): Promise<Result<HarnessWindow, CdpError>> => {
+ const pending = inFlight.get(client);
+ if (pending) {
+ const shared = await pending;
+ // `freshlyCreated` is a claim on the seed tab, and only the caller that
+ // started the creation may hold it. Everyone waiting on the same window
+ // must open a tab of their own beside it, or two callers would drive the
+ // very same tab.
+ return shared.success ? ok({ targetId: shared.data.targetId, freshlyCreated: false }) : shared;
+ }
+ const attempt = ensureHarnessWindowUncoordinated(client).finally(() => inFlight.delete(client));
+ inFlight.set(client, attempt);
+ return attempt;
+};
+
+const ensureHarnessWindowUncoordinated = async (
+ client: BrowserClient,
+): Promise<Result<HarnessWindow, CdpError>> => {
+ const targets = await listPageTargets(client);
+ if (!targets.success) return targets;
+ const live = new Set(targets.data.map((t) => t.targetId));
+
+ const ownership = client.ownership();
+ const pinnedCtx = client.profileContextId();
+ // A tab may only be reused when we can prove which profile it is in. With a
+ // pin set but no context resolved yet — a fresh connection, or a browser that
+ // restarted — the recorded tabs cannot be verified, so we seed a new window
+ // rather than risk adopting one from the wrong profile. (Sessions close their
+ // owned tabs on shutdown, so this is the normal, no-cost case.)
+ const canReuse = client.profilePin() === null || pinnedCtx !== undefined;
+ const inPinnedProfile = (targetId: string): boolean => {
+ if (!pinnedCtx) return true;
+ const info = targets.data.find((t) => t.targetId === targetId);
+ return info?.browserContextId === pinnedCtx;
+ };
+
+ if (canReuse) {
+ const harnessWindow = ownership.harnessWindow();
+ if (harnessWindow && live.has(harnessWindow) && inPinnedProfile(harnessWindow)) {
+ return ok({ targetId: harnessWindow, freshlyCreated: false });
+ }
+ const survivor = ownership.list().find((id) => live.has(id) && inPinnedProfile(id));
+ if (survivor) {
+ ownership.setHarnessWindow(survivor);
+ return ok({ targetId: survivor, freshlyCreated: false });
+ }
+ }
+
+ const seeded = client.profilePin()
+ ? await client.seedPinnedProfileWindow()
+ : await createDedicatedWindow(client);
+ if (!seeded.success) return seeded;
+ return ok({ targetId: seeded.data, freshlyCreated: true });
+};
+
+/** Unpinned path: a fresh dedicated window, exactly as the harness always did. */
+const createDedicatedWindow = async (client: BrowserClient): Promise<Result<string, CdpError>> => {
+ const created = await client.session().callBrowser("Target.createTarget", { url: "about:blank", newWindow: true });
+ if (!created.success) return created;
+ const { targetId } = created.data as { targetId: string };
+ const ownership = client.ownership();
+ ownership.setHarnessWindow(targetId);
+ ownership.add(targetId);
+ const win = await client.session().callBrowser("Browser.getWindowForTarget", { targetId });
+ if (win.success) {
+ const windowId = (win.data as { windowId?: number }).windowId;
+ if (typeof windowId === "number") ownership.setHarnessWindowId(windowId);
+ }
+ return ok(targetId);
+};
+
+/**
+ * Open a harness-owned tab beside `openerTargetId`, in the same window and —
+ * when a profile is pinned — the same profile. The tab is registered as owned.
+ */
+export const openHarnessTab = async (
+ client: BrowserClient,
+ openerTargetId: string,
+): Promise<Result<string, CdpError>> => {
+ const spawned = client.profileContextId()
+ ? await spawnTabViaOpener(client, openerTargetId)
+ : await (async (): Promise<Result<string, CdpError>> => {
+ const created = await client.session().callBrowser("Target.createTarget", {
+ url: "about:blank",
+ openerId: openerTargetId,
+ });
+ if (!created.success) return created;
+ return ok((created.data as { targetId: string }).targetId);
+ })();
+ if (!spawned.success) return spawned;
+ client.ownership().add(spawned.data);
+ return ok(spawned.data);
+};