aboutsummaryrefslogtreecommitdiff
path: root/src/cdp/target-factory.ts
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/target-factory.ts
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/target-factory.ts')
-rw-r--r--src/cdp/target-factory.ts223
1 files changed, 223 insertions, 0 deletions
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);
+};