browser-automation

Browser Automation

Use this skill when you need the browser tool for anything beyond a single page check.

Operating Loop

1. Check browser state before acting:

• openclaw browser doctor or action="status" when the browser/plugin setup itself may be broken.
• action="status" for availability.
• action="profiles" if login state or profile choice matters.
• action="tabs" before opening a new tab if retries/timeouts may have left windows behind.

2. Prefer stable tab handles:

• Open important tabs with label, for example label="meet".
• After action="tabs" or action="open", store suggestedTargetId and pass it as targetId in later calls.
• suggestedTargetId is the label when one exists, otherwise the stable tabId handle like t1.
• Avoid relying on raw DevTools targetId except for immediate diagnostics; it can change under Chromium target replacement.

3. Read before you click:

• For “read the page and answer X,” use action="text" with optional selector and maxChars for bounded visible prose (first selector match, otherwise article/main/body). On existing-session profiles, use snapshot instead. Efficient snapshots omit most prose.
• For virtualized lists, scroll through each segment, capture only the relevant rows, then merge the results.
• Use action="snapshot" on the intended targetId.
• Add snapshot query to find lines containing all query tokens, ignoring case; matching lines keep their refs.
• Use the same targetId for follow-up actions so refs stay on the same tab.
• For durable Playwright refs, request refs="aria" when supported. If you receive axN refs from snapshotFormat="aria", use them only after that same snapshot call; stale or unbound axN refs fail fast and need a fresh snapshot.
• Use urls=true when link text is ambiguous or a direct navigation target would avoid brittle clicks.
• Use labels=true on snapshot or screenshot when visual position matters. On Playwright-backed profiles, the response includes an annotations array ({ref, number, role, name?, box}) with each ref's bounding box in the captured image's coordinate space, so you can reason about position without re-snapshotting; screenshot labels can also combine with fullPage=true (CLI: --full-page) to label the whole document, or ref / element to clip to one element. profile="user" and other existing-session (chrome-mcp) profiles render an overlay into page screenshots but do not attach annotations or use the Playwright full-page/ref/element projection helper, so read positions from the labeled image itself on those profiles. The raw-CDP fallback (no Playwright) does not support labeled screenshots at all and returns a 501, so only request labels when Playwright is available.

4. Act narrowly:

• Prefer action="act" with a ref from the latest snapshot.
• navigate returns the loaded page's compact snapshot inline, and batch act results that report a cross-document navigation include fresh page state; use those refs directly instead of a follow-up snapshot call.
• After a single act that triggers navigation, and after modal changes or form submissions, snapshot again before the next action.
• Avoid blind waits. Wait for visible UI state when possible.
• Use action="emulate" with device, colorScheme, timezoneId, or locale when testing those settings; snapshot again afterward. Existing-session profiles do not support emulation.

5. Report real blockers:

• Debug network failures with action="requests", optional URL/type filter, and limit (default 50 recent entries). clear=true clears the collected log after reading. Use a managed profile; existing-session profiles do not support this log.
• Debug page errors with action="errors" and limit (default 50 recent entries). clear=true clears the collected log after reading. Existing-session profiles do not support this log.
• If the page needs login, permission, captcha, 2FA, camera/microphone approval, or another manual step, stop and tell the user exactly what is needed.
• Do not claim the browser is not logged in just because the current page shows a permission or onboarding dialog. Inspect the visible UI first.

Browser batch CLI

openclaw browser batch runs an array of nested /act actions in one /act call (the same kind="batch" runtime reached through the agent tool), so CLI users and scripts can combine actions like wait, click, type, and evaluate into a single replayable plan without per-action round trips. Each entry in actions[] is a BrowserActRequest — the closed union the /act route accepts — not arbitrary openclaw browser subcommands. batch is not supported on profile="user" and other existing-session (chrome-mcp) profiles; send actions individually there.

• CLI: openclaw browser batch --actions '<json>', --actions-file plan.json, or --actions-file - for stdin. --actions-file and stdin input are capped at 1,000,000 bytes; split larger plans into multiple batch commands. --continue sets stopOnError=false; default stops on first error.
• Ref lifecycle: refs come from a snapshot run before the batch (snapshot is not a nested action). A nested action that changes page state — such as a click that triggers navigation, or an evaluate that mutates the DOM — can invalidate earlier refs for the rest of the batch; put state-changing actions first, or split into a follow-up batch after re-snapshotting. Navigation and re-snapshotting happen outside the batch, since open, navigate, and snapshot are not /act kinds.
• Target id: nested actions share the request's tab; an explicit nested targetId that resolves to a different tab is rejected with ACT_TARGET_ID_MISMATCH.
• Response: { "results": [{ "ok": true } | { "ok": false, "error": "..." }, ...] } in order; with default stopOnError the array ends at the first failure. Any failed entry exits nonzero; use --json to preserve the full response in scripts.

Code Mode Loop

When tools.codeMode is enabled, the Browser tool has no normal turn — it is cataloged behind exec/wait. Call it from exec cells as an async global, using the callable name the exec quick index advertises for the Browser tool (normally browser; colliding names get suffixed, and a client tool can win an identical name). An exact catalog.search("browser") returns a handle already bound to the effective callable name, so resolve the handle in each cell and call it instead of hard-coding the literal global; an empty result means the Browser tool is not cataloged in this run.

Keep the same labeled tab through the loop, and alternate reads with actions. Each exec cell starts a fresh VM — bindings from a completed cell are gone in the next, and only runs left waiting keep their state until wait resumes them — so carry comparison state across cells by returning it and re-embedding the returned values in the next cell:

// previous = the url/newElements returned by the last completed cell (a fresh
// VM runs this cell, so prior bindings do not exist here).
const previous = { url: "https://example.com/inbox", newElements: 0 };
const [browser] = await catalog.search("browser", { limit: 1 });
const details = await browser({
  action: "snapshot",
  snapshotFormat: "ai",
  targetId: "task",
  refs: "aria",
  interactive: true,
});
const changed =
  details?.url !== previous.url ||
  (details?.newElements ?? 0) > 0 ||
  details?.blockedByDialog === true;
return {
  targetId: details?.targetId,
  url: details?.url,
  newElements: details?.newElements,
  stats: details?.stats,
  changed,
};

• Code-mode calls return the tool's structured details directly (targetId, url, newElements, stats, blockedByDialog); rendered page text is not returned to code cells.
• To read text inside code mode, run a targeted act evaluate (requires the evaluate capability; browser.evaluateEnabled can disable it) and keep the returned value bounded, because page-script output is untrusted:

const [browser] = await catalog.search("browser", { limit: 1 });
const read = await browser({
  action: "act",
  kind: "evaluate",
  fn: "() => document.body.innerText.slice(0, 2000)",
  targetId: "task",
});
return { url: read?.url, text: read?.result };

When evaluate is unavailable, keep the loop on structured state only.

• Return only the fields the next step needs; never return the whole details object.
• Completed cells share no state: re-embed the previous cell's returned url/newElements in the next cell, or keep the comparison inside one cell. Only waiting runs persist, resumed by wait.
• Interleave each act with a URL or tabs check before the next dependent act.
• If a batch returns aborted, take a fresh snapshot before continuing.
• If newElements is positive, inspect those elements first, then update the re-embedded state.
• Use separate act calls when navigation is expected between steps.

Tab Hygiene

Before creating a tab for a named task, list tabs and reuse an existing matching label or URL when it is still usable.

Example:

{ "action": "tabs" }

If no suitable tab exists:

{ "action": "open", "url": "https://example.com", "label": "task" }

Then target it by label:

{ "action": "snapshot", "targetId": "task", "refs": "aria" }

If a retry creates duplicates, close the extras by tabId:

{ "action": "close", "targetId": "t3" }

Do not pass bare numbers like "2" as targetId. Numeric tab positions are only for the CLI openclaw browser tab select 2 helper; browser tool calls need a suggestedTargetId, label, tabId, or raw target id.

Stale Ref Recovery

If an action fails with a missing or stale ref:

1. Snapshot the same targetId again.

2. Find the current visible control.

3. Retry once with the new ref.

4. If the UI moved to a blocker state, report the blocker instead of looping.

Existing User Browser

Use profile="user" only when existing cookies/login matter. This attaches to the user's running Chromium-based browser.

On macOS, action="importprofile" is the alternative when the agent should use an isolated managed browser with cookies copied from a real Chrome-family profile. First use action="profiles" and inspect systemProfiles, then import into a fresh managed profile name. Import asks for one Keychain/Touch ID consent prompt. It copies cookies, not local storage or IndexedDB; device-bound session credentials (DBSC) mean some Google sessions may still require re-authentication.

For profile="user" and other existing-session profiles, omit timeoutMs on act:type, hover, scrollIntoView, drag, select, and fill; that driver rejects per-call timeout overrides for those actions. act:evaluate accepts timeoutMs.

Google Meet Notes

When creating or joining a Meet:

• Treat camera/microphone permission screens as progress, not login failure.
• If asked whether people can hear you, click the microphone option when voice is required.
• If Google asks for sign-in, 2FA, account chooser confirmation, or permission that needs user approval, report the exact manual action.
• Use one labeled tab per meeting flow, for example label="meet", and reuse it during retries.