List all open tabs with IDs, URLs and state. Call it first in every session, after a reconnect, or when unsure; reuse a listed tab ID instead of opening duplicates. Cheap, call liberally.

See what is on the page: text plus stable element refs for click/type/fill_form. Default filter 'interactive' lists actionable elements; for paragraphs or table cells call view_page(ref, filter: 'all'). Collapsed containers show as [eXX role, N items] — expand with view_page(ref: 'eXX', filter: 'all').

Click an element by ref, CSS selector, visible text, or viewport x/y (canvas, pixel-precise targets). Dispatches real CDP mouse events. A click that opens a new tab is reported in the response. The DOM diff (NEW/REMOVED/CHANGED) arrives with the next response, or in this one with wait_for_diff: true.

Type text into an input identified by ref or CSS selector. For 2+ fields use fill_form; for special keys (Enter, Escape, Tab, arrows) or shortcuts (Ctrl+K) use press_key.

Fill a whole form in one call: text inputs, (by value or visible label), checkboxes (boolean) and radio buttons. One round-trip; partial errors do not abort and each field reports its own status. On per-field errors call view_page and retry the failing fields.

Press a key or shortcut (Enter, Escape, Tab, arrows, Ctrl+K). Optionally focus an element first via ref or selector.

Scroll the page, a container, or an element into view. Reports the position and content growth (scrollHeight delta — detects lazy-loaded content) and handles settle timing. Use container_ref/container_selector plus direction to scroll inside a container.

Drag via native CDP mouse events. Works for CSS-driven drag: slider thumbs, resize handles, text selection, mouse-based reorder lists (SortableJS in mouse mode). NOT for the HTML5 Drag&Drop API (draggable=true with dragstart/drop listeners, React DnD HTML5Backend, Vuedraggable, ng2-dnd) — that needs Input.dispatchDragEvent. Source: from_ref/from_selector or from_x+from_y; target: to_ref/to_selector or to_x+to_y.

Navigate the active tab to a URL, or action 'back' / 'reload' (all refs become stale after reload). Waits for settle. Overwrites the user's active tab — check virtual_desk first; the first call per session is redirected to virtual_desk.

Open a new tab, switch to a tab by ID (from virtual_desk), or close one. Prefer 'open' over navigate when the user's active tab must stay untouched. Refs from the previous tab are invalid afterwards — call view_page before acting.

Active tab's cached URL, title, ready state and errors — a cheap mid-workflow sanity check ('did my click navigate?'). Not for tab discovery or page content.

Wait until a condition holds: element visible, page text present, URL match, network idle, or a JS expression true. Prefer condition 'text' over a JS expression for 'has the page said X yet'. assert: true checks once and fails instead of waiting.

Watch an element for changes instead of polling with MutationObserver/setInterval code in evaluate. collect: record text/attribute changes for 'duration' ms. until: wait for a condition, then optionally click at once (then_click). click_first fires the triggering action after the observer is armed, so nothing is missed.

Pixel-level screenshot (WebP, max 800px, <100KB). Only for canvas or chart content without DOM text, pixel-level rendering or animation checks, or when the user explicitly asks for a screenshot. Returns no refs and reads no text — that is view_page.

Structured layout data: bounding boxes, computed styles, paint order, colors; refs match view_page. Only for spatial questions view_page cannot answer (is A above B? what color?).

Configure handling of alerts, confirms and prompts. Set it BEFORE triggering the action that opens the dialog. Uses CDP Page.javascriptDialogOpening, so it works even while the dialog blocks all JS.

Upload file(s) to an identified by ref or CSS selector; file paths must be absolute.

Read collected browser console logs; filter by level (info/warning/error/debug) and/or regex; optionally clear the buffer after reading.

Capture network requests via CDP, including those the page issues itself. Workflow: start → trigger the action → get(pattern: 'api').

Wait for pending downloads or list this session's downloaded files. Downloads start by themselves when you click a download link or open a file URL (PDF, CSV, …); this tool never triggers them. download() waits for a pending download to finish; download({ action: 'list' }) returns at once.

View or set session defaults for recurring parameters (tab, timeout, …). Without params: show current defaults and auto-promote suggestions; autoPromote: true applies them. Set profile BEFORE any browser interaction to launch Chrome with a named profile.

Batch the next 2+ known actions (click, type, scroll, view_page chains) here instead of N separate calls: a sequence of tool steps, executed server-side in one call. Variables via vars and saveAs ($name), conditions (if), suspend/resume to ask the agent mid-plan, errorStrategy abort | continue | capture_image, and parallel groups per tab: parallel: [{ tab, steps }].

Visit several URLs in sequence and run the same JS expression on each. For controlled checks across known pages where view_page/run_plan would be too chatty; not for normal reading, clicking or form work.

Write a payload larger than 1 MB into window.__pb_data[key], chunked past the CDP 1 MB message limit. Source: inline (data) or file (absolute path, read as binary). The page reads window.__pb_data[key] (string or ArrayBuffer per encoding) and window.__pb_data[key + '__complete'] === true. Never write one key from parallel calls — they race. Under ~200 KB use evaluate; for a real use file_upload.

Run JavaScript in the page. Good uses: computation, style mutations (.style.X = ..., classList), shadow-root traversal, in-page fetch(), app-specific side effects no dedicated tool covers. Scope is shared between calls; top-level const/let/class are wrapped in an IIFE. If/else blocks may return undefined — use a ternary or an explicit return.