sz-chrome-remote-cdp.git/src/prompt.ts, branch master

feat(prompt): say which Chrome browser_* drives

2026-10-14T11:19:26+00:00

The prompt told the model it drives "the user's running instance". With this fork's default that is wrong: it is castle's shared Chrome, signed out of every account. It now matters which is which, because pi-chrome's chrome_* tools drive the user's signed-in Brave, and the model has to route between the two. getBrowserSystemPrompt() takes the resolved target and describes it: castle's shared browser for the built-in default, the user's own Chrome for local, the endpoint otherwise.

refactor: remove duplicate browser prompt instructions (#35)

2026-10-11T18:25:38+00:00

Remove browser instruction text repeated across tool descriptions, parameter schemas, tool guidelines and the global browser prompt. Tool names, schemas, handlers and concurrency are unchanged; shared recovery and ownership guidance is now available before and after the browser connects, and the prompt names which tools are serialized versus observations. Co-Authored-By: Claude Fable 5.1

feat: add per-tab request headers (#30)

2026-09-08T18:35:42+00:00

Expose explicit set and clear tools so environment-routed pages can be opened without leaking header values or carrying headers across unrelated browsing. Co-Authored-By: Claude Sonnet 4.6 noreply@anthropic.com Co-authored-by: zouzhigang

feat: add forms domain and durable window binding (v0.9.0) (#14)

2026-07-21T19:29:58+00:00

- Add forms domain with a universal field setter that auto-detects element type and fires framework-compatible input events (React native-setter trick) - Add window-binding helper to capture and bind the real Chrome windowId as the session's durable window identity on every new-window code path - Wire supporting changes across CDP session/ownership, client, navigate, isolated-tab, prompt, and state - Add manual tests for forms and window binding - Bump version 0.8.3 -> 0.9.0 Co-authored-by: Claude Opus 4.8 (1M context)

feat: address elements by stable refs across re-renders (#8)

2026-06-28T18:32:54+00:00

Interaction tools could only target elements by raw viewport coordinates (browser_click) or model-guessed CSS selectors (browser_fill/focus/ select_option/upload). Neither survives a re-render: on React/SPA forms, every save or edit reflows the page, so captured @(x,y) coordinates go stale and guessed selectors miss — leaving the agent to fall back to hand-rolled execute_js DOM walks and unnoticed failed saves. Add a stable ref system, mirroring Playwright MCP / browser-use: - snapshot assigns each interactive element a ref (e1, e2, …), shown as [eN] in the outline, and publishes a per-tab ref → backendNodeId map - interaction tools accept an optional `ref` that re-resolves the element at call time (via DOM.resolveNode / getBoxModel), so it stays valid across re-renders; coordinates/selectors remain as fallbacks - mutating tools append a compact diff of changed / newly-appeared (*) / removed interactive elements, so silent failed saves surface immediately - stale refs return an actionable "re-snapshot" error instead of a miss Ref map is replaced per snapshot (bounded memory); fill keeps the native _valueTracker write path so React controlled inputs still update. Co-authored-by: Claude Opus 4.8

feat: add per-tab isolation for multi-agent safety

2026-05-07T18:48:15+00:00

Replace singleton dialog, pageInfoDirty, networkBuffer, and consoleBuffer with per-tab TabSession objects stored in a Map. - Add TabSession type (sessionId, targetId, dialog, pageInfoDirty, networkBuffer, consoleBuffer) and tabs/sessionIdToTargetId Maps - Add ev.sessionId filter guard in consumeEvents to prevent cross-tab event contamination - Rework switchTo to create/reuse TabSession without clearing buffers, updating sessionId on re-attach - Route all CDP events (dialog, network, console) through resolveTab to the correct TabSession - takeDialog/drainPageInfoInvalidations/drainNetworkBuffer/ drainConsoleBuffer read from current TabSession - Target.targetDestroyed prunes dead TabSession entries - attachFirstPage creates initial TabSession and prunes dead entries - Per-tab pageCaches Map in client.ts replaces pageCache singleton - listTabs reconciliation prunes dead pageCaches entries - console-buffer.ts clear() resets nextSeq to 1 (per-tab seq space) - Multi-agent warning in prompt.ts Parallel Execution section

release: v0.5.0 — browser_console tool for JS error/console diagnostics

2026-05-07T07:24:12+00:00

feat: parallel tool execution with automatic mutation serialization

2026-05-04T17:14:55+00:00

- Add lightweight async mutex (src/util/mutex.ts) for FIFO serialization - Add serialized?: boolean to BrowserToolDefinition - Wire mutex acquisition into registerBrowserTool execute wrapper - Expose mutationMutex() on BrowserClient - Mark all mutation tools (click, type, scroll, navigate, switch_tab, etc.) as serialized - Leave observation tools (screenshot, page_info, execute_js, http_get, etc.) unguarded - Update prompt and skill docs to reflect parallel-safe behavior - Fix scroll tool: add Page.bringToFront, explicit button:none/buttons:0/pointerType:mouse - Update .gitignore to ignore scripts/ and data/ folders

feat: render screenshots inline in TUI via Image component; add parallelization guidance to SKILL.md

2026-05-02T19:13:43+00:00

- browser_screenshot now has renderResult that creates an Image component for inline display in Kitty/iTerm2/Ghostty/WezTerm terminals - Falls back to dim text placeholder on terminals without image support - Updated system prompt table description to mention TUI inline rendering - Added Parallelization section to SKILL.md teaching the agent to batch independent operations (browser_open_urls, browser_http_get, etc.)

refactor: drop legacy daemon usage from index/setup; trim state; move 4 files to strict tsconfig

2026-05-02T11:14:52+00:00

Co-Authored-By: Claude Sonnet 4.6