aboutsummaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Collapse)Author
2026-05-02fix: replace @ts-expect-error with @ts-ignore for dynamic sharp importamankumarsingh77
2026-05-02release: v0.3.1 — audit fixes for list_tabs IDs, switch_tab prefix ↵amankumarsingh77
matching, download auto-mkdir, session recovery, docs updates Bug fixes: - list_tabs: show full 32-char targetIds (was truncated to 8 chars) - switch_tab: prefix matching fallback for hex prefixes >= 8 chars - download: auto-create directory with mkdir -p - ensureAlive: Runtime.evaluate probe to recover from crashed page targets Docs: - dispatch_key: clarify DOM-only event behavior - navigate: warn about Google anti-bot limitation - network_log: update deprecated promptSnippet - SKILL.md: document actual daemon API (evaluateJs, pageInfo, session.call) - SKILL.md: add troubleshooting for sharp/maxDim and Google navigation - sharp: add to optionalDependencies for screenshot maxDim auto-resize
2026-05-02chore: address final-review minors — surface event-consumer crashes, ↵amankumarsingh77
document IIFE-wrap heuristic, log shutdown failures, fix CHANGELOG file-size claim Five tweaks from the whole-implementation review: - session.ts: log unexpected event-consumer rejections instead of silent swallow - client.ts: comment the return-substring IIFE-wrap false-positive case - transport.ts: comment that ws.onclose post-open settle is no-op-by-design - index.ts: log client.stop() failures during shutdown - CHANGELOG.md: correct largest-file claim (transport.ts and client.ts are ~220 each, not "client.ts at ~180") Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02chore: final cleanup — drop unused keyCode exportamankumarsingh77
2026-05-02refactor: delete legacy daemon, tools, protocol, renderers; collapse to ↵amankumarsingh77
single tsconfig
2026-05-02refactor: drop legacy daemon usage from index/setup; trim state; move 4 ↵amankumarsingh77
files to strict tsconfig Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-02feat(domains): migrate execute_js and run_script with path allowlist + ↵amankumarsingh77
timeout + return validation
2026-05-02feat(domains): migrate http_get (timeout covers body) and get_network_log ↵amankumarsingh77
(deprecation note)
2026-05-02feat(domains): migrate drag_and_dropamankumarsingh77
2026-05-02feat(domains): migrate viewport_resizeamankumarsingh77
2026-05-02feat(domains): migrate upload_file (safeJs), download (validated dir), ↵amankumarsingh77
print_to_pdf
2026-05-02feat(domains): migrate tab tools (list, current, switch, new)amankumarsingh77
2026-05-02feat(domains): migrate go_back, go_forward, reloadamankumarsingh77
2026-05-02feat(domains): migrate navigate (NavOutcome) and open_urlsamankumarsingh77
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-02feat(domains): migrate screenshot, add typed sharp shim, restore click ↵amankumarsingh77
crosshair overlay
2026-05-02feat(domains): migrate handle_dialogamankumarsingh77
2026-05-02feat(domains): migrate page_info, wait, wait_for_load with typed timeoutamankumarsingh77
2026-05-02feat(domains): migrate scroll with W3C deltaY semantics and dialog guardamankumarsingh77
2026-05-02feat(domains): migrate type, press_key, dispatch_key with safeJs and ↵amankumarsingh77
matched-count validation
2026-05-02feat(domains): migrate browser_click to defineBrowserTool — vertical sliceamankumarsingh77
Implements Task 9: adds src/domains/click.ts with the new architecture, updates registry.ts to register clickTool, removes the legacy browser_click block from tools.ts, and wires BrowserClient alongside BrowserDaemon in index.ts so both systems coexist during migration. Also fixes AnyBrowserToolDefinition variance: uses never-arg renderCall in the erased type and a boundary cast in registerBrowserTool so concrete tool definitions (with specific Static<S> args) are assignable to the registry array without widening.
2026-05-02feat: add defineBrowserTool helper, truncation, schemas/common, empty registryamankumarsingh77
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-02fix(cdp): serialize event consumer; persist dialog until taken; validate ↵amankumarsingh77
page info shape
2026-05-02feat: add CDP session and BrowserClient factoryamankumarsingh77
2026-05-02fix(cdp): validate inbound CDP messages with a runtime type guardamankumarsingh77
2026-05-02feat(cdp): add factory-based transport with Result and event AsyncIterableamankumarsingh77
2026-05-02fix(cdp): clear socket timer on probe success; surface non-ENOENT readFile ↵amankumarsingh77
errors
2026-05-02feat(cdp): port DevToolsActivePort discovery to Resultamankumarsingh77
2026-05-02feat(cdp): add types and error model for new transport layeramankumarsingh77
2026-05-02docs(util): clarify safeJs trust boundary and unsupported value typesamankumarsingh77
2026-05-02feat(util): add pure keycodes and safeJs template helperamankumarsingh77
2026-05-02fix(util): preserve AbortSignal.reason; validate namespace in temp pathsamankumarsingh77
2026-05-02feat(util): add result, time, and paths primitives for v0.3 rewriteamankumarsingh77
2026-05-02feat: v0.2.1 — feature parity with browser-use/browser-harnessamankumarsingh77
Adds the missing tools called out in docs/browser-harness-comparison.md: upload_file, dispatch_key, download (configure dir), viewport_resize, drag_and_drop, print_to_pdf, get_network_log, plus the iframe-target helper. Updates promptGuidelines and the system prompt's tools table. Tracked in todo.md. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02perf: v0.2.0 — event-based waitForLoad, fast ensureAlive, JPEG ↵amankumarsingh77
screenshots, page info caching 5 performance optimizations (14-36% faster end-to-end, output quality unchanged): - fast ensureAlive(): WS state check instead of CDP roundtrip (96% faster per-call) - event-based waitForLoad(): CDP load events instead of 300ms polling (99.5% faster for loaded tabs) - JPEG screenshot support: 29-49% smaller files, faster CDP transfer - page info caching: 1s TTL eliminates redundant evaluateJS calls - parallel domain enables: Promise.all instead of sequential await in switchTab() Benchmark: 3622ms vs 4243ms baseline on 3-tab navigation + screenshot task.
2026-04-30Replace dynamic tool registration with browser_run_scriptamankumarsingh77
Remove register_tool/remove_tool/list_dynamic_tools and the entire dynamic-tools.ts module. Replace with a single browser_run_script tool that executes temporary scripts from disk with daemon access. Scripts are now written to disk before execution, making them auditable and re-runnable. Same bindings (daemon, require, params, etc.) as before via the same AsyncFunction mechanism.
2026-04-30fix: stop Chrome remote-debugging consent popup stormamankumarsingh77
Previously a single consent-pending socket could spawn up to 5 stacked 'Allow remote debugging?' dialogs. Three causes: - onopen reset _reconnectAttempts, but Chrome accepts the WS upgrade before the user clicks Allow, so a held socket looked healthy. - ensureAlive's health probe used the full 15s CDP timeout; while the user was reading the dialog the probe would time out, trigger a stop()+start(), and a fresh popup would stack on top. - onclose auto-reconnected unconditionally even when consent had never been granted on that connection. Now a connection is only considered healthy once the first CDP roundtrip completes (attachFirstPage). ensureAlive does a 2s short probe before tearing down the socket. onclose bails out of auto- reconnect when consent was never observed, so a denied dialog surfaces a clean error instead of looping.
2026-04-29Replace socket daemon with direct CDP WebSocket connectionamankumarsingh77
Drops the Unix socket subprocess in favor of talking CDP directly over WebSocket from the extension. Removes the protocol's send/health helpers, simplifies setup to just verifying Chrome's remote debugging port, and tightens types in dynamic-tools. Bumps Node engine to >=22 and adds the ws dependency.
2026-04-29Initial release: pi-browser-harnessamankumarsingh77
Browser control extension for pi — 20 browser_* tools for navigating, clicking, typing, screenshotting, and extracting data from real Chrome via CDP. Includes self-extending harness (register_tool/remove_tool), guided /browser-setup, session persistence, and custom TUI renderers.
generated by cgit v1.2.3 (git 2.39.1) at 2026-11-15 11:46:23 +0000