all repos — sz-chrome-remote-cdp @ f73941cbca4a2d765b140d474ab4e05e1008d93f

pi-browser-harness, patched to drive a Chrome on another host over CDP, with castle_cdp_search web search

f73941cb
fix: prevent TUI crash when screenshot path overflows terminal width (#2)

The Image text-fallback render does not respect the rendered width,
so a long file path can blow past the terminal width and crash the
host TUI. Wrap the component to truncate each rendered line with
truncateToWidth so it fits the available width.

Co-authored-by: amankumarsingh77 <amankumarsingh7702@gmal.com>
Aman Kumar 145339995+amankumarsingh77@users.noreply.github.com
Tue, 05 May 2026 00:52:11 +0530
71da8e07
feat: parallel tool execution with automatic mutation serialization

- 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
amankumarsingh77 amankumarsingh7702@gmal.com
Mon, 04 May 2026 22:44:55 +0530
2a98be01
Revert "chore: add pre-parallel-execution latency baseline"

This reverts commit 361f4b31f7870f0a8bbd46793edc46c9967fdd69.
amankumarsingh77 amankumarsingh7702@gmal.com
Mon, 04 May 2026 21:18:34 +0530
361f4b31
chore: add pre-parallel-execution latency baseline
amankumarsingh77 amankumarsingh7702@gmal.com
Mon, 04 May 2026 21:17:21 +0530
7d70b2ba
docs: add speed-optimizations research; chore: improve browser detection in setup
amankumarsingh77 amankumarsingh7702@gmal.com
Mon, 04 May 2026 21:14:30 +0530
cb9a51eb
feat: render screenshots inline in TUI via Image component; add parallelization guidance to SKILL.md

- 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.)
amankumarsingh77 amankumarsingh7702@gmal.com
Sun, 03 May 2026 00:43:43 +0530
ff485923
fix: replace @ts-expect-error with @ts-ignore for dynamic sharp import
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 22:15:41 +0530
167c50de
chore: update lock file for sharp optional dependency
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 22:01:18 +0530
a1df2d3e
release: v0.3.1 — audit fixes for list_tabs IDs, switch_tab prefix 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
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 21:59:30 +0530
c9d1605b
chore: address final-review minors — surface event-consumer crashes, 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>
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:53:34 +0530
500dd206
chore(release): v0.3.0 — internal rewrite
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:50:13 +0530
43b74f78
chore: final cleanup — drop unused keyCode export
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:48:19 +0530
bb691459
refactor: delete legacy daemon, tools, protocol, renderers; collapse to single tsconfig
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:46:12 +0530
c86b220d
refactor: drop legacy daemon usage from index/setup; trim state; move 4 files to strict tsconfig

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:44:52 +0530
0f717bc7
feat(domains): migrate execute_js and run_script with path allowlist + timeout + return validation
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:41:15 +0530
b7fd72a6
feat(domains): migrate http_get (timeout covers body) and get_network_log (deprecation note)
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:36:50 +0530
96934b77
feat(domains): migrate drag_and_drop
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:35:30 +0530
dc07a515
feat(domains): migrate viewport_resize
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:34:39 +0530
5664dc8f
feat(domains): migrate upload_file (safeJs), download (validated dir), print_to_pdf
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:32:07 +0530
e8650dc5
feat(domains): migrate tab tools (list, current, switch, new)
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:28:15 +0530
1d0873c7
feat(domains): migrate go_back, go_forward, reload
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:26:01 +0530
3dfc4f11
feat(domains): migrate navigate (NavOutcome) and open_urls

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:24:23 +0530
6708da54
feat(domains): migrate screenshot, add typed sharp shim, restore click crosshair overlay
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:20:09 +0530
9ead6a05
feat(domains): migrate handle_dialog
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:16:24 +0530
1b11036e
feat(domains): migrate page_info, wait, wait_for_load with typed timeout
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:14:52 +0530
307f9e74
feat(domains): migrate scroll with W3C deltaY semantics and dialog guard
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:12:36 +0530
41e3b69b
feat(domains): migrate type, press_key, dispatch_key with safeJs and matched-count validation
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:08:50 +0530
0f962ef9
feat(domains): migrate browser_click to defineBrowserTool — vertical slice

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.
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:05:09 +0530
6a4bfa31
feat: add defineBrowserTool helper, truncation, schemas/common, empty registry

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 16:00:58 +0530
d3d86f9d
fix(cdp): serialize event consumer; persist dialog until taken; validate page info shape
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 15:55:44 +0530
71228dea
feat: add CDP session and BrowserClient factory
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 15:52:10 +0530
52fd9523
fix(cdp): validate inbound CDP messages with a runtime type guard
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 15:48:28 +0530
22019a65
feat(cdp): add factory-based transport with Result and event AsyncIterable
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 15:46:05 +0530
73caf309
fix(cdp): clear socket timer on probe success; surface non-ENOENT readFile errors
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 15:43:52 +0530
962ae380
feat(cdp): port DevToolsActivePort discovery to Result
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 15:42:07 +0530
ede4b89e
feat(cdp): add types and error model for new transport layer
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 15:40:27 +0530
10f44002
build: enable strict tsconfig flags for new code, keep legacy lenient
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 15:39:06 +0530
60ddf56f
docs(util): clarify safeJs trust boundary and unsupported value types
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 15:38:07 +0530
31afcecd
feat(util): add pure keycodes and safeJs template helper
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 15:36:13 +0530
64cb4c87
fix(util): preserve AbortSignal.reason; validate namespace in temp paths
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 15:33:27 +0530
310d0a73
feat(util): add result, time, and paths primitives for v0.3 rewrite
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 15:31:01 +0530
6759b6fd
feat: v0.2.1 — feature parity with browser-use/browser-harness

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>
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 15:29:23 +0530
5b76aa34
docs: add v0.3.0 harness rewrite implementation plan

27 tasks: foundations → CDP transport/session/client → defineTool helper
→ vertical slice (click) → 13 domain migrations → wire-up + delete legacy
→ smoke + release. Each task has concrete code, exact file paths, and a
typecheck checkpoint.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 15:17:27 +0530
f6204b10
docs: add v0.3.0 internal-rewrite design spec

Per-domain module split, frozen tool names, normalized params, unified
Result+details contract. Captures the full audit (predictability bugs,
security gaps) and the structural fixes for each.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 15:05:19 +0530
fa54f769
perf: v0.2.0 — event-based waitForLoad, fast ensureAlive, JPEG 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.
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 11:40:20 +0530
b77c5ec3
ci: suppress npm pack notice output
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 00:42:32 +0530
e865b26f
fix: commit package-lock.json for CI reproducibility

Removes package-lock.json from .gitignore so npm ci works in CI.
Without the lock file, actions/setup-node cache resolution fails
and npm ci has no dependency tree to install from.
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 00:40:51 +0530
5762eae6
docs: rewrite README — add hero image, condense tools, fix accuracy

- Add hero image banner at top
- Merge 4 tool tables into 1 compact reference table
- Fix tool syntax to match actual parameter schemas
- Add Core Patterns section (navigation, form fill, extraction, research)
- Add Dialogs, SPAs, Keyboard modifiers subsections
- Add What NOT to do section
- Add Architecture diagram
- Add Contributing link
- Remove verbose/duplicate usage examples
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 00:38:39 +0530
40c18b22
chore: update hero image
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 00:30:00 +0530
a122a32a
fix: normalize repository.url for npm
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 00:09:37 +0530
ae223796
chore: prepare v0.1.0 release

- Add hero image for pi package gallery
- Update CHANGELOG with release date
- Update README with npm install instructions
- Add assets/ to npm package files
- Add CONTRIBUTING.md and GitHub templates
- Add CI workflow for typecheck and pack validation
amankumarsingh77 amankumarsingh7702@gmal.com
Sat, 02 May 2026 00:08:22 +0530
28578d1d
Replace dynamic tool registration with browser_run_script

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.
amankumarsingh77 amankumarsingh7702@gmal.com
Thu, 30 Apr 2026 17:52:26 +0530
b6d75222
fix: stop Chrome remote-debugging consent popup storm

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.
amankumarsingh77 amankumarsingh7702@gmal.com
Thu, 30 Apr 2026 13:09:27 +0530
63b16957
Replace socket daemon with direct CDP WebSocket connection

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.
amankumarsingh77 amankumarsingh7702@gmal.com
Wed, 29 Apr 2026 01:38:17 +0530
5317b329
Fix repo/bug URLs to point to amankumarsingh77/pi-browser-harness
amankumarsingh77 amankumarsingh7702@gmal.com
Wed, 29 Apr 2026 00:41:40 +0530
8fff9152
Initial release: pi-browser-harness

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.
amankumarsingh77 amankumarsingh7702@gmal.com
Wed, 29 Apr 2026 00:40:36 +0530