| Age | Commit message (Collapse) | Author |
|---|
|
Browser.setDownloadBehavior was sent without a browserContextId, so the override applied to the
user's default context and outlived the session. browser_download now takes restore:true, tracks
the override this process set, and a clean session shutdown restores Chrome's default with a
bounded call that is skipped when the browser is already gone.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
|
|
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 <noreply@anthropic.com>
|
|
node_modules (#28)
Inside a Bun-compiled pi binary (pi.exe), createRequire().resolve("tsx/cli") is rooted at the
embedded virtual filesystem and cannot see the extension's real node_modules, so browser_setup
failed instantly. The resolver result is now checked on disk and, when it fails, the tsx CLI is
found by walking up the node_modules chain. Under Bun the daemon runs on `node` from PATH
(process.execPath is the pi binary itself); PI_BROWSER_NODE overrides it.
Fixes #27
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
|
|
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 <zouzhigang@bytedance.com>
|
|
ARCHITECTURE.md: the layer map gains domains/cdp-call.ts as the single
door and the helper-module/tool-module split; the "cdpCall vs
session.call" section is replaced, since snapshot.ts no longer mixes
styles — it swallows failures through cdpCall instead of around it. Rule 1
now says tool files export only tools, rule 7 names the enforced scanner
rules, and the two 250-line exceptions are recorded as largely settled
(snapshot 477 to 256, form 409 to 283). Also notes the one honest gap:
session.attach and session.windowId perform CDP calls the rules do not
match.
README: BU_CDP_WS carries its daemon-restart caveat, BH_DEBUG_CLICKS is
documented as the flag's equivalent, and the tool count matches the
registry (38 to 40).
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
|
The harness ships browser tools; orchestrating a multi-agent research
workflow on top of them is the agent's job, not this extension's. Drops
the skill, the /deep-research command, and the web-search-researcher
subagent config.
browser_web_search and browser_read_page are untouched — the two tests
that covered their pure parsers move to test/domains/, where the test
glob still picks them up.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
|
|
|
* feat: pin the agent to a chosen browser profile (#15)
Harness tabs were created with a bare Target.createTarget, which places
them in Chrome's defaultBrowserContextId — and that value follows window
focus. Which profile the agent acted as therefore depended on which
browser window the user last clicked, so the same task could run as a
work account on one run and a personal account on the next.
/browser-profile lists the connected browser's profiles as "Name (email)"
and pins one to ~/.pi/agent/browser-harness.json, so the choice outlives
the session. The same picker appears on first browser_setup when nothing
is pinned; with no interactive UI, or on cancel, setup continues with a
note and the previous behavior.
Chrome offers no direct route to another profile: Target.createTarget
rejects a foreign browserContextId, and openerId does not inherit the
opener's context. The window is opened through the browser's own command
line (--profile-directory, handed to the running browser by Chromium's
ProcessSingleton) and identified by a unique file:// sentinel page, since
a bare about:blank#token argument is discarded. Further tabs come from
window.open evaluated with userGesture: true — the only CDP-reachable way
to place a tab in a non-default browser context — correlated by a unique
token so concurrent isolated tabs stay distinct. A failed handshake is
reported, never silently redirected to another profile.
All four tab-creation sites now funnel through cdp/target-factory, so
open_urls and the isolated tabs behind web_search / read_page cannot run
with a different profile's cookies than the visible tabs.
Also fixed along the way: snap Chromium is discovered, Windows uses
%LOCALAPPDATA%, browsers launched with an explicit --user-data-dir are
found, the running browser is chosen by ranking candidates against the
connected user-data-dir rather than taking the first process found, and
an installed-but-closed browser no longer reads as running.
CI runs the profile suites and a real-browser end-to-end test on ubuntu,
macOS, and Windows — profile discovery is the one part of the harness
whose behavior genuinely differs per OS.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix: single-flight harness window creation
Isolated tabs run concurrently (browser_read_page is registered
unserialized), so several could each find "no harness window" and create
one — two blank windows before this feature, two LAUNCHED profile windows
after it. ensureHarnessWindow now shares one in-flight creation per
client.
Sharing introduces a second hazard: freshlyCreated is a claim on the seed
tab, and if every waiter received it, they would all drive the same tab.
Only the caller that started the creation keeps the claim; the rest open
their own tab beside it.
Covered by test/manual/profile-concurrency-test.ts (five concurrent
isolated tabs, pinned and unpinned: distinct targets, one window, correct
profile), wired into CI on Linux only — the coordination is pure JS and
identical across platforms.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix: tilde expansion differs by purpose on Windows
CI on windows-latest caught this: join("~", "x") yields "~\x" there, and
expandTilde only handled "~/".
The two uses are not the same, so they no longer share a helper. The
agent dir stays byte-compatible with pi's own expandTildePath ("~/" only,
every platform) — being more lenient would put the pin file somewhere pi
never looks. $CHROME_USER_DATA_DIR is ours to interpret, so it accepts
"~\" as well, which is what a Windows user would type.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
|
The README taught the coordinate-first interaction model that the harness
replaced with stable [eN] refs, and documented 22 of the 38 registered
tools. Restructured so each section answers one question, and rewrote the
content against the actual tool registry.
- Teach the ref-first model: snapshot yields [eN] handles that re-resolve
at action time, with coordinates as the fallback rather than the default.
- Document the 16 missing tools: the forms path (fill/select_option/focus),
console, wait_for, dispatch_key, drag_and_drop, upload_file, download,
print_to_pdf, viewport_resize, close_tab, and setup.
- Rebuild the comparison table as prose cells grouped by dimension. Drops
the unverifiable "unknown" rows and the duplicated click/dispatch claims,
and adds a provenance line so competitor claims stay correctable.
- Remove stale guidance: /browser-reload-daemon as the fix for a Chrome
restart (auto-reconnect landed in 0.6.0), and the unbenchmarked "10-50x
faster" claim on http_get.
- Add sections for concurrency and tab isolation, flags and environment
variables (BU_CDP_WS, BU_CDP_PORTS, BH_SCRIPT_DIR), and a troubleshooting
table keyed to the errors the harness actually emits.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
|
deep-research skill fans out to isolated web-search-researcher subagents (now
using browser_web_search + browser_read_page instead of the non-existent
web_search/web_fetch), coverage-driven loop with a hard ceiling, synthesizes a
cited Markdown report. /deep-research command as explicit entry point. Docs updated.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
|
Adds a "Why pi-browser-harness?" comparison table (vs Playwright MCP, Stagehand,
Puppeteer MCP) at the top, surfacing the differentiators a chooser actually
cares about: real Chrome, coordinate clicks through iframes/shadow DOM, inline
TUI rendering, AX tree with @(x,y) coords, parallel execution, scripts.
Tool list reorganized into "Page inspection (use these by default)" / "Visual
(last resort)" / Navigation / Interaction / Utility — adds browser_snapshot,
browser_network_requests, browser_close_tab. Patterns rewritten snapshot-first;
form filling and research no longer screenshot. New sections for parallel
execution and tab ownership. Temporary scripts example fixed to use the actual
daemon.session().call() binding. Three explicit anti-screenshot rules in
"What NOT to do".
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
|
- 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
|
|
- 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
|
|
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.
|
|
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.
|
|
|
|
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.
|
