| Age | Commit message (Collapse) | Author |
|---|
|
The grant lives on globalThis so /reload keeps it, but nothing cleared it
when pi replaced the session in the same process. After /new, /resume or
/fork the next session started authorized and announced it in the footer.
Drop the saved grant on session_shutdown for new, resume and fork. Reload
keeps it. Quit leaves it alone, so a subagent quitting in the same process
does not take its parent's grant with it.
grant-scope.test.mjs loads the shipped module once per runtime in one
shared context, the way pi keeps globalThis across reloads and switches,
and checks the tools and the footer after each. It fails on 85b4988, and
its /chrome authorize cases fail with only the PI_CHROME_AUTHORIZE fix.
|
|
The env grant was saved to globalThis like a /chrome authorize grant. After
a /reload or a session switch (/resume, /fork, /new) the new runtime restored
it, skipped the env branch, and left envGranted false, so the footer
announced a grant the user never gave.
Read the variable again on each session_start instead of persisting it.
A restored grant now always comes from /chrome authorize. A timed env grant
restarts its countdown on each reload or switch.
|
|
page.upload and a raw DOM.setFileInputFiles through cdp.call now have to name
files whose real path is under /tmp/pi-chrome-uploads (PI_CHROME_UPLOAD_DIR),
on the broker's host. Anyone holding the token could otherwise attach any file
the user can read to a page.
|
|
A standing PI_CHROME_AUTHORIZE is not session state worth a line at the
bottom of every session that has it; announce only access the user granted
through /chrome authorize.
|
|
fork's own extension
|
|
|
|
pi 0.99+ ships MCP as a built-in, and the adapter suppresses it. The gate moves
from the adapter's approval event, which the built-in never emits, to pi's own
tool_call hook on mcp__<server>__*, which every call passes through, codemode
included. approveTools went with the adapter, so nothing backs the gate up: a
decision it cannot reach now denies rather than throws. server.mjs also treats
a client named plain "pi" as pi, which is how the built-in introduces itself.
From change request 562974, filed from the work laptop.
|
|
The README told pi users to install pi-chrome directly and run /chrome
authorize every session. That is not how this is used: pi reaches the same MCP
server through pi-mcp-adapter, with pi's own pi-chrome switched off, which is
why nobody types /chrome authorize.
pi/browser-gate.ts is that setup's missing piece, generalised from the one in
use: it answers pi-mcp-adapter's approval broker for one server, asking once per
session instead of once per call (the adapter's own grant only covers identical
arguments, so for a browser it asks nearly every time). /browser authorize,
/browser revoke, and PI_BROWSER_AUTHORIZE for headless runs. approveTools stays
on in mcp.json as the backstop if the gate does not load.
The README now leads with that: install the adapter, register the server in
mcp.json, copy the gate. Installing pi-chrome in pi is kept as the alternative,
with what it costs - two definitions of the browser, /chrome authorize per
session, and the trap of loading the extension twice.
Tested on an isolated pi config against a stand-in browser: with
PI_BROWSER_AUTHORIZE the call reaches the browser, without it the gate denies it.
|
|
|
|
PI_CHROME_REMOTE=host:port sends every command to a broker/broker.mjs there,
with its bearer token, instead of binding a bridge on this machine. Unset, the
extension behaves as upstream. A remote session never binds or takes over a
port: when the broker is unreachable the tools fail rather than drive some
other browser.
A pi-chrome-remote prompt section says which browser chrome_* drives and how
files move to and from its host; chrome_upload_file wants absolute paths there.
PI_CHROME_AUTHORIZE grants every session up front.
|
|
Upstream's bridge lives inside whichever pi session started first on the
machine running the browser, and only serves that machine. The broker takes
its place permanently: upstream's HTTP contract to the extension on loopback,
and /command and /status on a second, private address for other hosts, behind
a bearer token (PI_CHROME_TOKEN, or PI_CHROME_TOKEN_COMMAND).
|
|
|
|
0.15.54 opened Pi's automation target as a tab in the user's window while it
was full screen, assuming macOS would merge a new window into it as a hidden
window tab. Chrome disables automatic window tabbing (app_controller_mac.mm),
so that never happens; the hidden tabs came from the tab-group bug fixed in
0.15.56. Always prefer Pi's own window.
|
|
Chrome ignores clicks and typing in hidden pages. Doctor now asks the worker
whether this session's own tab is visible (automation.status includeVisibility,
which never creates or activates a tab) and reports the reason and fix when it
is hidden.
|
|
storage.session is wiped when the extension reloads, which it does on every
pi-chrome update, so Pi lost track of its automation window and session tabs
and left them behind. Mirror ownership to storage.local, restore it only when
the session copy is missing, re-check every restored tab (same window; adopted
tabs still in Pi's group), and drop the local copy on browser startup.
|
|
Fill whole textareas; cover new tabs' first page with early capture
|
|
chrome.tabs.group without createProperties.windowId creates the group in the
current (user's) window and moves the tab there, so a session's automation tab
left its dedicated window and became a hidden inactive tab. Make the unit mock
match Chrome's behavior.
|
|
|
|
chrome_fill's triple-click selected one line of a multi-line textarea, so fill
replaced only that line. Select value fields with the selectAll editing command
before deleting. Early capture now waits for in-flight tab.new creations, so a
first page that commits before the tab is tracked is still captured.
|
|
|
|
Make Chrome primer and authorization log prompt-cache friendly
|
|
- Contribute the primer as a structured prompt section instead of forcing systemPrompt.
- Log pi-chrome-tool-change as a rendered custom entry that is not sent to the model.
|
|
Stop console capture from tripping DevTools detection; scope early capture to Pi tabs
|
|
to Pi tabs
Fixes #9. Sites like BOSS Zhipin log an object with a getter/toString trap and
close the tab if it is read. Store captured console args raw and serialize them
on read without running page code (data properties only, accessors as [getter],
built-ins via native getters). Inject document-start capture only into Pi's
automation tab and session-tracked tabs.
|
|
Report hidden-tab input, append targeted typing, smarter uploads, prune screenshots; release 0.15.54
|
|
screenshots; release 0.15.54
- Check page visibility before trusted input: Chrome drops input to hidden pages (inactive tabs,
covered/minimized windows, macOS window tabs behind full screen). Type/key/hover/scroll/tap/drag
fail fast with the reason; click/fill use their DOM fallback immediately (or reject with
domFallback:false).
- Use an inactive tab instead of a new window for the automation target while the user's window is
full screen.
- chrome_type with uid/selector moves the caret to the end (moveToEndOfDocument) after its focus click.
- chrome_upload_file: labels/wrappers resolve to their file input, same-origin iframe search, and
intercepted file chooser for upload buttons (trusted click when visible, user-gesture click when
hidden); reject multiple paths for single-file inputs; no duplicate change event.
- Prune default-folder chrome_screenshot captures (7 days, newest 20 kept, retentionDays override).
- input.debug without a target no longer calls tabs.get(-1).
- New hidden-input unit suite.
|
|
Absorb fork fixes and features; release 0.15.53
|
|
Adapted from community forks (ardhiqii, kkunkunya, nihar-oracle, steimerbyte):
- Abort stalled /next long polls after 45s; time out, retry, and single-post results.
- Fall back to CDP Runtime.evaluate when chrome.scripting is refused (about:blank automation tabs).
- Load pi-chrome in same-process subagent sessions as a bridge client; client chrome_launch reports owner status.
- Add chrome_cdp (validated raw CDP passthrough, background-guarded, payload summarization) and chrome_cdp_targets.
- chrome_type reports before/after values, insertedAt, splice/unchanged warnings; add replace=true.
- includeSnapshot waits for navigations started by the action; tab.new reports the settled tab.
- CDP timeouts surface as timeouts and are not re-sent after the cleanup detach.
- Activate/deactivate chrome_find and chrome_inspect with the rest of the chrome_* tools.
- New unit suites: bridge-resilience, cdp-passthrough, type-evidence.
|
|
Simplify Chrome status commands and release 0.15.51
|
|
|
|
docs: clarify background controls and release 0.15.50
|
|
|
|
docs: improve pi-chrome README and onboarding
|
|
|
|
Improve Chrome input reliability and release 0.15.49
|
|
|
|
Enforce hard background and release 0.15.48
|
|
|
|
Fix session cleanup and release 0.15.47
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
