Commit Graph
411 Commits
Author SHA1 Message Date
Chris Tate 82386b1c60 fix links (#699) 2026-03-09 17:33:40 -05:00
Chris Tate c309535691 sandbox docs (#698)
* sandbox docs

* format
2026-03-09 17:09:05 -05:00
Mason Williams d0651f14bc Make KERNEL_API_KEY optional for external credential injection (#687)
* Make KERNEL_API_KEY optional for external credential injection

When running inside environments with external credential injection
(e.g. Vercel Sandbox credentials brokering), the KERNEL_API_KEY env
var can be omitted. The network layer injects the Authorization header
on outbound requests to api.onkernel.com, so the API key never needs
to exist inside the sandbox.

If KERNEL_API_KEY is set, it's used as before. If not, requests are
sent without an Authorization header, allowing external injection.
Without either, the Kernel API returns 401.

Made-with: Cursor

* Make KERNEL_API_KEY optional in native Rust daemon too

Applies the same change to the native Rust connect_kernel() function
so both the Node.js and native code paths support external credential
injection.

Made-with: Cursor

* Address review feedback: fix type errors, cargo fmt, always send cleanup DELETE

- Fix kernelApiKey assignment: use ?? null for undefined -> null
- Fix closeKernelSession signature: accept string | undefined
- Always send DELETE on cleanup even without local API key (external
  injection covers it)
- Run cargo fmt on Rust code

Made-with: Cursor
2026-03-09 17:04:58 -05:00
Chris Tate 5bf9fedd58 fix environments demo (#696)
* fix

* fixes

* fixes

* update docs

* fixes

* fixes

* sandbox tokens

* better logging
2026-03-09 17:00:30 -05:00
Chris Tate c0a525c9e4 rate limits for demo (#695) 2026-03-09 15:43:25 -05:00
Chris Tateandctate cc3c70dc86 next.js example (#694)
* next.js guide

* better

* shadcn

* fixes

* fix: correct screenshot test assertion to check path instead of base64

The daemon returns { path: savePath } for screenshot commands, not base64.

* fix: cross-platform Chrome detection and gitignore hardening

- Replace hardcoded macOS Chrome path with findLocalChrome() that
  searches common paths on macOS, Linux, and WSL, with a clear error
  message when no Chrome is found.
- Add .env and .env*.local to .gitignore to prevent accidental
  secret commits.

* fix: correct Vercel deploy button repo URL to vercel-labs/agent-browser

* clean up

* demo

* next page

---------

Co-authored-by: ctate <366502+ctate@users.noreply.github.com>
2026-03-09 15:24:44 -05:00
pixqc 3649787268 fix security docs url in readme (#690) 2026-03-09 15:13:21 -05:00
github-actions[bot]andgithub-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> 00a0e0707e chore: version packages (#693)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-03-09 12:40:37 -05:00
Chris Tate 94cd888ecb chore: add patch changeset for release (#692) 2026-03-09 11:24:04 -05:00
Chris Tate 644a4f5b63 add scale factor to set viewport for retina screenshots (#691)
* device scale

* fix node.js daemon

* fix cargo fmt formatting for scale factor code

* fixes
2026-03-09 11:10:22 -05:00
a0bd0c2f0f Add webview support for Electron apps in native mode (#671)
* Add webview support for Electron apps in native mode

Fixes #580

* Fix cargo fmt violations in actions.rs and browser.rs

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Revert unrelated refactors, keep only webview support changes

- Restore is_none_or (was changed to map_or unnecessarily)
- Restore single-if WebDriver check (was split into nested ifs)
- Restore simple needs_relaunch logic (was expanded into 4 branches)
- Restore find_frame signature (unused selector param was added)
- Restore flat download handler condition (was nested unnecessarily)
- Restore wait_or_kill and graceful close() to preserve cookie flushing

---------

Co-authored-by: ctate <366502+ctate@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 17:41:40 -05:00
github-actions[bot]andgithub-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> 2bab729f26 chore: version packages (#684)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-03-08 13:24:22 -05:00
Chris Tate 94521e7a8c chore: add minor changeset for release (#683) 2026-03-08 11:22:56 -05:00
d9387aae58 ci: add clippy check to Rust CI workflow (#675)
Add `cargo clippy -- -D warnings` step to the Rust CI job so that
clippy warnings fail the build. Also fix the one new lint
(`unnecessary_map_or`) introduced in the current stable clippy.

Fixes #672

Co-authored-by: hyunjinee <leehj0110@kakao.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-07 00:41:56 -06:00
aba2353112 Fix clippy warnings across CLI codebase (#654)
* Fix clippy warnings across CLI codebase

Fixes #653

* Fix remaining items_after_test_module clippy warnings

Move functions defined after `mod tests` blocks to before the test
modules in recording.rs and webdriver/client.rs.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: ctate <366502+ctate@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-06 16:18:51 -06:00
68cebe5192 Fix Chrome extensions not loading by forcing headed mode when extensions present (#652)
* Fix Chrome extensions not loading by forcing headed mode when extensions present

Fixes #640

* Restore wait_or_kill() and add tests for headless+extensions logic

Restore the ChromeProcess::wait_or_kill() method that was accidentally
removed. It is still referenced by BrowserProcess in browser.rs and is
needed for graceful shutdown / cookie persistence (PR #650).

Add unit tests verifying --headless=new is omitted when extensions are
present.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Fix window-size leak in headed+extensions mode and remove unused channel option

- Skip --window-size=1280,720 when extensions force headed mode (native)
- Remove unexplained channel: 'chromium' from extensions launch path (TS)
- Add window-size assertion to existing extension test

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: ctate <366502+ctate@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-06 14:58:18 -06:00
Qiaochu Hu f262ff1bf3 docs: improve snapshot usage guidance and add reproducibility check (#630)
Fixes #566: Clarify snapshot vs snapshot -i usage
- Add guidance that snapshot -i is for clickable/fillable elements
- Add guidance that snapshot (no flag) is for reading page content

Fixes #565: Add reproducibility verification before collecting evidence
- Add guidance to verify issues are reproducible before recording video
- Prevent wasting turns on false positives
2026-03-06 14:31:04 -06:00
Li Yang 788ad0e61f chore: add cargo fmt check to Rust CI and fix existing violations (#620)
TypeScript CI has prettier --check but Rust CI only runs cargo test.
Add cargo fmt --check to catch formatting issues early, and fix the
8 pre-existing formatting violations on main.
2026-03-06 13:32:26 -06:00
Chris Tate b7e7a2548e fix: persist auth cookies on close in native mode (#650) 2026-03-06 12:46:03 -06:00
Chris Tate 492830accb Fix: Suppress Google Translate bar in native headless mode (#649)
Fixes #617
2026-03-06 12:36:32 -06:00
Chris Tate 7acde7e29a fix: native auth login fails due to incompatible encryption format (#648)
* fix: native auth login fails due to incompatible encryption format

* fixes

* fixes
2026-03-06 12:31:12 -06:00
Chris Tate 0da54c7038 lightpanda (#646)
* lightpanda

* lightpanda benchmarks

* improvements

* fixes

* improvements
2026-03-06 11:16:37 -06:00
Chris Tate 36c2e06f89 add benchmarks (#637) 2026-03-06 00:46:59 -06:00
layla 8f6ad817f1 Fix dialog dismiss command parsing (#605) 2026-03-04 17:14:12 -06:00
Li Yang de5ea1d8cf fix: use reqwest for CDP port discovery instead of broken hand-rolled HTTP client (#619)
reqwest_get_string() was hand-rolling HTTP/1.1 over raw TCP despite reqwest
being an existing dependency. The hand-rolled implementation had two bugs:

1. URL path parsing: url.find('/') matched the first '/' in 'http://',
   producing path '//127.0.0.1:9222/json/version' instead of '/json/version'

2. read_to_end() hangs: Chrome's DevTools HTTP server ignores Connection: close
   and keeps the socket open, so read_to_end() waits for EOF that never comes

This caused 'agent-browser --cdp <port>' to always timeout when AGENT_BROWSER_NATIVE=1.

Fix: replace 49 lines of broken TCP code with reqwest::get(), which was
already in Cargo.toml.
2026-03-04 16:32:01 -06:00
Chris Tate 139dd0ec5a fix: surface daemon startup errors instead of opaque timeout message (#614)
When the daemon process crashes during startup (e.g., missing
Playwright), stderr was discarded via Stdio::null(), so users only
saw "Daemon failed to start (port: ...)" with no diagnostic info.

Now captures daemon stderr via Stdio::piped() and detects early process
exit with try_wait() during the startup polling loop. If the daemon
crashes, the actual error from stderr is shown to the user.

Also forwards --debug flag to the daemon process as AGENT_BROWSER_DEBUG
so debug logging works end-to-end.

Closes #56
2026-03-04 01:05:33 -06:00
github-actions[bot]andgithub-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> 794a77e26e chore: version packages (#613)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-03-04 01:02:34 -06:00
Chris Tate 7d2c8957ac chore: add patch changeset for release (#612) 2026-03-04 00:30:54 -06:00
Li Yang eaa968e229 fix: suppress spurious --native warning when set via env var (#611)
* fix: suppress spurious --native warning when set via env var

When AGENT_BROWSER_NATIVE=1 is set via environment variable, every
command after the first would warn:

  ⚠ --native ignored: daemon already running.

This is a false positive — the daemon was already spawned in native
mode and inherited the env var. The warning should only fire when
--native is explicitly passed on the CLI to an already-running daemon.

Add cli_native flag (consistent with existing cli_* pattern) to
distinguish CLI origin from env var origin.

* fix: add flag to test cfg

* fix: cli_native should track flag presence, not value

--native false on CLI should still warn when daemon is already
running, since the user is explicitly trying to change the mode.
2026-03-04 00:17:14 -06:00
github-actions[bot]andgithub-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> 7edc5d596c chore: version packages (#610)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-03-03 23:56:46 -06:00
Chris Tate 01ac5574d4 chore: add patch changeset for release (#609) 2026-03-03 23:07:56 -06:00
Chris Tate e5fd26eb9e headed mode (#607)
* headed mode

* fixes

* fixes

* docs

* fixes

* fixes

* fixes
2026-03-03 22:34:07 -06:00
github-actions[bot]andgithub-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> a493d02c66 chore: version packages (#604)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-03-03 17:59:02 -06:00
Chris Tate c4180c8cb1 chore: add patch changeset for release (#603) 2026-03-03 17:51:29 -06:00
Chris Tate 56260f68b0 Native: auto-detect sandbox/container environments for Chrome launch (#602)
Fixes #600

Three improvements to `--native` Chrome launching:

- `find_chrome()` now falls back to Playwright's browser cache (`~/.cache/ms-playwright/`) when no system Chrome is found
- Auto-detect containers/VMs (root, Docker, Podman, cgroups) and inject `--no-sandbox`
- Chrome stderr is now captured and included in launch error messages, with a hint when sandbox errors are detected
2026-03-03 17:45:23 -06:00
Chris Tate 324a9e4e0c windows 8 cores (#599)
* windows 8 cores

* add workflow dispatch
2026-03-03 17:26:22 -06:00
Chris Tate 7f42eed031 faster ci (#598) 2026-03-03 16:45:57 -06:00
github-actions[bot]andgithub-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> c10981413f chore: version packages (#597)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-03-03 16:18:08 -06:00
Chris Tate 05018b309a prepare v0.16.0 (#596) 2026-03-03 16:09:39 -06:00
Chris Tate 9d0454d229 fix: switch from native-tls to rustls for cross-compilation (#595)
The native PR introduced tokio-tungstenite and reqwest with native-tls,
which depends on openssl-sys (C library). This breaks the release
workflow's cargo-zigbuild cross-compilation on Linux because zig's C
compiler can't find the system OpenSSL headers.

Switch to rustls (pure Rust TLS) which has zero C dependencies and
cross-compiles trivially. Also shrinks the dependency tree.
2026-03-03 15:45:20 -06:00
Chris Tate 51f5fa484c native (#594)
* Native Rust rewrite of agent-browser daemon

Single-binary Rust implementation replacing the Node.js/Playwright daemon
with direct CDP (Chrome DevTools Protocol) communication. Includes full
command parity, WebDriver/Safari/iOS backend routing, request tracking,
frame context management, CDP protocol codegen, and comprehensive tests.

* improvements

* fix ci

* fixes

* faster builds
2026-03-03 15:15:57 -06:00
github-actions[bot]andgithub-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> 857c0b25df chore: version packages (#591)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-03-03 08:21:58 -06:00
Chris Tate 62241b50e9 chore: add patch changeset for release (#589) 2026-03-03 08:08:02 -06:00
Chris Tate c6a33b6338 fix(windows): resolve daemon startup failures and Git Bash compatibility (#582)
* fix(windows): resolve daemon startup failures and Git Bash compatibility

Three root causes behind 27 open Windows issues:

1. Path::canonicalize() returns \\?\ prefixed paths on Windows that
   Node.js cannot parse, preventing daemon startup. Strip the prefix
   before passing to Node. (fixes #522, #390, #56, #25, #37, #89)

2. Git Bash/MSYS2 translates Unix-style paths and resolves node to
   a shell wrapper script. Use node.exe explicitly and set
   MSYS_NO_PATHCONV/MSYS2_ARG_CONV_EXCL to prevent argument mangling.
   (fixes #148, #108, #171)

3. postinstall fixWindowsShims() hardcoded x64 arch and did not verify
   the native binary exists before rewriting shims. Now detects arch
   dynamically and validates the binary path. (fixes #262)

Also:
- Error messages now show TCP port on Windows instead of Unix socket path
- Windows CI expanded to test full daemon lifecycle (open, snapshot, close)

* fix(windows): strip \\?\ prefix in auth-cli path (fixes #579)

Same canonicalize() issue as the daemon spawn path, but in
run_auth_cli() which passes the script path to Node.js.
2026-03-03 08:00:14 -06:00
github-actions[bot]andgithub-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> d97e2016f5 chore: version packages (#585)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-03-02 17:16:52 -06:00
Chris Tate 6aea316c82 chore: add patch changeset for release (#583) 2026-03-02 17:10:32 -06:00
Chris Tate c7fa10cb1b remove skill creator (#581) 2026-03-02 16:26:19 -06:00
Giulio Leone b304a4188c fix: correct misleading output for cookies clear and tab close (#556) (#563)
Bug 1: `cookies clear` printed 'Request log cleared' instead of 'Cookies cleared'
because the output handler matched the generic `{ cleared: true }` response shape
without checking the action context. Now uses the `action` parameter to distinguish
`cookies_clear` from `requests --clear`.

Bug 2: `tab close` printed 'Browser closed' instead of 'Tab closed' because the
output handler matched the generic `{ closed: ... }` response shape without checking
the action context. Now uses the `action` parameter to distinguish `tab_close` from
`close` (full browser close).

Closes #556
2026-03-01 12:23:23 -06:00
neilmixandClaude Opus 4.6 e912f541f2 fix: treat EPERM from kill(pid, 0) as "process exists" in daemon liveness checks (#564)
Per POSIX, kill(pid, 0) returns EPERM when the process exists but the
caller lacks permission to signal it, and ESRCH when it does not exist.
The daemon liveness checks in both the Rust CLI and TypeScript daemon
treated any kill failure as "not running", which is incorrect when
running inside a macOS sandbox that restricts signal delivery to
(target self). This caused the CLI to delete the real daemon's socket
and PID files, then spawn a duplicate daemon.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-01 10:12:37 -06:00
7238b7da4c fix: resolve unnamed element refs matching multiple elements (#573)
* fix: resolve unnamed element refs matching multiple elements (#500)

When a page has one unnamed button among several named buttons,
clicking its ref fails with "matched N elements" because the
locator `getByRole('button')` matches all buttons on the page.

Normalize unnamed interactive elements to `name: ""` so the
selector becomes `getByRole('button', { name: "", exact: true })`
which matches only buttons with empty accessible names.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: remove dead code branch in buildSelector

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* refactor: make RefMap.name required string, remove dead code branches

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: hyunjinee <leehj0110@kakao.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-01 09:42:05 -06:00