7309 Commits

Author SHA1 Message Date
Magnus Müller 007e7a8dcc Bump version from 0.9.1 to 0.9.2 0.9.2 2025-10-27 17:00:04 -07:00
Alexander Yue 9e90541792 Bu install with merge conflict fixed (#3438)
<!-- This is an auto-generated description by cubic. -->
## Summary by cubic
Adds a simple browser-use install CLI command to install Chromium +
system deps in one step. Updates docs to use the new command, and fixes
the basic search example and an AGENTS.MD merge conflict.

- **New Features**
- Added install subcommand to browser_use CLI that runs Playwright’s
Chromium install with deps and can run before other CLI dependencies
load.

- **Docs**
- Replaced Playwright install instructions with uvx browser-use install
in README, Quickstart, and vibetest example.
- Added Mac/Linux and Windows tabs for virtualenv activation in
AGENTS.MD.

<!-- End of auto-generated description by cubic. -->
2025-10-27 12:31:34 -07:00
Alezander9 195f1f1f0f address cubic comments 2025-10-27 12:28:06 -07:00
Alezander9 409d270aa5 fix basic search example that was messed up some time ago 2025-10-27 11:56:52 -07:00
Alezander9 830f8d6473 fix merge conflict in agents md 2025-10-27 11:56:24 -07:00
Magnus Müller 83af6a3709 test-broken-navigation (#3434)
Auto-generated PR for branch: test-broken-navigation

<!-- CURSOR_SUMMARY -->
---

> [!NOTE]
> Add CI tests for browser navigation edge cases and multi-tab
operations using a mock HTTP server and mock LLM.
> 
> - **Tests (CI)**:
>   - **Navigation edge cases** (`tests/ci/browser/test_navigation.py`):
> - Handles broken HTML (`/broken`), slow pages (`/slow` delay 10s),
404s (`/notfound`), and non-existing domains.
> - Verifies agent recovery and continued LLM calls; enforces
`max_steps=3`, 120s timeouts.
>   - **Multi-tab operations** (`tests/ci/browser/test_tabs.py`):
> - Create/switch across 3+ tabs, close tabs (with `use_vision=True`),
background tab opens, and rapid tab ops.
> - Confirms browser state retrieval between steps; `max_steps=5`, 120s
timeouts; asserts final results and tab counts.
> 
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
0ad363cb29. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
2025-10-26 17:07:39 -07:00
Magnus Müller 0ad363cb29 Tab test 2025-10-26 17:05:00 -07:00
Magnus Müller 8ff9dbe090 Remove unnecessary blank lines in the eval-on-pr workflow file to improve readability and maintainability. 2025-10-26 16:40:57 -07:00
Magnus Müller f29be2aa58 Change browser session fixture scope from 'module' to 'function' in navigation tests for improved isolation and reliability. 2025-10-26 16:39:51 -07:00
Magnus Müller 135664432c Broken nav 2025-10-26 16:35:01 -07:00
Magnus Müller c5c7839e49 eval on pr (#3431)
Auto-generated PR for: eval on pr

<!-- CURSOR_SUMMARY -->
---

> [!NOTE]
> Add a CI workflow to trigger and report PR evaluation runs via an
external API for authorized authors.
> 
> - **CI/GitHub Actions**:
> - **New workflow** `/.github/workflows/eval-on-pr.yml` to auto-trigger
PR evaluation on `pull_request` (`opened`, `synchronize`, `reopened`).
> - Runs only for authors with `OWNER`/`MEMBER`/`COLLABORATOR`
association.
> - Calls external eval API via `curl` using `secrets.EVAL_PLATFORM_URL`
and `secrets.EVAL_PLATFORM_KEY`; passes `commitSha`, `prNumber`,
`branchName`, `githubRepo`, and `testCase` (from `vars.EVAL_TEST_CASE`
defaulting to `InteractionTasks_v6`).
> - Parses response with `jq` to determine success; posts a PR comment
via `actions/github-script@v7` indicating start or failure.
> 
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
c23137f21e. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
2025-10-26 16:10:59 -07:00
Magnus Müller 67a0919fe1 remove comment 2025-10-26 16:10:47 -07:00
Magnus Müller c23137f21e New logs 2025-10-26 16:07:03 -07:00
Magnus Müller 45448477d6 New logs 2025-10-26 15:51:33 -07:00
Magnus Müller 3b09df2b01 New logs 2025-10-26 15:43:31 -07:00
Magnus Müller bf41b0ef23 Pass PR branch name to evaluation platform
- Add branchName parameter to API call
- This allows the UI to show the actual PR branch instead of 'main'

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-26 15:34:41 -07:00
Magnus Müller d3fdc3bbfd New logs 2025-10-26 15:28:20 -07:00
Magnus Müller 0a896a0eaf New logs 2025-10-26 15:19:19 -07:00
Magnus Müller 162a8d3a2d New logs 2025-10-26 15:15:04 -07:00
Magnus Müller 83ccb630cc New logs 2025-10-26 15:03:04 -07:00
Magnus Müller 9915af7e1b New logs 2025-10-26 15:00:07 -07:00
Magnus Müller 2e083f050d Remove commented options from eval-on-pr.yml to streamline the workflow configuration 2025-10-26 14:55:48 -07:00
Magnus Müller b09af25e86 Remove commented options from eval-on-pr.yml to streamline the workflow configuration 2025-10-26 14:54:14 -07:00
Magnus Müller a0bb331c7c Update error message in eval-on-pr.yml for clarity 2025-10-26 13:27:32 -07:00
Magnus Müller 7b962095e7 Update error message in eval-on-pr.yml for clarity 2025-10-26 13:24:59 -07:00
Magnus Müller 659c0d5652 Update error message in eval-on-pr.yml for clarity 2025-10-26 13:17:36 -07:00
Magnus Müller c1e86bc46d Update error message in eval-on-pr.yml for clarity 2025-10-26 13:13:24 -07:00
Magnus Müller 9e05f10b34 New logs 2025-10-26 13:08:46 -07:00
Magnus Müller 37df2bdc69 New logs 2025-10-26 13:04:03 -07:00
Magnus Müller e7b628ff95 New logs 2025-10-26 12:53:47 -07:00
Magnus Müller 394484d9ec New logs 2025-10-26 12:49:29 -07:00
ShawnPana 1ca1307545 Make install command work without CLI dependencies 2025-10-26 12:37:39 -07:00
Magnus Müller 89fbccd5c3 New logs 2025-10-26 12:37:07 -07:00
Magnus Müller 81edf51b44 New logs 2025-10-26 12:24:53 -07:00
Magnus Müller 82300c7ca5 New logs 2025-10-26 11:58:40 -07:00
Magnus Müller 0a81e787ce New logs 2025-10-26 11:07:58 -07:00
Magnus Müller bdc9f024a8 Less errors 2025-10-26 11:04:51 -07:00
Magnus Müller a9d3c4dd59 Less errors 2025-10-26 10:46:40 -07:00
Magnus Müller d64004a039 Less errors 2025-10-26 10:43:11 -07:00
Magnus Müller 1e4ea53616 Update 2025-10-26 10:40:45 -07:00
Magnus Müller 974069e9dd Trigger eval 2025-10-26 10:36:02 -07:00
Magnus Müller a46deaec61 eval on pr 2025-10-26 10:27:33 -07:00
ShawnPana ce36f3c65d Update vibetest-use.mdx to use uvx browser-use install 2025-10-25 22:35:22 -07:00
ShawnPana e62d3fa1c8 Update docs/quickstart.mdx to use uvx browser-use install in uv tab 2025-10-25 22:35:02 -07:00
ShawnPana da5c997c79 Update docs to use uvx browser-use install 2025-10-25 22:30:46 -07:00
Saurav Panda 5ef30230cf Add documentation for monitoring using OpenLIT (#3408)
Hi Team

I am one of the maintainers of
[OpenLIT](https://github.com/openlit/openlit). Adding an integration doc
for OpenLIT. Would prefer to have refactored the Observability doc but
did not want to do it without taking input from the team.

DO let me know what would be the best way to do this, A seperate doc for
each observability tool or mention in the same main observability
documentation
    
<!-- This is an auto-generated description by cubic. -->
---

## Summary by cubic
Added an OpenLIT monitoring guide for OpenTelemetry-native tracing in
Browser Use, covering setup, usage, configuration, self-hosted
deployment, and integrations. Updated docs.json to include the new page
in the Monitoring section.

<!-- End of auto-generated description by cubic. -->
2025-10-25 21:17:20 -07:00
ShawnPana b36524c0ba Apply ruff formatting fixes 2025-10-25 20:37:51 -07:00
Saurav Panda 9fa10f9702 Merge branch 'main' into main 2025-10-25 20:31:41 -07:00
ShawnPana 2b3caa3940 init 2025-10-25 19:41:36 -07:00
Gregor Žunič fa6656a6e5 Updated agents.md (#3428) 2025-10-25 19:28:08 -07:00