510c28ad16
lint
2026-01-24 15:23:24 -05:00
874d90d33d
fix css escaping and multi-id aria-controls parsing
...
use attribute selector instead of id selector to avoid css escaping issues with special chars (e.g. :r1:). parse aria-controls/aria-owns as space-separated list per aria spec.
2026-01-24 15:18:20 -05:00
cded687fe6
fix portal dropdown aria-controls resolution
...
Portal-based dropdowns render options in a separate container via aria-controls. Resolve aria-controls/aria-owns to find options outside the trigger element's descendants.
2026-01-24 15:05:49 -05:00
6b23672c3c
Merge branch 'main' into cache-anthropic
2026-01-23 18:10:11 -08:00
80a08a4a03
Merge branch 'main' into #3557
2026-01-23 18:06:47 -08:00
b63ae37008
Merge branch 'main' into gemini-add-thinking-level
2026-01-23 15:21:17 -08:00
2774be5cc6
Merge branch 'main' into fix/cli-chatbrowseruse-support
2026-01-23 15:18:19 -08:00
bb3b1e8cf5
added minimal model for gemini 3 flash
2026-01-23 15:11:13 -08:00
041d03a93f
feat: updated the thinking budget
2026-01-23 14:42:59 -08:00
5b06f4edd9
set default thinking to 0 for gemini-3 models
2026-01-23 13:44:29 -08:00
a75fa14d14
increase char limit for extraction
2026-01-23 16:38:38 -05:00
f85bbb49c8
pass model_name to SystemPrompt
2026-01-23 16:33:28 -05:00
2f24f53900
use longer prompts for opus/haiku 4.5 to allow caching
2026-01-23 16:20:25 -05:00
f3aad3c145
Added browser use 2-0 support
2026-01-23 13:17:56 -08:00
37586c9e9f
Added support for new browser use model
2026-01-23 12:39:10 -08:00
1a01e5dff7
feat(cli): add ChatBrowserUse support for BROWSER_USE_API_KEY
...
The CLI 'run' command now supports BROWSER_USE_API_KEY as an LLM option,
using ChatBrowserUse which is optimized for browser automation tasks.
This aligns the CLI behavior with the documented supported models at
https://docs.browser-use.com/supported-models which shows ChatBrowserUse
as a valid LLM option using BROWSER_USE_API_KEY.
Changes:
- Add ChatBrowserUse as first LLM option in get_llm() when BROWSER_USE_API_KEY is set
- Update error message to mention BROWSER_USE_API_KEY
2026-01-22 17:18:08 +01:00
b6bdc17bcb
addresses cubic
2026-01-21 22:17:07 -08:00
5fc3a428c7
better remote session management
2026-01-21 22:12:51 -08:00
c7c5cae20e
remote browser fixes + readme
2026-01-21 21:49:26 -08:00
08c72f67ba
chore: Remove auxiliary planning docs
2026-01-21 21:20:44 -08:00
5e75df3eb0
fix: Clean up Python command output format
2026-01-21 21:16:20 -08:00
4716ae50ce
fix: State command now outputs LLM representation, add CLI aliases
...
- State command outputs same format that browser-use agents see
- Added aliases: bu, browser (all work the same)
- Headed mode now correctly shows browser window
2026-01-19 09:36:20 -08:00
0f9e955276
refactor: Rename CLI from 'bu' to 'browser-use'
...
- Change main entry point to 'browser-use'
- Move TUI to 'browser-use-tui'
- Add README with human instructions
- Update SKILL.md references
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-19 09:11:39 -08:00
c4ffaca6e7
feat: Add fast CLI for browser automation (bu command)
...
Implements a fast, persistent browser automation CLI per CLI_SPEC.md:
- Fast CLI layer using stdlib only (<50ms startup)
- Session server with Unix socket IPC (TCP on Windows)
- Browser modes: chromium, real, remote
- Commands: open, click, type, input, scroll, back, screenshot,
state, switch, close-tab, keys, select, eval, extract
- Python execution with persistent namespace (Jupyter-like REPL)
- Agent task execution (requires API key)
- JSON output mode
The CLI maintains browser sessions across commands, enabling complex
multi-step workflows. Includes Claude skill description for AI-assisted
browser automation.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-19 01:05:35 -08:00
dd8a63ce41
Improve placeholder handling for 2FA secrets in registry service
2026-01-16 17:05:50 -08:00
147db04c1c
Merge branch 'main' into add-ax-name-fallback-rerun
2026-01-15 11:03:27 -08:00
9339935c1f
added check for history item state
2026-01-15 10:50:07 -08:00
9c042d7d98
make event bus timeout configurable using env
2026-01-15 10:44:44 -08:00
97d71b84fa
added a fix for multi menu dropdown
2026-01-15 10:17:59 -08:00
6bccc224ca
Remove comma
2026-01-10 20:01:14 -08:00
aac5cad62a
Fix system prompt code use
2026-01-10 20:00:18 -08:00
5652ba5dd9
Small comment
2026-01-10 19:03:35 -08:00
c4b9710a84
Less priming for scroll
2026-01-10 18:33:17 -08:00
680d2551df
Scroll element
2026-01-10 18:20:32 -08:00
1e0fd4d814
Remove CTA
2026-01-10 17:36:43 -08:00
9609aa10e5
Prompt
2026-01-10 17:25:36 -08:00
fc2dc27c63
Prompts
2026-01-10 17:24:07 -08:00
d9943a0246
Merge branch 'main' into feat/multi-tab-recording
2026-01-07 17:49:16 +01:00
2c06eabf5f
Added ax-name fallback for history rerun.
2026-01-06 12:07:10 -08:00
6b77410683
refactor: Replace print with logger.debug in actor/page.py
2025-12-25 14:39:05 +08:00
1073fc9e7a
Merge branch 'main' into rerun-history-add-exp-retry
2025-12-23 20:16:27 -08:00
319d0acd45
fixed the edge case for handling max index
2025-12-23 19:29:43 -08:00
2f6a18a64e
Merge branch 'main' into 3771-feature-request-add-support-for-openai-responses-api-for-azure-openai
2025-12-23 19:28:17 -08:00
2aa23f01dc
fixed backend_node_id based element counting.
2025-12-23 17:25:38 -08:00
0da9457f6b
feat: added exp backoff retry and minimum element load
2025-12-23 17:02:28 -08:00
bb13679f85
feat: remove redundant retry step from history
2025-12-23 16:25:52 -08:00
29c9f1a416
feat: add support for openai responses model
2025-12-22 22:16:56 -08:00
bd6c1d76e2
style: use single quotes to satisfy ruff formatter
2025-12-23 06:06:33 +05:30
d17f10fe45
fix: use str | None type hint to satisfy linter
2025-12-23 06:00:22 +05:30
285995ecce
fix: resolve Gemini API error on empty action schemas
2025-12-23 05:48:12 +05:30
Laith Weinberger