Commit Graph

4189 Commits

Author SHA1 Message Date
Saurav Panda fe52a3a8ce added message compaction 2026-02-05 11:33:09 -08:00
Laith Weinberger b00ffd5380 lint 2026-01-27 18:28:53 -05:00
laithrw 5a3f8b4d54 Merge branch 'main' into fix/respect-use-vision-in-judge-fix 2026-01-27 18:22:06 -05:00
Saurav Panda c011c529fc feat: add bu-2-0 pricing 2026-01-27 10:35:41 -08:00
laithrw c62ceafa25 Merge branch 'main' into fix/3889-draftjs-first-char 2026-01-26 19:51:08 -05:00
Laith Weinberger ca049c67a1 clean comments 2026-01-26 19:28:45 -05:00
Saurav Panda ee35b53b12 Merge branch 'main' into saurav/change-gemini-thinking-to-auto 2026-01-26 12:46:52 -08:00
Saurav Panda 6d54f521cf set default gemini thinking to auto 2026-01-26 12:44:51 -08:00
laithrw 7cf8575e4a Merge branch 'main' into main 2026-01-26 15:24:11 -05:00
laithrw 7bacbbbfa2 Merge branch 'main' into 3538 2026-01-26 15:15:27 -05:00
zhongzhenyu b1fad345d6 style: remove trailing whitespace 2026-01-25 22:05:01 -08:00
zhongzhenyu f13d8246e9 fix: Fix Draft.js space prepending to only apply when clear=True 2026-01-25 21:58:18 -08:00
Laith Weinberger e1c4eeef35 fix(#3538): always index scrollable dropdown containers regardless of interactive descendants 2026-01-25 17:05:10 -05:00
Laith Weinberger 6f8c077932 lint 2026-01-25 15:49:49 -05:00
Laith Weinberger 64ada81915 fix(#2867): verify dropdown selection and retry if reverted
addresses select_dropdown silently claiming success even when frameworks intercepted and reverted the selection
2026-01-25 15:40:22 -05:00
Saurav Panda acd05e30e0 removed duplicate --headed flag from skill cli 2026-01-25 11:34:09 -08:00
laithrw d1a53a158e Merge branch 'main' into main 2026-01-25 12:31:43 -05:00
laithrw 468d149588 Merge branch 'main' into fix/3292-table-row-clickability 2026-01-25 10:48:47 -05:00
laithrw 794b68b448 Merge branch 'main' into fix/label-span-interactive-antd 2026-01-25 10:43:27 -05:00
Laith Weinberger 0b8aa55d54 Merge branch 'main' into fix/label-span-interactive-antd 2026-01-24 17:19:38 -05:00
Laith Weinberger 1794849886 don't mutate page
instead of writing markers to DOM, collect element references in JS, resolve them to internal Chrome node IDs via CDP, and store those IDs in Python
2026-01-24 16:36:14 -05:00
Laith Weinberger 20f51c7fef detect JS event listeners for clickable elements
uses CDP Runtime.evaluate with includeCommandLineAPI to access getEventListeners() and mark elements with click/mousedown/pointerdown listeners before DOM snapshot capture
2026-01-24 14:44:08 -05:00
Magnus Müller 6b23672c3c Merge branch 'main' into cache-anthropic 2026-01-23 18:10:11 -08:00
Magnus Müller 80a08a4a03 Merge branch 'main' into #3557 2026-01-23 18:06:47 -08:00
Magnus Müller d9dec964be Merge branch 'main' into fix/3889-draftjs-first-char 2026-01-23 16:24:34 -08:00
Saurav Panda b63ae37008 Merge branch 'main' into gemini-add-thinking-level 2026-01-23 15:21:17 -08:00
Saurav Panda 2774be5cc6 Merge branch 'main' into fix/cli-chatbrowseruse-support 2026-01-23 15:18:19 -08:00
Saurav Panda bb3b1e8cf5 added minimal model for gemini 3 flash 2026-01-23 15:11:13 -08:00
Saurav Panda 041d03a93f feat: updated the thinking budget 2026-01-23 14:42:59 -08:00
Saurav Panda 5b06f4edd9 set default thinking to 0 for gemini-3 models 2026-01-23 13:44:29 -08:00
Laith Weinberger a75fa14d14 increase char limit for extraction 2026-01-23 16:38:38 -05:00
Laith Weinberger f85bbb49c8 pass model_name to SystemPrompt 2026-01-23 16:33:28 -05:00
Laith Weinberger 2f24f53900 use longer prompts for opus/haiku 4.5 to allow caching 2026-01-23 16:20:25 -05:00
Saurav Panda f3aad3c145 Added browser use 2-0 support 2026-01-23 13:17:56 -08:00
Saurav Panda 37586c9e9f Added support for new browser use model 2026-01-23 12:39:10 -08:00
BouquetAntoine 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
Gregor Žunič b6bdc17bcb addresses cubic 2026-01-21 22:17:07 -08:00
Gregor Žunič 5fc3a428c7 better remote session management 2026-01-21 22:12:51 -08:00
Gregor Žunič c7c5cae20e remote browser fixes + readme 2026-01-21 21:49:26 -08:00
Gregor Žunič 08c72f67ba chore: Remove auxiliary planning docs 2026-01-21 21:20:44 -08:00
Gregor Žunič 5e75df3eb0 fix: Clean up Python command output format 2026-01-21 21:16:20 -08:00
Gregor Žunič 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
Gregor Žunič 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
Gregor Žunič 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
LarsenCundric dd8a63ce41 Improve placeholder handling for 2FA secrets in registry service 2026-01-16 17:05:50 -08:00
zhongzhenyu c0f4f39570 fix(#3889): Draft.js editors lose first character when typing
CDP's dispatchKeyEvent doesn't trigger beforeinput events that Draft.js
relies on for text input. This causes the first character to be dropped.

Solution: Detect Draft.js editors via specific DOM attributes (DraftEditor
class, data-contents, data-block, data-offset-key) and prepend a sacrifice
space character that Draft.js will drop, preserving the actual text.
2026-01-15 18:13:25 -08:00
Saurav Panda 147db04c1c Merge branch 'main' into add-ax-name-fallback-rerun 2026-01-15 11:03:27 -08:00
Saurav Panda 9339935c1f added check for history item state 2026-01-15 10:50:07 -08:00
Saurav Panda 9c042d7d98 make event bus timeout configurable using env 2026-01-15 10:44:44 -08:00
Saurav Panda 97d71b84fa added a fix for multi menu dropdown 2026-01-15 10:17:59 -08:00