Commit Graph

4340 Commits

Author SHA1 Message Date
Gregor Žunič 9d7a0c74ed Add bu tunnel command and remote-browser skill
- New `tunnel` command: expose localhost ports via Cloudflare quick tunnels
  (`bu tunnel 3000` → trycloudflare.com URL, idempotent, auto-cleanup on session close)
- New `skills/remote-browser/SKILL.md`: guides sandboxed agents through
  cloud browser + tunnel workflow
- TunnelInfo dataclass on SessionInfo for tunnel lifecycle management
- Tunnel dispatch in both SessionServer and CLI arg parser

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-09 10:14:42 -08:00
laithrw 9131c88f98 Merge branch 'main' into 3615 2026-02-08 17:34:07 -05:00
Laith Weinberger e1e170a5fd fix agent not stopping: consecutive_failures counter was resetting on multi-action error steps 2026-02-08 17:25:39 -05:00
Laith Weinberger 53c1b0dfb9 Merge origin/issue-2748 into HEAD 2026-02-08 16:37:44 -05:00
Laith Weinberger 1737c5bea4 lint 2026-02-08 16:36:45 -05:00
laithrw 1724d314de Merge branch 'main' into issue-2748 2026-02-08 16:30:56 -05:00
Laith Weinberger 4d05218d7d fix: redirect logging to stderr so MCP stdio doesn't break (#2748) 2026-02-08 16:29:05 -05:00
Laith Weinberger 1629799dd3 fix(openai): structured output call shouldn't depend on schema injection
Fix indentation so structured-output request executes even when add_schema_to_system_prompt is false; add regression tests for choices=null in both structured and non-structured paths.
2026-02-08 16:03:21 -05:00
laithrw d15f0a32c7 Merge branch 'main' into fix/3897-llm-response-parsing 2026-02-08 15:43:05 -05:00
Laith Weinberger 62d19f0c9a fix(openai): handle proxy responses with missing/null choices; undo test change
Avoid indexing response.choices[0] when proxies return choices=null/empty; raise a clear ModelProviderError (with base_url hint) and use the validated first choice for content/finish_reason
2026-02-08 15:37:59 -05:00
laithrw 880b636422 Merge branch 'main' into 3895 2026-02-08 11:15:44 -05:00
Laith Weinberger 9e95241bbb stop agent if browser closed 2026-02-08 11:14:49 -05:00
laithrw d86be39eeb Merge branch 'main' into fix/structured-output-schema-collision 2026-02-05 23:44:03 -05:00
Saurav Panda d1c9a38c00 Merge branch 'main' into message-compaction 2026-02-05 20:29:03 -08:00
Saurav Panda 6b9910a546 changed the threshold for compaction 2026-02-05 16:41:08 -08:00
Laith Weinberger 04da1fd30c strip success from JSON schema so invisible to the LLM, avoiding confusion 2026-02-05 16:49:36 -05:00
Saurav Panda 79501fe2cd added message compaction for agent 2026-02-05 12:26:11 -08:00
Saurav Panda 3c57cdc756 Merge branch 'main' into update-action-loop-prompt 2026-02-05 12:08:33 -08:00
Saurav Panda 995cb0176b updated default max step to 500 2026-02-05 11:20:47 -08:00
Saurav Panda bb5914f251 added milder nudge for action loop 2026-02-05 11:17:20 -08:00
laithrw 99be7b1b48 Merge branch 'main' into fix/no-tab-switch 2026-02-04 21:24:34 -05:00
laithrw 9d81f64b2e Merge branch 'main' into kalil0321/har_watchdog 2026-02-04 21:17:10 -05:00
Laith Weinberger 7455b3c1af deduplicate code; allow CDP events to propagate; error handling 2026-02-04 21:14:14 -05:00
Laith Weinberger d66181cdc6 notify agent if new tab opened 2026-02-04 21:02:13 -05:00
Saurav Panda 332694bf1a Added date info to simple judge 2026-02-04 17:04:39 -08:00
Saurav Panda cec4aea3bc increased threshold for loop detection 2026-02-04 16:34:42 -08:00
Saurav Panda d24dea0aa4 Merge branch 'main' into improve-input-field-handling 2026-02-03 18:22:19 -08:00
Saurav Panda 5d7ff041d3 improved concatenation heuristic 2026-02-03 18:02:58 -08:00
Saurav Panda bbf3cc0164 Merge branch 'main' into action-detection-loop 2026-02-03 17:18:06 -08:00
Saurav Panda b96b9436fc fixed agent loop detection 2026-02-03 16:00:08 -08:00
Saurav Panda bd4ead5d2e Action Loop detection 2026-02-03 15:19:59 -08:00
Laith Weinberger f9c36f11a4 lint 2026-02-03 17:59:24 -05:00
laithrw bcb5a2ad63 Merge branch 'main' into feat/smart-pdf-reading 2026-02-03 17:44:37 -05:00
Laith Weinberger 799e714c2b mitigate injection; don't drop overbudget pages
- restricted read_long_content file access to only paths in available_file_paths or browser_session.download_files to mitigate injection
- made PDF page selection truncate pages that exceed char budget instead of dropping them entirely
- fixed truncation hint in file_system.py to reference read_long_context instead of search_page
2026-02-03 17:42:02 -05:00
laithrw a511ba2f1e Merge branch 'main' into 3619 2026-02-03 17:32:46 -05:00
Saurav Panda 2a5768f3da fixed pyright issues 2026-02-03 13:02:03 -08:00
Saurav Panda 749fa56d1a improve text field handling 2026-02-03 12:52:56 -08:00
Laith Weinberger 38fb5b12df Merge remote-tracking branch 'origin/main' into feat/smart-pdf-reading 2026-02-03 14:15:49 -05:00
Saurav Panda da5b4237ba fixed lint issue 2026-02-02 23:01:52 -08:00
Saurav Panda 0dba38ed95 Merge branch 'main' into align-agent-success-with-judge 2026-02-02 22:16:11 -08:00
Saurav Panda 8565c7d267 updated agent success with simple judge 2026-02-02 22:14:45 -08:00
Saurav Panda 65405d8a79 Merge branch 'main' into align-agent-success-with-judge 2026-02-02 21:50:02 -08:00
Saurav Panda bce72138c4 fixed lint issue 2026-02-02 21:49:48 -08:00
Saurav Panda 4d5976c427 Merge branch 'main' into improve-agent-planning 2026-02-02 21:45:06 -08:00
Saurav Panda dae6dc6d0e update agent success with judge verdict 2026-02-02 18:34:11 -08:00
Saurav Panda 023367052c in flash mode disable planning 2026-02-02 18:28:28 -08:00
Saurav Panda 74e26e0b93 Merge branch 'main' into align-agent-success-with-judge 2026-02-02 17:14:43 -08:00
Saurav Panda f1fbdbc1a8 removed self verify injection to agent 2026-02-02 17:10:01 -08:00
Saurav Panda 4a522a6f1c dynamic planing exploration 2026-02-02 16:26:50 -08:00
Saurav Panda 6224e19758 added fallback incase of no task for judge 2026-02-02 16:24:31 -08:00