319d0acd45
fixed the edge case for handling max index
2025-12-23 19:29:43 -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
07b7a6d8c0
fix: include shadow DOM form elements in selector_map even without snapshot data
2025-12-19 18:32:40 -08:00
cf0894ff8d
add support for external skillservice
2025-12-18 19:10:47 -08:00
b9c8346499
fix: change max_step_interval to 45s
2025-12-18 16:45:21 -08:00
afa5b71747
feat: added Unique attribute match and better error logging for rerun
2025-12-17 11:20:46 -08:00
1779e9717d
improve hashing of elements using cascading hash
2025-12-17 00:55:27 -08:00
05b41f64a9
Dont skip failrues by default
2025-12-16 20:04:28 -08:00
e9c047be92
include ax_name for rerun history element hash
2025-12-16 17:05:48 -08:00
dc0db88215
kv caching for BU agents
2025-12-15 18:23:22 -08:00
dd6aa26301
Merge branch 'main' into mert/rerunhistory
2025-12-14 13:36:12 -08:00
a0996ba39e
max wait between execution
2025-12-14 13:35:27 -08:00
a8eb91d852
Merge branch 'main' into main
2025-12-14 13:11:55 -08:00
38703d5ad7
perf: lazy import for openai and reportlab to reduce startup latency
...
- agent/views.py: Move RateLimitError import inside format_error() function
to avoid loading openai SDK (~800ms) at module level
- llm/messages.py: Replace openai.BaseModel with pydantic.BaseModel directly
to remove unnecessary openai dependency
- filesystem/file_system.py: Move reportlab imports inside sync_to_disk_sync()
to avoid ~40ms startup cost when PDF generation is not used
- utils.py: Convert OpenAIBadRequestError and GroqBadRequestError to lazy
loaders to avoid loading SDKs at module level
This improves import time for users who don't use OpenAI provider,
especially when using Anthropic, Google, or other providers.
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2025-12-14 01:48:47 +09:00
cba65772f8
Fix XAI vision check to only disable for grok-3 and grok-code models
...
Previously all grok models had vision disabled. Only grok-3 variants
(grok-3, grok-3-mini, grok-3-fast) and grok-code models don't support
vision. grok-2 and grok-4 models now correctly retain vision support.
2025-12-13 12:40:21 +01:00
9b894150d5
fix structured output for sandboxes
2025-12-12 15:35:34 -08:00
20247d5c56
make coordinates optionally available
2025-12-12 14:26:13 -08:00
8ba95aefa8
Fix: Filter sensitive data from state messages
...
This change ensures that sensitive data in action results is filtered before being included in state messages sent to the LLM. This prevents accidental leakage of private information. New tests are added to verify this functionality.
Co-authored-by: mailmertunsal <mailmertunsal@gmail.com >
2025-12-11 00:00:37 +00:00
110b96dc8d
update system prompts
2025-12-10 18:50:10 +00:00
1b75166122
Merge branch 'main' into feature/skills-integration
2025-12-09 16:48:11 -08:00
6c49e622a6
skills_ids = skills, added docs
2025-12-09 16:37:05 -08:00
063d03e796
quick fix
2025-12-09 16:13:31 -08:00
1489d55210
fix structured output when tools is passeD
2025-12-09 23:27:15 +00:00
e8ebc8eebf
fixed skill calling
2025-12-08 19:32:46 -08:00
b768174094
skill slugs
2025-12-08 18:42:01 -08:00
91cdc8b3b3
added proper output types
2025-12-08 18:18:58 -08:00
b1e4d6e686
primitive skills impl (with cookies)
2025-12-08 18:07:00 -08:00
71d529d14d
simple browser use integration
2025-12-05 16:46:36 -08:00
a4e77e2070
Merge branch 'main' into add-ai-step-for-extraction
2025-12-03 09:14:26 -08:00
885a3dbb38
Merge branch 'main' into add-model-fallback
2025-12-03 05:59:03 -08:00
d0e181216e
feat: added fallback llm support
2025-12-03 18:53:29 +05:30
ef03559d51
Bugfix to #3702
2025-12-02 17:00:46 -08:00
7d2c6dc79e
AI: add ai_step to replace extract_content on rerun
2025-12-01 21:34:09 +05:30
a742645416
Revert "Improve demo mode"
2025-11-29 13:09:20 -08:00
02cf38e864
Revert "allowing MUCH MORE with coordinates"
2025-11-28 04:00:22 -08:00
79df8fc818
hotfix
2025-11-27 15:03:48 -08:00
46cb1a0ae1
allowing MUCH MORE with coordinates
2025-11-27 14:48:23 -08:00
f98eb7a838
env var to disable version check
2025-11-26 13:06:03 -08:00
81fe5c0573
Merge branch 'main' into kalil0321/demo-mode
2025-11-26 10:28:04 -08:00
ed7cfa4ab2
fix title problem in schema as well as enum problems
2025-11-25 13:02:39 -08:00
e9cd88e6a5
Refactor page boundary indicators in prompts and formatting
...
Co-authored-by: mailmertunsal <mailmertunsal@gmail.com >
2025-11-24 22:10:08 +00:00
c951b94193
Merge branch 'main' into kalil0321/demo-mode
2025-11-22 13:43:07 +01:00
444825f307
Checkpoint before follow-up message
...
Co-authored-by: mailmertunsal <mailmertunsal@gmail.com >
2025-11-22 08:08:44 +00:00
2df1faabe8
Apply suggestions from code review
2025-11-21 17:49:28 -08:00
1cb1676779
Refine action rules for sequential browser actions
...
Co-authored-by: mailmertunsal <mailmertunsal@gmail.com >
2025-11-22 01:43:40 +00:00
9388800a9d
Refine action rules for better state verification
...
Co-authored-by: mailmertunsal <mailmertunsal@gmail.com >
2025-11-22 01:35:29 +00:00
1a46aee4b8
Merge branch 'main' into cursor/update-agent-prompts-for-action-limits-and-verification-claude-4.5-sonnet-thinking-e3b0
2025-11-21 17:32:53 -08:00
d1b47eba50
Refactor: Reduce max actions per step to 3
...
Co-authored-by: mailmertunsal <mailmertunsal@gmail.com >
2025-11-22 01:29:59 +00:00
Saurav Panda