Commit graph

386 commits

Author SHA1 Message Date
STJ
7d44be7d53 Improve concurrency test 2026-04-01 13:49:30 -07:00
STJ
940a23c9ae Update test_browser_isolation.py 2026-04-01 13:49:30 -07:00
STJ
6ae56c0cbb more extensive tests for edge cases 2026-04-01 13:49:30 -07:00
STJ
3982d50573 Lean up implementation 2026-04-01 13:49:30 -07:00
STJ
0a5d0f288b cleanup + concurrency test 2026-04-01 13:49:30 -07:00
STJ
48ea4d15d6 fix: properly isolate context 2026-04-01 13:49:30 -07:00
STJ
c7eb83bec9 comment cleanup 2026-04-01 13:49:30 -07:00
STJ
323766180e add run test 2026-04-01 13:49:30 -07:00
STJ
37942d0857 cleanup logging in browser_actions (to test) 2026-04-01 13:49:30 -07:00
STJ
65fd7168b3 base integration tests 2026-04-01 13:49:30 -07:00
STJ
eccc62b5a7 Update schema with correct(er) names 2026-04-01 13:49:30 -07:00
STJ
74061b7781 remove file name parameter from schema definition 2026-04-01 13:49:30 -07:00
STJ
c023468b23 cleanup renderer 2026-04-01 13:49:30 -07:00
STJ
d80578c415 suppress cdp + add logging 2026-04-01 13:49:30 -07:00
STJ
57ddce161f slim down cdp functionality 2026-04-01 13:49:30 -07:00
STJ
b434d87601 remove docker entrypoint slop 2026-04-01 13:49:30 -07:00
STJ
c4c953ed32 remove upload files 2026-04-01 13:49:30 -07:00
STJ
d5344ade75 simplify actions, remove ones that cannot be used 2026-04-01 13:49:30 -07:00
STJ
f91c9ef62e important notes 2026-04-01 13:49:30 -07:00
STJ
1ffcbcf9d3 slim down browser-manager 2026-04-01 13:49:30 -07:00
STJ
e461905ab9 prevent browseruse from killing cdp connection 2026-04-01 13:49:30 -07:00
STJ
f35f287dff Update docker_runtime.py 2026-04-01 13:49:30 -07:00
STJ
26a55865a6 qol on chat browser 2026-04-01 13:49:30 -07:00
STJ
b6695cd2e1 remove slop comments 2026-04-01 13:49:30 -07:00
STJ
d9d6fb2e42 metadata + cleanup some actions 2026-04-01 13:49:30 -07:00
STJ
9836e3fc84 streamline into tool-server 2026-04-01 13:49:30 -07:00
STJ
3718943134 qol 2026-04-01 13:49:30 -07:00
STJ
4c2b368976 small changes (QOL) 2026-04-01 13:49:30 -07:00
STJ
79890b760e Update renderer 2026-04-01 13:49:30 -07:00
STJ
f3bb25919c refactor 2026-04-01 13:49:30 -07:00
Shanyu Thibaut Juneja
550690ee30 remove built-in llm, use langchain 2026-04-01 13:49:30 -07:00
Shanyu Thibaut Juneja
9fc09e86a4 fix: improve support for non-vision models 2026-04-01 13:49:30 -07:00
Shanyu Thibaut Juneja
f99b7ebd4f Refines browser state handling and healthcheck
Enhances browser command robustness by gracefully handling cases where
the DOM state is not yet available, returning an informative error
instead of asserting.

Updates the container healthcheck to directly probe Chromium's internal
CDP port, simplifying the check by removing previous indirection.
2026-04-01 13:49:30 -07:00
Shanyu Thibaut Juneja
bbf6e08bab debug: disable 2026-04-01 13:49:30 -07:00
Shanyu Thibaut Juneja
0e4307d625 harden: authentication for cdp 2026-04-01 13:49:30 -07:00
Shanyu Thibaut Juneja
428ae57e59 fix greptile 2026-04-01 13:49:30 -07:00
Shanyu Thibaut Juneja
d8b2a18425 simplify entrypoint 2026-04-01 13:49:30 -07:00
Shanyu Thibaut Juneja
b880ed454c feat: browser-use tool initial migration 2026-04-01 13:49:30 -07:00
STJ
38b2700553
feat: Migrate from Poetry to uv (#379) 2026-03-31 17:20:41 -07:00
alex s
e78c931e4e
feat: Better source-aware testing (#391) 2026-03-31 11:53:49 -07:00
0xallam
7d5a45deaf chore: bump version to 0.8.3 2026-03-22 22:10:17 -07:00
0xallam
dec2c47145 fix: use anthropic model in anthropic provider docs example 2026-03-22 22:08:20 -07:00
0xallam
4f90a5621d fix: strengthen tool-call requirement in interactive and autonomous modes
Models occasionally output text-only narration ("Planning the
assessment...") without a tool call, which halts the interactive agent
loop since the system interprets no-tool-call as "waiting for user
input." Rewrite both interactive and autonomous prompt sections to make
the tool-call requirement absolute with explicit warnings about the
system halt consequence.
2026-03-22 22:08:20 -07:00
0xallam
640bd67bc2 chore: bump sandbox image to 0.1.13
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-22 22:08:20 -07:00
0xallam
4e836377e7 refine system prompt, add scope verification, and improve tool guidance
- Rewrite system prompt: refusal avoidance, system-verified scope, thorough
  validation mandate, root agent orchestration role, recon-first guidance
- Add authorized targets injection via system_prompt_context in strix_agent
- Add set_system_prompt_context to LLM for dynamic prompt updates
- Prefer python tool over terminal for Python code in tool schemas
- Increase LLM retry backoff cap to 90s
- Replace models.strix.ai footer with strix.ai

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-22 22:08:20 -07:00
0xallam
a2f1aae5ed chore: update default model to gpt-5.4 and remove Strix Router from docs
- Change default model from gpt-5 to gpt-5.4 across docs, tests, and examples
- Remove Strix Router references from docs, quickstart, overview, and README
- Delete models.mdx (Strix Router page) and its nav entry
- Simplify install script to suggest openai/ prefix directly
- Keep strix/ model routing support intact in code

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-22 22:08:20 -07:00
Ahmed Allam
b6a0a949a3 Simplify tool file copying in Dockerfile
Removed specific tool files from Dockerfile and added a directory copy instead.
2026-03-22 16:01:39 -07:00
0xallam
c9d2477144 fix: address review feedback on tool registration gating 2026-03-19 23:50:57 -07:00
0xallam
8765b1895c refactor: move tool availability checks into registration 2026-03-19 23:50:57 -07:00
Ahmed Allam
31d8a09c95
Guard TUI chat rendering against invalid Rich spans (#375) 2026-03-19 22:28:42 -07:00