Ahmed Allam and GitHub
0607abf9e5
fix(tui): scrollbar visibility, findings scrolling, and report navigation ( #1006 )
2026-08-07 06:14:22 -07:00
Ahmed Allam and GitHub
82dcd31357
fix(tui): keep a long error inside the status row ( #970 )
2026-08-04 07:26:22 -07:00
Ahmed Allam
ea6d53f4e9
build: add types-requests to dev deps
...
The old openai-agents pin pulled types-requests in transitively; 0.19.0 does
not, so mypy lost the requests stubs. Depend on them directly.
2026-08-04 06:14:54 +03:00
Ahmed Allam
3bcf3778f0
fix(core): settle a non-interactive agent's status before its exception unwinds
...
An exception escaping a non-interactive cycle re-raised before the status
handling, so a dying child stayed 'running' and its parent waited out the
timeout on a completion report the child could no longer send. Set the
terminal status and wake the parent on the way out too.
2026-08-04 06:14:54 +03:00
Ahmed Allam
4a455b1e62
fix(core): recover from hallucinated tool names instead of ending the scan
...
A tool call for a name Strix does not register raised ModelBehaviorError
from the SDK turn resolver, which nothing retries: the root agent's raise
tore down the whole scan and a sub-agent died before its status was set.
Opt into the SDK's tool_not_found_behavior="return_error_to_model" so the
unknown call comes back as a tool result and the agent self-corrects.
The setting landed in openai-agents 0.19.0, which requires openai>=2.45,
so both pins move.
2026-08-04 06:14:54 +03:00
Ahmed Allam and GitHub
8ec54d9e2b
chore: release v1.3.0 ( #849 )
2026-07-22 09:21:24 -07:00
Ahmed Allam and GitHub
1f7373714b
Local viewer: prominent scan switcher + rename to "pentest" terminology ( #848 )
2026-07-22 09:17:52 -07:00
Ahmed Allam and GitHub
ef07bad945
Local viewer: UI polish and a Feedback & support tab ( #847 )
2026-07-22 08:34:52 -07:00
Ahmed Allam and GitHub
af65796ec0
fix(runtime): close the docker client on session cleanup ( #787 )
2026-07-16 11:06:18 -07:00
Ahmed Allam and GitHub
e2eb39a02e
fix(runtime): cap sandbox container logs to prevent host disk exhaustion ( #785 )
2026-07-16 09:17:46 -07:00
Ahmed Allam and GitHub
81a8b2139b
Update README
2026-07-13 17:57:40 -07:00
Ahmed Allam and GitHub
f28ebe3668
Update README ( #705 )
2026-07-06 07:38:52 -07:00
Ahmed Allam and GitHub
69e82f0258
chore(deps): refresh uv.lock to latest compatible versions ( #606 )
2026-06-29 19:10:18 -07:00
Ahmed Allam and GitHub
52ca641679
Update readme ( #607 )
2026-06-29 19:09:58 -07:00
Ahmed Allam and GitHub
60d68d85f3
Readme update
2026-06-29 19:00:46 -07:00
Ahmed Allam and GitHub
cc23eeb65d
Bump 1.0.3 -> 1.0.4 ( #557 )
2026-06-09 09:41:44 -07:00
Ahmed Allam and GitHub
7217abfe23
Strip ANSI escapes and control bytes from terminal tool output ( #554 )
2026-06-09 09:22:50 -07:00
Ahmed Allam and GitHub
f7e3af49bd
Strip all images from session on vision-rejection, not just the latest ( #553 )
2026-06-09 02:48:30 -07:00
Ahmed Allam and GitHub
6202131028
Swallow sandbox container races in the stream consumer ( #552 )
2026-06-09 01:46:23 -07:00
Ahmed Allam and GitHub
45409cef0d
Make TUI quit instant by SIGKILL-ing the sandbox container ( #548 )
2026-06-08 23:40:45 -07:00
Ahmed Allam and GitHub
250fe2cf3e
Bump 1.0.2 -> 1.0.3 ( #537 )
2026-06-08 18:05:02 -07:00
Ahmed Allam and GitHub
6c99829325
Simplify cost ledger to one bucket ( #531 )
2026-06-08 15:56:28 -07:00
Ahmed Allam and GitHub
1c9ab993bb
Use observed LiteLLM cost for LiteLLM-routed calls ( #529 )
...
Register a litellm.success_callback that captures kwargs['response_cost']
into a new observed-cost bucket on LLMUsageLedger. record() skips the
tokens-times-registry estimate for LiteLLM-routed models so we do not
double-count with the callback; OpenAI direct routes keep estimating
since LiteLLM is not invoked for them. Per-agent attribution for
LiteLLM-routed calls is apportioned by token share at to_record() time.
2026-06-08 15:01:48 -07:00
Ahmed Allam and GitHub
04eb03febe
Gate Reasoning(effort=...) on registry support ( #528 )
...
OpenAI's Responses API rejects reasoning.effort on non-reasoning
models like gpt-4o with `unsupported_parameter`, so any scan with
the default STRIX_REASONING_EFFORT=high against gpt-4o crashed at
the first model call. drop_params=True absorbs the rejected param
on LiteLLM-routed models but the SDK's native OpenAI path has no
equivalent.
Lift model_supports_reasoning to a public helper that strips
litellm/, any-llm/, openai/ prefixes and falls back to last-segment
lookup so prefixed forms like anthropic/claude-opus-4-7 resolve
through the bare model_cost entry. make_model_settings regains
model_name and skips Reasoning() when the registry doesn't confirm
support. uses_chat_completions_tool_schema reuses the same helper
(was duplicating the lookup under a misleading name).
2026-06-08 13:18:07 -07:00
Ahmed Allam and GitHub
ac0fef2ed7
Show "Send message to resume" on the left of the status bar ( #525 )
2026-06-07 17:41:06 -07:00
13046cc74a
fix: gate reasoning_effort by LiteLLM model registry ( closes #517 ) ( #523 )
...
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com >
2026-06-07 12:24:48 -07:00
1aad460f6e
fix: SDK tracing leak + orphan docker on TUI quit ( closes #512 ) ( #522 )
...
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com >
2026-06-07 11:28:06 -07:00
d0321510d2
fix: reasoning models reject tool_choice=required; bump to 1.0.2 ( closes #503 , #505 ) ( #508 )
...
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com >
2026-05-28 11:55:10 -07:00
Ahmed Allam and GitHub
3bd9d56814
fix: PyInstaller bundle is broken (missing agents SDK data + wrongly excluded gql); bump to 1.0.1 ( #502 )
2026-05-26 20:04:01 -07:00
Ahmed Allam and GitHub
63faecd3b5
Strix v1.0.0 release
...
Strix v1.0.0 — Native tool calling, save & resume, multi-agent control
2026-05-26 14:42:13 -07:00
Ahmed Allam and GitHub
62e9af36d2
Add Strix GitHub Actions integration tip
2026-04-12 12:43:41 -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
Ahmed Allam and GitHub
31d8a09c95
Guard TUI chat rendering against invalid Rich spans ( #375 )
2026-03-19 22:28:42 -07:00
Ahmed Allam and GitHub
9a0bc5e491
fix: prevent ScreenStackError when stopping agent from modal ( #374 )
2026-03-19 20:39:05 -07:00
Ahmed Allam
f0f8f3d4cc
Add tip about Strix integration with GitHub Actions
2026-03-17 22:14:11 -07:00
Ahmed Allam
f71e34dd0f
Update web search model name to 'sonar-reasoning-pro'
2026-03-11 14:20:04 -07:00
Ahmed Allam and GitHub
72c3e0dd90
Update README
2026-03-03 03:33:46 +04:00
Ahmed Allam and GitHub
d30e1d2f66
Update models.mdx
2026-03-03 03:33:14 +04:00
Ahmed Allam and GitHub
551b780f52
Update installation instructions
...
Removed pipx installation instructions for strix-agent.
2026-02-22 00:10:06 +04:00
Ahmed Allam and GitHub
6166be841b
Resolve LLM API Base and Models ( #317 )
2026-02-20 07:14:10 -08:00
Ahmed Allam and GitHub
b8cabdde97
Update README
2026-02-01 05:13:59 +04:00
Ahmed Allam and GitHub
83ce9ed960
Update README.md
2026-02-01 05:11:44 +04:00
Ahmed Allam and GitHub
655ddb4d7f
Update README with full details section
2026-01-23 23:05:26 +04:00
Ahmed Allam and GitHub
6bacc796e2
Update README
2026-01-23 06:56:10 +04:00
Ahmed Allam and GitHub
c50c79084b
Update README
2026-01-23 06:55:35 +04:00
Ahmed Allam and GitHub
ceeec8faa8
Update README
2026-01-16 02:34:30 +04:00
Ahmed Allam and GitHub
d16bdb277a
Update README
2026-01-14 05:00:16 +04:00
Ahmed Allam and greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
d932602a6b
Update args in strix/interface/main.py
...
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2026-01-09 20:00:01 -08:00
Ahmed Allam and GitHub
49421f50d5
Remove title from README
2026-01-10 02:35:20 +04:00
Ahmed Allam and GitHub
8b0bb521ba
Update link in README
2026-01-03 08:28:03 +04:00
Ahmed Allam and GitHub
f25cf9b23d
Remove PyPI Downloads badge from readme
2026-01-01 23:27:00 +04:00
Ahmed Allam and GitHub
0fcd5c46b2
Fix badge in README.md
2025-12-15 19:39:47 +04:00
Ahmed Allam and GitHub
624f1ed77f
feat(tui): add markdown rendering for agent messages ( #197 )
...
Add AgentMessageRenderer to render agent messages with basic markdown support:
- Headers (#, ##, ###, ####)
- Bold (**text**) and italic (*text*)
- Inline code and fenced code blocks
- Links [text](url) and strikethrough
Update system prompt to allow agents to use simple markdown formatting.
2025-12-14 22:53:07 +04:00
Ahmed Allam and GitHub
2b926c733b
feat(tools): add dedicated todo tool for agent task tracking ( #196 )
...
- Add new todo tool with create, list, update, mark_done, mark_pending, delete actions
- Each subagent has isolated todo storage keyed by agent_id
- Support bulk todo creation via JSON array or bullet list
- Add TUI renderers for all todo actions with status markers
- Update notes tool to remove priority and todo-related functionality
- Add task tracking guidance to StrixAgent system prompt
- Fix instruction file error handling in CLI
2025-12-14 22:16:02 +04:00
Ahmed Allam and GitHub
a075ea1a0a
feat(tui): add syntax highlighting for tool renderers ( #195 )
...
Add Pygments-based syntax highlighting with native hacker theme:
- Python renderer: Python code highlighting
- Browser renderer: JavaScript code highlighting
- Terminal renderer: Bash command highlighting
- File edit renderer: Auto-detect language from file extension, diff-style display
2025-12-14 04:39:28 +04:00
Ahmed Allam and GitHub
e57b7238f6
Update README to remove duplicate demo image
2025-12-12 21:59:16 +04:00
Ahmed Allam and GitHub
13fe87d428
Add DeepWiki docs for Strix
2025-12-12 21:58:28 +04:00
Ahmed Allam and GitHub
b74132b2dc
Update README.md
2025-12-03 20:09:22 +00:00
Ahmed Allam and GitHub
62f804b8b5
Update link in README
2025-12-01 16:04:46 +04:00
Ahmed Allam and GitHub
5ff10e9d20
Add acknowledgements in README
2025-11-29 19:27:30 +04:00
Ahmed Allam and GitHub
2ae1b3ddd1
Update README
2025-11-23 22:29:44 +04:00
Ahmed Allam and GitHub
6a2a62c121
chore: Fix formatting in README.md
2025-11-14 16:07:54 +00:00
Ahmed Allam and GitHub
f1d2961779
Update README
2025-11-12 19:29:01 +04:00
Ahmed Allam and GitHub
b6d9d941cf
Update README
2025-11-08 15:07:53 +04:00
Ahmed Allam and GitHub
85209bfc20
chore: replaced Discord invite link with open invite
...
(remove the unneeded join application)
2025-10-31 15:19:46 +02:00
Ahmed Allam and GitHub
7de9c4efe1
feat: Add prompt module collections and contributing.md ( #40 )
2025-10-10 10:41:42 +01:00
Ahmed Allam and GitHub
7979b84cc3
Update issue templates
2025-09-29 02:19:04 +01:00
Ahmed Allam and GitHub
c8b23720df
Fix tool server http requests issues ( #37 )
2025-09-24 04:41:23 +01:00
Ahmed Allam and GitHub
7d8ffe1e32
Fix escape issues causing tui to crash ( #36 )
2025-09-24 04:14:08 +01:00
Ahmed Allam and GitHub
aabf97af0a
Adding more verbose logging for llm failed requests ( #30 )
2025-09-14 15:56:07 -07:00
Ahmed Allam and Ahmed Allam
d43fb5be03
Update README
2025-09-08 10:31:16 -07:00
Ahmed Allam and GitHub
cb57426cc6
Running all agents under same container ( #12 )
2025-08-18 21:58:38 +01:00
Ahmed Allam and GitHub
198a5e4a61
Redesigning the terminal tool ( #11 )
2025-08-17 07:43:29 +01:00
Ahmed Allam and GitHub
ccab853c0f
Clone git repositories internally ( #10 )
2025-08-16 23:47:36 +01:00
Ahmed Allam and GitHub
337d64d362
Adding full support for gpt-5 models ( #5 )
2025-08-15 21:02:39 +01:00