mirror of
https://github.com/usestrix/strix.git
synced 2026-08-28 05:25:00 +00:00
6a0441e072
Models sometimes request very large wait timeouts (hours or more). The raw value went straight into the inner asyncio.wait_for, so the SDK's tool-call ceiling fired first and aborted the call instead of returning the clean timeout payload that tells the agent to keep working or finish. Clamp the requested value into [1s, 300s], wait on the clamped value, and echo it back. |
||
|---|---|---|
| .. | ||
| agents | ||
| config | ||
| core | ||
| interface | ||
| llm | ||
| report | ||
| runtime | ||
| skills | ||
| telemetry | ||
| tools | ||
| utils | ||
| __init__.py | ||