mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-11 08:38:24 +00:00
The proxy attaches its shared aiohttp session to every request and a default stream_timeout to every stream, and the messages detectors treated both as Python-only features, so no proxy request reached Rust. A shared session is only a connection-reuse hint and no native client reads it, so the common caller_client detector now fires only for an explicit client. The native messages call now takes the one timeout Python's messages handler resolves from timeout, request_timeout, stream_timeout and an httpx.Timeout, so no timeout shape keeps a messages call on Python |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| conftest.py | ||
| data.py | ||
| test_body_hooks.py | ||
| test_callbacks.py | ||
| test_dispatch.py | ||
| test_failures.py | ||
| test_lifecycle.py | ||
| test_requests.py | ||
| test_settings.py | ||
| test_streaming.py | ||