mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-14 09:03:16 +00:00
When the upstream connection drops or stalls mid-stream on the Rust Messages path, the caller gets the raw httpx error without litellm_debug_info, so the llm_exceptions alert names no API base, model group or deployment. Python's stream iterator attaches that info to the same error, and the Rust host now does too. |
||
|---|---|---|
| .. | ||
| routes | ||
| __init__.py | ||
| test_cache.py | ||
| test_callbacks_legacy_python.py | ||
| test_model_capabilities.py | ||
| test_model_cost.py | ||
| test_preflight.py | ||
| test_redis_credentials.py | ||
| test_redis_events.py | ||
| test_secret_manager.py | ||
| test_settings.py | ||