mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-15 09:12:18 +00:00
3dcc550aae
* fix(router): stop a Responses fallback from replaying a delivered tool call A tool-only Responses stream carries no output text, so a retriable error or response.failed after a completed function call was treated as a failure before output and the fallback replayed the whole request, running the tool twice. Check for a started tool call before the before-output shortcut so the primary error surfaces instead. Pre-output fallback and text continuation are unchanged. * test(router): read the delivered tool call events one at a time Consume the created and output_item.done events with anext and expect the primary error on the next read, so the raises block holds a single statement. --------- Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| audio_transcription | ||
| auth | ||
| batches | ||
| chat | ||
| decisions | ||
| embedding | ||
| files | ||
| guardrail_translation | ||
| harness | ||
| realtime | ||
| rerank | ||
| responses | ||
| search | ||
| vector_store | ||
| __init__.py | ||
| test_base_managed_resource.py | ||
| test_base_model_iterator.py | ||
| test_base_utils.py | ||
| test_managed_resource_isolation.py | ||
| test_managed_resources_utils.py | ||