mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-20 00:11:50 +00:00
8d040d89e6
The streaming pipeline step only takes a post-call hook on routes whose translation assembles the streamed response (chat completions, Responses, Messages). On /v1/completions, the Gemini streamGenerateContent route, and A2A streams the pipeline is skipped with the merge-base warning and the hook runs on its own afterwards, instead of getting a None response while the header says the guardrail ran. A guardrail that overrides async_post_call_streaming_iterator_hook next to its post-call hook keeps its native per-chunk path rather than running buffered through the adapter |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| test_attachment_registry.py | ||
| test_condition_evaluator.py | ||
| test_pipeline_executor.py | ||
| test_policy_engine_endpoints.py | ||
| test_policy_matcher.py | ||
| test_policy_resolver.py | ||
| test_policy_validator.py | ||
| test_policy_versioning.py | ||
| test_policy_versioning_e2e.py | ||