mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-15 23:31:29 +00:00
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 | ||
| _harness_smoke_test.py | ||
| conftest.py | ||
| test_alerting.py | ||
| test_callback_capabilities_class.py | ||
| test_callback_capabilities_dataclass.py | ||
| test_during_call_hook.py | ||
| test_guardrail_pipeline.py | ||
| test_internal_usage_cache.py | ||
| test_lifecycle.py | ||
| test_mcp_bridging.py | ||
| test_module_helpers.py | ||
| test_post_call_failure_hook.py | ||
| test_post_call_success_hook.py | ||
| test_pre_call_hook.py | ||
| test_streaming_hooks.py | ||