litellm/tests/llm_responses_api_testing
mateo-berri 7edf5b36cf fix(guardrails): deliver modify_response block as valid SSE on streaming chat and Responses
A guardrail modify_response verdict on a streaming request only produced a
proper replacement on /v1/messages: the chat completions and Responses API
translations had no build_block_sse_chunks, so the ModifyResponseException
re-raised and surfaced as an in-stream 500 error frame (or a whole-request
500 in buffered mode) instead of the documented 200 replacement.

Implement build_block_sse_chunks for both OpenAI translations: chat emits a
content delta plus a finish_reason content_filter chunk with real usage;
Responses emits the typed event sequence (standalone via
build_synthetic_response_events pre-stream, or an output-item continuation
under the in-progress response id mid-stream) ending in response.completed.
2026-08-31 16:01:39 -07:00
..
base_responses_api.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
conftest.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_anthropic_responses_api.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_anthropic_tool_result_empty_call_id.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_anthropic_tool_result_fix.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_azure_responses_api.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_base_responses_api_streaming_iterator.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_google_ai_studio_responses_api.py test: drop the cwd-relative sys.path.insert calls from the test suite (#37802) 2026-08-22 09:25:58 -07:00
test_openai_responses_api.py test(responses): use a reasoning-legal temperature in the gpt-5.5 extra_body merge test 2026-08-29 01:36:45 -07:00
test_responses_hooks.py fix(guardrails): deliver modify_response block as valid SSE on streaming chat and Responses 2026-08-31 16:01:39 -07:00