litellm/tests/test_litellm/llms/openai
mateo-berri 28ff7f3f0b fix(guardrails): scan function-role results and dedupe returned tools
Under scan_only_tool_results, legacy OpenAI function-role messages now count as tool results, and duplicate names among guardrail-returned tools keep only the first occurrence. CustomGuardrail.structured_messages_cover_full_request lets CrowdStrike AIDR declare that its writeback already rebuilds the whole conversation, so handlers install it as-is instead of merging it into the full message list a second time and duplicating out-of-scope rows. Lint budget ceilings ratchet down to match the tree
2026-08-06 00:52:16 -07:00
..
chat fix(guardrails): scan function-role results and dedupe returned tools 2026-08-06 00:52:16 -07:00
completion Litellm oss 090626 (#30021) 2026-06-10 10:34:07 -07:00
embeddings/guardrail_translation
evals test: cover volcengine responses and openai evals transformations 2026-07-27 12:57:21 -07:00
image_generation
realtime feat: litellm oss 110626 (#30202) 2026-06-11 22:30:26 -07:00
responses feat(guardrails): add Compresr guardrail for query-aware context compression (#33295) 2026-07-15 13:53:41 -07:00
speech
transcriptions chore: litellm oss staging (#31185) 2026-06-26 09:17:44 -07:00
vector_store_files
vector_stores
videos
test_data_residency.py
test_gpt5_transformation.py
test_is_model_gpt_5_model.py feat(models): add GPT-5.6 (sol/terra/luna) pricing and metadata (#32659) 2026-07-09 11:51:12 -07:00
test_o_series_transformation.py
test_openai_common_utils.py Revert "revert: "fix(caching): close evicted LLM clients so their connections are reclaimed (#35492)"" 2026-08-04 18:23:06 -07:00
test_openai_empty_response.py
test_openai_file_content_streaming.py
test_openai_image_edit_transformation.py
test_use_chat_completions_api_no_leak.py fix: stop use_chat_completions_api flag from leaking into provider request body (#29447) 2026-06-01 14:04:42 -07:00