Yucheng Zhu 0e6c4279b6 fix(guardrails): record not_run evaluation when scoping leaves nothing to scan ... Replaces the metadata transfer approach: that block read top-level litellm_metadata which guardrail info never populates, and the SLP builder already reads the nested bucket it lands in, so it was dead code and is reverted. Real cause of missing evaluations: process_input_messages skips apply_guardrail entirely when message scoping (skip_system_message, skip_tool, scan_only_tool_results) leaves no scannable content, so the guardrail shows up in applied_guardrails with no guardrail_information entry. Now records a not_run entry unless the guardrail records its own information.		2026-08-31 21:35:32 -07:00
..
chat	fix(guardrails): record not_run evaluation when scoping leaves nothing to scan	2026-08-31 21:35:32 -07:00
completion	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
embeddings/guardrail_translation	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
evals	test: cover volcengine responses and openai evals transformations	2026-07-27 12:57:21 -07:00
image_generation	fix(otel): emit LLM Call spans for speech, image, moderation, ocr and transcription (#37752)	2026-08-22 11:11:21 -07:00
realtime	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
responses	fix(responses): count input_file tokens instead of silently dropping the file	2026-08-31 13:17:43 -07:00
speech	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
transcriptions	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
vector_store_files	fix: encode upstream URL path identifiers	2026-04-29 22:02:39 -07:00
vector_stores	fix: encode upstream URL path identifiers	2026-04-29 22:02:39 -07:00
videos	fix(videos): forward uploaded source file on /v1/videos/edits to the provider	2026-08-24 15:34:21 -07:00
test_cost_calculation.py	fix(transcription): stop a zero output rate from zeroing transcription cost (#36914)	2026-08-14 15:12:37 -07:00
test_data_residency.py	feat(openai): apply regional-processing cost uplift for EU/US data residency (#28626)	2026-05-25 20:36:14 -07:00
test_gpt5_transformation.py	fix(gpt-5): resolve temperature support from the model's default reasoning effort	2026-08-27 18:46:18 -07:00
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	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
test_openai_common_utils.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_empty_response.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_file_content_streaming.py	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
test_openai_image_edit_transformation.py	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
test_openai_workload_identity.py	fix(openai): treat empty api_key as unset for WIF resolution	2026-08-31 19:55:29 +00:00
test_use_chat_completions_api_no_leak.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00