litellm/litellm
Peter Golm c215b3a79f
fix: preserve llm_provider-* headers in error responses (#19020)
Extract and preserve provider-specific headers (llm_provider-*) when
handling error responses from LLM providers. This ensures that useful
debugging information from providers is available even when requests
fail with BadRequestError or similar exceptions.
2026-01-14 22:49:39 +05:30
..
a2a_protocol
anthropic_interface [bug fix] do not fallback to token counter if disable_token_counter is enabled (#19041) 2026-01-13 16:53:38 -08:00
assistants
batch_completion
batches
caching
completion_extras
containers
endpoints/speech/speech_to_completion_bridge
experimental_mcp_client
files [Feat] Manus FILES API - Add File upload, get, delete, list (#18904) 2026-01-10 13:27:54 -08:00
fine_tuning
google_genai fix(google_genai): forward extra_headers in generateContent adapter (#18935) 2026-01-12 16:23:58 +05:30
images
integrations Merge pull request #19079 from BerriAI/main 2026-01-14 16:44:31 +05:30
interactions
litellm_core_utils fix(gemini): dereference $defs/$ref in tool response content (#19062) 2026-01-14 22:28:28 +05:30
llms fix: preserve llm_provider-* headers in error responses (#19020) 2026-01-14 22:49:39 +05:30
ocr
passthrough
proxy fix: preserve llm_provider-* headers in error responses (#19020) 2026-01-14 22:49:39 +05:30
rag
realtime_api
rerank_api
responses fix: anthropic Extra inputs are not permitted error 2026-01-14 11:15:56 +09:00
router_strategy
router_utils
search
secret_managers
skills
types Merge pull request #19042 from BerriAI/litellm_staging_01_13_2026 2026-01-14 21:29:09 +05:30
vector_store_files
vector_stores
videos
__init__.py
_lazy_imports_registry.py
_lazy_imports.py
_logging.py
_redis.py
_service_logger.py
_uuid.py
_version.py
budget_manager.py
constants.py fix(ui): use non-streaming method for endpoint v1/a2a/message/send in… (#19025) 2026-01-14 03:29:10 +05:30
cost_calculator.py [Feat] New Model - Azure Model Router on LiteLLM AI Gateway (#19054) 2026-01-13 18:31:43 -08:00
cost.json
exceptions.py fix: preserve llm_provider-* headers in error responses (#19020) 2026-01-14 22:49:39 +05:30
main.py Add retry policy support to responses API 2026-01-14 14:55:17 +05:30
model_prices_and_context_window_backup.json Fix: Responses content can't be none 2026-01-14 12:13:18 +05:30
mypy.ini
py.typed
router.py Fix all 130126 tests 2026-01-14 17:42:52 +05:30
scheduler.py
timeout.py
utils.py Add retry policy support to responses API 2026-01-14 14:55:17 +05:30