| .. |
|
a2a_protocol
|
fix: fix ruff linting errors
|
2025-12-16 07:38:07 +05:30 |
|
anthropic_interface
|
|
|
|
assistants
|
|
|
|
batch_completion
|
|
|
|
batches
|
Revert batch utils with original logic
|
2025-12-10 17:01:21 +05:30 |
|
caching
|
|
|
|
completion_extras
|
Guardrails API - support LLM tool call response checks on /chat/completions, /v1/responses, /v1/messages on regular + streaming calls (#17619)
|
2025-12-15 18:19:52 +05:30 |
|
containers
|
[Feat] Containers API - add new container API file management + UI Interface (#17745)
|
2025-12-09 17:33:26 -08:00 |
|
endpoints/speech/speech_to_completion_bridge
|
|
|
|
experimental_mcp_client
|
|
|
|
files
|
Add support for expires after param
|
2025-12-12 10:01:18 +05:30 |
|
fine_tuning
|
|
|
|
google_genai
|
fix: Preserve systemInstructions for vertex ai generate content request
|
2025-12-11 09:52:32 +05:30 |
|
images
|
feat(custom_llm): add image_edit and aimage_edit support (#17999)
|
2025-12-15 14:16:36 -08:00 |
|
integrations
|
Guardrails API - support LLM tool call response checks on /chat/completions, /v1/responses, /v1/messages on regular + streaming calls (#17619)
|
2025-12-15 18:19:52 +05:30 |
|
litellm_core_utils
|
fix: filter internal params in fallback code and fix test issues (#17941)
|
2025-12-13 15:05:26 -08:00 |
|
llms
|
feat(venice.ai): add support for Venice.ai API via providers.json (#17962)
|
2025-12-16 08:24:16 +05:30 |
|
ocr
|
|
|
|
passthrough
|
|
|
|
proxy
|
[Feat] New provider - Agent Gateway, add pydantic ai agents (#18013)
|
2025-12-15 17:40:58 -08:00 |
|
rag
|
|
|
|
realtime_api
|
|
|
|
rerank_api
|
Add tests for header forwarding
|
2025-12-12 17:54:17 +05:30 |
|
responses
|
Merge pull request #17980 from BerriAI/litellm_add_provider_specific_tools_in_responses
|
2025-12-15 22:53:08 +05:30 |
|
router_strategy
|
|
|
|
router_utils
|
fix(router): add minimum request threshold for error rate cooldown (#17464)
|
2025-12-12 04:36:10 -08:00 |
|
search
|
|
|
|
secret_managers
|
fix: cyberark allow setting ssl verfiy to false (#17433)
|
2025-12-03 18:54:31 -08:00 |
|
skills
|
|
|
|
types
|
Guardrails API - support LLM tool call response checks on /chat/completions, /v1/responses, /v1/messages on regular + streaming calls (#17619)
|
2025-12-15 18:19:52 +05:30 |
|
vector_store_files
|
|
|
|
vector_stores
|
Fix vector store configuration synchronization failure
|
2025-12-05 11:46:14 +05:30 |
|
videos
|
fix: respect videos content db creds
|
2025-12-10 23:00:01 +05:30 |
|
__init__.py
|
refactor: lazy load get_modified_max_tokens (#18002)
|
2025-12-15 12:33:01 -08:00 |
|
_lazy_imports.py
|
refactor: lazy load get_modified_max_tokens (#18002)
|
2025-12-15 12:33:01 -08:00 |
|
_logging.py
|
|
|
|
_redis.py
|
|
|
|
_service_logger.py
|
|
|
|
_uuid.py
|
|
|
|
_version.py
|
|
|
|
budget_manager.py
|
|
|
|
constants.py
|
fix(router): add minimum request threshold for error rate cooldown (#17464)
|
2025-12-12 04:36:10 -08:00 |
|
cost_calculator.py
|
fix: default quality cost calculation of gpt-image 1 model
|
2025-12-15 08:16:25 +05:30 |
|
cost.json
|
|
|
|
exceptions.py
|
|
|
|
main.py
|
Merge pull request #17747 from BerriAI/litellm_feat_mcp-chat-completions
|
2025-12-13 05:05:21 +09:00 |
|
model_prices_and_context_window_backup.json
|
[fix] add qwen3-embedding-8b input per token price (#18018)
|
2025-12-16 07:38:21 +05:30 |
|
mypy.ini
|
|
|
|
py.typed
|
|
|
|
router.py
|
refactor(router): replace time.perf_counter() with time.time() for timing measurements (#17881)
|
2025-12-12 08:51:18 -08:00 |
|
scheduler.py
|
|
|
|
timeout.py
|
|
|
|
utils.py
|
fix(openai/responses/guardrail_translation): fix basemodel import (#17977)
|
2025-12-15 16:13:45 +05:30 |
