..
a2a_protocol
[Fix] A2a Gateway - Allow supporting old A2a card formats ( #19949 )
2026-01-28 15:02:08 -08:00
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
litellm_fix(azure): Fix acancel_batch not using Azure SDK client initialization ( #20168 )
2026-01-31 11:45:25 -08:00
caching
Add support for caching for responses API
2026-01-14 13:33:07 +05:30
completion_extras
_add_web_search_tool
2026-01-31 11:21:40 -08:00
containers
Make keepalive_timeout parameter work for Gunicorn ( #19087 )
2026-01-16 03:32:59 +05:30
endpoints/speech /speech_to_completion_bridge
experimental_mcp_client
fix MCP client
2026-01-31 11:25:21 -08:00
files
fix(mypy): fix type errors in files, opentelemetry, gemini transformation, and key management ( #20161 )
2026-01-31 10:09:07 -08:00
fine_tuning
google_genai
Add custom vertex ai mapping to the output
2026-01-22 15:18:24 +05:30
images
Add None as default image value
2026-01-19 09:08:38 +05:30
integrations
Fix: Slack alert issue
2026-02-02 16:49:10 +05:30
interactions
litellm_core_utils
perf: cache _get_relevant_args_to_use_for_logging() at module level ( #20077 )
2026-02-02 10:54:49 -08:00
llms
fix: litellm_core_utils/prompt_templates/factory.py:3431
2026-02-02 19:00:12 +05:30
ocr
passthrough
[Fix] VertexAI Pass through - Ensure only anthropic betas are forwarded down to LLM API ( #19542 )
2026-01-21 19:12:04 -08:00
proxy
fix: MCP "Session not found" error on VSCode reconnect ( #20298 )
2026-02-02 14:15:31 -08:00
rag
[Feat] RAG API - Add s3_vectors as provider on /vector_store/search API + UI for creating + PDF support for /rag/ingest ( #19895 )
2026-01-27 16:30:59 -08:00
realtime_api
Add bedrock route in realtim main.py
2026-02-02 12:16:05 +05:30
rerank_api
responses
fix: Include hidden params in chat response to responses api response transformation ( #20084 )
2026-02-02 18:24:21 +05:30
router_strategy
router_utils
fix: prevent error when max_fallbacks exceeds available models ( #20071 )
2026-02-02 18:23:53 +05:30
search
secret_managers
fix: make HTTPHandler mockable in OIDC secret manager tests ( #19803 )
2026-01-26 11:00:42 -08:00
skills
types
feat: enforce model-level TPM/RPM limits (enforce_model_rate_limits) … ( #19230 )
2026-02-02 18:18:46 +05:30
vector_store_files
vector_stores
videos
__init__.py
remove key blocking
2026-01-31 16:46:17 -08:00
_lazy_imports_registry.py
fix(hosted_vllm): route through base_llm_http_handler to support ssl_verify ( #19893 )
2026-01-28 22:33:07 -08:00
_lazy_imports.py
_logging.py
Fix: log duplication when json_logs is enabled ( #19705 )
2026-01-24 11:09:04 -08:00
_redis.py
_service_logger.py
fix(langfuse_otel): ignore service logs and fix callback shadowing ( #19298 )
2026-01-19 05:53:47 -08:00
_uuid.py
_version.py
budget_manager.py
constants.py
[Feat] New Model - amazon.nova-2-pro-preview-20251202-v1:0 ( #20033 )
2026-01-29 16:55:55 -08:00
cost_calculator.py
[Feat] v2 - Logs view with side panel and improved UX ( #20091 )
2026-01-30 18:34:13 -08:00
cost.json
exceptions.py
Fix unsafe access to request attribute ( #19573 )
2026-01-22 10:58:29 -08:00
main.py
Fix open_ai_embedding_models to have custom_llm_provider None
2026-02-02 15:18:56 +05:30
model_prices_and_context_window_backup.json
feat(vertex_ai): add global endpoint support for Qwen MaaS models
2026-02-02 18:13:10 +05:30
mypy.ini
py.typed
router.py
feat: enforce model-level TPM/RPM limits (enforce_model_rate_limits) … ( #19230 )
2026-02-02 18:18:46 +05:30
scheduler.py
Fix queue persistence to Redis ( #19304 )
2026-01-19 19:01:34 -08:00
timeout.py
utils.py
perf: optimize wrapper_async with CallTypes caching and reduced lookups ( #20204 )
2026-02-02 10:42:12 -08:00
923b1cfd92