..
containers
feat(containers): Azure routing, managed container IDs, delete response parsing ( #25287 )
2026-04-11 09:21:01 -07:00
google_genai
fix(mypy): fix scattered 1-off type errors across 14 files
2026-03-13 00:08:57 +00:00
images
Litellm oss staging 030626 ( #29578 )
2026-06-03 11:01:51 -07:00
integrations
chore(oss): litellm oss staging 120626 ( #30292 )
2026-06-12 09:49:25 -07:00
interactions
[internal copy of #28008 ] Support MCP OAuth passthrough and issuer-scoped JWT auth ( #28356 )
2026-06-02 12:22:04 -07:00
litellm_core_utils
include server_tool_use in streaming usage ( #16826 )
2025-11-25 14:50:17 -08:00
llms
feat: litellm oss 110626 ( #30202 )
2026-06-11 22:30:26 -07:00
management_endpoints
feat: routing groups ui
2026-05-04 18:09:14 -07:00
mcp_server
feat(litellm): add models and repository layers ( #29686 )
2026-06-06 20:59:33 -07:00
passthrough_endpoints
fix(proxy): Bedrock Knowledge Base pass-through: preserve SigV4 headers and signed request body ( #27526 )
2026-05-25 19:21:55 +05:30
prompts
style: run black formatter on files from main merge
2026-04-17 13:02:59 -07:00
proxy
feat(guardrails): add Cisco AI Defense integration ( #28249 ) ( #30338 )
2026-06-12 23:21:23 -07:00
responses
refactor: extract duplicated stdout/stderr → logs logic to shared helper
2026-03-18 22:05:27 -03:00
secret_managers
style: run black formatter on entire codebase
2026-03-11 17:07:57 -03:00
videos
style: run black formatter on files from main merge
2026-04-17 13:02:59 -07:00
access_group.py
allow editing of access group names
2026-02-13 17:03:41 -08:00
adapter.py
agents.py
Fix : a2a bugs 030626 ( #29566 )
2026-06-03 11:14:15 -07:00
caching.py
fix(caching): restore stored prompt_tokens on embedding cache hits instead of recomputing ( #30046 )
2026-06-10 15:49:20 +05:30
completion.py
fix: correct CompletionRequest messages type to match OpenAI API spec ( #12980 )
2025-07-28 16:47:20 -07:00
compression.py
Prompt Compression - add it to the proxy ( #25729 )
2026-04-20 15:08:00 -07:00
embedding.py
files.py
style: run black formatter on entire codebase
2026-03-11 17:07:57 -03:00
fine_tuning.py
(feat) POST /fine_tuning/jobs support passing vertex specific hyper params ( #7490 )
2025-01-01 07:44:48 -08:00
guardrails.py
feat(guardrails): add Cisco AI Defense integration ( #28249 ) ( #30338 )
2026-06-12 23:21:23 -07:00
mcp.py
feat(mcp): add OBO MCP Auth ( #27421 )
2026-05-07 15:35:21 -07:00
memory_management.py
feat(proxy): add /v1/memory CRUD endpoints ( #26218 )
2026-04-24 18:38:07 -07:00
policy_engine.py
[Feat] New LiteLLM Policy engine - create policies to manage guardrails, conditions - permissions per Key, Team ( #19612 )
2026-01-22 19:49:53 -08:00
rag.py
style: run black formatter on entire codebase
2026-03-11 17:07:57 -03:00
realtime.py
feat: litellm oss 110626 ( #30202 )
2026-06-11 22:30:26 -07:00
rerank.py
style: run black formatter on files from main merge
2026-04-17 13:02:59 -07:00
router.py
chore(oss): litellm oss staging 150626 ( #30463 )
2026-06-16 12:06:41 -07:00
scheduler.py
Squashed commit of the following: ( #9709 )
2025-04-02 21:24:54 -07:00
search.py
style: run black formatter on files from main merge
2026-04-17 13:02:59 -07:00
services.py
[Fix] CI/CD - mypy & check_code_and_doc_quality & mcp_testing ( #17920 )
2025-12-13 08:18:43 -08:00
tag_management.py
style: run black formatter on entire codebase
2026-03-11 17:07:57 -03:00
tool_management.py
Bug Fix: auto-inject prompt caching support for Gemini models ( #21881 )
2026-03-03 20:25:35 -08:00
utils.py
chore(lint): remove PLR0915 too-many-statements ruff rule ( #30574 )
2026-06-16 16:52:49 -07:00
vector_store_files.py
Vector store files Stable Release ( #16643 )
2025-11-15 13:00:33 -08:00
vector_stores.py
feat(vector-stores): forward per-request params to Vertex AI Search ( #29459 )
2026-06-02 12:51:20 -07:00