Uzair Ali 3e9540f589 feat: enable custom fields in mcp_info configuration (#14794) ... Allow proxy admins to add arbitrary metadata fields to MCP servers in config.yaml under mcp_servers.<server>.mcp_info, similar to how model_info already works. Changes: - Changed MCPInfo from TypedDict to Dict[str, Any] for flexibility - Updated load_servers_from_config to preserve all custom fields - Updated add_update_server to handle arbitrary fields from database - Added comprehensive unit tests covering all scenarios		2025-09-22 21:15:35 -07:00
..
_experimental/mcp_server	feat: enable custom fields in mcp_info configuration (#14794)	2025-09-22 21:15:35 -07:00
anthropic_endpoints	test fixes	2025-06-25 18:42:06 -07:00
auth	feat(proxy): Assign default budget to auto-generated JWT teams	2025-09-14 12:04:43 -07:00
client	[Feat] Proxy CLI Auth - Allow re-using cli auth token (#14780)	2025-09-22 10:07:16 -07:00
common_utils	Format code	2025-09-03 11:20:52 +08:00
db	test_recreate_prisma_client_successful_disconnect	2025-08-01 15:38:48 -07:00
experimental/mcp_server
google_endpoints	fix token count error when proxy gemini cli to openai like model	2025-09-01 20:02:53 +08:00
guardrails	Update test_bedrock_guardrails.py	2025-09-18 19:48:16 -07:00
health_endpoints
hooks	test: fix unit test to work on github action	2025-09-22 17:38:11 -07:00
image_endpoints
management_endpoints	[Feat] Proxy CLI Auth - Allow re-using cli auth token (#14780)	2025-09-22 10:07:16 -07:00
management_helpers	[MCP Gateway] access group UI object permission fix (#12523)	2025-07-11 18:25:40 -07:00
middleware
openai_files_endpoint	Revert "fix vertex ai file upload" (#14501)	2025-09-12 12:02:24 -07:00
pass_through_endpoints	[Fix] Perf fix: Heavy RAM Usage over time when using Passthrough Routes (#14305)	2025-09-06 19:22:25 -07:00
spend_tracking	test_sanitize_request_body_for_spend_logs_payload_mixed_types	2025-09-20 12:33:37 -07:00
test_configs
ui_crud_endpoints	Litellm encrypt admin UI values (#12675)	2025-07-17 22:24:58 -07:00
vector_store_endpoints	[Feat] LLM API Endpoint - Expose OpenAI Compatible /vector_stores/{vector_store_id}/search endpoint (#12749)	2025-07-18 18:18:53 -07:00
test_batch_metadata_none_fix.py	Fix issue #13995: Handle None metadata in batch requests (#13996)	2025-08-27 14:51:09 -07:00
test_caching_routes.py
test_common_request_processing.py	[Feat] Allow using x-litellm-stream-timeout header for stream timeout in requests (#14147)	2025-09-01 15:59:14 -07:00
test_custom_proxy.py
test_fastapi_offline_routes.py	[Bug Fix] - Get Routes (#13466)	2025-08-09 12:52:23 -07:00
test_health_check_functions.py
test_litellm_pre_call_utils.py	User Headers X LiteLLM Users Mapping feature (#14485)	2025-09-12 11:49:37 -07:00
test_proxy_cli.py	LiteLLM SDK <-> Proxy: support user param + Prisma - remove use_prisma_migrate flag - redundant as this is now default (#13555)	2025-08-12 22:03:39 -07:00
test_proxy_server.py	test: update tests	2025-08-23 12:09:19 -07:00
test_proxy_types.py
test_proxy_utils.py	litellm/proxy: preserve model order of /v1/models and /model_group/info (#13178)	2025-08-02 08:57:38 -07:00
test_route_llm_request.py	Fix create, search vector store error (#13285)	2025-08-06 11:15:17 -07:00
test_spend_log_cleanup.py	Fix/gemini api key environment variable support (#12507)	2025-07-29 15:56:01 -07:00
test_swagger_chat_completions.py	[Bug Fix] Allow using Swagger for /chat/completions (#13469)	2025-08-09 15:35:45 -07:00
test_team_member_update.py	fix mapped tests (#12320)	2025-07-04 10:04:43 -07:00