_experimental /mcp_server
Merge pull request #38724 from BerriAI/litellm_mcp_oauth_identity_binding
2026-09-10 14:44:11 -07:00
fix(a2a): reject malformed protocolVersion suffixes while keeping semver prereleases
2026-07-21 13:24:58 -07:00
fix(a2a): forward caller identity headers on message/send and message/stream ( #40305 )
2026-09-08 15:56:52 -07:00
feat(ui): add error-code drilldown for failed requests on caching page
2026-08-24 15:45:45 -07:00
test(proxy): pass the request to get_marketplace in the archive marketplace test
2026-09-10 14:54:46 -07:00
fix(proxy): let internal users read request/response for their own spend logs
2026-09-10 15:04:15 -07:00
fix(batches): register ownership for every batch create path ( #39810 )
2026-09-04 23:59:51 -07:00
feat(proxy): expose reversible Claude Code model listing aliases ( #40515 )
2026-09-09 22:04:37 -07:00
fix(reset_budget_job): reset end users by budget link, not by user id
2026-09-10 16:57:53 -07:00
feat(proxy): add SAML 2.0 SSO for the admin UI ( #31429 )
2026-07-24 12:51:28 -07:00
fix(containers): page upstream until a non-admin container list fills its limit
2026-09-02 21:26:34 -07:00
Merge branch 'litellm_internal_staging' into fix-credential-endpoints-raise-not-return
2026-09-03 05:36:50 -07:00
feat(proxy): let the in-container pgbouncer follow rotating RDS IAM and Azure Entra tokens ( #40623 )
2026-09-10 16:18:00 -07:00
feat(auth): enforce configurable password policy and SSO-only login ( #39381 )
2026-09-02 14:28:13 -07:00
feat(proxy): push-based OTLP billable-request metering for enterprise deployments ( #31592 )
2026-07-15 12:12:52 -07:00
experimental /mcp_server
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
Merge pull request #40270 from BerriAI/litellm_bedrock_sign_request_off_loop
2026-09-09 19:31:58 -07:00
feat(pointfive): answer the ui health check with a liveness ping
2026-09-10 14:02:35 +03:00
fix(rate_limiter): skip non-Latin-1 x-litellm-priority header on /v1/messages ( #40636 )
2026-09-10 17:48:46 -07:00
fix(proxy): keep a ProxyException's status and label 408s in the OpenAI error payload
2026-09-08 12:16:08 -07:00
feat: page the public model hub table off /public/v1/model_hub, keeping every filter ( #39691 )
2026-09-03 22:36:16 -07:00
fix(usage): recover aliases for v1.99 double-hashed spend keys
2026-09-03 14:21:25 +00:00
feat(ui): search, sort and role filter for the team member table
2026-09-11 01:37:48 +00:00
feat(proxy): granular key/team access control for Claude Code marketplace plugins ( #40518 )
2026-09-10 14:26:09 -07:00
feat(proxy): add a search param to key, memory, audit, and spend log listings
2026-09-03 15:20:13 -07:00
feat(proxy): resolve root_path per request from a configured prefix list (SERVER_ROOT_PATHS) ( #35935 )
2026-09-07 11:54:59 -07:00
fix(ocr): validate body req_format in the proxy endpoint and run its tests in CI
2026-08-17 18:29:35 +00:00
fix(proxy): label a 408 invalid_request_error again and pin the in-route status on the files and realtime tails
2026-09-08 13:11:24 -07:00
Merge branch 'litellm_internal_staging' into litellm_lit_7022_azure_ai_passthrough_config
2026-09-09 19:42:28 -07:00
Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_legacy_hook_streaming_pipeline_step
2026-09-09 15:52:48 -07:00
fix(prompts): accept a string prompt_version and carry the viewed environment into code snippets
2026-08-29 12:55:34 -07:00
feat(proxy): offload spend tracking to a pod-local collector sidecar ( #40545 )
2026-09-10 17:14:13 -07:00
test(proxy): drop docstrings from the Add Model provider tests
2026-09-07 15:12:41 -07:00
fix(proxy): emit SSE keepalives on queue, rag, azure passthrough, usage chat and policy enrich streams ( #39273 )
2026-09-03 18:23:37 -07:00
test(proxy): type the realtime WebRTC fixtures with Protocols instead of a bare Callable
2026-09-08 15:01:17 -07:00
fix(proxy): keep a ProxyException's status and label 408s in the OpenAI error payload
2026-09-08 12:16:08 -07:00
fix(count_tokens): preserve image inputs when counting Responses API tokens
2026-08-31 12:43:17 -07:00
feat(proxy): native /health/drain preStop hook for graceful shutdown ( #29439 )
2026-06-02 16:30:44 -07:00
feat(proxy): offload spend tracking to a pod-local collector sidecar ( #40545 )
2026-09-10 17:14:13 -07:00
fix(proxy): resolve router_settings.plugins dotted paths and load plugins from installed packages ( #33644 )
2026-07-17 11:23:18 -07:00
feat(mcp): semantic tool search for the native MCP Gateway ( #39404 )
2026-09-02 15:09:44 -07:00
Merge pull request #39539 from BerriAI/litellm_fix_health_check_db_storm
2026-09-10 14:45:59 -07:00
fix(proxy): let authorized internal users open vector store details ( #40150 )
2026-09-07 13:10:09 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
fix(videos): forward uploaded source file on /v1/videos/edits to the provider
2026-08-24 15:34:21 -07:00
test(proxy): keep a leaked llm_router out of the next test in the worker
2026-08-20 23:19:17 -07:00
test(proxy): pin the request-validation contracts in proxy/_types.py
2026-08-25 23:29:26 -07:00
fix(proxy): match /v1/audio/speech content-type to the returned audio format
2026-08-29 13:44:43 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
test(proxy): give the x-litellm-model fallback test deterministic openai env creds
2026-08-17 12:42:57 -07:00
fix(guardrails): remove the module-global translation mapping that leaked between tests
2026-09-03 03:28:52 -07:00
perf(proxy): pipeline spend counter increments into one Redis call per request ( #40371 )
2026-09-09 10:35:50 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
test: run the 30 test files stranded in the second mirror ( #37595 )
2026-08-20 10:59:43 -07:00
feat(proxy): offload spend tracking to a pod-local collector sidecar ( #40545 )
2026-09-10 17:14:13 -07:00
fix(router): resolve team-scoped auto-routers by their public name ( #40432 )
2026-09-09 15:53:05 -07:00
feat(proxy): authenticate to Azure Postgres with Microsoft Entra ID tokens
2026-08-20 11:50:16 -07:00
test(proxy): stop monkeypatch.undo re-planting fixture-mocked prisma_client
2026-08-13 20:11:06 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
fix(proxy): serve aggregate MCP endpoint on bare /mcp instead of 307-redirecting ( #34845 )
2026-08-14 17:04:32 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
test: require a match= on broad pytest.raises, and drop duplicate parametrize cases ( #37769 )
2026-08-20 20:24:49 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
fix(proxy): release the health check save window lock on failure or cancel
2026-09-03 12:36:04 +02:00
fix(proxy): derive auto-router health from its underlying models ( #38174 )
2026-08-26 16:41:54 -07:00
test: run the 30 test files stranded in the second mirror ( #37595 )
2026-08-20 10:59:43 -07:00
chore(callbacks): guard dynamic integration hosts
2026-04-30 14:27:19 -07:00
refactor(proxy): type the snapshot fragments and wrap a long test line
2026-08-26 14:39:51 -07:00
fix(proxy): accept non-string callback vars in default_team_settings ( #40458 )
2026-09-09 15:40:15 -07:00
fix(mcp): surface upstream 401 for token-forwarding MCP servers ( #27847 )
2026-05-13 12:03:36 -07:00
test(batches): move orphan tests into tests/test_litellm for CI coverage ( #30510 )
2026-06-16 10:20:59 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
feat(proxy): add x-litellm-model-name response header with deployment model string ( #33698 )
2026-07-17 20:29:42 -07:00
fix(proxy): align /v1/model/info with router deployments ( #30025 )
2026-06-10 19:38:21 -07:00
fix(proxy): apply key/team router_settings.model_group_alias ( #35486 )
2026-08-03 22:09:47 +00:00
feat(proxy): hide unhealthy models from model listings, opt-in
2026-08-26 00:13:52 -07:00
fix(proxy): use e.request_data for logging_obj in ModifyResponseException streaming passthrough ( #30800 )
2026-06-18 23:29:08 -07:00
fix(proxy): keep the token's team model list in the websocket passthrough gate without a database
2026-09-04 19:05:35 -07:00
fix(proxy): preserve HTTP operations when injecting WebSocket stubs into OpenAPI schema
2026-05-06 00:28:42 +02:00
feat: litellm plugin architecture v2 ( #30688 )
2026-06-20 20:37:22 -07:00
feat(pointfive): add pointfive to the dashboard logging integrations
2026-09-10 14:02:35 +03:00
feat(pointfive): list pointfive in the proxy callback registry
2026-09-10 14:02:35 +03:00
fix(proxy): fold litellm_metadata into metadata on chat routes so tag routing sees merged tags
2026-08-29 00:42:43 -07:00
fix(proxy): recreate the Prisma client when the writer session turns read-only ( #40610 )
2026-09-10 13:53:42 -07:00
fix(proxy): keep a failed prisma generate from failing the migration entrypoint ( #37947 )
2026-08-22 11:45:19 -07:00
feat(deploy): metrics sidecar and separate metrics port in Helm and Terraform ( #40163 )
2026-09-08 13:31:07 -07:00
feat(deploy): metrics sidecar and separate metrics port in Helm and Terraform ( #40163 )
2026-09-08 13:31:07 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
test(proxy): isolate reaper state and reap Prisma fixture children
2026-09-08 17:35:43 -07:00
test(proxy): give the pipeline-managed native hook audit test its chat completions route
2026-09-09 14:15:01 -07:00
Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_lit_5546_count_tokens_offload
2026-09-09 18:18:17 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
feat(proxy): let the in-container pgbouncer follow rotating RDS IAM and Azure Entra tokens ( #40623 )
2026-09-10 16:18:00 -07:00
Implement normalize_nonempty_secret_str function to trim whitespace from secrets and treat empty values as unset. Update proxy_server to use this function for Grafana credentials. Enhance tests to validate the new normalization behavior.
2026-05-04 18:17:31 +00:00
feat: add minimal rust router + axum ai-gateway calling router.realtime (2/2) ( #31135 )
2026-06-23 19:16:34 -07:00
fix(proxy): share per-model budget counters across replicas through the spend counter cache ( #39375 )
2026-09-02 12:40:59 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
test: drop the cwd-relative sys.path.insert calls from the test suite ( #37802 )
2026-08-22 09:25:58 -07:00
chore(proxy): guard sensitive public endpoints
2026-04-30 11:52:47 -07:00
fix(proxy): derive auto-router health from its underlying models ( #38174 )
2026-08-26 16:41:54 -07:00
test: require a match= on broad pytest.raises, and drop duplicate parametrize cases ( #37769 )
2026-08-20 20:24:49 -07:00
fix(proxy): avoid misleading multi-method operation ids
2026-04-30 20:44:14 -07:00
feat(ui): add budget duration to edit team member form ( #29717 )
2026-06-06 17:24:55 -07:00
test: require a match= on broad pytest.raises, and drop duplicate parametrize cases ( #37769 )
2026-08-20 20:24:49 -07:00
fix(anthropic): close hybrid tool-name allowlist gap and keep native tools through guardrails
2026-08-26 20:37:11 -07:00
feat(complexity_router): custom classifier plugins via classifier_type 'custom' ( #37249 )
2026-08-18 14:09:19 -07:00
a9bd86b371