Commit Graph

38232 Commits

Author SHA1 Message Date
shin-berri 9397409c5b Merge pull request #26961 from BerriAI/yj_bump_apr30
[Infra] Bump Versions
1.84.0.dev2
2026-04-30 21:46:50 -07:00
Yuneng Jiang 6da13efcec uv lock 2026-04-30 21:40:09 -07:00
Yuneng Jiang dd549d9c50 bump: version 0.4.69 → 0.4.70 2026-04-30 21:39:37 -07:00
Sameer Kankute efa33bfe50 Merge pull request #26222 from BerriAI/litellm_anthropic-json-mode-nonstreaming-mixed-tools
fix(anthropic): json response_format + user tools non-streaming
2026-05-01 08:24:38 +05:30
Sameer Kankute 72ddbce50e Merge pull request #25499 from BerriAI/litellm_vertex_request_metadata_labels
feat(vertex_ai): propagate metadata labels to embedding, Imagen, rerank
2026-05-01 08:20:55 +05:30
yuneng-jiang ebbe2f49ff Merge pull request #26826 from BerriAI/litellm_health_status_pagination
Add pagination controls to model health status
2026-04-30 18:45:40 -07:00
Michael-RZ-Berri 05e6402bdb Merge pull request #26829 from BerriAI/litellm_budgetEnforcementMultiPod
[Fix] Refresh Redis TTL on counter writes, skip stale in-memory in Redis
2026-04-30 18:14:41 -07:00
Michael-RZ-Berri e4fb325a3a Merge pull request #26914 from BerriAI/litellm_googleGenContentHooks
Run pre_call_hook on Google generateContent endpoints
2026-04-30 17:53:38 -07:00
Michael Riad Zaky 4e26835098 Reorder counter invalidation to run after DB write 2026-04-30 17:50:58 -07:00
Michael Riad Zaky ff2a938847 Match docstring style on async_increment_cache 2026-04-30 17:50:58 -07:00
Michael Riad Zaky fed5f36a3d Invalidate spend counters on budget reset 2026-04-30 17:50:58 -07:00
Michael Riad Zaky 9f08db91f9 Refresh Redis TTL on counter writes and skip stale in-memory on Redis miss 2026-04-30 17:50:58 -07:00
ryan-crabbe-berri 76e43b7bb2 Merge pull request #26949 from BerriAI/litellm_/condescending-hawking-19bdeb
[Fix] Responses API: Omit Empty Body On DELETE
2026-04-30 17:49:30 -07:00
Yuneng Jiang bd638245e8 [Fix] Responses API: Omit Empty Body On DELETE
The async/sync delete_response_api_handler always passed json=data into
httpx.delete, where data is {} from the transformer. httpx serializes that
to a 2-byte body. The Azure Responses DELETE endpoint now rejects any
request body with code: unexpected_body, breaking
test_basic_openai_responses_delete_endpoint on the llm_responses_api_testing
job. Build the kwargs dict and only set json= when data is truthy.

Add unit tests that patch httpx.delete and assert json/data are not in the
captured kwargs for the Azure DELETE path (sync and async).
2026-04-30 17:39:55 -07:00
yuneng-jiang 326bcd6cec Merge pull request #26941 from BerriAI/litellm_/stoic-jemison-cbb6cf
[Test] Proxy E2E: Opt In To Client Mock Response For Model Access Tests
2026-04-30 17:35:16 -07:00
yuneng-jiang bdcc23853c Merge pull request #26835 from stuxf/codex/cli-sso-flow-binding
chore(cli): tighten CLI SSO session flow
2026-04-30 17:10:27 -07:00
yuneng-jiang 15b7386859 Merge pull request #26815 from stuxf/fix/get-image-lfi-ssrf
chore(proxy): contain UI_LOGO_PATH / LITELLM_FAVICON_URL on unauthenticated asset endpoints
2026-04-30 17:10:15 -07:00
yuneng-jiang 71d5015975 Merge pull request #26827 from stuxf/fix/passthrough-auth-default
chore(passthrough): default auth=True and drop enterprise gate on the safe option
2026-04-30 17:06:37 -07:00
Yuneng Jiang be0e9914dc [Test] Proxy E2E: Opt In To Client Mock Response For Model Access Tests
The proxy's ingress hardening (commit 842eea0131) now strips client-supplied
`mock_response` from the request body unless the calling key or team has the
`allow_client_mock_response: true` admin-metadata flag set. The e2e model
access tests rely on `mock_response` to short-circuit the LLM call, so without
the flag they hit real backends — the bedrock wildcard route fakes out to a
shared example endpoint that now 404s on unsupported paths, causing
`test_model_access_patterns[key_models2-bedrock/anthropic.claude-3-True]`
(and the bedrock/anthropic.* row that pytest -x never reaches) to fail.

Set `allow_client_mock_response: true` on every key and team this test file
provisions so `mock_response` is preserved end-to-end.
2026-04-30 17:05:31 -07:00
Michael Riad Zaky 053e040171 run pre_call_hook on Google generateContent endpoints 2026-04-30 16:43:42 -07:00
Michael-RZ-Berri e810d8735d Merge pull request #26934 from BerriAI/litellm_lazyStartupTestFix
[Fix] Replace subprocess startup-import diff with static source scan
2026-04-30 16:42:52 -07:00
Michael Riad Zaky 47b2832d6f test: replace subprocess startup-import diff with static source scan 2026-04-30 16:15:46 -07:00
yuneng-jiang 256e05e474 Merge pull request #26849 from stuxf/fix/mcp-oauth-discovery-ssrf
chore(mcp): SSRF guard on OAuth metadata discovery follow-up fetches
2026-04-30 13:44:16 -07:00
yuneng-jiang 174c770b07 Merge pull request #26836 from stuxf/fix/byok-credential-encryption
chore(mcp): encrypt user-scoped MCP credentials at rest
2026-04-30 13:42:57 -07:00
yuneng-jiang 4ff8f0e901 Merge pull request #26851 from stuxf/codex/fix-callback-env-secret-resolution
chore(proxy): block env callback refs in key metadata
2026-04-30 13:11:32 -07:00
yuneng-jiang aa76ab2df7 Merge pull request #26862 from stuxf/codex/control-field-sanitization
chore(proxy): harden request control fields
2026-04-30 13:10:58 -07:00
Michael-RZ-Berri 9637d8c17b Merge pull request #26802 from BerriAI/litellm_lazyLoadedFrontPage
[Feat / Fix] Lazy loaded imports, lazy loaded front page
2026-04-30 13:04:42 -07:00
yuneng-jiang 08541f49ee Merge pull request #26910 from BerriAI/litellm_fix/drop-milvus-db-params
fix: drop milvus dbName and partitionNames from MILVUS_OPTIONAL_PARAMS
2026-04-30 12:53:18 -07:00
Yassin Kortam d84b35cc40 Merge pull request #26906 from BerriAI/litellm_fix/validate-aws-region
fix: validate aws region name
2026-04-30 12:52:31 -07:00
user 51a3e90451 fix(mcp): reuse safe URL fetch for OAuth discovery 2026-04-30 12:42:52 -07:00
yuneng-jiang 3c060364fb Merge pull request #26840 from stuxf/codex/mcp-oauth-root-visibility
chore(mcp): tighten OAuth root endpoint resolution
2026-04-30 11:59:03 -07:00
yuneng-jiang a9db887bdd Merge pull request #26843 from stuxf/codex/fix-onboarding-invite-token
chore(auth): harden invite-link onboarding token flow
2026-04-30 11:56:26 -07:00
Yassin Kortam dfc080f580 fix: drop milvus dbName and partitionNames from MILVUS_OPTIONAL_PARAMS 2026-04-30 11:51:32 -07:00
yuneng-jiang 0efa8b8828 Merge pull request #26854 from stuxf/fix/team-authz-available-team-bypass
chore(team): close authz bypass via the available-team check
2026-04-30 11:47:19 -07:00
user b67a81da47 test(proxy): align favicon remote asset expectations 2026-04-30 11:46:45 -07:00
yuneng-jiang d51d96f405 Merge pull request #26859 from stuxf/chore/audit-log-team-callback-mutations
chore(team): audit-log team-callback admin mutations
2026-04-30 11:46:31 -07:00
Cursor Agent 21c7864d75 Fix Vertex label metadata fallback 2026-04-30 18:44:03 +00:00
Yassin Kortam d47948ab23 fix: validate aws region name 2026-04-30 11:35:30 -07:00
user b8a141cefd fix(static-assets): stop serving stale logo cache 2026-04-30 11:34:25 -07:00
user 215f538d4f fix(static-assets): browser-load remote branding assets 2026-04-30 11:30:57 -07:00
mateo-berri b5df9d9778 test(vertex_ai): add e2e tests for rerank userLabels propagation
Cover the full litellm.rerank()/arerank() path with HTTP mocked, asserting
metadata.requester_metadata reaches the Discovery Engine :rank body as
userLabels (and stays absent when no metadata is set). Catches plumbing
regressions that unit tests on transform_rerank_request alone would miss.
2026-04-30 18:25:38 +00:00
user f48dfdbdd9 fix(proxy): require opt in for audit header fallback 2026-04-30 11:17:04 -07:00
Mateo Wang 3bbb5c7fd7 Remove dead _transform_response_for_json_mode wrapper
The wrapper had no production callers after transform_parsed_response
was refactored to call _resolve_json_mode_non_streaming directly.
Updated the parametrized test to call the underlying method.
2026-04-30 18:03:44 +00:00
Mateo Wang 609454d0f1 Merge pull request #26852 from BerriAI/litellm_oss_staging
Litellm oss staging
2026-04-30 10:56:05 -07:00
user 09c4d0d01e fix(proxy): gate redaction opt out controls 2026-04-30 00:49:33 -07:00
user c52be31663 fix(logging): redact standard logging choice metadata 2026-04-30 00:35:29 -07:00
user ea4e83e066 fix(proxy): keep mcp audit attribution typed 2026-04-30 00:13:34 -07:00
user 697331b534 fix(proxy): apply audit attribution helper consistently 2026-04-30 00:07:43 -07:00
user db00e674e2 test(proxy): cover control field hardening branches 2026-04-29 23:57:50 -07:00
user 119c70b576 fix(proxy): gate delegated audit attribution 2026-04-29 23:10:14 -07:00