BerriAI/litellm v1.86.0 on GitHub

Note

Two things to be aware of about the non-root image in this release:

Dockerfile build patch. The non-root Dockerfile failed to build at the v1.86.0 tag, and a patch was applied to produce ghcr.io/berriai/litellm-non_root:v1.86.0. The non-root image was built from commit a13cd212c82f00d73456a375dd0d89cef85244a8.
No cosign attestation. The non-root image was published without a cosign signature. If you run cosign verify on images before deploying, this image will not pass verification and you will not be able to upgrade to it.

The ghcr.io/berriai/litellm:v1.86.0 and ghcr.io/berriai/litellm-database:v1.86.0 images are signed normally. v1.86.1 ships early next week with signed builds of all three images.

Verify Docker Image Signature

All LiteLLM Docker images are signed with cosign. Every release is signed with the same key introduced in commit 0112e53.

Verify using the pinned commit hash (recommended):

A commit hash is cryptographically immutable, so this is the strongest way to ensure you are using the original signing key:

cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \
  ghcr.io/berriai/litellm:v1.86.0

Verify using the release tag (convenience):

Tags are protected in this repository and resolve to the same key. This option is easier to read but relies on tag protection rules:

cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/v1.86.0/cosign.pub \
  ghcr.io/berriai/litellm:v1.86.0

Expected output:

The following checks were performed on each of these signatures:
  - The cosign claims were validated
  - The signatures were verified against the specified public key

What's Changed

fix: tighten budget field validation and authorization checks by @krrish-berri-2 in #27897
fix(guardrails): improve CrowdStrike AIDR input handling by @kenany in #26658
feat(lasso): add tool-calling support to LassoGuardrail by @vladpolevoi in #27648
perf: optimize chat completions fast path by @yassin-berriai in #27858
ci(mutmut): enable mutate_only_covered_lines to fit in CI budget by @ryan-crabbe-berri in #27910
fix(rate-limit): stop v3 limiter from leaking internal stash to provider body by @mateo-berri in #27913
fix: allow for allowlisted redirect URIs by @dennishenry in #27761
Emit native web_search_tool_result blocks for Anthropic clients (Claude Desktop / Cowork citations) by @ishaan-berri in #27886
test(vcr): classify cache verdicts, surface cost leaks, and fix the two biggest leakers by @mateo-berri in #27795
chore(ci): remove unused GitHub Actions workflows and orphan files by @yuneng-berri in #27957
test(ui): preserve global Button/Tooltip mocks in per-file @tremor/react vi.mock by @yuneng-berri in #27958
fix(mcp): expose delegate_auth_to_upstream in MCP server list API by @Sameerlite in #27936
feat(proxy): fix vector store retrieve/list/update/delete without model by @Sameerlite in #27929
fix(managed_batches): convert raw output_file_id to managed ID in CheckBatchCost poller by @Sameerlite in #27984
fix(vertex-ai): fix zero cost/usage on completed Vertex AI batch jobs by @Sameerlite in #27912
ci: use --cov=./litellm so coverage paths resolve unambiguously in Codecov by @yuneng-berri in #27960
fix(mcp): delegate PKCE bypass for internal MCP servers by @Sameerlite in #27977
Feat: Add Weighted-Routing Failover by @Sameerlite in #27980
fix(bedrock-mantle): use /anthropic/v1/messages path for Mantle endpo… by @ishaan-berri in #27976
fix(utils): import get_secret at runtime by @Sameerlite in #28014
chore(ci): modernize model references in tests and configs by @mateo-berri in #27856
fix(proxy): make /config/update env-var encryption idempotent by @yuneng-berri in #28022
feat: support OTEL GenAI semconv by @Michael-RZ-Berri in #27418
test(proxy): isolate run_server CLI tests from prisma DB-setup path by @yuneng-berri in #28029
test(interactions): validate response fields against Interaction schema by @yuneng-berri in #28037
test(gemini): de-flake test_gemini_image_size_limit_exceeded by @yuneng-berri in #28039
feat: componentize gateway, ui-backend, and ui as separate services by @yassin-berriai in #27557
test(ci): add reasoning_effort grid e2e regression suite by @mateo-berri in #28036
fix(ci): flag codecov uploads, enable carryforward, close coverage gaps by @yuneng-berri in #28028
feat(otel): OTel-standard attributes on the proxy SERVER span (status code, route/path, preprocessing latency) by @ryan-crabbe-berri in #28040
build(deps): pin openai==2.33.0 in uv.lock by @yuneng-berri in #28088
feat(model_catalog): add Azure AI Foundry GPT-5.4 model metadata by @shivamrawat1 in #28030
feat(otel): set http.response.status_code on the success SERVER span by @ryan-crabbe-berri in #28090
[IInfra] Build UI by @yuneng-berri in #28095
fix(proxy): sort BYOK models by their displayed name in /v2/model/info by @shivamrawat1 in #28079
feat(terraform): add AWS ECS + GCP Cloud Run stacks for componentized gateway by @yassin-berriai in #27673
fix(mcp-oauth): PROXY_BASE_URL escape hatch + diagnostic logging for {"detail":"invalid_request"} by @mateo-berri in #28086
[Infra] Bump versions by @yuneng-berri in #28094
[Infra] Promote internal staging to main by @yuneng-berri in #28100

New Contributors

@vladpolevoi made their first contribution in #27648

Full Changelog: v1.85.0...v1.86.0