v1.96.0-dev.1Pre-release
Added 4
- Add service_tier label to latency and spend metrics in Prometheus
- Publish a generated JSON schema for model_prices_and_context_window.json
- Split failed requests into their own series on the cache dashboard in UI
- Add shareable log links via log_id query param on the logs page in UI
Fixed 15
- Keep keep-alive connector config when an aiohttp session is rebuilt
- Pin bundled postgres and redis to bitnamilegacy images in Helm
- Decide rawPredict passthrough streaming from the request body for Vertex
- Translate stop_sequences and disabled thinking for non-Claude targets in anthropic-adapter
- Allow /v1/messages for JWT teams by default
- Skip team model aliases that point at deleted deployments in proxy
- Report when a model write does not survive the post-write reload in proxy
- Reject model writes that corrupt an auto-router pseudo-model in proxy
- Serialize latency for non-chat responses in lowest-latency routing
- Preserve callback order in get_combined_callback_list logging
- Honor explicit priority=0 in router acompletion
- Open the first content block with the real upstream type so reasoning-first streams start with thinking in anthropic-adapter
- Stop provisioning nested group ids as internal users in SCIM
- Size Object Permissions card grid by container width in UI
- Allow /key/update to identify the key by key_alias in proxy
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:v1.96.0-dev.1
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/v1.96.0-dev.1/cosign.pub \
ghcr.io/berriai/litellm:v1.96.0-dev.1
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
- feat(prometheus): add service_tier label to latency and spend metrics by @yassin-berriai in https://github.com/BerriAI/litellm/pull/34966
- fix(aiohttp): keep keep-alive connector config when a session is rebuilt by @yassin-berriai in https://github.com/BerriAI/litellm/pull/34962
- fix(helm): pin bundled postgres and redis to the bitnamilegacy images by @yassin-berriai in https://github.com/BerriAI/litellm/pull/34963
- fix(vertex): decide rawPredict passthrough streaming from the request body by @tin-berri in https://github.com/BerriAI/litellm/pull/34672
- fix(anthropic-adapter): translate stop_sequences and disabled thinking for non-Claude targets by @tin-berri in https://github.com/BerriAI/litellm/pull/34589
- ci: publish a generated JSON schema for model_prices_and_context_window.json by @mateo-berri in https://github.com/BerriAI/litellm/pull/34816
- fix(jwt_auth): allow /v1/messages for JWT teams by default by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/34222
- fix(proxy): skip team model aliases that point at deleted deployments by @mateo-berri in https://github.com/BerriAI/litellm/pull/34993
- fix(proxy): report when a model write does not survive the post-write reload by @tin-berri in https://github.com/BerriAI/litellm/pull/34861
- fix(proxy): reject model writes that corrupt an auto-router pseudo-model by @tin-berri in https://github.com/BerriAI/litellm/pull/34151
- fix(router_strategy): serialize latency for non-chat responses in lowest-latency routing by @mihidumh in https://github.com/BerriAI/litellm/pull/33290
- fix(logging): preserve callback order in get_combined_callback_list by @Harsh23Kashyap in https://github.com/BerriAI/litellm/pull/33008
- fix(router): honor explicit priority=0 in acompletion by @Harsh23Kashyap in https://github.com/BerriAI/litellm/pull/33214
- fix(router_strategy): serialize latency for non-chat responses in lowest-latency routing by @tin-berri in https://github.com/BerriAI/litellm/pull/35048
- fix(anthropic-adapter): open the first content block with the real upstream type so reasoning-first streams start with thinking by @Napuh in https://github.com/BerriAI/litellm/pull/34433
- test(e2e): poll MCP tools across multi-worker lag by @mubashir1osmani in https://github.com/BerriAI/litellm/pull/35047
- fix(scim): stop provisioning nested group ids as internal users by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/34997
- chore(typing): clear basedpyright Any errors in proxy management endpoints by @mateo-berri in https://github.com/BerriAI/litellm/pull/35074
- fix(ui): size Object Permissions card grid by container width by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/35019
- fix(proxy): allow /key/update to identify the key by key_alias by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/34851
- feat(ui): split failed requests into their own series on the cache dashboard by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/34862
- feat(ui): shareable log links via log_id query param on the logs page by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/34879
- fix(ui): show public model names in usage breakdowns by @mateo-berri in https://github.com/BerriAI/litellm/pull/35107
- fix(ui): point the navbar and sidebar logos at the dashboard home route by @yuneng-berri in https://github.com/BerriAI/litellm/pull/35041
- fix(proxy): stop serving stale team model allowlist after /team/update by @mateo-berri in https://github.com/BerriAI/litellm/pull/34266
- feat(ui): deep link team detail page via ?team= query param by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/35112
- feat(ui): deep link organization detail page via ?org= query param by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/35117
- fix(proxy): resolve named credentials on provider-only batch and files calls by @mateo-berri in https://github.com/BerriAI/litellm/pull/35028
- fix(router): drop duplicate Mapping import that fails ruff F811 by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/35122
- refactor(rust): make litellm-core the callable messages() SDK; drop the ai-gateway handler by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/35044
- fix(otel): make OTLP export work against Grafana Cloud by @yassin-berriai in https://github.com/BerriAI/litellm/pull/35060
- test(e2e): remove the Presidio guardrail suite by @mubashir1osmani in https://github.com/BerriAI/litellm/pull/35129
- feat(dashscope): add qwen3.7-plus and qwen3.7-max to the model cost map by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/35123
- feat(ui): link organization teams to their team detail pages by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/35120
- fix(tests): assert Content variants are identified by type, not by the discriminator keyword by @yassin-berriai in https://github.com/BerriAI/litellm/pull/35161
- fix(mcp): never write discovery results to the row, heal already-stamped rows, and retry failed discovery with backoff by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/34990
- fix(vertex_ai): honor per-model gcs_bucket_name on managed-file read path by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/34847
- feat(cli): read base_url from persistent config file by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/35015
- fix(auth): resolve managed batch/file deployment model_id to model name for team access checks by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/32587
- fix(vertex_ai): forward function_call id on Vertex Gemini 3+ tool turns by @ljogeiger in https://github.com/BerriAI/litellm/pull/34603
- build(makefile): give local basedpyright runs the node heap CI uses by @mateo-berri in https://github.com/BerriAI/litellm/pull/35173
- fix(complexity_router): capture the classifier request body in spend logs by @tin-berri in https://github.com/BerriAI/litellm/pull/35164
- test(managed-files): lock in store_unified_file_id idempotency on batch retrieve by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/32601
- fix(vertex_ai): skip context caching when the cached block ends on a model turn by @mateo-berri in https://github.com/BerriAI/litellm/pull/35172
- refactor(bedrock): remove the dead BedrockLLM invoke code path by @mateo-berri in https://github.com/BerriAI/litellm/pull/35188
- fix(pricing): correct gpt-5.4-mini and gpt-5.4-nano token limits by @mateo-berri in https://github.com/BerriAI/litellm/pull/35182
- feat(cookbook): add a Grafana dashboard for the OTel GenAI metrics by @yassin-berriai in https://github.com/BerriAI/litellm/pull/35159
- chore(typing): clear basedpyright Any errors in proxy auth, repositories, and openai transforms by @mateo-berri in https://github.com/BerriAI/litellm/pull/35240
- fix(batches): calculate cost and usage for completed Vertex AI batches by @mateo-berri in https://github.com/BerriAI/litellm/pull/35186
- feat(ui): give auto-routers their own tab on Models + Endpoints by @tin-berri in https://github.com/BerriAI/litellm/pull/35009
- refactor(batches): aggregate batch output cost, usage, and models in a single pass by @mateo-berri in https://github.com/BerriAI/litellm/pull/35205
- feat(router): record why the auto-router picked a tier in spend logs by @tin-berri in https://github.com/BerriAI/litellm/pull/35016
- fix(otel): cap tool-definition attributes so they cannot evict gen_ai.* from the LLM span by @yassin-berriai in https://github.com/BerriAI/litellm/pull/34828
- feat(mcp): enforce per-user MCP tool-call entitlements in the auth module by @yassin-berriai in https://github.com/BerriAI/litellm/pull/35146
- fix(otel): record the GenAI duration metric on failed requests by @yassin-berriai in https://github.com/BerriAI/litellm/pull/35152
- chore: bump litellm 1.95.0 -> 1.96.0 by @yuneng-berri in https://github.com/BerriAI/litellm/pull/35254
- revert(proxy)!: stop enforcing user budget on team keys by @yuneng-berri in https://github.com/BerriAI/litellm/pull/35271
- fix(otel): label retrieval and agent metrics correctly and emit gen_ai.provider.name by @yassin-berriai in https://github.com/BerriAI/litellm/pull/35151
- test(e2e): align budget e2e with the team-key budget hierarchy by @yuneng-berri in https://github.com/BerriAI/litellm/pull/35276
- feat(mcp): scan and mask MCP tool results via post_mcp_call guardrails by @yassin-berriai in https://github.com/BerriAI/litellm/pull/35155
- docs(claude): require 15-25 word human-readable replies to AI PR review bots by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/35266
- fix(redis): stop an unreachable Redis from blocking every request by @yassin-berriai in https://github.com/BerriAI/litellm/pull/35273
- fix(rate-limits): keep the v3 limiter out of provider-facing metadata on responses routes by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/35207
- docs(pr-template): require e2e proof on all three LLM endpoints when applicable by @mateo-berri in https://github.com/BerriAI/litellm/pull/35280
- feat(mcp): manual authorization-code delivery for headless MCP clients by @tin-berri in https://github.com/BerriAI/litellm/pull/34848
- feat(db): opt-in REPLICA IDENTITY FULL after prisma migrations by @yassin-berriai in https://github.com/BerriAI/litellm/pull/35267
- fix(ui): stop clamping the budgets Budget ID column at 15 characters by @yuneng-berri in https://github.com/BerriAI/litellm/pull/35268
- fix(proxy): only enforce budgets on routes that can spend by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/35274
- chore(ci): promote internal staging to main by @yuneng-berri in https://github.com/BerriAI/litellm/pull/35285
New Contributors
- @Harsh23Kashyap made their first contribution in https://github.com/BerriAI/litellm/pull/33008
- @ljogeiger made their first contribution in https://github.com/BerriAI/litellm/pull/34603
Full Changelog: https://github.com/BerriAI/litellm/compare/v1.95.0-rc.1...v1.96.0-dev.1