Starstruk Logo MarkStarstruk

v1.102.0

BerriAI/litellmv1.102.0Sep 22, 2026by yuneng-berri

Upgrading?

What changed from v1.101.0 → v1.102.0?What's new in v1.100.2 after v1.102.0?

AI Summary

This release focuses on enhancing the LiteLLM proxy with robust guardrail capabilities, improved routing strategies, and expanded model support including new real-time audio features. It introduces significant updates to the UI, MCP (Model Context Protocol), and enterprise deployment tools like Helm and Terraform. Additionally, the release emphasizes security by signing all Docker images with Cosign.

Key Highlights

  • All Docker images are now cryptographically signed using Cosign for verification.
  • Post-call guardrail pipelines are executed on streaming responses and Responses API.
  • Enhanced Claude Code integration allows running the coding agent directly through the proxy.
  • New MCP features include schema discovery proxy mode and per-server OAuth relay.
  • Support added for Meta Muse Voice transcription and TwelveLabs embeddings.

New Features

  • Execute post_call guardrail pipelines on streaming responses
  • Add 'lite pi' command to run the coding agent through the proxy
  • Add GovCloud pricing for Bedrock models
  • Add inspect_embeddings toggle for AIM and Cato guardrails
  • Add per-server OAuth relay discovery for MCP
  • Add Lyria model support
  • Add text-to-speech support for Mistral
  • Add root_path resolution per request from SERVER_ROOT_PATHS
  • Add cost map guard check
  • Add key-scoped auto-router usage tab in UI
  • Add semantic search over the skill registry
  • Add image edit support for hosted_vllm
  • Add metrics sidecar support in Helm/Terraform
  • Add Conduct Guard integration
  • Add Claude Code configuration via gateway key

Full Release Notes

## Verify Docker Image Signature

All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d726492c814b3644b7d376029d0).

**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:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \
  ghcr.io/berriai/litellm:v1.102.0
```

**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:

```bash
cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/v1.102.0/cosign.pub \
  ghcr.io/berriai/litellm:v1.102.0
```

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
* feat(policy_engine): execute post_call guardrail pipelines on streaming responses by @mateo-berri in https://github.com/BerriAI/litellm/pull/38788
* fix(policy_engine): apply post_call pipeline text rewrites on streams by @mateo-berri in https://github.com/BerriAI/litellm/pull/39233
* fix(proxy): redact provider keys from pass-through failure tracebacks by @mateo-berri in https://github.com/BerriAI/litellm/pull/39964
* fix(file_search): scope emulated file_search to the request's vector stores by @mateo-berri in https://github.com/BerriAI/litellm/pull/39972
* feat(cli): add lite pi to run the pi coding agent through the proxy by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/36841
* feat(pricing): add GovCloud pricing for every live but unpriced Bedrock model by @mateo-berri in https://github.com/BerriAI/litellm/pull/39764
* fix(azure_sentinel): split batches under the 1MB ingestion cap by @yucheng-berri in https://github.com/BerriAI/litellm/pull/39880
* feat(guardrails): add inspect_embeddings toggle for AIM and Cato by @yucheng-berri in https://github.com/BerriAI/litellm/pull/39918
* refactor(ui): route the sidebar by pathname and shrink the ?page= shim to a redirect table by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/39978
* fix(anthropic): keep provider_specific_fields off the native /v1/messages wire by @tin-berri in https://github.com/BerriAI/litellm/pull/39967
* fix(headroom): inject headroom_retrieve only for service-declared ccr_hashes and keep assistant content blocks intact by @tin-berri in https://github.com/BerriAI/litellm/pull/39974
* fix(auto_router): build the semantic route layer off the event loop by @moe-berri in https://github.com/BerriAI/litellm/pull/39954
* fix(adaptive_router): fall back to model_info for cost-weighted scoring by @moe-berri in https://github.com/BerriAI/litellm/pull/39957
* fix(adaptive_router): add the persisted delta to the cold-start prior on load by @moe-berri in https://github.com/BerriAI/litellm/pull/39955
* feat(mcp): add opt-in per-server oauth relay discovery by @tin-berri in https://github.com/BerriAI/litellm/pull/39936
* refactor(ui): render the Virtual Keys page without the legacy user dashboard by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/39991
* feat(router): gate heuristic v1 tuning by @tin-berri in https://github.com/BerriAI/litellm/pull/39952
* fix(docker): ship pymongo in the proxy images for the MongoDB vector store by @yuneng-berri in https://github.com/BerriAI/litellm/pull/39995
* fix(router): treat a routing entry with no latency samples as zero latency by @mateo-berri in https://github.com/BerriAI/litellm/pull/39970
* ci(e2e): run a PR's changed e2e tests three times behind a human-approved environment by @yuneng-berri in https://github.com/BerriAI/litellm/pull/39416
* feat(vertex): add Lyria model support by @emerzon in https://github.com/BerriAI/litellm/pull/30856
* ci: run unit tests on Python 3.12 by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/39989
* fix(anthropic_responses): preserve Responses refusal blocks in Anthropic messages translation by @Atharva-Kanherkar in https://github.com/BerriAI/litellm/pull/39723
* fix(batches): account a batch's cost once, from the first retrieve that sees it final by @mateo-berri in https://github.com/BerriAI/litellm/pull/39980
* feat(cost-map): add azure_ai/gpt-6-astra Foundry pricing by @mateo-berri in https://github.com/BerriAI/litellm/pull/39983
* chore(lint): stop ratcheting *-budget.json on PR branches by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/39937
* ci: simplify Rust checks and remove wheel PR comments by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/39975
* fix(router): skip the refusing deployment when retrying a non-transient error by @mateo-berri in https://github.com/BerriAI/litellm/pull/40014
* feat(mistral): add text-to-speech support for /v1/audio/speech by @mateo-berri in https://github.com/BerriAI/litellm/pull/38755
* fix(mcp): apply key and team guardrails to MCP tool calls by @mubashir1osmani in https://github.com/BerriAI/litellm/pull/39629
* test(ui): pin wire contracts for key, model and MCP server forms by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40019
* refactor(rust): remove per-request enablement arguments by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/39928
* test(ocr): trace callback lifecycle parity by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40063
* fix(router): serialize heuristic tuning quota filters for Prisma by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40140
* docs(claude): have runs embed their own QA screenshots on visual changes by @mateo-berri in https://github.com/BerriAI/litellm/pull/39800
* fix(oci): stream Cohere tool-calling answers once by @mateo-berri in https://github.com/BerriAI/litellm/pull/39965
* fix(async): move remote image fetches off the event loop for Snowflake, Bedrock invoke Claude, Mantle and Gemini by @mateo-berri in https://github.com/BerriAI/litellm/pull/39839
* fix(ai-gateway): dial upstream WebSockets over an explicit rustls provider by @mateo-berri in https://github.com/BerriAI/litellm/pull/39530
* fix(cost): bill realtime reasoning tokens nested in text_tokens once by @mateo-berri in https://github.com/BerriAI/litellm/pull/39850
* fix: keep provider id and metadata on Responses API bridged chat completions by @mateo-berri in https://github.com/BerriAI/litellm/pull/39981
* fix(make check): lint the test tree on tests-only changes like CI does by @mateo-berri in https://github.com/BerriAI/litellm/pull/39870
* fix(ci): stop the auto-close duplicates job colliding with the required test check by @mateo-berri in https://github.com/BerriAI/litellm/pull/40015
* fix: capture provider request id in failure logging payloads by @yucheng-berri in https://github.com/BerriAI/litellm/pull/40045
* test(ui): make navigation smoke resilient to router refactors by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40026
* test(e2e/ui): cover member role and budget edits, member permission delegation, and team guardrail removal by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40042
* test(ocr): add SDK callback E2E parity by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40061
* test(e2e): prove the virtual key lifecycle on every gateway replica by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40023
* fix(spend_logs): keep partition DDL transactions alive for their statement timeout by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40098
* feat(proxy): resolve root_path per request from a configured prefix list (SERVER_ROOT_PATHS) by @gym-cmd in https://github.com/BerriAI/litellm/pull/35935
* fix(router): preserve heuristic defaults across releases by @tin-berri in https://github.com/BerriAI/litellm/pull/40007
* fix(proxy): enforce key and team model access on Bedrock passthrough routes (internal copy of #34244) by @mateo-berri in https://github.com/BerriAI/litellm/pull/39660
* feat(ci): add the cost map guard check by @mateo-berri in https://github.com/BerriAI/litellm/pull/39835
* feat(ui): add key-scoped auto-router usage tab by @tin-berri in https://github.com/BerriAI/litellm/pull/39999
* fix(ui): hide the Create Vector Store flow from non proxy admins by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40148
* fix(ui): send empty vector_stores when the last team vector store is removed by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40144
* feat(skills): semantic search over the LiteLLM-hosted skill registry by @yassin-berriai in https://github.com/BerriAI/litellm/pull/39401
* fix(ui): show inherited MCP servers on the internal user editor and flag access groups with no members by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40036
* feat(keys): allow editing soft budget on existing keys by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/39002
* fix(guardrails): block Prompt Security file modifications by @davida-ps in https://github.com/BerriAI/litellm/pull/38204
* fix(router): keep provider response headers on streaming chat completions by @yucheng-berri in https://github.com/BerriAI/litellm/pull/40091
* ci: prepare workflows for main default branch by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40149
* fix(proxy): let authorized internal users open vector store details by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40150
* feat(ui): make automatic auto-router setup discoverable and show what it configured by @tin-berri in https://github.com/BerriAI/litellm/pull/40146
* fix(docs): fix stale file paths in ARCHITECTURE.md by @jrlprost in https://github.com/BerriAI/litellm/pull/40157
* fix(guardrails): accept on_violation block and alert for mcp_security by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40155
* fix(spend): price caching savings on the billed request basis by @tin-berri in https://github.com/BerriAI/litellm/pull/40160
* fix(responses): drop unsupported reasoning param for openai non-reasoning models by @mateo-berri in https://github.com/BerriAI/litellm/pull/38842
* fix(guardrails): resolve generateContent routes and async-first passthrough call types by @mateo-berri in https://github.com/BerriAI/litellm/pull/38869
* fix(mcp): forward staged credentials on /mcp-rest/test/connection like /test/tools/list by @mateo-berri in https://github.com/BerriAI/litellm/pull/38806
* fix(proxy): register SkillsInjectionHook at proxy startup instead of import time by @mateo-berri in https://github.com/BerriAI/litellm/pull/38914
* feat(ui): list the ChatGPT subscription provider in the Add Model form by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40170
* test(guardrails): pin the presidio spend-log record and the UI's masked-entity persistence by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40038
* test(e2e/ui): automate the RC checklist's Presidio guardrail walk by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40041
* ci: follow the default branch in development tooling by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40162
* fix(mcp): encrypt stored static headers and stdio environment by @tin-berri in https://github.com/BerriAI/litellm/pull/40164
* feat(fireworks_ai): add native Responses API config by @mateo-berri in https://github.com/BerriAI/litellm/pull/39826
* feat(ui): itemize auto-router classification spend by @tin-berri in https://github.com/BerriAI/litellm/pull/40168
* fix(bedrock): keep x-amzn-RequestId on chat error responses by @yucheng-berri in https://github.com/BerriAI/litellm/pull/40089
* fix(mcp): clear error when an agent-bound key is denied a scoped MCP server + agent MCP grants in the UI by @mateo-berri in https://github.com/BerriAI/litellm/pull/39234
* fix(anthropic): skip one-shot Claude Code cache injection by @tin-berri in https://github.com/BerriAI/litellm/pull/40175
* feat(complexity_router): add declarative custom dimensions to the heuristic scorer by @tin-berri in https://github.com/BerriAI/litellm/pull/40156
* fix(proxy): log budget reservation notice once at config load by @yucheng-berri in https://github.com/BerriAI/litellm/pull/40167
* test: add Rust extension pytest contract by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40181
* test: drop tests that only pin static cost-map values by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40195
* fix(vertex_ai): support fine-tuned Gemini endpoints in managed batches by @mubashir1osmani in https://github.com/BerriAI/litellm/pull/39668
* fix(spend): compare auto-router targets by deployment identity by @tin-berri in https://github.com/BerriAI/litellm/pull/40206
* feat(ui): show auto-router classification rate by @tin-berri in https://github.com/BerriAI/litellm/pull/40192
* feat(mcp): start the named server's OAuth directly for a resource-scoped gateway flow by @tin-berri in https://github.com/BerriAI/litellm/pull/39933
* fix(router): rank streaming latency routing by raw TTFT, not TTFT per token by @clement-paradex in https://github.com/BerriAI/litellm/pull/40202
* fix(tool_permission): log expected skip and deny events below WARNING by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40208
* fix(proxy): kill the whole prisma process group when a boot migration command times out by @mateo-berri in https://github.com/BerriAI/litellm/pull/39509
* fix(proxy): load db credentials in the model reconcile so a worker never serves a model before its credential by @mateo-berri in https://github.com/BerriAI/litellm/pull/39876
* fix(router): give cooldowns their own cache so siblings see a bench in ~1s by @mateo-berri in https://github.com/BerriAI/litellm/pull/40025
* fix(least-busy): share in-flight request counts across proxy workers by @mateo-berri in https://github.com/BerriAI/litellm/pull/40009
* fix(proxy-extras): rebuild indexes left INVALID by a migration deadlock by @mateo-berri in https://github.com/BerriAI/litellm/pull/39384
* fix(guardrails): keep guardrail telemetry when a policy pipeline blocks or modifies the response by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40211
* fix(ocr): run post-call logging hooks by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40154
* fix(guardrails): allow framework-supported logging-only mode by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40267
* fix(responses bridge): keep mid-conversation system messages in input instead of folding them into instructions by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40269
* fix(proxy): initialize string success/failure callbacks at startup after config load by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/38226
* fix(responses): record spend for native Responses API WebSocket sessions by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/38856
* feat(complexity_router): rebalance heuristic weights in the dashboard and grade custom dimensions by match count by @tin-berri in https://github.com/BerriAI/litellm/pull/40205
* feat(deploy): metrics sidecar and separate metrics port in Helm and Terraform by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40163
* feat(router): resolve max_tokens to the tier model's ceiling on auto-routed requests by @tin-berri in https://github.com/BerriAI/litellm/pull/40209
* chore: bump litellm-proxy-extras 0.4.94 -> 0.4.95, litellm 1.101.0 -> 1.102.0 by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40287
* feat(otel): make the OTel v2 trace export URL configurable by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40286
* fix(router): keep per-request routing_strategy override selectors out of global callbacks by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40229
* fix(router): count allowed_fails in the shared router cache so multi-worker proxies bench a deployment fleet-wide by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40224
* fix(router): let simple-shuffle weight by any deployment's weight/rpm/tpm by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40222
* fix(router): give cost-based routing its own cache key so it stops overwriting latency samples by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40225
* fix(router): keep deployment tags out of retry and fallback tag routing by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40226
* fix(proxy): keep team member budget enforced at the cap and across Redis counter expiry by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40304
* fix(utils): honor string drop_params values from config and DB deployments by @mateo-berri in https://github.com/BerriAI/litellm/pull/33738
* fix(policy_engine): execute post_call guardrail pipelines on responses and streams by @mateo-berri in https://github.com/BerriAI/litellm/pull/38721
* feat(ui): batch observability on the logs page by @mubashir1osmani in https://github.com/BerriAI/litellm/pull/39626
* feat(otel): add http/json export protocol for OTel v2 traces by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40290
* feat: move MongoDB vector search to an optional sidecar (BETA) by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40203
* perf: move Anthropic, Vertex Anthropic, Ollama and HF template fetches off the event loop by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40311
* fix(router): move retry-policy retries off the refusing deployment on every router entrypoint by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40306
* fix(proxy): default max_idle_connection_lifetime on componentized DB URLs by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40285
* fix(a2a): forward caller identity headers on message/send and message/stream by @yassin-berriai in https://github.com/BerriAI/litellm/pull/40305
* feat(team): let a team admin manage their own team's logging callbacks by @yucheng-berri in https://github.com/BerriAI/litellm/pull/37667
* fix(proxy): give each spend-log queue monitor its own flush event by @mateo-berri in https://github.com/BerriAI/litellm/pull/39556
* fix(mlflow): prevent _stream_id_to_span leak and mlflow 2.x end_trace TypeError by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/39049
* feat(otel v2): send a key's or team's whole trace to its own destination by @yucheng-berri in https://github.com/BerriAI/litellm/pull/39654
* chore(ui): update dashboard dependencies by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40312
* feat(bedrock): add TwelveLabs Marengo Embed 3.0 embeddings by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40180
* fix(proxy): stop shipping the literal string "None" as error type and param by @mateo-berri in https://github.com/BerriAI/litellm/pull/39536
* chore(ci): merge main into internal staging by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40323
* test(azure_sentinel): pin batch_size as a per-request bound under concurrent events by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40320
* fix(fireworks_ai): fold instructions and developer items into one leading system message on the Responses path by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40268
* feat(auto_router): opt-in NON_REASONING tier below SIMPLE by @moe-berri in https://github.com/BerriAI/litellm/pull/40273
* fix(budget_reservation): don't reserve budget on token counting routes by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/36718
* feat(mcp): add schema discovery proxy mode by @tin-berri in https://github.com/BerriAI/litellm/pull/40298
* test(proxy): fix Prisma timeout cleanup after subreaper tests by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40333
* fix(otel v2): restore the Datadog auth span and the last-wins callback merge by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40335
* chore(ci): extend diskcache scan exception to October 1 by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40336
* fix(anthropic): key the /v1/messages prompt cache on Claude Code's session_id only by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40342
* feat(auto-router): refresh family reasoning presets by @tin-berri in https://github.com/BerriAI/litellm/pull/40341
* feat(cost_map): report which revision of the price map the proxy is serving by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40179
* test(mcp): fix proxy fixture isolation after manager reload by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40347
* chore: bump litellm-enterprise 0.1.65 -> 0.1.66 by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40334
* chore(ci): promote internal staging to main by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40307
* fix(mcp): preserve proxy logging and authorization coverage by @tin-berri in https://github.com/BerriAI/litellm/pull/40337
* fix(spend-tracking): recover key alias for session tokens from spend logs by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40275
* fix(stream_chunk_builder): guard empty choices and missing role in build_base_response by @ZXT-zjbiliy in https://github.com/BerriAI/litellm/pull/37781
* fix(mcp): log proxy tool dispatch exceptions by @tin-berri in https://github.com/BerriAI/litellm/pull/40351
* fix(azure_ai): price seven Foundry catalog names and charge the model router fee once by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40189
* test(e2e/ui): cover team-scoped model visibility, re-editing litellm params, and model health checks by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40039
* test(e2e/ui): cover key budget window, non-admin model scope edit, and key blocking by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40027
* fix(mcp): honor an explicit null on toolset update, cover MCP lifecycle e2e by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40022
* fix(batches): clean up E2E resources across providers by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40161
* fix(model-management): honor an explicit null as a clear on model update by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40047
* feat(guardrails): map each guardrail scan id to its guardrail, stage and provider by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40327
* revert(model-management): roll back #40047 by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40383
* fix(proxy): apply team model aliases on the JWT auth path by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/39985
* fix(integrations): pass original request object to post-call guardrail hooks by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40414
* fix(cost-map): keep first fetch blocking, run retries in background by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40350
* fix(ui): repair pass-through delete confirm dialog and disable delete for config endpoints by @mubashir1osmani in https://github.com/BerriAI/litellm/pull/40303
* feat(proxy): price cache and reasoning tokens in /cost/estimate by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40174
* fix(mcp): surface connection failures across transports by @joshua-berri in https://github.com/BerriAI/litellm/pull/40359
* perf(proxy): pipeline spend counter increments into one Redis call per request by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40371
* fix(proxy): ignore team_id="" on /key/update so team-less keys can be updated and imported by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40421
* feat(router): support percentile-based TTFT routing by @clement-paradex in https://github.com/BerriAI/litellm/pull/40352
* perf(proxy): collapse per-worker SGR upserts into one statement per flush by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40362
* fix(router): strip encrypted reasoning on an auto-router tier change instead of a 503 by @tin-berri in https://github.com/BerriAI/litellm/pull/40280
* test: isolate bedrock aws tests from ambient SSL env vars by @CaptainAni187 in https://github.com/BerriAI/litellm/pull/40425
* fix(proxy): pin multi-root CA bundle to the server's root before handing it to Prisma by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40428
* fix(cli): skip remote model cost map fetch in lite CLI processes by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40372
* chore(lint): bring ANN202 and BLE001 back under the strict-rule budget by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40444
* feat(guardrails): run post_call policy pipelines on background Responses retrieval by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40274
* feat(auth): add disable_env_credential_login setting with admin ui warning by @ojensen-berri in https://github.com/BerriAI/litellm/pull/40116
* test(ui): derive reasoning-effort assertion from the anthropic preset by @cursor[bot] in https://github.com/BerriAI/litellm/pull/40456
* feat(hosted_vllm): add image edit support by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40329
* fix(proxy): keep a body litellm_session_id in SpendLogs under missing_session_id omit by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40379
* fix(rate_limiter): attach v3 priority rate limit headers on /v1/messages by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/37228
* feat(guardrails): deliver tool-call rewrites into buffered chat, Responses, and Messages streams by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40271
* fix(proxy): accept non-string callback vars in default_team_settings by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40458
* fix(router): resolve team-scoped auto-routers by their public name by @tin-berri in https://github.com/BerriAI/litellm/pull/40432
* fix(langfuse): give each call in a session header its own trace instead of upserting one trace per session by @yucheng-berri in https://github.com/BerriAI/litellm/pull/40177
* fix(databricks): keep top-level reasoning_content from OpenAI-compatible gateway models by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40449
* fix(convert_dict_to_response): handle empty choices list without raising 500 APIError by @shotsan in https://github.com/BerriAI/litellm/pull/40294
* fix(router): resolve route candidate ids through the router's own resolver by @tin-berri in https://github.com/BerriAI/litellm/pull/40491
* fix(jwt): cascade-delete JWT key mappings when their virtual key is deleted by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/33703
* fix(databricks): route Unity model services through AI Gateway by @tin-berri in https://github.com/BerriAI/litellm/pull/40492
* fix(ui): preserve dotted MCP tool argument names by @joshua-berri in https://github.com/BerriAI/litellm/pull/40494
* feat(cli): add lite configure claude and lite unconfigure claude by @tin-berri in https://github.com/BerriAI/litellm/pull/40319
* fix(ui): scope shadow eval models to configured chat groups by @tin-berri in https://github.com/BerriAI/litellm/pull/40488
* fix(pricing): rolling model registry update: Bedrock gpt-6-astra, gpt-image-2.5, Cohere rerank 4, Vertex Grok 4.3/4.6/4.20, Gemini 3.5 audio, OpenAI web search fee, xAI Imagine video, Lyria 3.5, Voyage, ChatGPT GPT-5.5/5.6, Bedrock Mantle, Scaleway dates by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/31884
* fix(guardrails): scan and rewrite Responses custom_tool_call output items by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40461
* feat(guardrails): run legacy post-call hooks as streaming pipeline steps by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40284
* fix(azure): respect DEFAULT_MAX_RETRIES in initialize_azure_sdk_client (internal copy of #35771) by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40464
* fix: keep reasoning_effort for mode: responses bridge deployments by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40249
* fix(ui): guard playground cost metric against null and NaN by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40257
* fix(responses): echo a named tool_choice in the Responses API shape on the chat-completions bridge by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40462
* fix(azure_ai): reject unsupported n and size params on MAI image models by @mihidumh in https://github.com/BerriAI/litellm/pull/40074
* fix(bedrock): stop leaking Anthropic `thinking`/`reasoning_effort` into DeepSeek Converse requests by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/33409
* test(e2e): every spend row a virtual key writes joins its token across all write paths by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40465
* fix(token_counter): release the GIL for HuggingFace counts and cap exact counting per string by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40186
* fix(bedrock): sign requests off the event loop on every async path by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40270
* fix(cli): let the apiKeyHelper supply Claude Code's key under lite claude by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40489
* fix(responses): keep background polling alive after the client disconnects by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40114
* fix(terraform): preserve undeclared server-side key metadata on update by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40514
* fix(terraform): read team per-model rpm/tpm limits from metadata and clear them on removal by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40439
* feat(terraform): allow custom team_id on litellm_team by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40459
* fix(anthropic): replay OpenAI encrypted reasoning byte for byte through the /v1/messages bridge by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40451
* fix(terraform): send litellm_key model_max_budget as per-model BudgetConfig objects by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40450
* fix(mcp): refresh tool previews when editing connection settings by @joshua-berri in https://github.com/BerriAI/litellm/pull/40498
* fix(terraform): keep prior state when a virtual key update is rejected by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40512
* fix(terraform): send changed litellm_key duration on /key/update so expires is recomputed by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40511
* fix(terraform): drop litellm_key from state on 404 instead of failing the plan by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40443
* fix(terraform): read key fields the proxy stores in metadata back from /key/info by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40513
* chore(ci): promote internal staging to main by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40526
* chore(ui): bump smol-toml to fix GHSA-7w5x-hrqm-74c2 osv-scan failure by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40497
* fix(azure_ai): add passthrough config so router-model relays reach the deployment's own endpoint by @mateo-berri in https://github.com/BerriAI/litellm/pull/39863
* fix(mcp): report resolved upstream authentication in debug headers by @joshua-berri in https://github.com/BerriAI/litellm/pull/40454
* fix(mcp): challenge and scope gateway-owned server authentication by @joshua-berri in https://github.com/BerriAI/litellm/pull/40453
* fix(mcp): respect optional discovery capabilities and quiet unsupported methods by @joshua-berri in https://github.com/BerriAI/litellm/pull/40525
* fix(proxy): surface runtime-registered callbacks in UI Logging page by @yucheng-berri in https://github.com/BerriAI/litellm/pull/38974
* feat(proxy): list gateway models to Claude Code under Claude-shaped ids and serve requests on them by @tin-berri in https://github.com/BerriAI/litellm/pull/40515
* fix(openai): drop tool schema regex patterns OpenAI's validator cannot compile by @tin-berri in https://github.com/BerriAI/litellm/pull/40485
* fix(proxy): bound concurrent key and spend-counter DB lookups to stop prisma pool thrash by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40387
* fix(s3_v2): freeze refreshable credentials before signing and retry 403 uploads with a fresh signature by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40187
* feat(prometheus): bucket latency by input sequence length by @yucheng-berri in https://github.com/BerriAI/litellm/pull/40059
* fix(model_prices): registry audit 2026-09-10, absorb open pricing PRs by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40581
* feat(bedrock): thread aws_session_tags into STS AssumeRole by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40446
* ci(lint): gate top-level tests/e2e and litellm files in the diff-scoped lint steps by @mateo-berri in https://github.com/BerriAI/litellm/pull/39272
* feat(pointfive): add the pointfive logging integration by @yinonkahta-p5 in https://github.com/BerriAI/litellm/pull/38509
* fix(dashscope): remap chat-shaped api_base to the live rerank route by @mateo-berri in https://github.com/BerriAI/litellm/pull/39237
* fix(terraform): restore d.Partial(true) on a rejected /key/update by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40527
* feat(mock): report admission-time input token count in mock_response usage by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40590
* perf(proxy): reuse cached model group and deployment info in budget reservation by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40593
* fix(router): strip Codex harness envelopes before classification by @moe-berri in https://github.com/BerriAI/litellm/pull/40599
* feat(ocr): add core foundation and Mistral adapter  by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40530
* feat(infra): scale gateway on per-pod RPS and TPS in Helm and Terraform by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40479
* feat(terraform): prometheus metrics sidecar for the GCP Cloud Run gateway by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40614
* fix(proxy): recreate the Prisma client when the writer session turns read-only by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40610
* feat(rust_bridge): count budget-check input tokens in Rust on all LLM routes by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40381
* fix(wandb): preserve reasoning_effort in chat completions by @WolframRavenwolf in https://github.com/BerriAI/litellm/pull/39190
* fix(router): classify encrypted delegated tasks with native Responses by @moe-berri in https://github.com/BerriAI/litellm/pull/40608
* fix(mcp): reject initialize with 403 when the key grants no MCP servers by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40616
* feat(claude-code): accept https zip archive plugin sources for skills by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40496
* feat(proxy): granular key/team access control for Claude Code marketplace plugins by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40518
* fix(voyage): accept flat list[str] input for contextual embeddings by @fzowl in https://github.com/BerriAI/litellm/pull/35091
* fix(mcp): bind per-user OAuth credentials to the authenticated LiteLLM caller by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/38724
* fix(proxy): dedup latest health checks in SQL and gate the DB save per window by @michelligabriele in https://github.com/BerriAI/litellm/pull/39539
* fix(proxy): resolve /v1/models limits from the deployment, not the alias by @michelligabriele in https://github.com/BerriAI/litellm/pull/39296
* feat(redis): add ElastiCache IAM authentication by @eugene-yao-zocdoc in https://github.com/BerriAI/litellm/pull/38413
* test(proxy): pass the request to get_marketplace in the archive marketplace test by @mateo-berri in https://github.com/BerriAI/litellm/pull/40626
* feat(proxy): share database connections across workers with an in-container pgbouncer by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/39683
* fix(proxy): let internal users read request/response for their own spend logs by @krth1k in https://github.com/BerriAI/litellm/pull/35448
* chore(github): disable blank issues so filers must use a template by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40629
* feat(router): log exact classifier input and masked source request by @moe-berri in https://github.com/BerriAI/litellm/pull/40604
* fix(redis): log an open circuit breaker once instead of a traceback per request and count sync timeouts as timeouts by @mateo-berri in https://github.com/BerriAI/litellm/pull/40620
* feat(proxy): let the in-container pgbouncer follow rotating RDS IAM and Azure Entra tokens by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40623
* fix(proxy): log rejected unknown-model requests under a placeholder model name by @mateo-berri in https://github.com/BerriAI/litellm/pull/40622
* feat(wandb): default unmapped W&B models to reasoning-capable by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40625
* test(ocr): isolate native Rust bridge contracts by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40410
* feat(proxy): gate organization endpoints on an enterprise license by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40613
* feat(proxy): offload spend tracking to a pod-local collector sidecar by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40545
* feat(newrelic): export team max and remaining budget gauges to the Metric API by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40542
* fix(reset_budget_job): reset end users by budget link, not by user id by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40639
* perf(mock): emit admission-time usage chunk on streaming mock_response by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40637
* fix(rate_limiter): skip non-Latin-1 x-litellm-priority header on /v1/messages by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40636
* test: fix stale completion response fixtures by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40638
* fix(logging): finish response metadata before the sync logging thread reads it by @mateo-berri in https://github.com/BerriAI/litellm/pull/39869
* feat(ui): link the Team, Organization, User and Created By cells on the Virtual Keys page by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40646
* test: respect optional logging payload fields by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40643
* fix(streaming): keep admitted mock streams alive with empty stream_options and honor zero prompt counts by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40650
* chore: bump litellm-proxy-extras 0.4.95 -> 0.4.96 by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40630
* fix(helm): give the collector sidecar the pod PgBouncer env when database.connectionPool is enabled by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40660
* feat(ui): link the entity cells on the team detail page's keys table by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40647
* fix(auto-router): omit Claude Code system text from classifier by @tin-berri in https://github.com/BerriAI/litellm/pull/40655
* chore(ci): promote internal staging to main by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40658
* fix(caching): keep an open Redis circuit breaker open and quiet on the sync read and spend counter paths by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40624
* fix(mcp): accept VS Code OAuth registration callbacks by @joshua-berri in https://github.com/BerriAI/litellm/pull/40664
* fix(mcp): check OpenAPI specifications without native MCP handshakes by @joshua-berri in https://github.com/BerriAI/litellm/pull/40665
* fix(model_prices): registry audit rolling PR: deepseek-flash, gpt-live-1, xAI/Groq deprecation dates, Perplexity Nemotron reasoning by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40606
* perf(proxy): lazy-load provider passthrough routes by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40691
* fix(proxy): give user-key objects their own in-memory cache partition by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40713
* fix(passthrough): parse Bedrock stream spend incrementally instead of buffering the whole response by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40724
* feat(secret_managers): support customer-managed KMS key for virtual keys stored in AWS Secrets Manager by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40475
* feat(proxy): make the in-memory management cache capacity configurable by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40725
* perf(proxy): register liveness and core inference routes first by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40687
* docs(router): name both affinity TTL knobs in the _claim_pin docstring by @anmolg1997 in https://github.com/BerriAI/litellm/pull/40663
* fix(mcp): explain refused OAuth registration and bound discovery retries by @joshua-berri in https://github.com/BerriAI/litellm/pull/40679
* fix(mcp): log upstream request method, body and response on tool-list and OAuth2 token failures by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40440
* fix(oci): pin one response id per streamed completion, skip the [DONE] sentinel by @mateo-berri in https://github.com/BerriAI/litellm/pull/39507
* fix(vector-stores): surface retrieval failures to the API caller by @mateo-berri in https://github.com/BerriAI/litellm/pull/39516
* fix(ai-gateway): build the release image again and cover it in CI by @mateo-berri in https://github.com/BerriAI/litellm/pull/39523
* fix(proxy): authorize every Responses API id, not only the ones the proxy issued by @mateo-berri in https://github.com/BerriAI/litellm/pull/39548
* fix(router): fall back from unhealthy auto-router tier by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40757
* fix(proxy): keep call_type and request start time on failed-request spend logs by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40558
* fix(proxy): retain metadata when retrieving public team aliases by @haydster7 in https://github.com/BerriAI/litellm/pull/40554
* test(e2e): wait for serving propagation in UI journeys by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40754
* refactor(ocr): route native requests through core by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40532
* feat(auto-router): show the routed model and session savings in Claude Code and Codex by @tin-berri in https://github.com/BerriAI/litellm/pull/40330
* fix(mcp): write failure spend log for guardrail-blocked /mcp-rest/tools/call by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40555
* feat(ocr): add Azure Mistral adapter and document fetching by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40533
* fix(datadog_llm_obs): keep tool call and result structure under redaction and emit tool output tokens by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40666
* fix(search): propagate GET provider HTTP errors by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40779
* fix(policy_engine): run global policy pipelines before scoped ones by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/39697
* fix(content_filter): log only scan time as streaming post_call guardrail duration by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40760
* fix(cost-map): bedrock reasoning effort flags, registry audit fixes for vertex/openai/together/openrouter, absorb cerebras and inception rows by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40740
* test(responses): fix stale Anthropic smoke request by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40786
* fix(ui): jump straight to the last Request Logs page instead of advancing one page by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40644
* feat(ocr): add Azure Mistral adapter with native authentication by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40502
* feat(ocr): add Azure Document Intelligence adapter by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40534
* feat(ocr): add Reducto legacy and v3 adapters by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40535
* feat(ocr): add Vertex Mistral adapter by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40507
* feat(ocr): add Vertex DeepSeek adapter and remove legacy OCR pipeline by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40509
* fix(vertex_ai): return 400 for invalid reasoning_effort instead of 500 by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40748
* fix(guardrails): stop logging the request payload as guardrail_response on pre_call hooks by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/39699
* feat(rust): count tiktoken cl100k_base admission tokens in Rust by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40777
* fix(hide-secrets): restore credential coverage lost to the 4.5 entropy limit by @yucheng-berri in https://github.com/BerriAI/litellm/pull/40190
* test(load): add a Redis timeout chaos load test by @kerry-berri in https://github.com/BerriAI/litellm/pull/40482
* feat(proxy): expose complexity routing headers by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40792
* fix(otel v2): name Langfuse traces from the langfuse_trace_name header or metadata.trace_name by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40793
* feat(ui): link the Organization cell on the Teams page by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40749
* docs(pr-template): note untested assumptions under Caveats by @kerry-berri in https://github.com/BerriAI/litellm/pull/40811
* feat(ui): link the User ID and Team ID cells on the Memory page by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40752
* feat(ui): link the User ID, Created By and Deleted By cells on Deleted Keys by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40750
* feat(ui): link the Created By cell on the Prompts page by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40753
* feat(ui): link the Organization and Deleted By cells on Deleted Teams by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40751
* fix(proxy): emit internal user budget webhook alerts by @jon-walton in https://github.com/BerriAI/litellm/pull/40396
* fix(proxy): prevent spend counter double counting by @dclarksymmetry in https://github.com/BerriAI/litellm/pull/40572
* fix(guardrails): keep post_call guardrail info on streamed chat completions by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40806
* fix(realtime): dial Azure's GA realtime upstream for GA clients by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40769
* fix(ui): preserve cleared shared select values by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40795
* feat(model_prices): add DeepSeek V4.1 Flash on Fireworks by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40812
* fix(fireworks_ai): keep reasoning_content on replayed assistant messages by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40682
* fix(shadow-eval): skip hosted web search samples by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40827
* fix(db): carry DATABASE_SSLMODE/DATABASE_SSLROOTCERT into the assembled writer and reader URLs by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40815
* fix(guardrails): fail closed with a named error when a Responses input rewrite cannot be applied by @csoni-cweave in https://github.com/BerriAI/litellm/pull/40609
* fix(ui): make the env-credential login warning banner dismissible by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40831
* test(pgbouncer): stop the never-listens replacement test flaking under CI load by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40830
* feat(ui): search, sort and role filter for the team member table by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40659
* fix(proxy): keep the raw model string out of the unknown-model spend-log error message by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40820
* fix(mcp): cache upstream discovery lists by @joshua-berri in https://github.com/BerriAI/litellm/pull/40790
* fix(mcp): match per-server OAuth metadata issuers by @joshua-berri in https://github.com/BerriAI/litellm/pull/40808
* fix(mcp): use gateway authentication for root discovery by @joshua-berri in https://github.com/BerriAI/litellm/pull/40791
* fix(bedrock_mantle): gate reasoning.summary on the OpenAI Responses path by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40798
* test(e2e): memory regression test for failing requests on the release gate by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40773
* test(e2e): reusable JWT fixtures and management lifecycle coverage by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/39990
* fix(proxy): expand access groups in /health scoping and allowlist health display fields by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40765
* test(ocr): exempt native parity requests from cassette replay by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40838
* fix(proxy): persist clearing user model budgets by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40837
* perf(auth): read user, team, membership, org, project and spend counters in one MGET, one query and one pipeline by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40834
* perf(proxy): one MGET and one pipeline for post-call spend counters, no team/user/org refetch on the response path by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40841
* fix(responses): preserve hosted web search calls by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40828
* feat(cli): configure Claude Code and Codex with a gateway key by @tin-berri in https://github.com/BerriAI/litellm/pull/40829
* fix(router): restore compression inheritance when clearing overrides by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40839
* fix(keys): support explicit project detachment by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40836
* feat(guardrails): add Conduct Guard integration with validated hooks and forwarded params by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40785
* fix(mcp): enforce end user mcp_tool_permissions on tools/list and tools/call by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40865
* refactor(ocr): complete native lifecycle and preserve Azure auth by @yujonglee-berri in https://github.com/BerriAI/litellm/pull/40734
* fix(ui): restore MCP catalog provider logos by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40781
* fix(ui): preserve clear and default semantics in local forms by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40826
* fix(ui): clarify blank TPM/RPM hint on budget modals by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40697
* test(e2e): verify cached answers and upstream request count by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40774
* fix(key): recover from a cascade-deleted key instead of failing the apply by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/40880
* fix(proxy): accept both deferred stream logging arg shapes on native routes by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40869
* perf(policy_engine): dedup attachments in one pass after sorting by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40883
* fix(ui): persist cleared budgets and reset intervals by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40895
* fix(guardrails): log mask when a guardrail adds request keys by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40882
* fix(ui): show loading state instead of stale rows while a table search is pending by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40656
* chore: bump litellm-enterprise 0.1.66 -> 0.1.67, litellm-proxy-extras 0.4.96 -> 0.4.97 by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40905
* test(fireworks): stop pinning prices in the cost-map tests by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40901
* feat(ui): search Key Activity by key alias, key hash, user id, or email by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40652
* fix(proxy): run migrations through python -m prisma when the prisma console script is not on PATH by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40768
* feat(proxy): serve registered skills as an Agent Skills well-known index by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40770
* test: deflake redis semantic cache sys.modules leak, LangSmith init loop patch, wall-clock stagger assertion, and zombie grandchild check in the fake prisma cli by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/39895
* fix(anthropic): price recovered tokens when a /v1/messages client disconnects mid-stream by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40766
* fix(proxy): resolve config include directives for bucket-hosted configs by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40772
* fix(registry): sync Azure/Together deprecation dates, fix computer-use-preview and OpenRouter metadata by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40855
* test: tighten regression tests added in #37974 by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40771
* fix(redis): count pool wait timeouts as breaker timeouts by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40764
* fix(cost): honour deployment custom pricing for OCR calls by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40767
* fix(cost): honour deployment custom pricing for OCR calls by @mihidumh in https://github.com/BerriAI/litellm/pull/36609
* feat(realtime): add Meta Muse Voice transcription by @seyeong-han in https://github.com/BerriAI/litellm/pull/39395
* fix(proxy): attribute gate-rejected requests to their endpoint in cache analytics by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40824
* feat(registry): add openai reasoning-family fallback generalization by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40902
* fix(proxy): allow key_alias substring matching on /key/list for non-admins by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40907
* fix(databricks): translate reasoning_effort to thinking for Gemini 2.5 by @devin-ai-integration[bot] in https://github.com/BerriAI/litellm/pull/40909
* fix(databricks): translate reasoning_effort to thinking for Gemini 2.5 by @cohml in https://github.com/BerriAI/litellm/pull/32786
* fix(model_management): stop persisting cost map pricing as a deployment override by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/36222
* chore: rebuild Admin UI bundle from staging by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40931
* chore(ci): promote internal staging to main by @yuneng-berri in https://github.com/BerriAI/litellm/pull/40933
* fix(responses): backport request-param leak fixes to rc/1.102.0 (#41018, #41141, #41144) by @yuneng-berri in https://github.com/BerriAI/litellm/pull/41342
* fix(images): backport the image[] and mask[] form key drop to rc/1.102.0 (#39512) by @mateo-berri in https://github.com/BerriAI/litellm/pull/41697
* fix(license): backport the wildcard license auto_router grant to rc/1.102.0 (#41684) by @mateo-berri in https://github.com/BerriAI/litellm/pull/41701
* fix: backport eight backport-stable fixes to rc/1.102.0 (#40596, #41046, #41086, #41171, #41178, #41283, #41495, #41689) by @mateo-berri in https://github.com/BerriAI/litellm/pull/41854
* fix(team): apply team_member_budget updates to members still on the team default (backport of #41347 to rc/1.102.0) by @mateo-berri in https://github.com/BerriAI/litellm/pull/41935
* test(e2e): backport the Nova Sonic nova-2-sonic model fix to rc/1.102.0 by @yuneng-berri in https://github.com/BerriAI/litellm/pull/42059

## New Contributors
* @gym-cmd made their first contribution in https://github.com/BerriAI/litellm/pull/35935
* @jrlprost made their first contribution in https://github.com/BerriAI/litellm/pull/40157
* @clement-paradex made their first contribution in https://github.com/BerriAI/litellm/pull/40202
* @ZXT-zjbiliy made their first contribution in https://github.com/BerriAI/litellm/pull/37781
* @CaptainAni187 made their first contribution in https://github.com/BerriAI/litellm/pull/40425
* @shotsan made their first contribution in https://github.com/BerriAI/litellm/pull/40294
* @yinonkahta-p5 made their first contribution in https://github.com/BerriAI/litellm/pull/38509
* @krth1k made their first contribution in https://github.com/BerriAI/litellm/pull/35448
* @haydster7 made their first contribution in https://github.com/BerriAI/litellm/pull/40554
* @jon-walton made their first contribution in https://github.com/BerriAI/litellm/pull/40396
* @dclarksymmetry made their first contribution in https://github.com/BerriAI/litellm/pull/40572

**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.101.0...v1.102.0

Related Repositories

public-apis/public-apis★ 491,140

A collective list of free APIs

NousResearch/hermes-agent★ 255,982

The agent that grows with you

yt-dlp/yt-dlp★ 200,082

A feature-rich command-line audio/video downloader

microsoft/markitdown★ 191,496

Python tool for converting files and office documents to Markdown.

Significant-Gravitas/AutoGPT★ 187,704

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.