v1.83.8-nightly

BerriAI/litellmv1.83.8-nightlyApr 15, 2026by github-actions[bot]

AI Summary

This nightly release focuses on stability improvements, security updates including vulnerable dependency bumps and Docker signing verification, and introduces new features like BM25-based prompt compression, PromptGuard integration, and Veo Lite support. It also includes a major infrastructure migration from Poetry to the 'uv' toolchain.

Key Highlights

Infrastructure migration: Packaging, CI, and Docker moved from Poetry to 'uv'.
New feature: 'litellm.compress()' for BM25-based prompt compression.
New feature: PromptGuard guardrail integration with per-team opt-out options.
New feature: Support for Gemini Veo Lite video pricing and resolution tiers.
Fix: Proxy cache invalidation logic and budget reset time alignment.

New Features

BM25-based prompt compression with retrieval tool (litellm.compress())
PromptGuard guardrail integration
Veo Lite pricing, video resolution usage, and tiered cost support
Prometheus latency histogram buckets (7m and 10m)
Advisor tool orchestration for non-Anthropic providers
New model offerings including kimi-k2.5 and minimax-m2.5

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:v1.83.8-nightly
```

**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/v1.83.8-nightly/cosign.pub \
  ghcr.io/berriai/litellm:v1.83.8-nightly
```

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(mcp): is_tool_name_prefixed validates against known server prefixes by @voidborne-d in https://github.com/BerriAI/litellm/pull/25085
* fix(s3_v2): use prepared URL for SigV4-signed S3 requests by @nehaaprasad in https://github.com/BerriAI/litellm/pull/25074
* fix(cache): Prevent 'multiple values' TypeError in get_cache_key by @hunterchris in https://github.com/BerriAI/litellm/pull/20261
* fix(presidio): use correct text positions in anonymize_text by @Dmitry-Kucher in https://github.com/BerriAI/litellm/pull/24998
* feat(prometheus): add 7m and 10m latency histogram buckets by @kulia26 in https://github.com/BerriAI/litellm/pull/25071
* fix(ui): resolve login redirect loop when reverse proxy adds HttpOnly to cookies by @jaxhend in https://github.com/BerriAI/litellm/pull/23532
* fix(proxy): set key_alias=user_id in JWT auth for Prometheus metrics by @michelligabriele in https://github.com/BerriAI/litellm/pull/25340
* fix(vertex_ai): normalize Gemini finish_reason enum through map_finis… by @abhyudayareddy in https://github.com/BerriAI/litellm/pull/25337
* fix: remove leading space from license public_key.pem by @milan-berri in https://github.com/BerriAI/litellm/pull/25339
* feat(dashscope): preserve cache_control for explicit prompt caching by @silencedoctor in https://github.com/BerriAI/litellm/pull/25331
* fix: expose reasoning effort fields in get_model_info + add together_ai/gpt-oss-120b by @avarga1 in https://github.com/BerriAI/litellm/pull/25263
* Add PromptGuard guardrail integration by @acebot712 in https://github.com/BerriAI/litellm/pull/24268
* Revert "fix(proxy): set key_alias=user_id in JWT auth for Prometheus metrics" by @krrish-berri-2 in https://github.com/BerriAI/litellm/pull/25438
* build: migrate packaging, CI, and Docker from Poetry to uv by @stuxf in https://github.com/BerriAI/litellm/pull/25007
* fix(security): bump vulnerable dependencies (22 of 25 dependabot alerts) by @stuxf in https://github.com/BerriAI/litellm/pull/25442
* blog: restyle docs.litellm.ai/blog to engineering blog aesthetic by @ishaan-berri in https://github.com/BerriAI/litellm/pull/25580
* blog: Ramp-style engineering blog restyle + Redis circuit breaker post by @ishaan-berri in https://github.com/BerriAI/litellm/pull/25583
* feat(advisor): advisor tool orchestration loop for non-Anthropic providers by @ishaan-berri in https://github.com/BerriAI/litellm/pull/25579
* Litellm dev 04 11 2026 p1 by @krrish-berri-2 in https://github.com/BerriAI/litellm/pull/25585
* blog: add back arrow to blog post pages by @ishaan-berri in https://github.com/BerriAI/litellm/pull/25587
* fix(proxy): cache invalidation double-hashes token in bulk update and key rotation by @dkindlund in https://github.com/BerriAI/litellm/pull/25552
* fix(proxy): model_max_budget silently broken for routed models by @dkindlund in https://github.com/BerriAI/litellm/pull/25549
* fix(embedding): omit null encoding_format for openai requests by @meutsabdahal in https://github.com/BerriAI/litellm/pull/25395
* fix(budget): align reset times for legacy entities (Team Members, End Users) with standardized calendar by @DmitriyAlergant in https://github.com/BerriAI/litellm/pull/25440
* feat(model):add wandb model offerings to include kimi-k2.5 and minimax-m2.5 by @csoni-cweave in https://github.com/BerriAI/litellm/pull/25409
* [Fix] Align field-level checks in user and key update endpoints by @yuneng-berri in https://github.com/BerriAI/litellm/pull/25541
* [Refactor] UI - Virtual Keys: migrate regenerate key modal to AntD by @yuneng-berri in https://github.com/BerriAI/litellm/pull/25406
* [Fix] tighten handling of environment references in request parameters by @yuneng-berri in https://github.com/BerriAI/litellm/pull/25592
* merge main by @Sameerlite in https://github.com/BerriAI/litellm/pull/25616
* Litellm oss staging 04 08 2026 by @krrish-berri-2 in https://github.com/BerriAI/litellm/pull/25397
* fix(auth): gate post-custom-auth DB lookups behind opt-in flag by @michelligabriele in https://github.com/BerriAI/litellm/pull/25634
* fix: blog dark mode - text invisible on dark background by @krrish-berri-2 in https://github.com/BerriAI/litellm/pull/25620
* [Fix] /spend/logs: align filter handling with user scoping by @yuneng-berri in https://github.com/BerriAI/litellm/pull/25594
* feat: add litellm.compress() — BM25-based prompt compression with retrieval tool by @krrish-berri-2 in https://github.com/BerriAI/litellm/pull/25637
* docs: week 2 checklist by @mubashir1osmani in https://github.com/BerriAI/litellm/pull/25452
* feat(guardrails): per-team opt-out for specific global guardrails by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/25575
* Litellm ishaan april11 by @ishaan-berri in https://github.com/BerriAI/litellm/pull/25586
* chore: remove deprecated tests/ui_e2e_tests/ suite by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/25657
* test(e2e): add edit team model TPM/RPM limits test by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/25658
* Litellm oss staging 04 09 2026 by @krrish-berri-2 in https://github.com/BerriAI/litellm/pull/25463
* [Feature] UI - Teams: Allow Editing Router Settings After Team Creation by @yuneng-berri in https://github.com/BerriAI/litellm/pull/25398
* [Infra] Merge dev branch with main by @yuneng-berri in https://github.com/BerriAI/litellm/pull/25647
* [Test] UI - Models: Add E2E tests for Add Model flow by @yuneng-berri in https://github.com/BerriAI/litellm/pull/25590
* Revert "fix(embedding): omit null encoding_format for openai requests" by @Sameerlite in https://github.com/BerriAI/litellm/pull/25698
* feat(bedrock): normalize custom tool JSON schema for Invoke and Converse by @Sameerlite in https://github.com/BerriAI/litellm/pull/25396
* feat(gemini): Veo Lite pricing, video resolution usage and tiered cost by @Sameerlite in https://github.com/BerriAI/litellm/pull/25348
* litellm_staging_04_04_2026 by @krrish-berri-2 in https://github.com/BerriAI/litellm/pull/25192
* Litellm oss staging 04 11 2026 by @krrish-berri-2 in https://github.com/BerriAI/litellm/pull/25589
* litellm oss staging 04/13/2026 by @krrish-berri-2 in https://github.com/BerriAI/litellm/pull/25665
* fix(cost-map): add us-south1 to vertex qwen3-235b-a22b-instruct-2507-maas by @ti3x in https://github.com/BerriAI/litellm/pull/25382
* feat: add litellm.compress() — BM25-based prompt compression with ret… by @krrish-berri-2 in https://github.com/BerriAI/litellm/pull/25650
* fix(ui): pre-select backend default for boolean guardrail provider fields by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/25700
* fix: isolate logs team filter dropdown from root teams state bleed by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/25716
* test(ui): add getCookie to cookieUtils mock in user_dashboard test by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/25719
* [Docs] Add release notes for v1.83.3-stable and v1.83.7.rc.1 by @yuneng-berri in https://github.com/BerriAI/litellm/pull/25723
* fix: default invite user modal global role to least-privilege by @ryan-crabbe-berri in https://github.com/BerriAI/litellm/pull/25721
* [Docs] Regenerate v1.83.3-stable release notes from previous stable by @yuneng-berri in https://github.com/BerriAI/litellm/pull/25726
* [Refactor] Remove Chat UI link from Swagger docs message by @yuneng-berri in https://github.com/BerriAI/litellm/pull/25727
* [Fix] Test - Together AI: replace deprecated Mixtral with serverless Qwen3.5-9B by @yuneng-berri in https://github.com/BerriAI/litellm/pull/25728
* fallbacks image by @shivamrawat1 in https://github.com/BerriAI/litellm/pull/25731
* [Test] Replace flaky bedrock gpt-oss tool-call live test with request-body mock by @yuneng-berri in https://github.com/BerriAI/litellm/pull/25739
* docs update by @shivamrawat1 in https://github.com/BerriAI/litellm/pull/25736
* fix: remove non-existent litellm_mcps_tests_coverage from coverage combine by @joereyna in https://github.com/BerriAI/litellm/pull/25737
* fix(ci): increase test-server-root-path timeout to 30m by @joereyna in https://github.com/BerriAI/litellm/pull/25741
* bump: version 1.83.7 → 1.83.8 by @yuneng-berri in https://github.com/BerriAI/litellm/pull/25730

## New Contributors
* @hunterchris made their first contribution in https://github.com/BerriAI/litellm/pull/20261
* @Dmitry-Kucher made their first contribution in https://github.com/BerriAI/litellm/pull/24998
* @kulia26 made their first contribution in https://github.com/BerriAI/litellm/pull/25071
* @jaxhend made their first contribution in https://github.com/BerriAI/litellm/pull/23532
* @abhyudayareddy made their first contribution in https://github.com/BerriAI/litellm/pull/25337
* @avarga1 made their first contribution in https://github.com/BerriAI/litellm/pull/25263
* @acebot712 made their first contribution in https://github.com/BerriAI/litellm/pull/24268
* @meutsabdahal made their first contribution in https://github.com/BerriAI/litellm/pull/25395

**Full Changelog**: https://github.com/BerriAI/litellm/compare/v1.83.7.rc.1...v1.83.8-nightly