From aff4c99469ccbc6fae57e19bf3a49b211046a369 Mon Sep 17 00:00:00 2001 From: Ishaan Jaffer Date: Sat, 7 Feb 2026 13:06:51 -0800 Subject: [PATCH] review 1 --- docs/my-website/release_notes/v1.81.9.md | 41 +++++++++--------------- 1 file changed, 15 insertions(+), 26 deletions(-) diff --git a/docs/my-website/release_notes/v1.81.9.md b/docs/my-website/release_notes/v1.81.9.md index f530bcf2079..14f3510ac0f 100644 --- a/docs/my-website/release_notes/v1.81.9.md +++ b/docs/my-website/release_notes/v1.81.9.md @@ -87,7 +87,6 @@ Let's dive in. - **[Google Gemini / Vertex AI](../../docs/providers/gemini)** - Add Gemini Deep Research model support - [PR #20406](https://github.com/BerriAI/litellm/pull/20406) - - Add support for delete and GET via file_id for Gemini - [PR #20329](https://github.com/BerriAI/litellm/pull/20329) - Fix Vertex AI Gemini streaming content_filter handling - [PR #20105](https://github.com/BerriAI/litellm/pull/20105) - Allow using OpenAI-style tools for `web_search` with Vertex AI/Gemini models - [PR #20280](https://github.com/BerriAI/litellm/pull/20280) - Fix `supports_native_streaming` for Gemini and Vertex AI models - [PR #20408](https://github.com/BerriAI/litellm/pull/20408) @@ -109,13 +108,13 @@ Let's dive in. - Add missing capability flags to models - [PR #20276](https://github.com/BerriAI/litellm/pull/20276) - **[GitHub Copilot](../../docs/providers/github_copilot)** - - Preserve system prompts and auto-add headers - [PR #20113](https://github.com/BerriAI/litellm/pull/20113) + - Fix system prompts being dropped and auto-add required Copilot headers - [PR #20113](https://github.com/BerriAI/litellm/pull/20113) - **[GigaChat](../../docs/providers/gigachat)** - - Disable merging of consecutive user messages - [PR #20341](https://github.com/BerriAI/litellm/pull/20341) + - Fix incorrect merging of consecutive user messages for GigaChat provider - [PR #20341](https://github.com/BerriAI/litellm/pull/20341) -- **[xAI](../../docs/providers/xai)** - - Add `/realtime` API support - works with LiveKit SDK - [PR #20381](https://github.com/BerriAI/litellm/pull/20381) +- **[xAI](../../docs/providers/xai_realtime)** + - Add xAI `/realtime` API support - works with LiveKit SDK - [PR #20381](https://github.com/BerriAI/litellm/pull/20381) - **[OpenAI](../../docs/providers/openai)** - Add `gpt-5-search-api` model and docs clarifications - [PR #20512](https://github.com/BerriAI/litellm/pull/20512) @@ -140,7 +139,7 @@ Let's dive in. #### Features -- **[A2A Agent Gateway](../../docs/providers/a2a)** +- **[A2A Agent Gateway](../../docs/a2a)** - Allow calling A2A agents through LiteLLM `/chat/completions` API - [PR #20358](https://github.com/BerriAI/litellm/pull/20358) - Use A2A registered agents with `/chat/completions` - [PR #20362](https://github.com/BerriAI/litellm/pull/20362) - Fix A2A agents deployed with localhost/internal URLs in their agent cards - [PR #20604](https://github.com/BerriAI/litellm/pull/20604) @@ -148,11 +147,7 @@ Let's dive in. - **[Files API](../../docs/providers/gemini)** - Add support for delete and GET via file_id for Gemini - [PR #20329](https://github.com/BerriAI/litellm/pull/20329) -- **[Realtime API](../../docs/providers/xai)** - - Add xAI `/realtime` API support - works with LiveKit SDK - [PR #20381](https://github.com/BerriAI/litellm/pull/20381) - - **General** - - Support 0 cost models - [PR #20249](https://github.com/BerriAI/litellm/pull/20249) - Add User-Agent customization support - [PR #19881](https://github.com/BerriAI/litellm/pull/19881) - Add `proxy_auth` for auto OAuth2/JWT token management in SDK - [PR #20238](https://github.com/BerriAI/litellm/pull/20238) - Fix search tools not found when using per-request routers - [PR #19818](https://github.com/BerriAI/litellm/pull/19818) @@ -192,11 +187,7 @@ Let's dive in. - Navbar: Option to Hide Community Engagement Buttons - [PR #20308](https://github.com/BerriAI/litellm/pull/20308) - Show team alias on Models health page - [PR #20359](https://github.com/BerriAI/litellm/pull/20359) - Admin Settings: Add option for Authentication for public AI Hub - [PR #20444](https://github.com/BerriAI/litellm/pull/20444) - - Refactor Usage Page: Spend By Provider - [PR #20539](https://github.com/BerriAI/litellm/pull/20539) - - Migrate Admin Page to AntD Tabs - [PR #20465](https://github.com/BerriAI/litellm/pull/20465) - Adjust daily spend date filtering for user timezone - [PR #20472](https://github.com/BerriAI/litellm/pull/20472) - - Migrate Ant Design notifications to use `App.useApp()` context - [PR #20549](https://github.com/BerriAI/litellm/pull/20549) - - Update Next.js to 16.1.6 - [PR #20220](https://github.com/BerriAI/litellm/pull/20220) - **SCIM** - Add base `/scim/v2` endpoint for SCIM resource discovery - [PR #20301](https://github.com/BerriAI/litellm/pull/20301) @@ -206,7 +197,7 @@ Let's dive in. #### Bugs -- Remove Key Blocking on Login - [PR #20210](https://github.com/BerriAI/litellm/pull/20210) +- Fix: Remove unnecessary key blocking on UI login that prevented access - [PR #20210](https://github.com/BerriAI/litellm/pull/20210) - UI - Team Settings: Disable Global Guardrail Persistence - [PR #20307](https://github.com/BerriAI/litellm/pull/20307) - UI - Model Info Page: Fix Input and Output Labels - [PR #20462](https://github.com/BerriAI/litellm/pull/20462) - UI - Model Page: Column Resizing on Smaller Screens - [PR #20599](https://github.com/BerriAI/litellm/pull/20599) @@ -217,16 +208,16 @@ Let's dive in. ## Logging / Guardrail / Prompt Management Integrations -#### Features +#### Bug Fixes - **[Langfuse](../../docs/proxy/logging#langfuse)** - - Fix Langfuse OTEL trace - [PR #20382](https://github.com/BerriAI/litellm/pull/20382) + - Fix Langfuse OTEL trace export failing when spans contain null attributes - [PR #20382](https://github.com/BerriAI/litellm/pull/20382) - **[Prometheus](../../docs/proxy/logging#prometheus)** - - Fix failure metrics labels - [PR #20152](https://github.com/BerriAI/litellm/pull/20152) + - Fix incorrect failure metrics labels causing miscounted error rates - [PR #20152](https://github.com/BerriAI/litellm/pull/20152) - **[Slack Alerts](../../docs/proxy/alerting)** - - Fix Slack alert issue - [PR #20257](https://github.com/BerriAI/litellm/pull/20257) + - Fix Slack alert delivery failing for certain budget threshold configurations - [PR #20257](https://github.com/BerriAI/litellm/pull/20257) #### Guardrails @@ -237,10 +228,10 @@ Let's dive in. - **Team-Based Guardrails** - Implement team-based isolation guardrails management - [PR #20318](https://github.com/BerriAI/litellm/pull/20318) -- **[OpenAI Moderations](../../docs/proxy/guardrails)** +- **[OpenAI Moderations](../../docs/apply_guardrail)** - Ensure OpenAI Moderations Guard works with OpenAI Embeddings - [PR #20523](https://github.com/BerriAI/litellm/pull/20523) -- **[GraySwan / Cygnal](../../docs/proxy/guardrails)** +- **[GraySwan / Cygnal](../../docs/apply_guardrail)** - Fix fail-open for GraySwan and pass metadata to Cygnal API endpoint - [PR #19837](https://github.com/BerriAI/litellm/pull/19837) - **General** @@ -250,7 +241,6 @@ Let's dive in. ## Spend Tracking, Budgets and Rate Limiting - **Support 0 cost models** - Allow zero-cost model entries for internal/free-tier models - [PR #20249](https://github.com/BerriAI/litellm/pull/20249) -- **Bedrock tiered caching costs** - Add 1hr tiered caching costs for long-context models - [PR #20214](https://github.com/BerriAI/litellm/pull/20214) ## MCP Gateway @@ -262,7 +252,7 @@ Let's dive in. - **Include Config Defined Search Tools** in `/search_tools/list` - [PR #20371](https://github.com/BerriAI/litellm/pull/20371) - **UI - Search Tools**: Show Config Defined Search Tools - [PR #20436](https://github.com/BerriAI/litellm/pull/20436) - **Ensure MCP permissions are enforced** when using JWT Auth - [PR #20383](https://github.com/BerriAI/litellm/pull/20383) -- **Ensure `gcs_bucket_name` passes** correctly - [PR #20491](https://github.com/BerriAI/litellm/pull/20491) +- **Fix `gcs_bucket_name` not being passed** correctly for MCP server storage configuration - [PR #20491](https://github.com/BerriAI/litellm/pull/20491) ## Performance / Loadbalancing / Reliability improvements @@ -276,9 +266,8 @@ Let's dive in. - **Guard debug log f-strings** and remove redundant dict copies - [PR #19961](https://github.com/BerriAI/litellm/pull/19961) - **Replace enum construction with frozenset lookup** - [PR #20302](https://github.com/BerriAI/litellm/pull/20302) - **Guard debug f-string in `update_environment_variables`** - [PR #20360](https://github.com/BerriAI/litellm/pull/20360) -- **Warn when budget lookup fails**; cache won't populate - [PR #20545](https://github.com/BerriAI/litellm/pull/20545) -- **Add INFO-level session reuse logging** per request - [PR #20597](https://github.com/BerriAI/litellm/pull/20597) -- **Add faster linting targets** for development workflow - [PR #19729](https://github.com/BerriAI/litellm/pull/19729) +- **Warn when budget lookup fails** to surface silent caching misses - [PR #20545](https://github.com/BerriAI/litellm/pull/20545) +- **Add INFO-level session reuse logging** per request for better observability - [PR #20597](https://github.com/BerriAI/litellm/pull/20597) ## Database Changes