●Change8

litellm-pres-dev-v1.81.15

📦 litellmView on GitHub →
✨ 12 features🐛 21 fixes🔧 5 symbols

Summary

This release introduces new features like custom proxy favicons, configurable semantic cache dimensions, and guardrail policy versioning. Numerous bug fixes address issues across Bedrock integration, budget tracking, testing stability, and data normalization.

Migration Steps

  1. If using Bedrock Converse API batch models, verify modelInput format.
  2. If relying on hardcoded timezone maps for budget calculations, note that this has been replaced with ZoneInfo.

✨ New Features

  • Show proxy URL in ModelHub.
  • Add custom favicon support for the LiteLLM proxy.
  • Support configurable vector dimensions for semantic-cache.
  • Add optional digest mode for Slack alert types.
  • Enable context-1m-2025-08-07 beta header for vertex_ai provider (after a revert/re-enable cycle).
  • Introduce Guardrail Policy Versioning.
  • Add Noma guardrails v2 based on custom guardrails.
  • Introduce LiteLLM network mock.
  • Implement Guardrail Monitor to measure guardrail reliability in production.
  • Add Singapore guardrail policies (PDPA + MAS AI Risk Management).
  • Add variant parameter to video content download.
  • Add Blog Dropdown in Navbar for the UI.

🐛 Bug Fixes

  • Correct modelInput format for Bedrock Converse API batch models.
  • Only tag selected deployment in access group creation.
  • Prevent double UUID in create_file S3 key for Bedrock.
  • Normalize camelCase thinking param keys to snake_case in utils.
  • Fix timezone config lookup and replace hardcoded timezone map with ZoneInfo in budget module.
  • Add missing return type annotations to iterator protocol methods in streaming_handler.
  • Avoid mutating caller-owned dicts in SpendUpdateQueue aggregation.
  • Revert enabling context-1m-2025-08-07 beta header for vertex_ai, then re-enable it via a separate fix.
  • Encode model arns for OpenAI compatible bedrock imported models.
  • Ensure arrival_time is set before calculating queue time.
  • Fix Anthropic model wildcard access issue.
  • Fix model cost map for anthropic fast and inference_geo.
  • Add Priority PayGo cost tracking for gemini/vertex ai.
  • Fix StopIteration in prisma self-heal cooldown test.
  • Use absolute path for model_prices JSON validation test.
  • Add INCOMPLETE to interactions status enum expected values for tests.
  • Make RPM limit test sequential to fix race condition.
  • Pass api_key from litellm_params to video remix handlers.
  • Fix Spend Update Queue Aggregation not triggering with default presets.
  • Fix content filter tests.
  • Fix presidio streaming false positives.

Affected Symbols

streaming_handlerSpendUpdateQueuevertex_aibedrockmodel_prices