litellm_presidio-dev-v1.81.15
📦 litellmView on GitHub →
✨ 8 features🐛 16 fixes🔧 3 symbols
Summary
This release introduces new features like custom favicon support for the proxy, configurable semantic cache dimensions, and guardrail monitoring. It also includes numerous bug fixes across providers like Bedrock and Anthropic, and utility improvements like parameter key normalization.
Migration Steps
- If you rely on camelCase keys for thinking parameters, ensure they are now passed as snake_case due to normalization in utils.
✨ New Features
- Show proxy URL in ModelHub.
- Add custom favicon support for the proxy.
- Support configurable vector dimensions for semantic-cache.
- Add optional digest mode for Slack alert types.
- Enable Guardrail Policy Versioning.
- Add Noma guardrails v2 based on custom guardrails.
- Introduce Litellm network mock.
- Implement Guardrail Monitor to measure guardrail reliability in production.
🐛 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 handling.
- 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 specific fix.
- Encode model ARNs for OpenAI compatible Bedrock imported models.
- Support optional regional STS endpoint in role assumption for Bedrock.
- Ensure arrival_time is set before calculating queue time.
- 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.
- Fix Anthropic model wildcard access issue.