Repository Issue Activity (beta)

#2607 GenAI templating drops thought metadata from text parts

#2603 `prepare_response_model` creates a new Pydantic class on every request, leaking one model class + validator per call

#2221 Structured outputs look authoritative but carry no trust signal — thoughts on metadata?

#2585 AutoCache/DiskCache key ignores temperature/seed/etc. — calls that only differ in sampling params silently return a stale cached response

#2580 v2 GenAI handlers regression: cached_content requests now include system_instruction/tools/tool_config → 400 INVALID_ARGUMENT

#2528 Your code contains @async_model_validator and @async_field_validator, but it seems to be dead code

#2576 OpenAI-compat: from_openai Mode.JSON with base_url /v1, not from_provider openai/

#2590 [HTTPXodus] Support `httpx2` in the OpenAI 3 path (complement to #2583)

#2567 TypedDict response_model ignores total=False and NotRequired, forcing every key to be required

#2526 merge_consecutive_messages drops tool-call fields from conversation history

#2535 from_litellm raises RegistryError when several threads make their first structured call concurrently

#2553 Adding support to openai v3.x.x

#2408 feat(bedrock): support Amazon Bedrock API key (bearer token) authentication

#2056 Security: Retry amplification and LLM validator injection findings

#2391 feat: expose cumulative token usage on successful responses + budget enforcement

#2365 Mistral AI v2 support

#2084 feat(bedrock): Add support for AWS Bedrock native structured outputs

#2076 Allow MD_JSON for bedrock client

#2404 feat: Add persistent memory cookbook with Dakera integration

#2403 Feature: Memory-backed extraction — recall past structured outputs for few-shot context

#2383 Add Azure AI Foundry as a first-class v2 provider

#2316 Feature request: OWASP ASI06 memory poisoning defense for structured output agents

#2272 Token-efficient serialization to reduce structured output overhead in production pipelines

#2260 feat: add MiniMax provider support

#2393 feat: schema complexity pre-flight analysis and automatic mode selection