Agent Frameworks
LangChain, LlamaIndex, and Pydantic
- high`create_agent` should support bounded forced retry after tool invocation validation errors
- highClearToolUsesEdit does not persist cleared state with checkpointer, causing eviction every turn
- highResponses API: parsed_arguments leaks from ParsedResponseFunctionToolCall into AIMessage content, breaking the next turn
- highShellSession times out when command output lacks trailing newline
- highAgent factory `_execute_model_async` uses non-streaming `ainvoke`, preventing `on_llm_new_token` callbacks
