SummarizationMiddleware

This release introduces significant improvements to the MCP (Multi-modal Conversational Protocol) handling, including new elicitation features and tool conversion. It also brings general bug fixes and refactors across various components.

This release introduces new features like exposing `trace_policy` on `AgentMiddleware` and adding `reasoning_effort` as a chat model parameter. It also includes several bug fixes, such as preserving history on summarization failures and handling malformed structured-output responses.

This release introduces AND-capable trigger conditions for `SummarizationMiddleware` and adds support for the `apply_patch` tool in OpenAI. It also updates several underlying dependencies.

This release introduces significant updates to streaming protocols (v2 and v3), enhances agent capabilities with new middleware features, and includes numerous dependency bumps and bug fixes across various components.

This release includes numerous performance improvements, dependency bumps, and feature additions like content-block-centric streaming (v2) and integration of stream_events(version='v3'). Several bug fixes address token counting, model recognition, and middleware configuration.

LangChain version 1.2.9 introduces support for state updates via `wrap_model_call` and threading context in agent flows, alongside several bug fixes related to schema normalization and token counting.

LangChain version 1.2.7 introduces dynamic tool registration through middleware and includes minor fixes to the summarization prompt and system message grammar.

This release primarily addresses a bug fix related to the signature and configuration invocation of the SummarizationMiddleware.

This release introduces UUIDv7 for run IDs and improves the accuracy of the SummarizationMiddleware by adjusting token counts based on the specific model used.

LangChain 1.1 introduces ModelRetryMiddleware, enhanced SummarizationMiddleware with context window support, and SystemMessage support in agent creation. It also includes critical fixes for tool call ordering and Anthropic tool execution.