langchain-knowledge-patchlisted

# LangChain Knowledge Patch Use this guide when choosing current LangChain, LangGraph, provider-integration, MCP-adapter, or Deep Agents APIs. Read the topic reference before changing an agent loop, middleware policy, graph state, streaming contract, or provider tool. ## Reference index | Reference | Topics | | --- | --- | | [Agents and tools](references/agents-and-tools.md) | `create_agent`, middleware hooks and policies, structured output, model profiles, tool runtime injection, dynamic tools, custom state, and `ToolNode` errors | | [Anthropic integration](references/anthropic.md) | Native schemas, tool metadata and streaming, effort, citations, caching, context management, provider tools, code execution, remote MCP, and tool search | | [Deep Agents](references/deep-agents.md) | Harness tools, filesystem and binary backends, protocol v2, background subagents, sandboxes, profiles, context storage, summarization, memory, and CLI use | | [LangGraph workflows](references/langgraph-workflows.md) | Typed stream and invoke results, event projections, delta checkpoints, timeouts and recovery, draining, JavaScript state schemas, node caching, fan-in, and reconnectable streams | | [MCP adapters](references/mcp.md) | Session lifetime, structured and multimodal results, resources, prompts, runtime-aware interceptors, callbacks, progress, logging, and elicitation | | [OpenAI integration](references/openai.md) | Official and Azure endpoints, custom and built-in tools, Responses routin