Agents Langgraph

Integrator wants a tool-calling agent and hand-builds a StateGraph from scratch, reimplementing the model/tool loop and introducing routing bugs.

Use langgraph.prebuilt.create_react_agent(model, tools) for the standard ReAct tool-calling loop; it wires the model node, ToolNode, and conditional routing back to the model. Drop to a custom StateGraph only when the prebuilt loop is insufficient.

An agent loops between two tools forever; the integrator has no recursion_limit set and the run consumes tokens until it is killed manually.

Set a sensible recursion_limit in the config so LangGraph raises GraphRecursionError when the step budget is exceeded, then handle it (surface to the user / inspect state). Do not raise the limit blindly to 'make it finish' — investigate the loop.

Integrator builds a new agent on the legacy AgentExecutor / initialize_agent path and expects checkpointing and interrupts to work.

Prefer the LangGraph agent (create_react_agent) for new builds; the legacy AgentExecutor is maintained but does not offer LangGraph's persistence, streaming, and interrupt features. If maintaining legacy code, do not assume LangGraph capabilities are present.