langchain_tool_invocation

Agents can enter infinite tool-calling loops when tool selection logic fails or tools return results that trigger repeated invocations, consuming tokens and delaying responses.

langchain_agent_intermediate_steps counts reasoning/tool-use iterations. Unbounded growth indicates agents spinning on complex tasks, inefficient tool selection, or poor stopping criteria, driving up latency and cost.

langchain_tool_error spikes often reflect downstream API failures, rate limits, or network issues—not application bugs. Treating tool errors in isolation misses the root cause: external service degradation.