Overview
The@fiddler-ai/langgraph package provides OpenTelemetry-based
instrumentation for LangGraph JS applications, enabling automatic
trace capture for agentic workflows monitored by Fiddler AI observability.
Mirrors the Python fiddler-langgraph SDK API.
Components
Callback-Handler
The LangChain callback handler that emits Fiddler spans.FiddlerCallbackHandler hooks into LangGraph/LangChain run-lifecycle events and translates them into OpenTelemetry spans.
Context
Conversation, session, and retrieval-context helpers.setConversationId/getConversationId tag spans with a conversation ID, addSessionAttributes/getSessionAttributes attach session-wide attributes, setLlmContext/getLlmContext attach retrieval context, and runWithContext scopes them to a callback.
- addSessionAttributes
- getConversationId
- getLlmContext
- getSessionAttributes
- runWithContext
- setConversationId
- setLlmContext
Instrumentor
One-time instrumentation setup.LangGraphInstrumentor patches the LangChain callback manager (CallbackManagerModule) so every LangGraph run automatically emits Fiddler spans.
Utils
Internal helpers for span serialization and formatting — message formatting (formatMessages, extractTextContent), provider detection (getProviderFromModel), and safe truncation/stringification (truncate, safeStringify).