Skip to main content
GET
Get a message's execution trace

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

messageId
string
required

The message id, from getConversationSummary's message list.

Query Parameters

conversationId
string
required

The conversation this message belongs to.

Response

The trace, lean-projected. trace is absent when Langfuse has not ingested it yet for this message — retry shortly, this is not an error.

The execution tree behind one processed message — steps, agent hand-offs, tool calls, routing decision, timing and errors — plus the model's persisted decision record (modelDecision): the sections it saw and used, the classifier routing, and the written reasoning. A LEAN projection: prompt/generation CONTENTS and section CONTENT are never included.

messageId
string
required

The message this trace was resolved for — from getConversationSummary's message list.

Example:

"6683f1c2a4b19e0012ab34cd"

projectName
string
required

The ClaudIA project this trace belongs to.

Example:

"acme_support"

conversationId
string
required

The conversation this message belongs to — the same id you passed as conversationId.

Example:

"3f1c8a52-1c4e-4d0a-9a1b-2f6de2a3c111"

assistants
object
required

Directory of the agents that ran, keyed by assistant_id/agent_id, so an observation's metadata.assistant_id can be resolved to a display name and role. Empty when there is no trace yet, or the directory could not be resolved.

trace
object | null

The trace itself. Absent when Langfuse has not ingested it yet for this message — retry shortly, this is not an error.

judge
object | null

The routing judge's validated decision for this message. Absent when the trace has no judge observation — a non-agentic path, or a trace predating this instrumentation.

modelDecision
object | null

What the model saw and used to produce this reply: the sections retrieved (with score and selection flags), the ids it declared it used, the classifier's routing, and the model's own written reasoning. Read from ClaudIA's persisted decision record, independent of the Langfuse trace — it can be present when trace is still absent. Absent for a message that has no decision record (e.g. a customer turn, or a reply the platform did not audit).