fetch_traces
Retrieve paginated Langfuse traces to monitor LLM pipeline executions with filtering by user, session, tags, and time range for observability analysis.
Instructions
Returns a paginated list of Langfuse traces.
Each trace represents one end-to-end LLM pipeline execution. The response includes: id, name, userId, sessionId, level (DEFAULT | DEBUG | WARNING | ERROR), latency (seconds), totalTokens, totalCost (USD), tags, timestamp.
All filter parameters are optional. Omit any filter you do not need — omitted filters are ignored and do not narrow the result set.
Pagination: page is 1-based (default 1), limit controls page size (default 20, max 100). To page through results, increment page while keeping limit fixed.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| page | Yes | Page number, 1-based. Omit to use default (1). | |
| limit | Yes | Results per page, max 100. Omit to use default (20). | |
| userId | Yes | Filter by the Langfuse user ID attached to the trace. Omit to return traces for all users. | |
| name | Yes | Filter by trace name — must be an exact string match. Omit to return all trace names. | |
| sessionId | Yes | Filter by session ID to return only traces belonging to that session. Omit to return traces across all sessions. | |
| tags | Yes | Filter by a single tag string. Omit to return traces regardless of tags. | |
| fromTimestamp | Yes | Start of time range in ISO-8601 format, e.g. 2025-01-01T00:00:00Z. Omit to include traces from the beginning of the project. | |
| toTimestamp | Yes | End of time range in ISO-8601 format, e.g. 2025-12-31T23:59:59Z. Omit to include traces up to the current time. |