fetch_traces
Filter and retrieve traces from Langfuse observability platform by age, name, user ID, session ID, metadata, or tags for debugging and analysis of LLM applications.
Instructions
Find traces based on filters. All filter parameters are optional.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| age | Yes | Minutes ago to start looking (e.g., 1440 for 24 hours) | |
| name | No | Name of the trace to filter by | |
| user_id | No | User ID to filter traces by | |
| session_id | No | Session ID to filter traces by | |
| metadata | No | Metadata fields to filter by | |
| page | No | Page number for pagination (starts at 1) | |
| limit | No | Maximum number of traces to return per page | |
| tags | No | Tag or comma-separated list of tags to filter traces by | |
| include_observations | No | If True, fetch and include the full observation objects instead of just IDs. Use this when you need access to system prompts, model parameters, or other details stored within observations. Significantly increases response time but provides complete data. | |
| output_mode | No | Controls the output format: 'compact' (default) returns summarized JSON, 'full_json_string' returns complete raw JSON as string, 'full_json_file' saves complete data to file and returns summary with path. | compact |