Create Session Eval Run
Create a filter-based session eval run.
Resolves sessions matching the provided filters, then dispatches a background Celery task that computes trace-level signals and aggregates them into session-level metrics.
Auth: Bearer + X-Project-ID | X-API-Key + X-Project-Name
Rate limit: 50/min
Documentation Index
Fetch the complete documentation index at: https://docs.pandaprobe.com/llms.txt
Use this file to discover all available pages before exploring further.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Create a filter-based session eval run.
Session metric names (e.g. ['agent_reliability']).
1Human-readable label.
Filters for session-level evaluation runs.
Fraction of sessions to evaluate.
0 <= x <= 1LLM model override for judge calls.
Override default signal weights.
Response
Successful Response
Full eval run representation used by both list and detail endpoints.
Lifecycle status of an evaluation job.
PENDING, RUNNING, COMPLETED, FAILED 
