Skip to main content
POST /reset is always the first call you make. It generates a new episode UUID, loads the appropriate messy CRM dataset for the configured task, snapshots the hidden ground truth into isolated per-episode server memory keyed by that UUID, and returns an initial CRMPipelineObservation. All in-memory Pandas DataFrames are freshly copied so that concurrent episodes cannot corrupt each other’s state.

Task Selection

The task loaded is controlled by the TASK_ID environment variable set on the server process. You do not pass this in the request body.
To switch tasks, set TASK_ID=t2 (or t3) in your Docker environment or shell before starting the server. A running server uses the value frozen at the time of the /reset call.

Request

POST /reset accepts an empty JSON body. No fields are required.

Response

The response always wraps a CRMPipelineObservation object alongside top-level convenience scalars.

Task 1 (t1) — Single Source

Task 2 (t2) — Two Sources

Task 3 (t3) — Three Sources with Conflict Rules

Response Fields

object
required
The full CRMPipelineObservation object representing the initial environment state.
float
Top-level convenience mirror of observation.reward. Always 0.0 after reset.
boolean
Top-level convenience mirror of observation.done. Always false after reset.

Extracting the Episode UUID

The episode UUID embedded in last_action_feedback is the key you pass to /grader/{episode_id}. Parse it out immediately:
You can also read it from GET /state at any point during the episode:
Each call to POST /reset creates a completely new episode and a new UUID. Calling /reset mid-episode discards all progress and all in-memory DataFrames accumulated from prior /step calls. The old episode’s ground truth snapshot is retained in server memory under the old UUID, but the active environment context is overwritten and the old UUID can no longer be used for new /step actions.