ck_outcome_tracker
Capture session outcomes and fetch performance leaderboards to close the reinforcement-learning loop, enabling data-driven routing decisions.
Instructions
Record session outcomes or retrieve agent performance leaderboards to close the reinforcement-learning feedback loop. Three modes: record persists a session outcome (write operation); get_session reads a specific outcome by session_id (read-only); get_leaderboard returns ranked agent performance (read-only). For record mode: pass session_id, outcome (success/partial/failure), agent_id, and task_type. For get_leaderboard: pass workspace_id and optional window (days) and limit. Call after task completion before ending the session so ck_route and ck_cost_optimizer have fresh performance data for future routing decisions.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes | Operation mode that determines the tool behavior and return shape. | |
| limit | No | Maximum number of results to return. | |
| window | No | ||
| outcome | No | Result classification of the operation. | |
| agent_id | No | ||
| task_type | No | ||
| session_id | No | Unique session identifier for correlating findings, proofs, budget, and audit trail. | |
| workspace_id | No | Workspace identifier for cross-session scope. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | ||
| entries | No | ||
| outcomes | No | ||
| recorded | No |