Part of CLPI Phase 2: Card Lifecycle & Trust Recovery. The Reclassification API enables violation reclassification and trust score recovery.
Endpoints
POST /agents/{agent_id}/reclassify
Reclassify a checkpoint’s verdict (to
clear, review_needed, or boundary_violation), optionally linked to a card amendment that closed the gap.POST /reputation/{agent_id}/recompute
Recompute an agent’s Trust Rating immediately, reflecting any reclassifications applied since the last computation.
GET /agents/{agent_id}/compliance-export
Export an agent’s compliance record (JSON or CSV, optionally scoped to a
from/to date range) for audit purposes.GET /agents/{agent_id}/reclassifications
List an agent’s reclassification history, paginated with
limit/offset.GET /agents/{agent_id}/card-amendments
List an agent’s alignment-card amendment history, paginated with
limit/offset.SDK usage
@mnemom/sdk does not yet include dedicated helpers for reclassification, score recomputation, or compliance export. Call these endpoints directly over HTTP:
See also
- Card Lifecycle — reclassification concepts and trust graph propagation
- Trust Recovery Guide — step-by-step workflow
- Reputation Scores — score computation
- Policy API — evaluating a card’s policy