memory_guard_after
Record a completed tool action against its preflight receipt to validate evidence, store redacted input/output traces, and update the agent's memory for future guard decisions.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | Working directory at the time of the action. | |
| tool | No | Tool or command family that completed, e.g. Bash, npm test, Edit, deploy. | |
| files | No | File paths to fingerprint (size + mtime + content hash). | |
| input | No | Tool input. Hashed and never stored raw; redacted metadata is only stored when retain_details is true. | |
| output | No | Tool output. Same redaction and storage policy as input. | |
| outcome | No | Outcome classification | |
| metadata | No | Arbitrary structured metadata (redacted before storage). | |
| receipt_id | Yes | Receipt id returned by memory_guard_before. | |
| session_id | No | Session identifier for grouping related guard events. | |
| error_summary | No | Short error description if the action failed. Redacted and truncated to 2 KB. | |
| retain_details | No | If true, redacted input and output payloads are stored alongside hashes. Defaults to false. | |
| override_reason | No | Reason for recording a succeeded outcome against a Guard receipt that blocked for a reason other than an exact-repeated failure. Not needed for acknowledged exact-failure retries. | |
| evidence_feedback | No | Map of evidence ids from the guard receipt to memory validation outcomes. |