memory_reflexes
Check past tool outcomes against planned actions to flag risky or repeated failures before execution. Set proactive warnings that recommend safer alternatives or block high-risk moves.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | Working directory for the action. | |
| mode | No | Underlying capsule mode. Defaults to conservative. | |
| tool | No | Tool or command family about to be used, e.g. Bash, npm test, Edit, deploy. | |
| files | No | File paths to fingerprint if record_event is true. | |
| limit | No | Max recall results to consider before preflight categorization. | |
| scope | No | agent restricts memory recall to this server agent identity. shared searches the whole store. Defaults to agent. | |
| action | Yes | Natural-language description of the action the agent is about to take. | |
| strict | No | If true, high-severity memory warnings produce decision=block instead of caution. | |
| session_id | No | Session identifier for grouping the optional preflight event. | |
| budget_chars | No | Capsule budget in characters. | |
| record_event | No | Record a redacted PreToolUse event for this preflight. Defaults to false. | |
| include_status | No | Include memory health in the response and warning calculation. Defaults to true. | |
| include_capsule | No | If false, omit the embedded Memory Capsule from the response. | |
| include_preflight | No | If true, include the full underlying preflight report. | |
| failure_window_hours | No | How far back to check failed tool events. Defaults to 168 hours. |