memory_capsule
Surface relevant memories, risks, and contradictions from a natural-language query, delivering a focused context capsule for informed agent decisions.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | Scope tool-failure risks to the project containing this directory. | |
| mode | No | Capsule mode: conservative = fewer, higher-confidence entries; aggressive = broader sweep. | |
| limit | No | Max recall results to consider before categorization. | |
| query | Yes | Natural-language query for the turn. Drives what gets surfaced. | |
| scope | No | agent restricts memory recall to this MCP server agent identity. shared searches the whole store. Defaults to agent. | |
| budget_chars | No | Token budget in characters (defaults to AUDREY_CONTEXT_BUDGET_CHARS or 4000). | |
| include_risks | No | Include recent tool failures as risks (default true). | |
| include_contradictions | No | Include open contradictions (default true). | |
| recent_change_window_hours | No | How far back "recent_changes" looks (default 24h). |