remember_server_finding
Save and recall server-specific findings like misconfigured crons, hidden dependencies, or port blocks not visible in fresh probes. Automatically inject relevant findings into future context based on confidence.
Instructions
Persist a hard-won, non-obvious discovery (quirk, gotcha, root-cause, constraint) about an instance that is NOT visible in a fresh probe — e.g. a misconfigured cron, a hidden dependency, a port blocked by an upstream policy, a bug triggered only under load. Saved locally immediately and queued for end-to-end encrypted sync. The title is the searchable recall key — keep it short and specific. Returns {finding_id, instance_id, title, auto_inject, superseded, secret_warning}. auto_inject=true means the title will be surfaced automatically in future context (confidence >= threshold); false = recall-only.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| instance_id | Yes | Instance ID, name, or custom-server name. | |
| title | Yes | Short, searchable title for this finding (≤200 chars). This is the primary recall key — make it specific. | |
| body | Yes | Full finding text, evidence, and context (≤8000 chars). | |
| tags | No | Optional tags for filtering (max 12, lowercased). | |
| confidence | No | Confidence score 0.0–1.0. Values >= threshold (default 0.6) cause the title to be auto-injected into future context; lower values are recall-only. | |
| supersede_id | No | ID of an existing finding this corrects or replaces. The old finding is marked superseded; pass the finding_id returned by a previous remember_server_finding call. |