Likely-prompt queries for saved facts
memory_queriesGenerate likely user prompts for saved facts so recall matches real queries; list facts missing queries or store up to 8 prompts per fact.
Instructions
Write, or list the facts that still lack, the likely-prompt queries recall matches a user's prompt against — for each fact, the prompts a user would type when that fact is what they need. Call it with {} at the end of a session that saved facts, or when bantamkit_status reports queries: n of m facts with n below m: it answers up to 10 facts with no queries yet (layer, name, description, a body excerpt), the writing instructions, and remaining. Then call it with {"facts": [{name, layer?, queries}]} to store what you wrote. Every item is checked before anything is written and the first bad one refuses the whole call — an unknown name or layer, more than 8 queries, one over 200 characters; queries: [] removes a fact's entry. No fact file changes: queries live in a per-layer sidecar under ~/.bantamkit/queries/, keyed to the fact's content, so a fact edited later is listed as missing again. memory_save takes queries directly for a fact you are saving now; this tool is for facts already on disk.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| facts | No | Omit to list the facts missing queries |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| facts | No | With `missing`: up to 10 {layer, name, description, body} still without queries. | |
| reason | No | With result `error`: one sentence saying why the call was refused. | |
| result | Yes | `missing` for the list call, `written` for the store call, `error` with `reason` when refused. | |
| written | No | With `written`: how many items were stored. | |
| remaining | No | How many facts across the readable layers still have no queries after this call. | |
| instructions | No | With `missing`: how to write good queries. |