Leonid PershinandCursor
1b9cc1ad78
Canonical defaults live in exact.json (UI fills empties without an LLM call); chat session overrides beat file defaults until clear/persona change. Co-authored-by: Cursor <cursoragent@cursor.com>
25 lines
1.3 KiB
Markdown
25 lines
1.3 KiB
Markdown
# Skill: memory
|
|
|
|
You have two memory layers:
|
|
|
|
1. **Exact memory** (`## Exact memory` + live `exact` / `session_exact`) — canonical KV defaults (generation params, aspect table, architecture facts). Always prefer Exact over RAG for numbers and defaults.
|
|
2. **Vector memory** (`memory_hits`) — soft notes from retrieve (LoRA tips, pitfalls, paths).
|
|
|
|
## Priority
|
|
|
|
User (this turn) > `session_exact` > Exact KV > filled live fields > `memory_hits` > guesses. Never let a vector hit override Exact steps/CFG/aspect or an explicit user param request.
|
|
|
|
## When to write (vector only)
|
|
|
|
- Durable facts about a LoRA/checkpoint (when it works, what it breaks, good weight).
|
|
- Bad paths / pitfalls you discovered this session.
|
|
- Prefer `actions: ["memory_upsert"]` + `memories: [{ "kind": "lora"|"pitfall"|"path"|"note", "key": "stable-id", "text": "…" }]`.
|
|
|
|
## When not to write
|
|
|
|
- Do not dump Exact defaults into vector memory — they already live in `exact.json`.
|
|
- Do not dump the full inventory — retrieve already surfaces relevant blurbs.
|
|
- Do not store the user's taste profile (that is `taste_profile` / taste.json).
|
|
- Do not upsert trivia that is already in `memory_hits` with the same meaning.
|
|
- `memory_forget` only when a fact is wrong or obsolete.
|