Bump Assistent to 0.7.0: Config personas, skills, and vector memory.

Move prompts into Config/_base and persona folders; seed model facts into SQLite via Ollama embed and retrieve as memory_hits each turn.

Co-authored-by: Cursor <cursoragent@cursor.com>

Config/_base/skills/creativity_sliders.json

@@ -0,0 +1,6 @@
+{
+  "id": "creativity_sliders",
+  "title": "Creativity lexicon",
+  "default": true,
+  "prompt_file": "creativity_sliders.md"
+}

Config/_base/skills/creativity_sliders.md

@@ -0,0 +1,4 @@
+# Skill: creativity & sliders (LLM-only)
+
+- `creativity`: `raw` | `low` | `medium` | `high` — how much **you** expand the user's wording into the prompt. Not a SwarmUI field.
+- Optional `intensity` / `complexity` / `movement` (−100..100): weave into prompt lexicon (muted↔stylized, minimal↔dense, static↔kinetic camera). Do not invent UI sliders.

Config/_base/skills/memory.json

@@ -0,0 +1,6 @@
+{
+  "id": "memory",
+  "title": "Vector memory",
+  "default": true,
+  "prompt_file": "memory.md"
+}

Config/_base/skills/memory.md

@@ -0,0 +1,16 @@
+# Skill: memory
+
+You have a persistent vector memory (`memory_hits` in live context).
+
+## When to write
+
+- 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 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.

Config/_base/skills/prompting.json

@@ -0,0 +1,6 @@
+{
+  "id": "prompting",
+  "title": "Prompt craft",
+  "default": true,
+  "prompt_file": "prompting.md"
+}

Config/_base/skills/prompting.md

@@ -0,0 +1,9 @@
+# Skill: prompting
+
+Write **natural prose** for a photographer/director — not Danbooru tags, not `(word:1.5)`, not `masterpiece / best quality / 8k`.
+
+Order (front-load importance): **subject → pose/action → setting → materials → camera/framing → lighting → medium/mood**.
+
+- Short user ideas: expand. Finished Krea-style paragraphs: keep wording; only fix anti-patterns.
+- Put LoRA trigger phrases near the subject they affect.
+- Prefer positives over negatives.