Ship Assistent 0.14.1: Exact generate params and cheap park/warm.

Client always merges Exact turbo|raw steps/cfg/sigma before Generate so sparse LLM omissions and leftover SD 20/7 cannot stick; Ollama park/warm skip no-op /api/ps round-trips when the chat model is already unloaded or resident.

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

Config/_base/core/core.md

@@ -16,7 +16,9 @@ When instructions conflict, apply this order (highest wins):
 
 Exact = defaults encyclopedia. About the user = human taste. Session = what Generate will run. Soft craft notes may appear in context from the server — never override Exact, About the user, or the user’s param request.
 
-**Sparse deltas only.** Do **not** re-emit `steps` / `cfg` / `sigma_shift` / `aspect` / full `prompt` when they already match the session and the user did not ask to change them.
+**Sparse deltas only.** Do **not** re-emit `steps` / `cfg` / `sigma_shift` / `aspect` / full `prompt` when they already match the session **and** Exact / `krea_profile` defaults, and the user did not ask to change them.
+
+When `"generate": true` (or legacy `actions:["generate"]`): omitting `steps` / `cfg` / `sigma_shift` is **safe** — the client always merges Exact `profiles.turbo` or `profiles.raw` for the live checkpoint before Generate. Prefer still emitting Exact numbers if live session has foreign leftovers (e.g. steps 20 / cfg 7 vs turbo 8 / 1) so the session stays honest. Never CFG 0.
 
 Never write a “JSON Patch” section in prose without an actual fenced ```json``` object. An empty `### JSON Patch` header is a failure — omit the section or emit a real fence. Chat prose may stay RU; **`prompt` must be English** (Krea 2). Keep prose short. **After the closing ``` of the JSON fence, STOP.** **One turn = one patch.** Several options → `variants` (2–4). Prompt structure lives in skill `prompting`.
 
@@ -57,6 +59,7 @@ Several options (still one fence):
 ### Patch rules
 
 - Omit unchanged params. Include `negative` when starting Generate if live/session negative is empty or the scene needs a specific omit.
+- On Generate, omitting `steps`/`cfg`/`sigma_shift` is fine — the UI applies Exact turbo|raw for the checkpoint. Prefer re-emitting them only when changing profile or the user requested numbers.
 - `loras` replaces the full intended set for this chat when you change LoRAs.
 - Prefer `aspect` over raw width/height.
 - Optional: seed, vary, init/mask, controls, pack, `variants`.

Config/_base/exact.json

@@ -34,7 +34,7 @@
     "prompt_language": "Chat model always prep's Generate prompt for Krea: English natural prose for Qwen3-VL, structured (subject→pose→setting→camera→light). Chat may be RU; never leave Russian or thin drafts in patch.prompt.",
     "negatives": "Qwen3-VL negatives are weak — still keep a short Swarm negative box. Prefer positives in `prompt`; for `negative`: create if live is empty (Exact generation.negative), lightly supplement if the scene needs a specific omit, or echo live unchanged. Never drop/clear the box on Generate. Built-in NSFW text-refiner may strip risque words; LoRAs/finetunes may restore — stay practical.",
     "prompt_images": "Prompt Images (refs in the prompt box) often overpower text — use sparingly and warn. Init Image = structure (img2img). Mask = local fix. They are not interchangeable. Cloud-only features (moodboards, Generative Sliders) are not in Swarm — emulate with prompt language + board refs.",
-    "turbo": "Krea 2 Turbo defaults live in exact.generation / exact.profiles.turbo. Never use CFG 0 — broken output. Side ~1024 (128–4096 OK).",
-    "raw": "Krea 2 RAW/Base: prefer exact.profiles.raw when checkpoint name/title looks like RAW (not Turbo). If a turbo LoRA exists, weight ~0.6 for photoreal (1.0 ≈ full turbo). Swarm Generate cannot run dual-sampler Comfy graphs — only suggest LoRA weight + steps/CFG the UI can set."
+    "turbo": "Krea 2 Turbo defaults live in exact.generation / exact.profiles.turbo. Never use CFG 0 — broken output. Side ~1024 (128–4096 OK). Checkpoint name must contain turbo to claim this profile.",
+    "raw": "Krea 2 RAW/Base: use when checkpoint name/title has raw, or when the name has neither turbo nor raw (e.g. realismByStableYogi finetunes). Prefer exact.profiles.raw. If a turbo LoRA exists, weight ~0.6 for photoreal (1.0 ≈ full turbo). Swarm Generate cannot run dual-sampler Comfy graphs — only suggest LoRA weight + steps/CFG the UI can set."
   }
 }

Config/_base/packs/compose_scene.md

@@ -15,4 +15,5 @@ Goal: co-create a scene / moodboard direction for **Krea 2** (local Swarm).
 ## Deliverable
 
 - Scene brief + JSON patch (`prompt`, optional `loras`, optional `aspect`).
-- `actions: ["generate"]` when ready to try the scene.
+- `actions: ["generate"]` / `"generate": true` when ready to try the scene.
+- Omitting `steps` / `cfg` / `sigma_shift` is safe — the client fills Exact turbo|raw for the live checkpoint. Prefer including them when live session disagrees with `krea_profile` (keeps the session honest).

Config/_base/packs/fix_params.md

@@ -5,7 +5,7 @@ Goal: adjust **generation parameters** for Krea 2 Turbo (or RAW if context says
 ## Guidelines
 
 - Prefer **Exact memory** (`profiles.turbo` / `profiles.raw`), live `recommended_params`, and `session_exact` over invented numbers. Never CFG 0.
-- Prefer live context field `krea_profile` (`turbo` | `raw`) when present.
+- Prefer live context field `krea_profile` (`turbo` | `raw`) when present. On Generate the client also fills Exact turbo|raw when the patch omits steps/cfg/sigma — emit those fields when you are changing them. If session steps/cfg disagree with that profile (leftover 20/7), patch Exact numbers even under a sparse delta.
 - **Aspect:** prefer patch field `aspect` from Exact `aspect_table` — UI maps to official 1K sizes. Else set width/height near 1024.
 - **Batch:** `images` or `batch` (1–4 typical).
 - **Seed:** `lock_seed: true` to reuse current; `vary: true` or `seed: -1` for a new roll; set numeric `seed` for exact reproducibility.

Config/_base/packs/ordinary.md

@@ -6,7 +6,7 @@ Default all-rounder. Handle this turn from the user message + **chat session** c
 
 - **Write / improve prompt** → sparse JSON with only changed fields (`prompt`, optional `negative`/`loras`) and `"generate": true` when they want a **new frame**. Chat / «нравится» / Q&A → prose only, **no** JSON. Do **not** `look_at` the last frame first.
 - **Light critique** → only when they ask to look / critique. Then `look_at: ["generate"]` if pixels are not already in the request.
-- **Params** → only when they ask (steps/CFG/aspect/seed); omit session-matching numbers otherwise.
+- **Params** → only when they ask (steps/CFG/aspect/seed); omit session-matching numbers otherwise. Exception: if live steps/cfg disagree with Exact/`krea_profile` (e.g. 20/7 under turbo), include Exact profile numbers when generating.
 - **Inpaint / img2img** → set init/mask fields when they ask.
 - Need full settings or LoRA list → `"ask": ["settings"]` or `"ask": ["inventory"]` (no other tool hops).