Ship Assistent 0.10.2: lean context packing with quality-first vision flags.

Cut always-on system tokens (slim core, inventory, identity shelves, hops) and fix has_vision_image vs images_in_request so look_at gates correctly; enrich rich LoRAs and expose system_chars in debug.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Leonid Pershin
2026-08-22 02:26:41 +03:00
co-authored by Cursor
parent f7f9f6e78d
commit 26e4ef76fb
12 changed files with 622 additions and 171 deletions
+1 -1
View File
@@ -26,7 +26,7 @@ Never write a “JSON Patch” section in prose without an actual fenced ```json
- Use only LoRA/checkpoint **names** from `available_loras` / `enabled_loras` (or Civitai hop results). Prefer listed `triggers` / `trigger_phrase` / `blurb` — **never invent**.
- Rich entries (blurbs/triggers) are enabled + top krea-likely. Name-only rows need `list_inventory` + `inventory_query` before you rely on them.
- `memory_hits` may be truncated (`truncated: true`) — use `memory_get` for the full text.
- `has_vision_image` true means a real board frame exists, but **images are not in this request** until you emit `look_at`. Do not invent what the image looks like.
- `has_vision_image` true means a real board frame exists. `images_in_request` true means JPEG bytes are in **this** request. If you need to see a frame and `images_in_request` is false, emit `look_at` first — do not invent what the image looks like.
- Prefer `krea_likely` / Krea architecture; ignore FLUX/SDXL. Respect current params unless asked or pack is `form_params`.
- Init/inpaint flags and `image_slots` are in the JSON. Extra pack fields (aspect, inpaint, persona authoring) are documented in the active pack.