mrleo1nid/swarm-assistent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -2,7 +2,7 @@
SwarmUI extension for **collaborative Krea 2** prompting via **Ollama**: chat + board (Generate | Refs tabs), LoRA chips, **persona presets** (`Config/personas/`), **About the user** prefs + craft vector memory, model cards with Civitai fetch, img2img/inpaint, slash commands, auto Generate.
**Version 0.10.0** — Settings panel (Поведение / Модели / Личности / О пользователе / Крафт / Ещё), **UserPrefs** (global + per-persona) with prompt weight, persona export/import, craft memory clear APIs. Legacy `taste` migrates into UserPrefs once.
**Version 0.10.2** — Vision flag fix (`has_vision_image` vs `images_in_request`), enrich rich LoRAs from disk, post-Generate look_at option, `system_chars` in chat debug. Lean Ollama context (quality-first): slim core, always-on voice/likes + rich top LoRAs, hops for inventory/lore/`memory.md`, JPEG only on `look_at`.
## Layout