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

Ship Assistent 0.10.18: settings as a peer tab, stream/VRAM chat fixes.

Browse Source 
Move settings beside Chat/Cards; stop fence ramble, sticky scroll, horny echo filter, and force-warm after Generate.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Leonid Pershin
2026-08-22 04:12:53 +03:00
co-authored by Cursor
parent 43984208fc
commit 536637714c
11 changed files with 490 additions and 163 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -4
View File
@@ -2,13 +2,13 @@
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 0.10.13** — Assistant prose renders `### Critique` as **Критика** (and similar headings); empty JSON Patch headers hidden. Builds on 0.10.12 aspect/critique fixes.
**Version 0.10.18** — Settings is a full subtab (Чат | Карточки | Настройки), not a header overlay. Builds on 0.10.17 post-Generate warm.
## Layout
- **Left — Board tabs:** **Generate** (full-height live view) | **Refs** (reference grid + badge `N · vision M`); **Посмотри результат** attaches the finished frame and asks for a verdict
- **Splitter:** drag to resize panes
- **Right:** Chat | Cards; persona / pack / Ollama chat model; **Ollama health** badge; ⚙ settings panel (6 tabs)
- **Right:** Chat | Cards | Settings; persona / pack / Ollama chat model; **Ollama health** badge
- **Chips / slash:** loaded from `Config/_base/ui.json` (persona can override)
## Config (bundled + overlay)
@@ -74,8 +74,8 @@ Two layers in `memory/assistent.sqlite` (`persona` column; empty = shared):
- `settings.json` and persona overlays stay files (layered merge + git). `.assistent.json` cards stay next to weights.
## VRAM handover
- Before Generate the chat model is unloaded only if **Park LLM** is enabled (`keep_alive: 0`) — default off so VL chat stays warm; enable when Generate OOMs
- When parked, after Generate the model is warmed again (`keep_alive 15m`) before the UI goes idle
- Before Generate the chat model is unloaded only if **Park LLM** is enabled (`keep_alive: 0`) — default off
- After Generate the chat model is **always** force-warmed (`AssistentWarmLlm`) — Krea still often evicts VL from VRAM even without park
- Embed / memory models are never parked — reloading them would stall every retrieve
## UX