Ship Assistent 0.8.1: split modules and shared+personal vector memory.
Personal RAG never leaks into the shared store; retrieve merges shared plus the persona chain, with personal overwrite on kind+key. Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Leonid Pershin
Cursor
@@ -2,13 +2,13 @@
|
||||
|
||||
SwarmUI extension for **collaborative Krea 2** prompting via **Ollama**: chat + board (Generate | Refs tabs), LoRA chips, **persona presets** (`Config/personas/`), **vector memory**, model cards with Civitai fetch, img2img/inpaint, slash commands, auto Generate.
|
||||
|
||||
**Version 0.7.6** — Bugfix: clear/new abort in-flight chat; Send blocked while generating; Interrupt always drops stream bubble; patch-clear resets lastPatch.
|
||||
**Version 0.8.1** — Chats live on disk (`Assistent/chats/`), the chat model is **parked out of VRAM** before every Generate, memory + wanted queue are editable in ⚙, Ollama health sits in the chat header. Vector memory is shared + personal: personal never leaks into shared; shared is visible to every persona; personal overwrites the same kind+key.
|
||||
|
||||
## Layout
|
||||
|
||||
- **Left — Board tabs:** **Generate** (full-height live view) | **Refs** (reference grid + badge `N · vision M`)
|
||||
- **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; settings gear (memory model + skills)
|
||||
- **Right:** Chat | Cards; persona / pack / Ollama chat model; **Ollama health** badge; settings gear (memory model + skills + **Память**)
|
||||
- **Chips / slash:** loaded from `Config/_base/ui.json` (persona can override)
|
||||
|
||||
## Config (bundled + overlay)
|
||||
@@ -16,12 +16,23 @@ SwarmUI extension for **collaborative Krea 2** prompting via **Ollama**: chat +
|
||||
```
|
||||
Config/
|
||||
_base/ # defaults (assistant, ui, models/krea2, exact.json, core, packs, skills, memory-seed, identity)
|
||||
personas/<id>/ # sparse preset: persona/voice/likes/dislikes/rules + optional exact.json / overrides
|
||||
personas/<id>/ # sparse preset: persona/voice/likes/dislikes/rules + optional exact.json / memory-seed / overrides
|
||||
```
|
||||
|
||||
Disk overlay (wins over bundled): `/mnt/swarm_data/Assistent/` — same layout, plus `settings.json`, `taste.json`, `personas.json` (legacy prompt overlay), `ollama-roles.json`, `memory/assistent.sqlite`.
|
||||
Disk overlay (wins over bundled): `/mnt/swarm_data/Assistent/` — same folder layout as `Config/`, i.e. drop `_base/…` and `personas/<id>/…` files to override any bundled preset. Plus this extension's own state:
|
||||
|
||||
Copy `personas/cinema/` → `noir/`, edit only differing JSON files.
|
||||
```
|
||||
Assistent/
|
||||
_base/ personas/<id>/ # overlay presets — same names as Config/, sparse
|
||||
settings.json # embed_model, base_url, per-persona skills
|
||||
ui-state.json # pack / persona / auto_* / pane_width / models — seeds a fresh browser
|
||||
taste.json # learned taste profile (wins over localStorage)
|
||||
chats/<id>.json # chat history, newest 60 kept
|
||||
ollama-roles.json # chat vs memory model tags
|
||||
memory/assistent.sqlite # vector store (shared + per-persona)
|
||||
```
|
||||
|
||||
Copy `personas/cinema/` → `noir/`, edit only differing JSON files. Persona prompt overrides belong in `personas/<id>/` — the old flat `personas.json` is legacy and only read when no overlay folder exists for that id.
|
||||
|
||||
## Exact memory (KV)
|
||||
|
||||
@@ -33,18 +44,34 @@ Copy `personas/cinema/` → `noir/`, edit only differing JSON files.
|
||||
|
||||
## Vector memory
|
||||
|
||||
Two layers in `memory/assistent.sqlite` (`persona` column; empty = shared):
|
||||
|
||||
- **Shared** — `Config/_base/memory-seed/`, model cards, `scope: "shared"` upserts. Visible to every persona.
|
||||
- **Personal** — `Config/personas/<id>/memory-seed/` and chat upserts (default). Never copied into shared. Other personas do not retrieve it.
|
||||
- Retrieve = shared ∪ this persona (and `extends` parents). Same `kind`+`key`: personal overwrites parent overwrites shared. Forget without `scope` only drops the personal overlay.
|
||||
- SQLite + Ollama `/api/embed` (default `nomic-embed-text`, pick in ⚙)
|
||||
- First chat seeds `Config/_base/memory-seed/` (pointers + pitfalls; numbers live in Exact)
|
||||
- Agents upsert via patch `memory_upsert` / `memory_forget`
|
||||
- Cards ingest on save; retrieve → `memory_hits` in live context (inventory slimmed)
|
||||
- Soft notes only — Exact and the user beat RAG for params
|
||||
- ⚙ → **Память** lists every row (scope · source · date) with a per-row forget; bundled rows are read-only because reseed brings them back
|
||||
|
||||
## Chats on disk
|
||||
|
||||
- Every chat is written to `Assistent/chats/<id>.json` (messages + a Generate params snapshot), so History survives a cleared browser and follows the data volume across VMs
|
||||
- localStorage stays as a fast cache; on first run with an empty `chats/` the old `swarm_assistent_chats_v1` store is migrated up once
|
||||
- `ui-state.json` seeds a **fresh** browser only — anything already in localStorage wins, and `auto_download` is never restored as on
|
||||
|
||||
## VRAM handover
|
||||
|
||||
- Before every Generate the chat model is unloaded (`keep_alive: 0`) so Krea 2 gets the whole GPU
|
||||
- Back in the Chat tab it is warmed again with a 1-token request (`keep_alive 15m`, `num_ctx` from `assistant.json`)
|
||||
- Embed / memory models are never parked — reloading them would stall every retrieve
|
||||
|
||||
## UX
|
||||
|
||||
- **Send to Assistent** under Generate/History → Ref + Assistent tab
|
||||
- Enter sends; Shift+Enter newline; Interrupt cancels chat epoch
|
||||
- Manual **Apply + Generate** / `/gen` always generate; Auto-generate checkbox only for LLM auto-path
|
||||
- Civitai Confirm required (unless auto-download)
|
||||
- **Посмотри результат** / auto-critique wait for a real Generate frame — model previews and unfinished batches are skipped
|
||||
- Civitai Confirm required (unless auto-download); queued-but-missing models show a `⏳ wanted` badge in Cards
|
||||
|
||||
### Slash commands (client-side, no LLM)
|
||||
|
||||
@@ -103,10 +130,14 @@ Restart / rebuild SwarmUI after clone. gpu-rent: `seed-extensions` + restart.
|
||||
| `AssistentGetPacks` | Prompt pack texts |
|
||||
| `AssistentGetCard` / `AssistentSaveCard` | `.assistent.json` cards (+ memory ingest) |
|
||||
| `AssistentGetCardMeta` | Local sidecar + optional Civitai by-hash |
|
||||
| `AssistentEnqueueWanted` | Wanted YAML queue |
|
||||
| `AssistentEnqueueWanted` / `AssistentListWanted` | Wanted YAML queue (write / read + count) |
|
||||
| `AssistentGetTaste` / `AssistentSaveTaste` | Persistent taste profile |
|
||||
| `AssistentSearchCivitai` | Civitai LoRA search |
|
||||
| `AssistentChat` / `AssistentChatWS` | Chat (+ memory retrieve + Civitai hop) |
|
||||
| `AssistentListMemory` / `AssistentUpsertMemory` / `AssistentForgetMemory` | Vector store (optional `scope` / `persona`) |
|
||||
| `AssistentListChats` / `AssistentGetChat` / `AssistentSaveChat` / `AssistentDeleteChat` | `Assistent/chats/<id>.json` |
|
||||
| `AssistentGetUiState` / `AssistentSaveUiState` | `Assistent/ui-state.json` |
|
||||
| `AssistentParkLlm` / `AssistentWarmLlm` | Unload / reload the chat model in VRAM |
|
||||
|
||||
## License
|
||||
|
||||
|
||||
Reference in New Issue
Block a user