Chips and quick patches apply params without auto-Generate; aspect sizes match Swarm Side Length 1024. HF import shows drafts after switching filter from approved-only; training status and job polling improved.
Co-authored-by: Cursor <cursoragent@cursor.com>
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>
Per-chat Generate session with sparse deltas; drop Cards/Civitai/wanted hops; rolling history summary via the same Ollama model with a budget chip and /compress.
Co-authored-by: Cursor <cursoragent@cursor.com>
Replace fake train loop with TRL SFTTrainer, HF column mapping with fiction preset,
safetensors to GGUF conversion, and ollama create using ollama_base plus ADAPTER.
Co-authored-by: Cursor <cursoragent@cursor.com>
Restructure UI with app-level tabs and chat history drawer; add dataset curation,
HF import, Modelfile/QLoRA hooks, and link approved samples to the agent immediately
via heard vector memory without waiting for fine-tuning.
Co-authored-by: Cursor <cursoragent@cursor.com>
Replace split Assets JS with a built bundle and aligned C#/config so SwarmUI loads one script and patch apply stays consistent; drop legacy terse persona and memory seed.
Co-authored-by: Cursor <cursoragent@cursor.com>
Silent Generate, pack selection, and loading UI no longer trip on Cyrillic or fake GPU loads; persona title is the assistant, not the user.
Co-authored-by: Cursor <cursoragent@cursor.com>
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>
Separate About-the-user memory (global + per-persona) from craft RAG, add tabbed settings with persona export/import and craft clear APIs.
Co-authored-by: Cursor <cursoragent@cursor.com>
Add Leonid as a shelf-based example with preference_bias slider; support /persona new clone-to-overlay and UI-only delete.
Co-authored-by: Cursor <cursoragent@cursor.com>
Runtime session data belongs in one DB so History can FTS-search and follow the volume; persona overlays and sidecar cards stay files.
Co-authored-by: Cursor <cursoragent@cursor.com>
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>
Persist chats with Generate param snapshots, always open a new chat on start, and abort in-flight work on clear/switch so replies cannot land in the wrong chat.
Co-authored-by: Cursor <cursoragent@cursor.com>
When the user explicitly asks to generate, auto-apply the patch and run Generate without the Apply button strip; Собрать + Gen reapplies the last patch (or current SwarmUI prompt) and generates.
Co-authored-by: Cursor <cursoragent@cursor.com>
Move prompts into Config/_base and persona folders; seed model facts into SQLite via Ollama embed and retrieve as memory_hits each turn.
Co-authored-by: Cursor <cursoragent@cursor.com>
Livebar and waiting_ollama phase while the model loads into GPU; bump context past Ollama's 4096 default that truncated Assistent packs.
Co-authored-by: Cursor <cursoragent@cursor.com>
Server inventory and streaming chat, auto-apply/generate with Interrupt, Civitai search cards (Confirm-only download), plus Init/Mask wiring and inpaint_edit pack.
Co-authored-by: Cursor <cursoragent@cursor.com>
Leonid PershinandCursor
mrleo1nid