feat: scene management for RP settings

README.md

@@ -27,6 +27,7 @@ open "build/Debug/MLX Server.app"
 ## App Features
 
 - **Chat interface** with markdown rendering and model-aware image attachments (file picker, drag & drop, clipboard paste, Finder copy-paste on vision-capable models)
+- **Scene-based chat starts** — New Chat opens a scene picker with Neutral plus saved scenes, each with an optional model override, a scene prompt layered onto the base system prompt, and an auto-sent starter prompt
 - **Model picker** in toolbar with local/download status indicators and re-download button
 - **Download progress modal** — shows file progress, percentage, and speed when downloading a new model
 - **Thinking mode** — models like Qwen3.5 can reason internally before responding; thinking content appears in a collapsible box. Toggle on/off in Settings.
@@ -34,7 +35,8 @@ open "build/Debug/MLX Server.app"
 - **Export chat** — File > Export Chat (Cmd+Shift+S) saves conversations as Markdown or RTF (Pages-compatible)
 - **Status bar** showing model name, context window, tokens/sec, token counts, GPU memory, API server status
 - **Keyboard shortcuts**: `Cmd+N` (new chat), `Cmd+Return` (send), `Escape` (stop), `Cmd+1/2/3/4` (switch models), `Cmd+Shift+S` (export)
-- **Settings** (`Cmd+,`): default model, thinking mode toggle, system prompt, API port, API auto-start, idle unload timeout
+- **Scene management** — create and edit reusable roleplay/task presets from the New Chat flow or Settings
+- **Settings** (`Cmd+,`): default model, thinking mode toggle, base system prompt, scene management, API port, API auto-start, idle unload timeout
 - **Idle auto-unload** — model is unloaded after configurable idle time (resets on both user input and model output), reloaded on next request
 
 ## API Server
@@ -91,10 +93,14 @@ MLXServer/
 ├── Models/
 │   ├── ModelConfig.swift           — Model definitions, alias/repoId resolution
 │   └── ChatMessage.swift           — Chat message data model, thinking tag parser
+│   └── ChatScene.swift             — Persisted chat scene presets (prompt + model + starter)
 ├── ViewModels/
 │   ├── ModelManager.swift          — Model loading/switching, download tracking, idle unload
 │   └── ChatViewModel.swift         — Chat state, ChatSession, API server lifecycle
+│   └── SceneStore.swift            — Scene persistence and editing operations
 ├── Views/
+│   ├── SceneSelectionView.swift    — New chat scene picker popover
+│   ├── SceneManagementView.swift   — Scene editor and list management
 │   ├── ModelPickerView.swift       — Toolbar model selector with re-download
 │   ├── ChatMessagesView.swift      — Scrollable message list with markdown + thinking blocks
 │   ├── ChatInputView.swift         — Text input + image attach (paste, drag, picker)
@@ -113,7 +119,7 @@ MLXServer/
     ├── LocalModelResolver.swift    — Offline-first HuggingFace cache resolution (sandbox + system)
     ├── ChatExporter.swift          — Export conversations to Markdown or RTF
     ├── FocusedValues.swift         — FocusedValue keys for menu bar integration
-    └── Preferences.swift           — UserDefaults wrapper
+    └── Preferences.swift           — UserDefaults wrapper, including scene persistence
 
 project.yml     — xcodegen project spec (dependencies, settings, deployment target)
 build.sh        — One-command build script (xcodegen + xcodebuild)