feat(settings): add permissions for git commands in settings.json

- AI_REFACTOR_PLAN.md: Electron-only, 7 phases, 18 steps
- BACKEND_PLAN.md: standalone FastAPI backend guide for separate repo

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.claude/CLAUDE.md

@@ -1,139 +1,164 @@
 # CLAUDE.md
 
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
-
 ## Commands
 
 ```bash
-# Development
-source ~/.nvm/nvm.sh && npm start          # Start Electron app with hot-reload
-
-# Build & Package
+source ~/.nvm/nvm.sh && npm start              # Dev with hot-reload
 source ~/.nvm/nvm.sh && npm run make            # Build distributable packages
-source ~/.nvm/nvm.sh && npm run package    # Package without making installers
-
-# Lint
-source ~/.nvm/nvm.sh && npm run lint       # ESLint over .ts/.tsx files
-
-# Database migrations (Drizzle)
-source ~/.nvm/nvm.sh && npx drizzle-kit generate   # Generate migration from schema changes
+source ~/.nvm/nvm.sh && npm run package         # Package without installers
+source ~/.nvm/nvm.sh && npm run lint            # ESLint (.ts/.tsx)
+source ~/.nvm/nvm.sh && npx drizzle-kit generate  # Generate migration from schema
 source ~/.nvm/nvm.sh && npx drizzle-kit push       # Push schema directly (dev only)
 ```
 
-There is no test suite currently.
+No test suite currently.
 
-## Architecture Overview
+## Architecture
 
-Adiuva is a local-first Electron desktop app. The three Electron processes communicate via a custom tRPC↔IPC bridge (the public `electron-trpc` package is incompatible with tRPC v11, so a custom implementation is used).
-
-### Process Boundaries
+Adiuva is a local-first Electron desktop app. The three processes communicate via a custom tRPC v11 ↔ IPC bridge (the public `electron-trpc` package is incompatible with tRPC v11).
 
 ```
-Renderer (React)  ──ipcLink──►  Preload (contextBridge)  ──IPC──►  Main (tRPC router + SQLite)
+Renderer (React 19)  ──ipcLink──►  Preload (contextBridge)  ──IPC──►  Main (tRPC router + SQLite)
 ```
 
-1. **Main process** (`src/main/`) — Node.js, owns the database and all business logic
-   - `index.ts` — Window creation, app lifecycle
-   - `ipc.ts` — Custom handler that bridges `ipcMain` to tRPC procedures
-   - `router/index.ts` — All tRPC routers (clients, projects, tasks, checkpoints, notes, settings, ai)
-   - `db/index.ts` — Drizzle + better-sqlite3, WAL mode, singleton `getDb()`
-   - `db/schema.ts` — All table definitions (clients, projects, tasks, checkpoints, notes)
-   - `store.ts` — electron-store for persistent UI settings (e.g., `sidebarCollapsed`)
+### Main Process (`src/main/`)
 
-2. **Preload** (`src/preload/trpc.ts`) — Exposes `window.electronTRPC` with `sendMessage()` / `onMessage()`
+Owns the database and all business logic.
 
-3. **Renderer** (`src/renderer/`) — React 19, never accesses Node APIs directly
-   - `lib/ipcLink.ts` — Custom TRPCLink that routes calls through `window.electronTRPC`
-   - `lib/trpc.ts` — `createTRPCReact<AppRouter>()` typed client
-   - `index.tsx` — QueryClient + tRPC + Router providers
-   - All data access is through `trpc.*.*useQuery()` / `trpc.*.*.useMutation()`
+| File | Purpose |
+|---|---|
+| `index.ts` | Window creation, app lifecycle |
+| `ipc.ts` | Bridges `ipcMain` to tRPC procedures |
+| `router/index.ts` | All tRPC sub-routers merged into `appRouter` |
+| `db/index.ts` | Drizzle + better-sqlite3, WAL mode, singleton `getDb()` |
+| `db/schema.ts` | Table definitions: clients, projects, tasks, checkpoints, notes, taskComments |
+| `db/vectordb.ts` | LanceDB vector store for note embeddings |
+| `store.ts` | electron-store for persistent UI settings |
+
+### Preload (`src/preload/trpc.ts`)
+
+Exposes `window.electronTRPC` with `sendMessage()` / `onMessage()`.
+
+### Renderer (`src/renderer/`)
+
+React 19 — never accesses Node APIs directly. All data through `trpc.*.useQuery()` / `trpc.*.useMutation()`.
+
+| File | Purpose |
+|---|---|
+| `lib/ipcLink.ts` | Custom TRPCLink routing through `window.electronTRPC` |
+| `lib/trpc.ts` | `createTRPCReact<AppRouter>()` typed client |
+| `index.tsx` | QueryClient + tRPC + Router providers |
 
 ### Routing
 
-File-based routing via TanStack Router. Add a file to `src/renderer/routes/` and the route tree (`src/renderer/routeTree.gen.ts`) is auto-regenerated by the Vite plugin on next `npm start`. Routes:
-- `__root.tsx` — Root layout wrapping everything in `AppShell`
-- `index.tsx`, `tasks.tsx`, `timeline.tsx`, `projects.tsx`
+File-based via TanStack Router (`tsr.config.json` at root). Route tree auto-generated at `routeTree.gen.ts`.
+
+Routes: `__root.tsx` (AppShell layout), `index`, `tasks`, `timeline`, `projects`, `notes.$noteId`
+
+### tRPC Routers
+
+`health`, `settings`, `clients`, `projects`, `tasks`, `checkpoints`, `notes`, `taskComments`, `ai`
 
 ### Database
 
-Schema lives in `src/main/db/schema.ts`. Migrations are in `src/main/db/migrations/`. The DB is created in Electron's `userData` directory as `adiuva.db`. On startup, `initDb()` runs non-destructive migrations (CREATE TABLE IF NOT EXISTS).
+Schema in `src/main/db/schema.ts`, migrations in `src/main/db/migrations/`. DB created in Electron's `userData` as `adiuva.db`. On startup, `initDb()` runs non-destructive migrations.
 
-To add a new table or column: edit `schema.ts`, run `drizzle-kit generate`, then `drizzle-kit push` (dev) or commit the migration file.
+To add a table/column: edit `schema.ts` → `drizzle-kit generate` → `drizzle-kit push` (dev) or commit the migration.
 
-### Adding a New Feature (end-to-end pattern)
+### Adding a Feature (end-to-end)
 
-1. **Schema** — Add table/columns to `src/main/db/schema.ts`
-2. **Router** — Add a tRPC sub-router in `src/main/router/index.ts`, merge it into `appRouter`
-3. **Types** — `AppRouter` is exported from `src/main/router/index.ts` and imported in `src/renderer/lib/trpc.ts` — types flow automatically
-4. **UI** — Create components under `src/renderer/components/<feature>/`, use `trpc.*.*useQuery()` for data
+1. **Schema** — `src/main/db/schema.ts`
+2. **Router** — Add sub-router in `src/main/router/index.ts`, merge into `appRouter`
+3. **Types** — Flow automatically via `AppRouter` export
+4. **UI** — Components in `src/renderer/components/<feature>/`, data via `trpc.*.useQuery()`
 
-### AI Subsystem (`src/main/ai/`)
+## AI Subsystem (`src/main/ai/`)
 
-LangGraph-based agentic system with pluggable LLM providers (OpenAI, Anthropic, GitHub Copilot).
+LangGraph-based agentic system with pluggable LLM providers.
 
-**Orchestrator** (`orchestrator.ts`): Classifies user intent → routes to one of three specialist agents:
-- **Project agent** — project-scoped Q&A with tools: `read_project_notes`, `add_task`, `get_summary`, `suggest_checkpoints`, `suggest_tasks`
-- **Knowledge agent** — cross-project semantic search via `vector_search_all`
-- **General agent** — workspace-wide `add_task`
+### Orchestrator (`orchestrator.ts`)
 
-Tool-calling strategy differs by provider: OpenAI/Anthropic use LangChain `bindTools()` + ToolMessage loop (max 5 iterations); Copilot uses SDK-native tools (loop handled internally).
+Classifies user intent → routes to a specialist agent:
 
-**Streaming**: Orchestrator calls `sendStreamChunk(sender, token, done)` over IPC channel `'ai:stream'`. Renderer subscribes via `window.electronAI.onStreamChunk()` in `AIChatPanel.tsx`. `<tool_call>` blocks are filtered before sending to renderer.
+| Agent | Scope | Tools |
+|---|---|---|
+| Project | Project-scoped Q&A | `read_project_notes`, `add_task`, `get_summary`, `suggest_checkpoints`, `suggest_tasks` |
+| Knowledge | Cross-project search | `vector_search_all` |
+| General | Workspace-wide | `add_task` |
 
-**Provider factory** (`llm.ts`): `gpt-4o-mini` (OpenAI), `claude-sonnet-4-20250514` (Anthropic), or ChatCopilot wrapper — all with `temperature: 0.3` and streaming enabled.
+All providers use LangChain `bindTools()` + ToolMessage loop (max 5 iterations).
 
-**Token storage** (`token.ts`) — three-tier fallback:
-1. keytar (OS keychain) — preferred, encrypted per-user
+Also exports `dailyBrief()` for AI-generated daily summaries (`ai.dailyBrief` tRPC mutation).
+
+### Streaming
+
+`sendStreamChunk(sender, token, done)` over IPC `'ai:stream'`. Renderer subscribes via `window.electronAI.onStreamChunk()` in `AIChatPanel.tsx`. `<tool_call>` blocks are filtered before display.
+
+### Providers (`llm.ts`)
+
+| Provider | Model | Notes |
+|---|---|---|
+| OpenAI | `gpt-4o-mini` | Via LangChain |
+| Anthropic | `claude-sonnet-4-20250514` | Via LangChain |
+| Copilot | `ChatCopilot` wrapper | `copilot.ts` / `chat-copilot.ts` |
+
+All use `temperature: 0.3`, streaming enabled. Provider management in `provider.ts`.
+
+### Token Storage (`token.ts`)
+
+Three-tier fallback (keytar service name: `'adiuva'`):
+1. keytar (OS keychain) — preferred; `keytarFailed` flag skips after first failure
 2. electron-store + `safeStorage` — encrypted at rest
 3. Plain electron-store — WSL fallback
 
-Keytar service name is `'adiuva'`. Once keytar fails, `keytarFailed` flag skips it for the session.
+### Vector Embeddings (`db/vectordb.ts`)
 
-**AI approval pattern**: Tasks and checkpoints have `isAiSuggested` (bool) and `isApproved` (bool) columns. AI-suggested items appear in the UI pending user approval before being treated as real records.
+LanceDB in `{userData}/vectors/`. Schema: `{ id, projectId, content, vector }` (1536-dim, `text-embedding-3-small` via `embeddings.ts`). Embedding priority: Copilot CLI token → OpenAI token.
 
-### Vector Embeddings (`src/main/db/vectordb.ts`)
+- `upsertNoteEmbedding()` on note create/update (fire-and-forget)
+- `migrateNotesIfNeeded()` backfills on first startup
+- `searchNotes(query, limit=5)` used by Knowledge agent
 
-LanceDB stored in `{userData}/vectors/`. Table schema: `{ id, projectId, content, vector }`. Vectors are 1536-dimensional (`text-embedding-3-small`). Embeddings use a priority chain: Copilot CLI token → OpenAI token.
+### AI Approval Pattern
 
-- Note create/update fires `upsertNoteEmbedding()` (fire-and-forget, errors swallowed)
-- `migrateNotesIfNeeded()` backfills existing notes on first startup
-- `searchNotes(query, limit=5)` is called by the Knowledge agent tool
+Tasks and checkpoints have `isAiSuggested` + `isApproved` columns. AI suggestions appear pending user approval (dashed borders in UI).
 
-### Key Config Notes
+## Config Notes
 
-- Vite configs use `.mts` extension (not `.ts`) to avoid ESM/CJS conflicts with electron-forge's externalize-deps plugin
-- `@/*` path alias resolves to `src/renderer/*` (TypeScript + Vite + shadcn/ui all share this alias)
-- shadcn/ui style: **new-york**, base color: **neutral**
-- Icons: **lucide-react** throughout — do not introduce other icon libraries
-- Tailwind 4 (not 3) — use CSS variable theming via `globals.css`, not `tailwind.config.js`
-- Notes use Milkdown (`@milkdown/crepe`) as the markdown editor (`src/renderer/components/notes/MilkdownEditor.tsx`)
-- Routes: `index`, `tasks`, `timeline`, `projects`, `notes.$noteId` (note ID is a URL param)
+- Vite configs use `.mts` (not `.ts`) — avoids ESM/CJS conflicts with electron-forge
+- `@/*` path alias → `src/renderer/*` (TypeScript + Vite + shadcn/ui)
+- **shadcn/ui**: new-york style, neutral base color
+- **Icons**: lucide-react only — do not introduce other icon libraries
+- **Tailwind 4** — CSS variable theming in `globals.css`, no `tailwind.config.js`
+- **Notes editor**: Milkdown (`@milkdown/crepe`) at `src/renderer/components/notes/MilkdownEditor.tsx`
 
 ## Design Context
 
-### Users
-Freelancers and solo professionals managing their own client work — projects, tasks, notes, and timelines. They work alone and need a single workspace that keeps everything organized without the overhead of enterprise tools. The AI assistant is a force multiplier, helping them stay on top of their workload.
+### Target User
+Freelancers and solo professionals managing client work (projects, tasks, notes, timelines). Single workspace, no enterprise overhead. AI as force multiplier.
 
-### Brand Personality
-**Calm, intelligent, warm.** Adiuva is a thoughtful companion, not a flashy tool. It should feel like a well-organized desk — everything in its place, nothing competing for attention. The tone is confident and understated, never loud or gamified.
+### Brand
+**Calm, intelligent, warm.** Thoughtful companion, not flashy tool. Confident and understated, never loud or gamified.
 
-### Aesthetic Direction
-- **Visual tone**: Editorial, premium, content-first. Inspired by Notion's clean typography and warm neutrals, but with a distinct identity through the warm pinkish-white canvas and golden yellow accent
-- **Light mode**: Soft and warm — pinkish-white (`#f4edf3`) canvas, golden yellow (`#fbc881`) primary, slate blue-gray (`#8a8ea9`) secondary, dusty lavender borders (`#c8c3cd`)
-- **Dark mode**: Stark monochrome — near-black canvas (`#0c0c0c`), crisp white text, dark gray surfaces (`#323232`). No color accent; primary is pure white
-- **Typography**: Geist (geometric sans-serif) at 400/500/600. Tight tracking on large headings (`-1px`). Body at `text-sm`, metadata at `text-xs`
-- **Corners**: 10px base radius, consistently rounded. Chat elements use `rounded-2xl`
-- **Signature effects**: Glassmorphism on AI inputs/floating chat (`backdrop-blur-xl`, transparency). Spring physics animations (stiffness 400, damping 30). Subtle scale-and-fade transitions
-- **Anti-references**: No gamification (badges, streaks, confetti). No corporate/enterprise density. Keep it mature and professional
+### Palette
+
+| | Canvas | Primary | Secondary | Borders |
+|---|---|---|---|---|
+| **Light** | Pinkish-white `#f4edf3` | Golden yellow `#fbc881` | Slate blue-gray `#8a8ea9` | Dusty lavender `#c8c3cd` |
+| **Dark** | Near-black `#0c0c0c` | Pure white | — | Dark gray `#323232` |
+
+### Typography
+Geist sans-serif, weights 400/500/600. Tight tracking (`-1px`) on headings. Body `text-sm`, metadata `text-xs`.
+
+### Visual Language
+- 10px border-radius, `rounded-2xl` for chat elements
+- Glassmorphism on AI inputs (`backdrop-blur-xl`, transparency)
+- Spring animations (stiffness 400, damping 30), scale-and-fade transitions
+- No gamification (badges, streaks, confetti). Mature and professional
 
 ### Design Principles
-
-1. **Clarity over cleverness** — Every element should communicate its purpose instantly. Prefer clear hierarchy and whitespace over decorative flourish. Information density should feel comfortable, not cramped.
-
-2. **AI as quiet partner** — The AI is deeply integrated (floating chat, suggestions) but never intrusive. AI-suggested items use dashed borders to signal "pending." The Sparkles icon is the consistent AI identity marker.
-
-3. **Warmth in restraint** — The palette is deliberately warm (pinkish whites, golden yellows) to feel approachable without being playful. Dark mode trades warmth for focus. Let the content breathe.
-
-4. **Motion with purpose** — Spring physics and glassmorphism create a sense of physicality and depth. Animations should feel natural and responsive, never decorative or slow. Every transition should reinforce spatial relationships.
-
-5. **Confidence through consistency** — Use the established token system (CSS variables, shadcn/ui primitives, Geist font). The user should feel in control — predictable patterns, keyboard-first interactions, no surprises.
+1. **Clarity over cleverness** — Clear hierarchy, generous whitespace, comfortable density
+2. **AI as quiet partner** — Deeply integrated but never intrusive. Dashed borders for pending AI items, Sparkles icon as AI marker
+3. **Warmth in restraint** — Warm palette feels approachable without being playful. Dark mode trades warmth for focus
+4. **Motion with purpose** — Animations reinforce spatial relationships, never decorative
+5. **Confidence through consistency** — CSS variable tokens, shadcn/ui primitives, Geist font. Predictable, keyboard-first

.claude/settings.json

@@ -0,0 +1,8 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(git add AI_REFACTOR_PLAN.md)",
+      "Bash(git commit:*)"
+    ]
+  }
+}

AI_REFACTOR_PLAN.md

@@ -0,0 +1,389 @@
+# AI Refactor Plan — Adiuva Electron App
+
+> **Objective:** Transform the Electron app from a single-process AI integration into a local-first multi-agent client with plugin-based batch agents, multi-provider LLM support, E2E encrypted backup, granular permissions, and cloud backend integration.
+>
+> **Backend:** Lives in a separate repository. See `BACKEND_PLAN.md` for the API contract and backend implementation guide.
+>
+> **Protocol:** Execute steps sequentially. Each step is atomic and committable. Mark `[x]` when done.
+
+---
+
+## Phase 0 — API Contracts & Types
+
+### Step 0.1 — Define backend API contract types
+- [ ] Create `src/shared/api-types.ts` with all interfaces the Electron app needs to communicate with the backend:
+  - `ExecutionPlan`, `PlanStep`, `PlanAction` (action types: `create_record`, `update_record`, `delete_record`, `index_document`, `send_notification`)
+  - `ChatRequest` (message, context, execution_mode: `'direct'` | `'plan'`)
+  - `ChatResponse` (response, actions)
+  - `ChatContext` (user_profile, relevant_documents, recent_tasks, conversation_history)
+  - `AgentManifest` (name, description, permissions, schedule)
+  - `PermissionGrant` (plugin, permission type, resource path, granted_at)
+  - `BackupMetadata` (version, timestamp, checksum, chunk_count)
+  - `BillingTier` enum (`free`, `pro`, `power`, `team`)
+  - `AuthTokens` (access_token, refresh_token, expires_at)
+  - `UserProfile` (id, email, tier)
+- [ ] Update `tsconfig.json` paths if needed to include `src/shared/`
+- **Files:** `src/shared/api-types.ts`, `tsconfig.json`
+- **Outcome:** Type-safe contracts for all backend communication. Backend repo mirrors these as Pydantic schemas.
+
+---
+
+## Phase 1 — LiteLLM Multi-Provider Client
+
+### Step 1.1 — Create unified LLM client wrapper
+- [ ] Create `src/main/llm/litellm-client.ts`:
+  - `LiteLLMClient` class with unified interface:
+    - `complete(messages: Message[], options?: CompletionOptions): Promise<CompletionResponse>`
+    - `stream(messages: Message[], options?: CompletionOptions): AsyncGenerator<string>`
+    - `embed(text: string): Promise<number[]>`
+  - `CompletionOptions`: model override, temperature, max_tokens, tools
+  - Provider-agnostic: internally maps to the correct provider SDK
+  - Fallback chain: tries primary provider, on failure tries secondary, logs each attempt
+  - Timeout handling: per-provider configurable timeouts
+- [ ] Create `src/main/llm/providers.ts`:
+  - `ProviderConfig` interface: name, apiKey, model, endpoint (for Ollama), timeout, isLocal
+  - `ProviderRegistry`: manages configured providers, persists to electron-store
+  - `getActiveProvider()`, `setActiveProvider(name)`, `addProvider(config)`, `removeProvider(name)`
+  - `getFallbackChain(): ProviderConfig[]`
+  - Supported providers: OpenAI, Anthropic, Google (Gemini), Mistral, Groq, Ollama (local)
+- [ ] Create `src/main/llm/embeddings.ts` (refactored):
+  - Support multiple embedding providers (OpenAI text-embedding-3-small, local ONNX with all-MiniLM-L6-v2)
+  - Auto-select: use local ONNX if available, fall back to API
+  - Same `embedText(text): Promise<number[]>` interface
+- **Files:** `src/main/llm/litellm-client.ts`, `src/main/llm/providers.ts`, `src/main/llm/embeddings.ts`
+- **Outcome:** Single LLM interface that all local components use. Supports 6+ providers with fallback.
+
+### Step 1.2 — Migrate existing AI code to use new LLM client
+- [ ] Update `src/main/ai/orchestrator.ts`:
+  - Replace direct `getLLM()` calls with `LiteLLMClient.complete()` / `LiteLLMClient.stream()`
+  - Keep local orchestration working with the new client (backend delegation comes in Phase 3)
+- [ ] Update `src/main/ai/llm.ts`:
+  - Deprecate. Redirect `getLLM()` to instantiate via `LiteLLMClient` as a thin compatibility shim
+- [ ] Update `src/main/ai/embeddings.ts` to delegate to `src/main/llm/embeddings.ts`
+- [ ] Update `src/main/ai/token.ts`:
+  - Add `listStoredProviders(): Promise<string[]>` to enumerate which providers have tokens
+- [ ] Ensure all existing AI features (chat, daily brief, tool calling) continue to work
+- **Files:** `src/main/ai/orchestrator.ts`, `src/main/ai/llm.ts`, `src/main/ai/embeddings.ts`, `src/main/ai/token.ts`
+- **Outcome:** Existing AI features work identically but go through the new unified LLM client.
+
+---
+
+## Phase 2 — Local Plugin System & Batch Agents
+
+### Step 2.1 — Create plugin manifest system and permission manager
+- [ ] Create `src/main/permissions/manifest-validator.ts`:
+  - `PluginManifest` interface: `name`, `description`, `version`, `permissions: PermissionRequest[]`, `schedule?: string` (cron), `entryPoint: string`
+  - `PermissionRequest`: `type` (read_folder, read_email, read_calendar, read_browser_history), `resource?: string` (path, account), `reason: string`
+  - `validateManifest(manifest): ValidationResult` — validates structure, checks for dangerous permissions
+- [ ] Create `src/main/permissions/permission-manager.ts`:
+  - `PermissionManager` class (singleton):
+    - `grantPermission(pluginName, permission): void` — persists to SQLite
+    - `revokePermission(pluginName, permission): void`
+    - `checkPermission(pluginName, permission): boolean`
+    - `getPluginPermissions(pluginName): PermissionGrant[]`
+    - `getAllGrants(): PermissionGrant[]`
+    - `logAccess(pluginName, permission, resource, timestamp): void` — activity log
+    - `getActivityLog(pluginName?, limit?): ActivityLogEntry[]`
+  - Permission grants stored in a new `plugin_permissions` SQLite table
+  - Activity log stored in a new `plugin_activity_log` SQLite table
+- [ ] Add `plugin_permissions` and `plugin_activity_log` tables to `src/main/db/schema.ts`
+- [ ] Generate and apply migration
+- **Files:** `src/main/permissions/manifest-validator.ts`, `src/main/permissions/permission-manager.ts`, `src/main/db/schema.ts`, `src/main/db/migrations/`
+- **Outcome:** Granular, opt-in permission system for plugins. Every access is logged.
+
+### Step 2.2 — Create worker pool and batch runner
+- [ ] Create `src/main/workers/worker-pool.ts`:
+  - `WorkerPool` class:
+    - Manages a pool of Node.js `worker_threads`
+    - `runPlugin(manifest, context): Promise<PluginResult>` — spawns or reuses a worker, sends manifest + context, receives result
+    - Worker lifecycle: create, send message, receive result, terminate on timeout
+    - Max concurrent workers: configurable (default 4)
+    - Error isolation: worker crash doesn't affect main process
+- [ ] Create `src/main/workers/batch-runner.ts`:
+  - `BatchRunner` class:
+    - `registerPlugin(manifest): void` — validates manifest, stores in registry
+    - `startScheduler(): void` — cron-based scheduler using `node-cron` or simple setInterval
+    - `runPlugin(name, triggerContext?): Promise<PluginResult>` — manual trigger
+    - `stopAll(): void` — graceful shutdown of all scheduled plugins
+    - Scheduler checks permissions before each run; skips if revoked
+    - Results logged to activity log
+- [ ] Create `src/main/workers/plugin-worker.ts`:
+  - Worker thread entry point
+  - Receives plugin config + context via `parentPort.on('message')`
+  - Dynamically imports the plugin entry point
+  - Executes `run(context)` with sandboxed access (only permitted resources)
+  - Posts result back via `parentPort.postMessage()`
+- **Files:** `src/main/workers/worker-pool.ts`, `src/main/workers/batch-runner.ts`, `src/main/workers/plugin-worker.ts`
+- **Outcome:** Isolated plugin execution environment with scheduling, permissions enforcement, and error isolation.
+
+### Step 2.3 — Implement batch agent plugins
+- [ ] Create `src/plugins/email-scanner.ts`:
+  - Manifest: requires `read_email` permission
+  - Connects to IMAP via `imapflow` (account configured in settings)
+  - Scans for new emails since last run
+  - Uses `LiteLLMClient` to classify each email (has actionable task? extract title, priority, description)
+  - Returns extracted task metadata (never raw email content) for execution via backend or local playbook
+- [ ] Create `src/plugins/file-watcher.ts`:
+  - Manifest: requires `read_folder` permission for each watched path
+  - Uses `chokidar` to watch approved directories
+  - On new/modified file: reads content, generates embedding, upserts into vector store
+  - Supports: .txt, .md, .pdf (text extraction), .docx (basic extraction)
+- [ ] Create `src/plugins/calendar-sync.ts`:
+  - Manifest: requires `read_calendar` permission
+  - Parses ICS files or connects to CalDAV endpoint
+  - Detects scheduling conflicts
+  - Suggests reorganizations via LLM analysis
+  - Returns calendar events + conflict reports
+- [ ] Create `src/plugins/browser-agent.ts`:
+  - Manifest: requires `read_browser_history` permission (explicit opt-in)
+  - Reads browser bookmarks and history from known browser paths (Chrome, Firefox, Edge)
+  - Indexes relevant entries into vector store
+  - Privacy-first: only indexes URLs and titles, not page content
+- **Files:** `src/plugins/email-scanner.ts`, `src/plugins/file-watcher.ts`, `src/plugins/calendar-sync.ts`, `src/plugins/browser-agent.ts`
+- **Outcome:** Four local batch agents running as isolated worker threads, using LiteLLM for analysis.
+
+---
+
+## Phase 3 — Backend Integration
+
+### Step 3.1 — Create backend HTTP/WebSocket client
+- [ ] Create `src/main/api/backend-client.ts`:
+  - `BackendClient` class:
+    - `baseUrl` configurable (default: production cloud URL, overridable for dev)
+    - `setAuthToken(jwt: string): void`
+    - `chat(request: ChatRequest): Promise<ChatResponse>` — POST /api/v1/chat
+    - `chatStream(request: ChatRequest): AsyncGenerator<string>` — WebSocket /api/v1/chat/stream
+    - `getPlaybooks(): Promise<ExecutionPlan[]>` — GET /api/v1/plans/playbook
+    - `uploadBackup(blob: Buffer, metadata: BackupMetadata): Promise<void>` — PUT /api/v1/backup
+    - `downloadBackup(): Promise<{ blob: Buffer, metadata: BackupMetadata }>` — GET /api/v1/backup
+    - Automatic retry with exponential backoff (max 3 attempts)
+    - Offline detection: returns cached playbook responses when offline
+  - `isOnline(): boolean` — connectivity check
+- [ ] Create `src/main/api/plan-runner.ts`:
+  - `PlanRunner` class:
+    - `execute(plan: ExecutionPlan): Promise<PlanResult>` — executes plan steps locally
+    - Step handlers: `create_record` (inserts into SQLite), `update_record`, `delete_record`, `index_document` (upserts into vector store), `send_notification` (Electron notification API)
+    - Each step logs to activity log
+    - Supports `data_from_step` references (pipeline execution)
+    - Validates plan structure before execution
+- **Files:** `src/main/api/backend-client.ts`, `src/main/api/plan-runner.ts`
+- **Outcome:** Electron can communicate with the cloud backend and execute returned plans locally.
+
+### Step 3.2 — Refactor orchestrator to delegate to backend
+- [ ] Update `src/main/ai/orchestrator.ts`:
+  - When online: forward chat requests to backend via `BackendClient.chatStream()`
+  - Build `ChatRequest` from local context: query SQLite for user profile, relevant documents (from vector store), recent tasks, conversation history
+  - Stream backend response tokens to renderer via existing `ai:stream` IPC channel
+  - Execute any returned actions via `PlanRunner`
+  - When offline: fall back to local orchestration (existing LangGraph pipeline) with degraded capabilities
+  - Remove direct agent logic (project agent, knowledge agent, general agent tool definitions) — these now live on the backend
+  - Keep `buildProjectContext()` and `buildGlobalContext()` as context builders for the request payload
+- [ ] Update `src/main/router/index.ts` `ai` sub-router:
+  - `chat` mutation: call refactored orchestrator (which now delegates to backend)
+  - Add `getPlaybooks` query: fetches cached playbooks
+  - Keep `dailyBrief` mutation: sends daily brief request to backend
+- [ ] Add IPC handler for plan execution results
+- **Files:** `src/main/ai/orchestrator.ts`, `src/main/router/index.ts`, `src/main/ipc.ts`
+- **Outcome:** Chat intelligence lives on the backend; Electron is the execution layer.
+
+### Step 3.3 — Implement Shared Memory (three-tier local memory)
+- [ ] Create `src/main/database/shared-memory.ts`:
+  - **Short-term memory**: In-memory conversation buffer
+    - `ConversationBuffer` class: stores last N messages per session
+    - `addMessage(sessionId, role, content)`, `getHistory(sessionId, limit?) -> Message[]`
+    - Cleared on session end
+  - **Long-term KV store**: SQLite-backed key-value store
+    - New `agent_memory` table: `id`, `namespace` (agent name), `key`, `value` (JSON text), `updated_at`
+    - `AgentMemoryStore` class: `get(namespace, key)`, `set(namespace, key, value)`, `delete(namespace, key)`, `listKeys(namespace)`
+    - Used by agents to persist learned facts, user preferences
+  - **Vector store**: Already exists (LanceDB). Enhance with:
+    - Multi-collection support: separate tables for notes, emails, files, calendar
+    - `searchByCollection(collection, query, limit) -> SearchResult[]`
+- [ ] Add `agent_memory` table to `src/main/db/schema.ts`
+- [ ] Generate migration
+- **Files:** `src/main/database/shared-memory.ts`, `src/main/db/schema.ts`, `src/main/db/migrations/`
+- **Outcome:** Three-tier memory system supporting short-term conversation, long-term agent facts, and semantic search.
+
+---
+
+## Phase 4 — Security: E2E Backup & Offline Mode
+
+### Step 4.1 — Implement E2E encrypted backup
+- [ ] Create `src/main/backup/e2e-crypto.ts`:
+  - `generatePassphrase(): string` — BIP39-compatible 12-word recovery phrase
+  - `deriveKey(passphrase: string, salt: Buffer): Promise<Buffer>` — Argon2id key derivation (time cost 3, memory 64MB, parallelism 1)
+  - `encrypt(data: Buffer, key: Buffer): { ciphertext: Buffer, iv: Buffer, authTag: Buffer }` — AES-256-GCM
+  - `decrypt(ciphertext: Buffer, key: Buffer, iv: Buffer, authTag: Buffer): Buffer`
+  - Uses `node:crypto` for AES and `argon2` npm package for key derivation
+- [ ] Create `src/main/backup/backup-manager.ts`:
+  - `BackupManager` class:
+    - `createBackup(passphrase: string): Promise<BackupBlob>` — Exports SQLite DB, encrypts, returns blob + metadata
+    - `restoreBackup(blob: Buffer, passphrase: string): Promise<void>` — Decrypts blob, replaces local DB, re-initializes
+    - `uploadBackup(passphrase: string): Promise<void>` — Creates backup, uploads via `BackendClient`
+    - `downloadAndRestore(passphrase: string): Promise<void>` — Downloads from backend, decrypts, restores
+    - Incremental backup: chunks DB into segments, encrypts each separately, tracks content hashes to skip unchanged chunks
+    - Metadata header: version, timestamp, checksum (SHA-256 of plaintext), chunk count
+- **Files:** `src/main/backup/e2e-crypto.ts`, `src/main/backup/backup-manager.ts`
+- **Outcome:** User data never leaves the device unencrypted. Backend stores only opaque blobs.
+
+### Step 4.2 — Implement offline sync queue
+- [ ] Create `src/main/backup/sync-queue.ts`:
+  - `SyncQueue` class:
+    - `enqueue(action: QueuedAction): void` — Adds action to persistent queue (SQLite table `sync_queue`)
+    - `processQueue(): Promise<void>` — Processes queued actions in FIFO order when online
+    - `getQueueSize(): number`
+    - `clearQueue(): void`
+    - Conflict resolution: last-write-wins with timestamps
+  - New `sync_queue` table: `id`, `action_type`, `payload` (JSON), `created_at`, `status` (pending/processing/failed), `retry_count`, `last_error`
+  - Auto-drain: watches connectivity, starts processing when online
+  - Failed actions: retry up to 3 times with exponential backoff, then mark as `failed` for user review
+- [ ] Add `sync_queue` table to schema
+- [ ] Integrate with `BackendClient`: when offline, chat/backup calls enqueue instead of failing
+- **Files:** `src/main/backup/sync-queue.ts`, `src/main/db/schema.ts`, `src/main/api/backend-client.ts`
+- **Outcome:** App works offline; queued actions sync automatically when connectivity returns.
+
+---
+
+## Phase 5 — Auth Integration & Database Encryption
+
+### Step 5.1 — Integrate auth into Electron app
+- [ ] Create `src/main/auth/auth-manager.ts`:
+  - `AuthManager` class:
+    - `login(email, password): Promise<void>` — Calls backend POST /api/v1/auth/login, stores JWT in secure storage (via token.ts)
+    - `register(email, password): Promise<void>` — Calls POST /api/v1/auth/register
+    - `logout(): void` — Clears stored JWT
+    - `getToken(): string | null` — Returns current JWT
+    - `refreshToken(): Promise<void>` — Auto-refresh before expiry
+    - `isAuthenticated(): boolean`
+    - `getCurrentTier(): BillingTier`
+  - Auto-refresh: checks token expiry every 5 minutes, refreshes if < 10 minutes remaining
+- [ ] Add tRPC procedures: `auth.login`, `auth.register`, `auth.logout`, `auth.status`, `auth.tier`
+- [ ] Wire `BackendClient` to use `AuthManager.getToken()` for all requests
+- **Files:** `src/main/auth/auth-manager.ts`, `src/main/router/index.ts`, `src/main/api/backend-client.ts`
+- **Outcome:** Electron app has full auth flow; backend requests are authenticated.
+
+### Step 5.2 — Migrate from better-sqlite3 to SQLCipher
+- [ ] Add `@journeyapps/sqlcipher` to dependencies (replaces `better-sqlite3`)
+- [ ] Update `src/main/db/index.ts`:
+  - Replace `better-sqlite3` import with `@journeyapps/sqlcipher`
+  - On first launch: derive DB key from OS keychain or prompt user
+  - `initDb(password)`: opens DB with `PRAGMA key = 'password'`
+  - Migration path for existing unencrypted DBs: detect → export → create encrypted → import → delete old
+  - WAL mode still enabled after keying
+- [ ] Update `src/main/index.ts`: pass password to `initDb()`
+- [ ] Test that all existing Drizzle operations work with SQLCipher
+- **Files:** `package.json`, `src/main/db/index.ts`, `src/main/index.ts`
+- **Outcome:** All local data encrypted at rest with SQLCipher.
+
+---
+
+## Phase 6 — Renderer UI Updates
+
+### Step 6.1 — Update Settings page for multi-provider config
+- [ ] Add provider management UI to Settings:
+  - List of configured providers with status (active/inactive/error)
+  - Add provider form: name dropdown (OpenAI, Anthropic, Google, Mistral, Groq, Ollama), API key input, model selection, endpoint (for Ollama)
+  - Set primary and fallback providers
+  - Test connection button per provider
+- [ ] Add auth section to Settings:
+  - Login/register form
+  - Current tier display with upgrade CTA
+  - Logout button
+- [ ] Add backup section to Settings:
+  - Create/view recovery passphrase
+  - Manual backup trigger
+  - Backup history with restore points
+  - Auto-backup schedule toggle
+- **Files:** `src/renderer/components/settings/` (new), route file
+- **Outcome:** Users can manage AI providers, auth, and backups from Settings.
+
+### Step 6.2 — Add Permission Dialog and Activity Log
+- [ ] Create `src/renderer/components/permissions/PermissionDialog.tsx`:
+  - Modal shown when a plugin requests new permissions
+  - Lists requested permissions with reasons
+  - Per-permission approve/deny toggles
+  - Shows plugin manifest info (name, description, version)
+- [ ] Create `src/renderer/components/permissions/ActivityLog.tsx`:
+  - Filterable table of all plugin activity
+  - Columns: timestamp, plugin name, action type, resource, status
+  - Filter by plugin, date range, action type
+  - Export as CSV
+- [ ] Add tRPC procedures for permission management and activity log queries
+- **Files:** `src/renderer/components/permissions/PermissionDialog.tsx`, `src/renderer/components/permissions/ActivityLog.tsx`, `src/main/router/index.ts`
+- **Outcome:** Transparent permission system with full activity audit trail.
+
+### Step 6.3 — Update AIChatPanel for backend-powered chat
+- [ ] Update `src/renderer/hooks/useAIChat.ts`:
+  - Support WebSocket streaming from backend (when online)
+  - Fall back to IPC streaming (when offline, using local orchestrator)
+  - Add connection status indicator (online/offline/reconnecting)
+  - Support execution plan responses: show plan preview, allow user to approve/modify before execution
+- [ ] Update `src/renderer/components/ai/AIChatPanel.tsx`:
+  - Add connection status badge
+  - Add tier indicator (shows current plan limitations)
+  - Plan approval UI: expandable plan steps with approve/reject buttons
+  - Enhanced error states: differentiate between offline, auth expired, rate limited, server error
+- [ ] Update `src/renderer/components/ai/FloatingChat.tsx`:
+  - Same streaming changes as AIChatPanel
+  - Compact plan approval for inline context
+- **Files:** `src/renderer/hooks/useAIChat.ts`, `src/renderer/components/ai/AIChatPanel.tsx`, `src/renderer/components/ai/FloatingChat.tsx`
+- **Outcome:** Chat UI seamlessly handles both online (backend) and offline (local) modes.
+
+---
+
+## Phase 7 — Cleanup & Hardening
+
+### Step 7.1 — Remove deprecated AI code
+- [ ] Delete `src/main/ai/copilot.ts` (Copilot SDK replaced by LiteLLM)
+- [ ] Delete `src/main/ai/chat-copilot.ts` (LangChain adapter no longer needed)
+- [ ] Delete or archive `src/main/ai/llm.ts` (replaced by `src/main/llm/litellm-client.ts`)
+- [ ] Remove `@github/copilot-sdk`, `@langchain/langgraph` from dependencies (if unused)
+- [ ] Clean up `src/main/ai/provider.ts`: simplify to delegate to `src/main/llm/providers.ts`
+- [ ] Remove `currentSender` module-level mutable state from orchestrator (proper context passing)
+- [ ] Update `src/main/index.ts` startup: remove `import './ai/copilot'`, add `BatchRunner.startScheduler()`, add `AuthManager` init
+- **Files:** Multiple files under `src/main/ai/`, `package.json`, `src/main/index.ts`
+- **Outcome:** No dead code; clean, maintainable codebase.
+
+### Step 7.2 — Add error handling and logging
+- [ ] Implement structured logging in main process:
+  - Log levels: debug, info, warn, error
+  - Log destinations: console (dev), file (production, rotated)
+  - Correlation IDs for request tracing across IPC → backend → response
+- [ ] Add error boundaries in renderer:
+  - Per-route error boundaries
+  - AI chat error boundary (graceful degradation)
+  - Plugin error boundary (shows which plugin failed)
+- **Files:** `src/main/utils/logger.ts` (new), `src/renderer/components/ErrorBoundary.tsx` (new)
+- **Outcome:** Production-ready error handling and observability.
+
+### Step 7.3 — Electron integration tests
+- [ ] Test BackendClient with mocked HTTP responses
+- [ ] Test PlanRunner with sample execution plans
+- [ ] Test SyncQueue offline → online transition
+- [ ] Test BackupManager encrypt → decrypt round-trip
+- [ ] Test PermissionManager grant → check → revoke cycle
+- **Files:** `src/main/__tests__/` (new test directory)
+- **Outcome:** Confidence that all Electron-side components work correctly.
+
+---
+
+## New Dependencies (package.json)
+
+| Package | Purpose |
+|---|---|
+| `@journeyapps/sqlcipher` | Encrypted SQLite (replaces `better-sqlite3`) |
+| `argon2` | Key derivation for E2E backup |
+| `node-cron` | Batch agent scheduling |
+| `chokidar` | File watching (FileWatcher plugin) |
+| `imapflow` | IMAP client (EmailScanner plugin) |
+| `onnxruntime-node` | Local embeddings (optional) |
+
+---
+
+## Execution Notes
+
+- **Each step is independently committable** and produces working code.
+- **Phases 1-2** (LLM client + plugins) are independent of the backend — can start immediately.
+- **Phase 3** (backend integration) requires the backend repo to have the `/api/v1/chat` endpoint ready.
+- **Phase 5.2** (SQLCipher) is intentionally late to avoid encryption overhead during active schema changes.
+- **The existing app continues to work** throughout the migration. Local orchestration is preserved until backend is ready (Step 3.2).

BACKEND_PLAN.md

@@ -0,0 +1,358 @@
+# Backend Plan — Adiuva Cloud API
+
+> **Separate repository.** This document defines the FastAPI backend that the Electron app communicates with.
+>
+> The backend owns: orchestration logic, chat agent intelligence, prompt IP, auth, billing, and backup blob storage.
+> The backend NEVER persists user data. It receives context in requests, uses it for orchestration, and discards it.
+
+---
+
+## Project Structure
+
+```
+adiuva-backend/
+├── app/
+│   ├── __init__.py
+│   ├── main.py                    # FastAPI entry + CORS + lifespan + router includes
+│   ├── core/
+│   │   ├── __init__.py
+│   │   ├── agent_registry.py      # Base classes + singleton registry
+│   │   ├── orchestrator.py        # LLM-based intent router
+│   │   ├── execution_plan.py      # Plan builder + cache
+│   │   └── plugin_loader.py       # Dynamic agent loading
+│   ├── agents/
+│   │   ├── __init__.py            # Auto-registers all agents
+│   │   ├── task_agent.py
+│   │   ├── calendar_agent.py
+│   │   ├── email_agent.py
+│   │   └── analytics_agent.py
+│   ├── api/
+│   │   ├── __init__.py
+│   │   ├── routes/
+│   │   │   ├── __init__.py
+│   │   │   ├── chat.py            # POST /chat + WS /chat/stream
+│   │   │   ├── plans.py           # GET /plans/playbook
+│   │   │   ├── backup.py          # PUT/GET /backup
+│   │   │   ├── auth.py            # Register/login/refresh
+│   │   │   └── billing.py         # Checkout/webhook/subscription
+│   │   └── middleware/
+│   │       ├── __init__.py
+│   │       ├── auth.py            # JWT validation
+│   │       ├── rate_limit.py      # Tier-aware rate limiting
+│   │       └── sanitizer.py       # Strip prompt metadata from responses
+│   ├── billing/
+│   │   ├── __init__.py
+│   │   ├── stripe_service.py      # Stripe checkout + webhooks
+│   │   └── tier_manager.py        # Feature matrix per tier
+│   └── config/
+│       ├── __init__.py
+│       └── settings.py            # Pydantic BaseSettings (env-based)
+├── tests/
+│   ├── __init__.py
+│   ├── conftest.py                # Fixtures: test client, mock agents, mock LLM
+│   ├── test_orchestrator.py
+│   ├── test_agents.py
+│   ├── test_auth.py
+│   └── test_backup.py
+├── alembic/                       # DB migrations (auth/billing tables only)
+│   ├── alembic.ini
+│   └── versions/
+├── requirements.txt
+├── Dockerfile
+├── docker-compose.yml             # App + PostgreSQL + Redis (dev)
+├── .env.example
+└── README.md
+```
+
+---
+
+## Step-by-Step Implementation
+
+### Step 1 — Project scaffolding
+- [ ] Initialize repo with the directory structure above
+- [ ] Write `requirements.txt`:
+  ```
+  fastapi>=0.115.0
+  uvicorn[standard]>=0.34.0
+  langchain>=0.3.0
+  langchain-openai>=0.3.0
+  pydantic>=2.10.0
+  python-jose[cryptography]>=3.3.0
+  stripe>=11.0.0
+  boto3>=1.35.0
+  slowapi>=0.1.9
+  sqlalchemy>=2.0.0
+  asyncpg>=0.30.0
+  alembic>=1.14.0
+  bcrypt>=4.2.0
+  python-dotenv>=1.0.0
+  httpx>=0.28.0
+  websockets>=14.0
+  pytest>=8.0.0
+  pytest-asyncio>=0.24.0
+  ```
+- [ ] Write `app/main.py`: FastAPI app with CORS (allow `app://`, `http://localhost:*`), lifespan (init DB pool, init agent registry), include all routers under `/api/v1`
+- [ ] Write `app/config/settings.py`: `Settings(BaseSettings)` with fields: `DATABASE_URL`, `JWT_SECRET`, `JWT_ALGORITHM` (default HS256), `STRIPE_SECRET_KEY`, `STRIPE_WEBHOOK_SECRET`, `S3_BUCKET`, `S3_REGION`, `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `OPENAI_API_KEY`, `CORS_ORIGINS`, `ENV` (dev/prod)
+- [ ] Write `Dockerfile`: Python 3.12 slim, multi-stage (builder + runtime), non-root user
+- [ ] Write `docker-compose.yml`: app, postgres:16, optional redis
+- [ ] Write `.env.example`
+- **Outcome:** Runnable FastAPI skeleton (returns 404 on all routes).
+
+### Step 2 — Pydantic schemas (API contracts)
+- [ ] Create `app/schemas.py` (mirrors `src/shared/api-types.ts` from Electron repo):
+  - `ChatRequest`: `message: str`, `context: ChatContext`, `execution_mode: Literal['direct', 'plan']`
+  - `ChatContext`: `user_profile: dict`, `relevant_documents: list[str]`, `recent_tasks: list[dict]`, `conversation_history: list[dict]`
+  - `ChatResponse`: `response: str`, `actions: list[PlanAction]`
+  - `PlanAction`: `type: Literal['create_record', 'update_record', 'delete_record', 'index_document', 'send_notification']`, `table: str | None`, `data: dict | None`
+  - `ExecutionPlan`: `agent: str`, `steps: list[PlanStep]`
+  - `PlanStep`: `action: str`, `prompt_template: str | None`, `variables: dict | None`, `data_from_step: int | None`
+  - `BackupMetadata`: `version: int`, `timestamp: int`, `checksum: str`, `chunk_count: int`
+  - `BillingTier`: `Literal['free', 'pro', 'power', 'team']`
+  - `AuthTokens`: `access_token: str`, `refresh_token: str`, `expires_at: int`
+  - `UserProfile`: `id: str`, `email: str`, `tier: BillingTier`
+- **Outcome:** All request/response models defined and validated.
+
+### Step 3 — Agent Registry + base classes
+- [ ] `app/core/agent_registry.py`:
+  - `BaseAgent(ABC)`:
+    - `user_id: str`, `shared_memory: dict`, `vector_store_context: list[str]`, `skills: list[str]`
+    - Abstract `get_name() -> str`, `get_description() -> str`
+  - `ChatAgent(BaseAgent)`:
+    - Abstract `async handle(query: str, context: dict) -> str`
+    - Abstract `get_tools() -> list` (LangChain tool definitions)
+    - Concrete `_tool_loop(llm, messages, tools, max_iter=5) -> str` — shared tool-calling loop
+  - `AgentRegistry` (singleton):
+    - `_agents: dict[str, ChatAgent]`
+    - `register(agent_class)` — decorator pattern
+    - `get(name) -> ChatAgent`
+    - `list_agents() -> list[dict]` — returns `[{name, description}]` for orchestrator prompt
+    - `async call_agent(name, query, context) -> str` — for inter-agent calls
+- [ ] Unit tests: register, get, list, call_agent with mock
+- **Outcome:** Pluggable agent framework.
+
+### Step 4 — Orchestrator
+- [ ] `app/core/orchestrator.py`:
+  - `async classify_intent(message, context, registry) -> str`:
+    - System prompt: "You are an intent classifier. Given the user message and context, decide which agent to route to. Available agents: {registry.list_agents()}. Respond with just the agent name."
+    - Uses gpt-4o-mini via LangChain for low latency
+    - Falls back to `task_agent` if no clear match
+  - `async route_single(agent_name, message, context) -> ChatResponse`:
+    - Instantiates agent from registry
+    - Calls `agent.handle(message, context)`
+    - Returns response + any actions the agent produced
+  - `async route_pipeline(agent_names, message, context) -> ChatResponse`:
+    - Executes agents in sequence
+    - Each agent receives `{...context, previous_results: [...]}`
+    - Final synthesis via LLM: "Summarize these agent results into a coherent response"
+  - `async orchestrate(request: ChatRequest) -> ChatResponse | ExecutionPlan`:
+    - Main entry point
+    - Classifies intent
+    - If `execution_mode == 'direct'`: route + return response
+    - If `execution_mode == 'plan'`: route + return execution plan with template IDs
+  - `async orchestrate_stream(request: ChatRequest) -> AsyncGenerator[str, None]`:
+    - Same as orchestrate but yields tokens for WebSocket streaming
+- [ ] Integration tests with mocked LLM and mocked agents
+- **Outcome:** Intelligent routing with single-agent and pipeline modes.
+
+### Step 5 — Execution Plan generator
+- [ ] `app/core/execution_plan.py`:
+  - `PromptTemplateRegistry`: dict of `template_id -> prompt_text`. Templates are server-side only — client receives IDs.
+  - `ExecutionPlanBuilder`:
+    - `add_step(action, params) -> self`
+    - `add_llm_step(template_id, variables) -> self`
+    - `add_data_step(action, data_from_step) -> self`
+    - `build() -> ExecutionPlan` — validates step references
+  - `PlanCache`:
+    - In-memory LRU (maxsize=1000)
+    - `cache_plan(key, plan)`, `get_plan(key)`, `get_all_playbooks() -> list[ExecutionPlan]`
+    - Playbooks are pre-built plans for common operations (e.g., "create task from email", "generate weekly report")
+- **Outcome:** Plans are cacheable as playbooks. Prompt IP never leaves the server.
+
+### Step 6 — Chat Agents
+- [ ] `app/agents/task_agent.py` — `@registry.register`:
+  - Description: "Manages tasks: create, update, list, suggest"
+  - Tools: `create_task(title, description, priority, due_date)`, `update_task(id, updates)`, `list_tasks(filters)`, `suggest_tasks(notes_context)`
+  - System prompt: PM-oriented, validates task structure, infers priority from context
+  - `handle()`: LLM + tool loop via `_tool_loop()`, returns response text + list of actions performed
+- [ ] `app/agents/calendar_agent.py` — `@registry.register`:
+  - Description: "Calendar management: events, conflicts, scheduling"
+  - Tools: `list_events(date_range)`, `detect_conflicts(events)`, `suggest_reschedule(conflict)`
+  - Works with event metadata passed in context (never raw calendar data stored)
+- [ ] `app/agents/email_agent.py` — `@registry.register`:
+  - Description: "Email analysis: classify, extract actions, draft responses"
+  - Tools: `classify_email(metadata)`, `extract_action_items(metadata)`, `draft_response(thread_context)`
+  - Only processes metadata sent by client — never raw email bodies
+- [ ] `app/agents/analytics_agent.py` — `@registry.register`:
+  - Description: "Workspace analytics: metrics, reports, trends"
+  - Tools: `calculate_metrics(task_data)`, `generate_report(period, data)`, `trend_analysis(data_points)`
+  - Crunches numbers from context, returns structured insights
+- [ ] `app/agents/__init__.py`: imports all agent modules to trigger `@registry.register` decorators
+- [ ] Unit tests per agent with mocked LLM
+- **Outcome:** Four specialized agents, all registered and tested.
+
+### Step 7 — API Routes
+
+#### 7a — Chat endpoint
+- [ ] `app/api/routes/chat.py`:
+  - `POST /api/v1/chat`:
+    - Request: `ChatRequest`
+    - Calls `orchestrate(request)` or `orchestrate()` + `build_plan()`
+    - Response: `ChatResponse` or `ExecutionPlan`
+  - `WebSocket /api/v1/chat/stream`:
+    - Client sends `ChatRequest` as first JSON frame
+    - Server yields token strings via `orchestrate_stream()`
+    - Final frame: JSON `ChatResponse` with `{"done": true, "response": "...", "actions": [...]}`
+    - Heartbeat ping every 30s to keep connection alive
+
+#### 7b — Plans endpoint
+- [ ] `app/api/routes/plans.py`:
+  - `GET /api/v1/plans/playbook`: Returns all playbooks available for the user's tier
+  - `GET /api/v1/plans/playbook/{plan_id}`: Returns a specific plan
+
+#### 7c — Backup endpoint
+- [ ] `app/api/routes/backup.py`:
+  - `PUT /api/v1/backup`: Accepts binary blob + metadata headers (`X-Backup-Version`, `X-Backup-Timestamp`, `X-Backup-Checksum`). Stores in S3 keyed by `{user_id}/{timestamp}`. Enforces tier limits:
+    - Free: 0 (no backup)
+    - Pro: 5 GB
+    - Power: 50 GB
+    - Team: unlimited
+  - `GET /api/v1/backup`: Returns latest blob for authenticated user. Supports `If-Modified-Since`.
+  - `GET /api/v1/backup/history`: Returns list of `BackupMetadata` (no blobs).
+  - `DELETE /api/v1/backup/{backup_id}`: Delete specific backup.
+
+#### 7d — Auth endpoint
+- [ ] `app/api/routes/auth.py`:
+  - `POST /api/v1/auth/register`: `{email, password}` → bcrypt hash → insert user → return `AuthTokens`
+  - `POST /api/v1/auth/login`: Validate credentials → return `AuthTokens`
+  - `POST /api/v1/auth/refresh`: Rotate refresh token → return new `AuthTokens`
+  - `GET /api/v1/auth/me`: Return `UserProfile` for current JWT
+
+#### 7e — Billing endpoint
+- [ ] `app/api/routes/billing.py`:
+  - `POST /api/v1/billing/checkout`: Creates Stripe checkout session → returns URL
+  - `POST /api/v1/billing/webhook`: Handles Stripe webhooks (subscription lifecycle)
+  - `GET /api/v1/billing/subscription`: Returns current subscription info
+  - `DELETE /api/v1/billing/subscription`: Cancels subscription
+
+- **Outcome:** Complete REST + WebSocket API.
+
+### Step 8 — Middleware
+
+#### 8a — Auth middleware
+- [ ] `app/api/middleware/auth.py`:
+  - FastAPI dependency: `get_current_user(token: str = Depends(oauth2_scheme)) -> UserProfile`
+  - Validates JWT signature, expiry, extracts `user_id` and `tier`
+  - Raises `401` on invalid/expired token
+  - Exempt routes: `/api/v1/auth/register`, `/api/v1/auth/login`, `/api/v1/billing/webhook`
+
+#### 8b — Rate limiter
+- [ ] `app/api/middleware/rate_limit.py`:
+  - Uses `slowapi` with `Limiter(key_func=get_user_id_from_jwt)`
+  - Tier-based limits:
+    - Free: 20 req/min
+    - Pro: 60 req/min
+    - Power: 120 req/min
+    - Team: 200 req/seat/min
+  - Custom 429 response with `Retry-After` header
+
+#### 8c — Sanitizer
+- [ ] `app/api/middleware/sanitizer.py`:
+  - Response middleware that scans response bodies
+  - Strips: system prompt fragments, agent internal reasoning, tool schemas, routing metadata
+  - Pattern-based detection + exact match against known prompt fingerprints
+  - Logs sanitization events for monitoring
+
+- **Outcome:** Secure, rate-limited API with prompt IP protection.
+
+### Step 9 — Billing & Tier management
+- [ ] `app/billing/stripe_service.py`:
+  - `create_checkout_session(user_id, tier) -> str`
+  - `handle_webhook(payload, sig_header) -> None`: processes `checkout.session.completed`, `customer.subscription.updated`, `customer.subscription.deleted`, `invoice.payment_failed`
+  - `get_subscription(user_id) -> dict | None`
+  - `cancel_subscription(user_id) -> None`
+- [ ] `app/billing/tier_manager.py`:
+  - `TierManager`:
+    - Feature matrix:
+      ```python
+      FEATURES = {
+          'free':  {'agents': 3, 'batch': False, 'providers': 1, 'backup_gb': 0},
+          'pro':   {'agents': -1, 'batch': True, 'providers': -1, 'backup_gb': 5},
+          'power': {'agents': -1, 'batch': True, 'providers': -1, 'backup_gb': 50, 'byok': True},
+          'team':  {'agents': -1, 'batch': True, 'providers': -1, 'backup_gb': -1, 'sso': True},
+      }
+      ```
+    - `get_tier(user_id) -> BillingTier`
+    - `check_feature(user_id, feature) -> bool`
+    - `get_rate_limit(tier) -> int`
+- **Outcome:** Stripe integration with tier-based feature gating.
+
+### Step 10 — Database (auth/billing only)
+- [ ] PostgreSQL schema via Alembic:
+  - `users`: `id UUID PK`, `email UNIQUE`, `password_hash`, `tier` (default 'free'), `stripe_customer_id`, `created_at`, `updated_at`
+  - `refresh_tokens`: `id UUID PK`, `user_id FK`, `token_hash`, `expires_at`, `created_at`
+  - `subscriptions`: `id UUID PK`, `user_id FK`, `stripe_subscription_id`, `tier`, `status`, `current_period_end`, `created_at`
+  - `backup_metadata`: `id UUID PK`, `user_id FK`, `s3_key`, `version`, `timestamp`, `checksum`, `size_bytes`, `created_at`
+- [ ] Initial Alembic migration
+- [ ] SQLAlchemy models in `app/models.py`
+- **Outcome:** Auth and billing persistence. Zero user data stored.
+
+### Step 11 — Testing & deployment
+- [ ] `tests/conftest.py`: TestClient fixture, mock LLM fixture (`AsyncMock` returning canned responses), mock agent fixture, test DB (SQLite in-memory for speed)
+- [ ] `tests/test_orchestrator.py`: classify_intent routing, single agent, pipeline, plan mode
+- [ ] `tests/test_agents.py`: each agent with mocked tools
+- [ ] `tests/test_auth.py`: register → login → access protected → refresh → expired token
+- [ ] `tests/test_backup.py`: upload → download → history → delete, tier limit enforcement
+- [ ] `Dockerfile` optimized for production (gunicorn + uvicorn workers)
+- [ ] GitHub Actions CI: lint (ruff), test (pytest), build Docker image
+- **Outcome:** Fully tested, deployable backend.
+
+---
+
+## API Contract Summary
+
+| Method | Endpoint | Auth | Request | Response |
+|--------|----------|------|---------|----------|
+| POST | `/api/v1/auth/register` | No | `{email, password}` | `AuthTokens` |
+| POST | `/api/v1/auth/login` | No | `{email, password}` | `AuthTokens` |
+| POST | `/api/v1/auth/refresh` | No | `{refresh_token}` | `AuthTokens` |
+| GET | `/api/v1/auth/me` | JWT | — | `UserProfile` |
+| POST | `/api/v1/chat` | JWT | `ChatRequest` | `ChatResponse \| ExecutionPlan` |
+| WS | `/api/v1/chat/stream` | JWT | `ChatRequest` (first frame) | Token stream + final JSON |
+| GET | `/api/v1/plans/playbook` | JWT | — | `ExecutionPlan[]` |
+| GET | `/api/v1/plans/playbook/:id` | JWT | — | `ExecutionPlan` |
+| PUT | `/api/v1/backup` | JWT | Binary blob + headers | `{ok: true}` |
+| GET | `/api/v1/backup` | JWT | — | Binary blob |
+| GET | `/api/v1/backup/history` | JWT | — | `BackupMetadata[]` |
+| DELETE | `/api/v1/backup/:id` | JWT | — | `{ok: true}` |
+| POST | `/api/v1/billing/checkout` | JWT | `{tier}` | `{checkout_url}` |
+| POST | `/api/v1/billing/webhook` | Stripe sig | Stripe event | `{ok: true}` |
+| GET | `/api/v1/billing/subscription` | JWT | — | Subscription info |
+| DELETE | `/api/v1/billing/subscription` | JWT | — | `{ok: true}` |
+| GET | `/api/v1/health` | No | — | `{status, version}` |
+
+---
+
+## Stack
+
+| Layer | Technology |
+|-------|-----------|
+| Framework | FastAPI + Uvicorn |
+| LLM | LangChain + langchain-openai |
+| Auth | PyJWT + bcrypt + OAuth2 |
+| Billing | stripe-python |
+| Storage | boto3 (S3) |
+| Database | PostgreSQL + SQLAlchemy + Alembic |
+| Rate limiting | slowapi |
+| Testing | pytest + pytest-asyncio + httpx |
+| Deployment | Docker → fly.io / Railway / AWS ECS |
+
+---
+
+## Development Rules
+
+1. **NEVER persist user data.** The DB stores only auth, billing, and backup metadata. User context arrives in requests and is discarded after processing.
+2. **NEVER expose prompts.** System prompts are composed server-side from fragments. Responses are sanitized before sending.
+3. **Stateless request handling.** No server-side session state. All context comes from the client + JWT.
+4. **Type hints everywhere.** All functions have full type annotations.
+5. **Test every agent.** Each chat agent has unit tests with mocked LLM responses.
+6. **Structured logging.** JSON logs with request ID correlation.

knip.json

@@ -0,0 +1,22 @@
+{
+  "$schema": "https://unpkg.com/knip@5/schema.json",
+  "tags": ["-lintignore"],
+  "entry": [
+    "src/main/index.ts",
+    "src/preload/index.ts",
+    "src/preload/trpc.ts",
+    "forge.config.ts",
+    "vite.main.config.mts",
+    "vite.preload.config.mts",
+    "vite.renderer.config.mts"
+  ],
+  "ignoreDependencies": [
+    "postcss",
+    "@electron-forge/shared-types",
+    "@milkdown/plugin-upload",
+    "@milkdown/prose"
+  ],
+  "ignore": [
+    "src/renderer/components/ui/**"
+  ]
+}

package-lock.json

@@ -17,7 +17,6 @@
         "@langchain/langgraph": "^1.1.5",
         "@langchain/openai": "^1.2.9",
         "@milkdown/crepe": "^7.18.0",
-        "@milkdown/kit": "^7.18.0",
         "@tailwindcss/typography": "^0.5.19",
         "@tailwindcss/vite": "^4.2.0",
         "@tanstack/react-query": "^5.90.21",
@@ -59,6 +58,7 @@
         "@tanstack/router-vite-plugin": "^1.161.1",
         "@types/better-sqlite3": "^7.6.13",
         "@types/electron-squirrel-startup": "^1.0.2",
+        "@types/node": "^25.3.3",
         "@types/react": "^19.2.14",
         "@types/react-dom": "^19.2.3",
         "@typescript-eslint/eslint-plugin": "^5.62.0",
@@ -69,6 +69,7 @@
         "eslint": "^8.57.1",
         "eslint-import-resolver-typescript": "^4.4.4",
         "eslint-plugin-import": "^2.32.0",
+        "knip": "^5.85.0",
         "postcss": "^8.5.6",
         "shadcn": "^3.8.5",
         "tailwindcss": "^4.2.0",
@@ -4930,6 +4931,306 @@
       "dev": true,
       "license": "MIT"
     },
+    "node_modules/@oxc-resolver/binding-android-arm-eabi": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-android-arm-eabi/-/binding-android-arm-eabi-11.19.1.tgz",
+      "integrity": "sha512-aUs47y+xyXHUKlbhqHUjBABjvycq6YSD7bpxSW7vplUmdzAlJ93yXY6ZR0c1o1x5A/QKbENCvs3+NlY8IpIVzg==",
+      "cpu": [
+        "arm"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "android"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-android-arm64": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-android-arm64/-/binding-android-arm64-11.19.1.tgz",
+      "integrity": "sha512-oolbkRX+m7Pq2LNjr/kKgYeC7bRDMVTWPgxBGMjSpZi/+UskVo4jsMU3MLheZV55jL6c3rNelPl4oD60ggYmqA==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "android"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-darwin-arm64": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-darwin-arm64/-/binding-darwin-arm64-11.19.1.tgz",
+      "integrity": "sha512-nUC6d2i3R5B12sUW4O646qD5cnMXf2oBGPLIIeaRfU9doJRORAbE2SGv4eW6rMqhD+G7nf2Y8TTJTLiiO3Q/dQ==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-darwin-x64": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-darwin-x64/-/binding-darwin-x64-11.19.1.tgz",
+      "integrity": "sha512-cV50vE5+uAgNcFa3QY1JOeKDSkM/9ReIcc/9wn4TavhW/itkDGrXhw9jaKnkQnGbjJ198Yh5nbX/Gr2mr4Z5jQ==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-freebsd-x64": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-freebsd-x64/-/binding-freebsd-x64-11.19.1.tgz",
+      "integrity": "sha512-xZOQiYGFxtk48PBKff+Zwoym7ScPAIVp4c14lfLxizO2LTTTJe5sx9vQNGrBymrf/vatSPNMD4FgsaaRigPkqw==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "freebsd"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-linux-arm-gnueabihf": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-linux-arm-gnueabihf/-/binding-linux-arm-gnueabihf-11.19.1.tgz",
+      "integrity": "sha512-lXZYWAC6kaGe/ky2su94e9jN9t6M0/6c+GrSlCqL//XO1cxi5lpAhnJYdyrKfm0ZEr/c7RNyAx3P7FSBcBd5+A==",
+      "cpu": [
+        "arm"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-linux-arm-musleabihf": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-linux-arm-musleabihf/-/binding-linux-arm-musleabihf-11.19.1.tgz",
+      "integrity": "sha512-veG1kKsuK5+t2IsO9q0DErYVSw2azvCVvWHnfTOS73WE0STdLLB7Q1bB9WR+yHPQM76ASkFyRbogWo1GR1+WbQ==",
+      "cpu": [
+        "arm"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-linux-arm64-gnu": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-linux-arm64-gnu/-/binding-linux-arm64-gnu-11.19.1.tgz",
+      "integrity": "sha512-heV2+jmXyYnUrpUXSPugqWDRpnsQcDm2AX4wzTuvgdlZfoNYO0O3W2AVpJYaDn9AG4JdM6Kxom8+foE7/BcSig==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-linux-arm64-musl": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-linux-arm64-musl/-/binding-linux-arm64-musl-11.19.1.tgz",
+      "integrity": "sha512-jvo2Pjs1c9KPxMuMPIeQsgu0mOJF9rEb3y3TdpsrqwxRM+AN6/nDDwv45n5ZrUnQMsdBy5gIabioMKnQfWo9ew==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-linux-ppc64-gnu": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-linux-ppc64-gnu/-/binding-linux-ppc64-gnu-11.19.1.tgz",
+      "integrity": "sha512-vLmdNxWCdN7Uo5suays6A/+ywBby2PWBBPXctWPg5V0+eVuzsJxgAn6MMB4mPlshskYbppjpN2Zg83ArHze9gQ==",
+      "cpu": [
+        "ppc64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-linux-riscv64-gnu": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-linux-riscv64-gnu/-/binding-linux-riscv64-gnu-11.19.1.tgz",
+      "integrity": "sha512-/b+WgR+VTSBxzgOhDO7TlMXC1ufPIMR6Vj1zN+/x+MnyXGW7prTLzU9eW85Aj7Th7CCEG9ArCbTeqxCzFWdg2w==",
+      "cpu": [
+        "riscv64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-linux-riscv64-musl": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-linux-riscv64-musl/-/binding-linux-riscv64-musl-11.19.1.tgz",
+      "integrity": "sha512-YlRdeWb9j42p29ROh+h4eg/OQ3dTJlpHSa+84pUM9+p6i3djtPz1q55yLJhgW9XfDch7FN1pQ/Vd6YP+xfRIuw==",
+      "cpu": [
+        "riscv64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-linux-s390x-gnu": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-linux-s390x-gnu/-/binding-linux-s390x-gnu-11.19.1.tgz",
+      "integrity": "sha512-EDpafVOQWF8/MJynsjOGFThcqhRHy417sRyLfQmeiamJ8qVhSKAn2Dn2VVKUGCjVB9C46VGjhNo7nOPUi1x6uA==",
+      "cpu": [
+        "s390x"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-linux-x64-gnu": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-linux-x64-gnu/-/binding-linux-x64-gnu-11.19.1.tgz",
+      "integrity": "sha512-NxjZe+rqWhr+RT8/Ik+5ptA3oz7tUw361Wa5RWQXKnfqwSSHdHyrw6IdcTfYuml9dM856AlKWZIUXDmA9kkiBQ==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-linux-x64-musl": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-linux-x64-musl/-/binding-linux-x64-musl-11.19.1.tgz",
+      "integrity": "sha512-cM/hQwsO3ReJg5kR+SpI69DMfvNCp+A/eVR4b4YClE5bVZwz8rh2Nh05InhwI5HR/9cArbEkzMjcKgTHS6UaNw==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-openharmony-arm64": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-openharmony-arm64/-/binding-openharmony-arm64-11.19.1.tgz",
+      "integrity": "sha512-QF080IowFB0+9Rh6RcD19bdgh49BpQHUW5TajG1qvWHvmrQznTZZjYlgE2ltLXyKY+qs4F/v5xuX1XS7Is+3qA==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "openharmony"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-wasm32-wasi": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-wasm32-wasi/-/binding-wasm32-wasi-11.19.1.tgz",
+      "integrity": "sha512-w8UCKhX826cP/ZLokXDS6+milN8y4X7zidsAttEdWlVoamTNf6lhBJldaWr3ukTDiye7s4HRcuPEPOXNC432Vg==",
+      "cpu": [
+        "wasm32"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "dependencies": {
+        "@napi-rs/wasm-runtime": "^1.1.1"
+      },
+      "engines": {
+        "node": ">=14.0.0"
+      }
+    },
+    "node_modules/@oxc-resolver/binding-wasm32-wasi/node_modules/@napi-rs/wasm-runtime": {
+      "version": "1.1.1",
+      "resolved": "https://registry.npmjs.org/@napi-rs/wasm-runtime/-/wasm-runtime-1.1.1.tgz",
+      "integrity": "sha512-p64ah1M1ld8xjWv3qbvFwHiFVWrq1yFvV4f7w+mzaqiR4IlSgkqhcRdHwsGgomwzBH51sRY4NEowLxnaBjcW/A==",
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "dependencies": {
+        "@emnapi/core": "^1.7.1",
+        "@emnapi/runtime": "^1.7.1",
+        "@tybys/wasm-util": "^0.10.1"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/Brooooooklyn"
+      }
+    },
+    "node_modules/@oxc-resolver/binding-win32-arm64-msvc": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-win32-arm64-msvc/-/binding-win32-arm64-msvc-11.19.1.tgz",
+      "integrity": "sha512-nJ4AsUVZrVKwnU/QRdzPCCrO0TrabBqgJ8pJhXITdZGYOV28TIYystV1VFLbQ7DtAcaBHpocT5/ZJnF78YJPtQ==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "win32"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-win32-ia32-msvc": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-win32-ia32-msvc/-/binding-win32-ia32-msvc-11.19.1.tgz",
+      "integrity": "sha512-EW+ND5q2Tl+a3pH81l1QbfgbF3HmqgwLfDfVithRFheac8OTcnbXt/JxqD2GbDkb7xYEqy1zNaVFRr3oeG8npA==",
+      "cpu": [
+        "ia32"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "win32"
+      ]
+    },
+    "node_modules/@oxc-resolver/binding-win32-x64-msvc": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/@oxc-resolver/binding-win32-x64-msvc/-/binding-win32-x64-msvc-11.19.1.tgz",
+      "integrity": "sha512-6hIU3RQu45B+VNTY4Ru8ppFwjVS/S5qwYyGhBotmjxfEKk41I2DlGtRfGJndZ5+6lneE2pwloqunlOyZuX/XAw==",
+      "cpu": [
+        "x64"
+      ],
+      "dev": true,
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "win32"
+      ]
+    },
     "node_modules/@radix-ui/number": {
       "version": "1.1.1",
       "resolved": "https://registry.npmjs.org/@radix-ui/number/-/number-1.1.1.tgz",
@@ -7934,9 +8235,9 @@
       }
     },
     "node_modules/@types/node": {
-      "version": "25.3.0",
-      "resolved": "https://registry.npmjs.org/@types/node/-/node-25.3.0.tgz",
-      "integrity": "sha512-4K3bqJpXpqfg2XKGK9bpDTc6xO/xoUP/RBWS7AtRMug6zZFaRekiLzjVtAoZMquxoAbzBvy5nxQ7veS5eYzf8A==",
+      "version": "25.3.3",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-25.3.3.tgz",
+      "integrity": "sha512-DpzbrH7wIcBaJibpKo9nnSQL0MTRdnWttGyE5haGwK86xgMOkFLp7vEyfQPGLOJh5wNYiJ3V9PmUMDhV9u8kkQ==",
       "devOptional": true,
       "license": "MIT",
       "dependencies": {
@@ -13488,6 +13789,16 @@
         "reusify": "^1.0.4"
       }
     },
+    "node_modules/fd-package-json": {
+      "version": "2.0.0",
+      "resolved": "https://registry.npmjs.org/fd-package-json/-/fd-package-json-2.0.0.tgz",
+      "integrity": "sha512-jKmm9YtsNXN789RS/0mSzOC1NUq9mkVd65vbSSVsKdjGvYXBuE4oWe2QOEoFeRmJg+lPuZxpmrfFclNhoRMneQ==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "walk-up-path": "^4.0.0"
+      }
+    },
     "node_modules/fd-slicer": {
       "version": "1.1.0",
       "resolved": "https://registry.npmjs.org/fd-slicer/-/fd-slicer-1.1.0.tgz",
@@ -13758,6 +14069,22 @@
         "node": ">= 6"
       }
     },
+    "node_modules/formatly": {
+      "version": "0.3.0",
+      "resolved": "https://registry.npmjs.org/formatly/-/formatly-0.3.0.tgz",
+      "integrity": "sha512-9XNj/o4wrRFyhSMJOvsuyMwy8aUfBaZ1VrqHVfohyXf0Sw0e+yfKG+xZaY3arGCOMdwFsqObtzVOc1gU9KiT9w==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "fd-package-json": "^2.0.0"
+      },
+      "bin": {
+        "formatly": "bin/index.mjs"
+      },
+      "engines": {
+        "node": ">=18.3.0"
+      }
+    },
     "node_modules/formdata-polyfill": {
       "version": "4.0.10",
       "resolved": "https://registry.npmjs.org/formdata-polyfill/-/formdata-polyfill-4.0.10.tgz",
@@ -15711,6 +16038,74 @@
         "node": ">=6"
       }
     },
+    "node_modules/knip": {
+      "version": "5.85.0",
+      "resolved": "https://registry.npmjs.org/knip/-/knip-5.85.0.tgz",
+      "integrity": "sha512-V2kyON+DZiYdNNdY6GALseiNCwX7dYdpz9Pv85AUn69Gk0UKCts+glOKWfe5KmaMByRjM9q17Mzj/KinTVOyxg==",
+      "dev": true,
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/webpro"
+        },
+        {
+          "type": "opencollective",
+          "url": "https://opencollective.com/knip"
+        }
+      ],
+      "license": "ISC",
+      "dependencies": {
+        "@nodelib/fs.walk": "^1.2.3",
+        "fast-glob": "^3.3.3",
+        "formatly": "^0.3.0",
+        "jiti": "^2.6.0",
+        "js-yaml": "^4.1.1",
+        "minimist": "^1.2.8",
+        "oxc-resolver": "^11.15.0",
+        "picocolors": "^1.1.1",
+        "picomatch": "^4.0.1",
+        "smol-toml": "^1.5.2",
+        "strip-json-comments": "5.0.3",
+        "zod": "^4.1.11"
+      },
+      "bin": {
+        "knip": "bin/knip.js",
+        "knip-bun": "bin/knip-bun.js"
+      },
+      "engines": {
+        "node": ">=18.18.0"
+      },
+      "peerDependencies": {
+        "@types/node": ">=18",
+        "typescript": ">=5.0.4 <7"
+      }
+    },
+    "node_modules/knip/node_modules/picomatch": {
+      "version": "4.0.3",
+      "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
+      "integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=12"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/jonschlinkert"
+      }
+    },
+    "node_modules/knip/node_modules/strip-json-comments": {
+      "version": "5.0.3",
+      "resolved": "https://registry.npmjs.org/strip-json-comments/-/strip-json-comments-5.0.3.tgz",
+      "integrity": "sha512-1tB5mhVo7U+ETBKNf92xT4hrQa3pm0MZ0PQvuDnWgAAGHDsfp4lPSpiS6psrSiet87wyGPh9ft6wmhOMQ0hDiw==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=14.16"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/sindresorhus"
+      }
+    },
     "node_modules/langsmith": {
       "version": "0.5.6",
       "resolved": "https://registry.npmjs.org/langsmith/-/langsmith-0.5.6.tgz",
@@ -18270,6 +18665,38 @@
         "url": "https://github.com/sponsors/ljharb"
       }
     },
+    "node_modules/oxc-resolver": {
+      "version": "11.19.1",
+      "resolved": "https://registry.npmjs.org/oxc-resolver/-/oxc-resolver-11.19.1.tgz",
+      "integrity": "sha512-qE/CIg/spwrTBFt5aKmwe3ifeDdLfA2NESN30E42X/lII5ClF8V7Wt6WIJhcGZjp0/Q+nQ+9vgxGk//xZNX2hg==",
+      "dev": true,
+      "license": "MIT",
+      "funding": {
+        "url": "https://github.com/sponsors/Boshen"
+      },
+      "optionalDependencies": {
+        "@oxc-resolver/binding-android-arm-eabi": "11.19.1",
+        "@oxc-resolver/binding-android-arm64": "11.19.1",
+        "@oxc-resolver/binding-darwin-arm64": "11.19.1",
+        "@oxc-resolver/binding-darwin-x64": "11.19.1",
+        "@oxc-resolver/binding-freebsd-x64": "11.19.1",
+        "@oxc-resolver/binding-linux-arm-gnueabihf": "11.19.1",
+        "@oxc-resolver/binding-linux-arm-musleabihf": "11.19.1",
+        "@oxc-resolver/binding-linux-arm64-gnu": "11.19.1",
+        "@oxc-resolver/binding-linux-arm64-musl": "11.19.1",
+        "@oxc-resolver/binding-linux-ppc64-gnu": "11.19.1",
+        "@oxc-resolver/binding-linux-riscv64-gnu": "11.19.1",
+        "@oxc-resolver/binding-linux-riscv64-musl": "11.19.1",
+        "@oxc-resolver/binding-linux-s390x-gnu": "11.19.1",
+        "@oxc-resolver/binding-linux-x64-gnu": "11.19.1",
+        "@oxc-resolver/binding-linux-x64-musl": "11.19.1",
+        "@oxc-resolver/binding-openharmony-arm64": "11.19.1",
+        "@oxc-resolver/binding-wasm32-wasi": "11.19.1",
+        "@oxc-resolver/binding-win32-arm64-msvc": "11.19.1",
+        "@oxc-resolver/binding-win32-ia32-msvc": "11.19.1",
+        "@oxc-resolver/binding-win32-x64-msvc": "11.19.1"
+      }
+    },
     "node_modules/p-cancelable": {
       "version": "2.1.1",
       "resolved": "https://registry.npmjs.org/p-cancelable/-/p-cancelable-2.1.1.tgz",
@@ -21397,6 +21824,19 @@
         "npm": ">= 3.0.0"
       }
     },
+    "node_modules/smol-toml": {
+      "version": "1.6.0",
+      "resolved": "https://registry.npmjs.org/smol-toml/-/smol-toml-1.6.0.tgz",
+      "integrity": "sha512-4zemZi0HvTnYwLfrpk/CF9LOd9Lt87kAt50GnqhMpyF9U3poDAP2+iukq2bZsO/ufegbYehBkqINbsWxj4l4cw==",
+      "dev": true,
+      "license": "BSD-3-Clause",
+      "engines": {
+        "node": ">= 18"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/cyyynthia"
+      }
+    },
     "node_modules/socks": {
       "version": "2.8.7",
       "resolved": "https://registry.npmjs.org/socks/-/socks-2.8.7.tgz",
@@ -23646,6 +24086,16 @@
       "integrity": "sha512-dpojBhNsCNN7T82Tm7k26A6G9ML3NkhDsnw9n/eoxSRlVBB4CEtIQ/KTCLI2Fwf3ataSXRhYFkQi3SlnFwPvPQ==",
       "license": "MIT"
     },
+    "node_modules/walk-up-path": {
+      "version": "4.0.0",
+      "resolved": "https://registry.npmjs.org/walk-up-path/-/walk-up-path-4.0.0.tgz",
+      "integrity": "sha512-3hu+tD8YzSLGuFYtPRb48vdhKMi0KQV5sn+uWr8+7dMEq/2G/dtLrdDinkLjqq5TIbIBjYJ4Ax/n3YiaW7QM8A==",
+      "dev": true,
+      "license": "ISC",
+      "engines": {
+        "node": "20 || >=22"
+      }
+    },
     "node_modules/watchpack": {
       "version": "2.5.1",
       "resolved": "https://registry.npmjs.org/watchpack/-/watchpack-2.5.1.tgz",

package.json

@@ -10,7 +10,8 @@
     "package": "electron-forge package",
     "make": "electron-forge make",
     "publish": "electron-forge publish",
-    "lint": "eslint --ext .ts,.tsx ."
+    "lint": "eslint --ext .ts,.tsx .",
+    "knip": "knip"
   },
   "keywords": [],
   "author": "rmusso",
@@ -28,6 +29,7 @@
     "@tanstack/router-vite-plugin": "^1.161.1",
     "@types/better-sqlite3": "^7.6.13",
     "@types/electron-squirrel-startup": "^1.0.2",
+    "@types/node": "^25.3.3",
     "@types/react": "^19.2.14",
     "@types/react-dom": "^19.2.3",
     "@typescript-eslint/eslint-plugin": "^5.62.0",
@@ -38,6 +40,7 @@
     "eslint": "^8.57.1",
     "eslint-import-resolver-typescript": "^4.4.4",
     "eslint-plugin-import": "^2.32.0",
+    "knip": "^5.85.0",
     "postcss": "^8.5.6",
     "shadcn": "^3.8.5",
     "tailwindcss": "^4.2.0",
@@ -53,7 +56,6 @@
     "@langchain/langgraph": "^1.1.5",
     "@langchain/openai": "^1.2.9",
     "@milkdown/crepe": "^7.18.0",
-    "@milkdown/kit": "^7.18.0",
     "@tailwindcss/typography": "^0.5.19",
     "@tailwindcss/vite": "^4.2.0",
     "@tanstack/react-query": "^5.90.21",

src/main/ai/orchestrator.ts

@@ -33,13 +33,13 @@ let currentSender: Electron.WebContents | undefined;
 // Types
 // ---------------------------------------------------------------------------
 
-export interface OrchestrateInput {
+interface OrchestrateInput {
   message: string;
   context: { type: 'global' | 'project'; projectId?: string; uiContext?: string };
   sender?: Electron.WebContents;
 }
 
-export interface OrchestrateResult {
+interface OrchestrateResult {
   response: string;
   error?: string;
 }

src/main/ai/provider.ts

@@ -33,7 +33,7 @@ export function getActiveProviderName(): string {
 }
 
 /** Switch to a different registered provider. */
-export function setActiveProviderName(name: string): void {
+function setActiveProviderName(name: string): void {
   const provider = providers.get(name);
   if (!provider) throw new Error(`Unknown AI provider: ${name}`);
   activeProvider = provider;

src/main/ai/token.ts

@@ -100,7 +100,7 @@ export async function setToken(providerName: string, token: string): Promise<voi
 }
 
 /** Delete a stored token for the given provider. */
-export async function deleteToken(providerName: string): Promise<boolean> {
+async function deleteToken(providerName: string): Promise<boolean> {
   if (useKeytar()) {
     try {
       return await keytar!.deletePassword(SERVICE_NAME, providerName);

src/main/ipc.ts

@@ -14,7 +14,7 @@ import {
   type AnyRouter,
 } from '@trpc/server';
 
-export const IPC_CHANNEL = 'trpc';
+const IPC_CHANNEL = 'trpc';
 
 /** Context passed to every tRPC procedure via the IPC bridge. */
 export type TRPCContext = {

src/renderer/components/ai/AIChatPanel.tsx

@@ -10,6 +10,9 @@ import { Skeleton } from '@/components/ui/skeleton';
 import { ScrollArea } from '@/components/ui/scroll-area';
 import { GradualBlur } from '@/components/ui/gradual-blur';
 
+/** Fluid font size for chat messages — scales with viewport width */
+const CHAT_FONT = 'clamp(1.125rem, 1.4vw, 1.375rem)';
+
 const SUGGESTION_CHIPS = [
   { icon: ListTodo, label: "What's on my plate today?" },
   { icon: TrendingUp, label: 'Summarize this week' },
@@ -78,17 +81,45 @@ export function AIChatPanel({
 
   const messagesContainerRef = useRef<HTMLDivElement | null>(null);
 
+  // --- Scroll-to-user-message + shrinking placeholder ---
+  const lastUserMsgRef = useRef<HTMLDivElement | null>(null);
+  const [streamingEl, setStreamingEl] = useState<HTMLDivElement | null>(null);
+  const [placeholderHeight, setPlaceholderHeight] = useState<number | null>(null);
+  const initialPlaceholderRef = useRef(0);
+  const pendingScrollRef = useRef(false);
+
   const briefMutation = trpc.ai.dailyBrief.useMutation();
 
-  const scrollToBottom = useCallback(() => {
-    const el = messagesContainerRef.current;
-    if (el) el.scrollTo({ top: el.scrollHeight });
-  }, []);
-
-  // Auto-scroll when messages change or streaming content updates
+  // When the user message appears in the list, set the placeholder and scroll it to the top
   useEffect(() => {
-    scrollToBottom();
-  }, [messages, streamingContent, scrollToBottom]);
+    if (!pendingScrollRef.current) return;
+    const lastMsg = messages[messages.length - 1];
+    if (!lastMsg || lastMsg.role !== 'user') return;
+
+    pendingScrollRef.current = false;
+    const ph = Math.round(window.innerHeight * 0.71);
+    initialPlaceholderRef.current = ph;
+    setPlaceholderHeight(ph);
+
+    // Double-rAF: wait for the placeholder div to actually paint before scrolling
+    requestAnimationFrame(() => {
+      requestAnimationFrame(() => {
+        lastUserMsgRef.current?.scrollIntoView({ block: 'start', behavior: 'smooth' });
+      });
+    });
+  }, [messages]);
+
+  // Shrink placeholder in real-time as AI streaming content grows
+  useEffect(() => {
+    if (!isStreaming || !streamingEl) return;
+    const MIN_PADDING = 80;
+    const observer = new ResizeObserver(() => {
+      const contentHeight = streamingEl.getBoundingClientRect().height;
+      setPlaceholderHeight(Math.max(MIN_PADDING, initialPlaceholderRef.current - contentHeight));
+    });
+    observer.observe(streamingEl);
+    return () => observer.disconnect();
+  }, [isStreaming, streamingEl]);
 
   // Auto-fire daily brief on home page
   useEffect(() => {
@@ -125,6 +156,7 @@ export function AIChatPanel({
 
   const handleSend = useCallback(() => {
     if (briefLoading) return;
+    pendingScrollRef.current = true;
     chatHandleSend();
   }, [briefLoading, chatHandleSend]);
 
@@ -135,7 +167,6 @@ export function AIChatPanel({
     }
   };
 
-
   const hasMessages = messages.length > 0 || isStreaming;
 
   // Derived values for home page
@@ -162,12 +193,14 @@ export function AIChatPanel({
                 <div className="flex-1" />
                 <button
                   onClick={() => setBriefExpanded((v) => !v)}
+                  aria-label={briefExpanded ? 'Collapse brief' : 'Expand brief'}
                   className="flex h-6 w-6 items-center justify-center rounded-md text-muted-foreground transition-colors hover:text-foreground hover:bg-muted/60"
                 >
                   {briefExpanded ? <ChevronUp size={14} /> : <ChevronDown size={14} />}
                 </button>
                 <button
                   onClick={() => setBriefDismissed(true)}
+                  aria-label="Dismiss brief"
                   className="flex h-6 w-6 items-center justify-center rounded-md text-muted-foreground transition-colors hover:text-foreground hover:bg-muted/60"
                 >
                   <X size={14} />
@@ -177,7 +210,7 @@ export function AIChatPanel({
               {!briefExpanded && (
                 <div className="px-4 pb-3 -mt-1">
                   <p className="text-xs text-muted-foreground truncate">
-                    {dailyBrief.replace(/[#*_~`>\-]/g, '').slice(0, 120)}...
+                    {dailyBrief.replace(/[#*_~`>-]/g, '').slice(0, 120)}...
                   </p>
                 </div>
               )}
@@ -324,12 +357,18 @@ export function AIChatPanel({
           <div className="mx-auto w-full max-w-6xl px-6 pt-8 pb-32">
             <div className="flex flex-col gap-4">
               {/* Chat messages */}
-              {messages.map((msg) => {
+              {messages.map((msg, idx) => {
+                const isLastMsg = idx === messages.length - 1;
+
                 if (msg.role === 'user') {
                   return (
-                    <div key={msg.id} className="flex justify-end">
+                    <div
+                      key={msg.id}
+                      ref={isLastMsg ? lastUserMsgRef : undefined}
+                      className="flex justify-end"
+                    >
                       <div className="ml-auto max-w-[75%] rounded-2xl bg-muted px-4 py-2">
-                        <ChatMarkdown content={msg.content} />
+                        <ChatMarkdown content={msg.content} fontSize={CHAT_FONT} />
                       </div>
                     </div>
                   );
@@ -338,7 +377,7 @@ export function AIChatPanel({
                 if (msg.error) {
                   return (
                     <div key={msg.id} className="mr-auto max-w-[75%]">
-                      <p className="text-sm text-destructive whitespace-pre-wrap">
+                      <p style={{ fontSize: CHAT_FONT }} className="text-destructive whitespace-pre-wrap">
                         {msg.content}
                       </p>
                     </div>
@@ -349,10 +388,10 @@ export function AIChatPanel({
                   <div key={msg.id} className="mr-auto max-w-[75%]">
                     <div className="flex items-center gap-1.5 mb-1">
                       <Sparkles size={16} className="text-foreground" />
-                      <span className="text-sm font-semibold">Adiuva</span>
+                      <span style={{ fontSize: CHAT_FONT }} className="font-semibold">Adiuva</span>
                     </div>
                     <div className="pl-[22px]">
-                      <ChatMarkdown content={msg.content} />
+                      <ChatMarkdown content={msg.content} fontSize={CHAT_FONT} />
                     </div>
                   </div>
                 );
@@ -360,14 +399,14 @@ export function AIChatPanel({
 
               {/* Streaming AI response */}
               {isStreaming && (
-                <div className="mr-auto max-w-[75%]">
+                <div ref={setStreamingEl} className="mr-auto max-w-[75%]">
                   <div className="flex items-center gap-1.5 mb-1">
                     <Sparkles size={16} className="text-foreground" />
-                    <span className="text-sm font-semibold">Adiuva</span>
+                    <span style={{ fontSize: CHAT_FONT }} className="font-semibold">Adiuva</span>
                   </div>
                   {streamingContent ? (
                     <div className="pl-[22px]">
-                      <ChatMarkdown content={streamingContent} />
+                      <ChatMarkdown content={streamingContent} fontSize={CHAT_FONT} />
                     </div>
                   ) : (
                     <div className="space-y-2 pl-[22px]">
@@ -377,6 +416,18 @@ export function AIChatPanel({
                   )}
                 </div>
               )}
+
+              {/* Placeholder: fills viewport after user message, shrinks as AI responds */}
+              {placeholderHeight !== null && (
+                <div
+                  aria-hidden
+                  style={{
+                    height: placeholderHeight,
+                    transition: 'height 180ms ease-out',
+                    flexShrink: 0,
+                  }}
+                />
+              )}
             </div>
           </div>
         )}
@@ -428,6 +479,7 @@ function ChatInput({
           onChange={(e) => onInputChange(e.target.value)}
           onKeyDown={onKeyDown}
           placeholder="Ask me anything..."
+          aria-label="Chat message"
           rows={1}
           className="flex-1 resize-none bg-transparent text-sm placeholder:text-muted-foreground outline-none max-h-[7.5rem] overflow-y-auto"
           style={{ fieldSizing: 'content' } as React.CSSProperties}
@@ -435,6 +487,7 @@ function ChatInput({
         <button
           onClick={onSend}
           disabled={!input.trim() || isStreaming}
+          aria-label="Send message"
           className="flex h-8 w-8 shrink-0 items-center justify-center rounded-lg bg-primary text-primary-foreground shadow-sm transition-all hover:bg-primary/90 active:scale-95 disabled:opacity-40 disabled:cursor-not-allowed disabled:active:scale-100"
         >
           <ArrowUp size={16} />
@@ -446,9 +499,12 @@ function ChatInput({
 
 /* ---------- ChatMarkdown: lightweight markdown renderer ---------- */
 
-export function ChatMarkdown({ content, size = 'sm' }: { content: string; size?: 'sm' | 'lg' }) {
+export function ChatMarkdown({ content, size = 'sm', fontSize }: { content: string; size?: 'sm' | 'lg'; fontSize?: string }) {
   return (
-    <div className={`prose dark:prose-invert max-w-none [&>*:first-child]:mt-0 [&>*:last-child]:mb-0 ${size === 'lg' ? 'prose-base' : 'prose-sm'}`}>
+    <div
+      className={`prose dark:prose-invert max-w-none [&>*:first-child]:mt-0 [&>*:last-child]:mb-0 ${size === 'lg' ? 'prose-base' : 'prose-sm'}`}
+      style={fontSize ? { fontSize } : undefined}
+    >
       <ReactMarkdown
         remarkPlugins={[remarkGfm]}
         components={{

src/renderer/components/ai/FloatingChat.tsx

@@ -6,7 +6,7 @@ import { X, ArrowUp } from 'lucide-react';
 import {
   useFloatingChat,
   computeDualAnchor,
-  CHAT_WIDTH,
+  getChatWidth,
   CHAT_HEIGHT,
   PADDING,
 } from '@/context/FloatingChatContext';
@@ -66,7 +66,7 @@ function FloatingChatInner() {
     if (route === 'project' && state.projectId) {
       // Navigate to the project page (stay on same project)
       // Project sections re-register on mount and pendingSection will auto-open
-      void navigate({ to: '/projects/$projectId', params: { projectId: state.projectId } });
+      void navigate({ to: '/projects', search: { projectId: state.projectId } });
     } else if (route.startsWith('/')) {
       void navigate({ to: route });
     }
@@ -154,7 +154,7 @@ function FloatingChatInner() {
       if (el) {
         const rect = el.getBoundingClientRect();
         if (rect.right > window.innerWidth || rect.bottom > window.innerHeight) {
-          el.style.left = `${Math.max(PADDING, Math.min(state.position.x, window.innerWidth - CHAT_WIDTH - PADDING))}px`;
+          el.style.left = `${Math.max(PADDING, Math.min(state.position.x, window.innerWidth - getChatWidth() - PADDING))}px`;
           el.style.top = `${Math.max(PADDING, Math.min(state.position.y, window.innerHeight - CHAT_HEIGHT - PADDING))}px`;
         }
       }
@@ -241,6 +241,10 @@ function FloatingChatInner() {
 
   const hasMessages = messages.length > 0 || isStreaming;
 
+  // Expand the messages panel upward if there's enough space above the input bar,
+  // otherwise expand downward. 320px = 300px max-h + 8px gap + 12px buffer.
+  const expandUp = state.position.y >= 320;
+
   return (
     <AnimatePresence>
       {state.isOpen && (
@@ -260,30 +264,37 @@ function FloatingChatInner() {
             width: state.position.width,
             zIndex: 9999,
           }}
-          className="flex flex-col gap-2"
+          className="relative"
         >
-          {/* ---- Messages panel (appears when chat has content) ---- */}
+          {/* ---- Messages panel — floats above or below the input bar ---- */}
           <AnimatePresence>
             {hasMessages && (
               <motion.div
                 key="messages-panel"
-                initial={{ opacity: 0, height: 0, scale: 0.97 }}
-                animate={{ opacity: 1, height: 'auto', scale: 1 }}
-                exit={{ opacity: 0, height: 0, scale: 0.97 }}
+                initial={{ opacity: 0, scale: 0.97, y: expandUp ? 8 : -8 }}
+                animate={{ opacity: 1, scale: 1, y: 0 }}
+                exit={{ opacity: 0, scale: 0.97, y: expandUp ? 8 : -8 }}
                 transition={{ type: 'spring', stiffness: 400, damping: 30 }}
-                className="rounded-2xl"
+                style={{
+                  position: 'absolute',
+                  width: '100%',
+                  ...(expandUp
+                    ? { bottom: 'calc(100% + 8px)' }
+                    : { top: 'calc(100% + 8px)' }),
+                }}
+                className="rounded-2xl overflow-hidden"
               >
                 <div
                   ref={scrollRef}
-                  className="max-h-[300px] overflow-y-auto rounded-2xl [&::-webkit-scrollbar]:w-2.5 [&::-webkit-scrollbar-track]:bg-transparent [&::-webkit-scrollbar-thumb]:rounded-full [&::-webkit-scrollbar-thumb]:bg-border"
+                  className="max-h-[300px] overflow-y-auto rounded-2xl [&::-webkit-scrollbar]:w-2.5 [&::-webkit-scrollbar-track]:bg-transparent [&::-webkit-scrollbar-thumb]:rounded-full [&::-webkit-scrollbar-thumb]:bg-border/40"
                 >
                   <div className="flex flex-col gap-2.5 p-3">
                     {messages.map((msg) => {
                       if (msg.role === 'user') {
                         return (
                           <div key={msg.id} className="flex justify-end">
-                            <div className="max-w-[80%] rounded-2xl rounded-br-md bg-accent text-primary-foreground px-3.5 py-2 shadow-sm">
-                              <p className="text-xs whitespace-pre-wrap leading-relaxed">
+                            <div className="glass-surface-subtle max-w-[80%] rounded-2xl rounded-br-md px-3.5 py-2">
+                              <p className="text-xs whitespace-pre-wrap leading-relaxed text-foreground">
                                 {msg.content}
                               </p>
                             </div>
@@ -294,7 +305,7 @@ function FloatingChatInner() {
                       if (msg.error) {
                         return (
                           <div key={msg.id} className="flex justify-start">
-                            <div className="max-w-[80%] rounded-2xl rounded-bl-md bg-destructive/10 px-3.5 py-2">
+                            <div className="glass-surface-subtle max-w-[80%] rounded-2xl rounded-bl-md px-3.5 py-2 !border-destructive/30">
                               <p className="text-xs text-destructive whitespace-pre-wrap leading-relaxed">
                                 {msg.content}
                               </p>
@@ -305,8 +316,8 @@ function FloatingChatInner() {
 
                       return (
                         <div key={msg.id} className="flex justify-start">
-                          <div className="max-w-[80%] rounded-2xl rounded-bl-md bg-primary text-primary-foreground px-3.5 py-2">
-                            <div className="text-xs">
+                          <div className="glass-surface-subtle max-w-[80%] rounded-2xl rounded-bl-md px-3.5 py-2">
+                            <div className="text-xs text-foreground">
                               <ChatMarkdown content={msg.content} />
                             </div>
                           </div>
@@ -317,9 +328,9 @@ function FloatingChatInner() {
                     {/* Streaming */}
                     {isStreaming && (
                       <div className="flex justify-start">
-                        <div className="max-w-[80%] rounded-2xl rounded-bl-md bg-primary text-primary-foreground px-3.5 py-2">
+                        <div className="glass-surface-subtle max-w-[80%] rounded-2xl rounded-bl-md px-3.5 py-2">
                           {streamingContent ? (
-                            <div className="text-xs">
+                            <div className="text-xs text-foreground">
                               <ChatMarkdown content={streamingContent} />
                             </div>
                           ) : (
@@ -338,7 +349,7 @@ function FloatingChatInner() {
           </AnimatePresence>
 
           {/* ---- Floating input bar ---- */}
-          <div className="relative rounded-2xl bg-background/80 backdrop-blur-2xl shadow-[0_8px_60px_-12px_rgba(0,0,0,0.5)] border border-border/30 ring-1 ring-white/5 transition-shadow focus-within:shadow-[0_8px_60px_-8px_rgba(0,0,0,0.7)] focus-within:ring-ring/20">
+          <div className="glass-surface relative rounded-2xl transition-shadow focus-within:shadow-[0_8px_60px_-8px_rgba(0,0,0,0.35)]">
             {/* Close button */}
             <button
               onClick={close}

src/renderer/components/layout/AppShell.tsx

@@ -29,14 +29,13 @@ import {
   SidebarMenuButton,
   SidebarMenuItem,
   SidebarProvider,
+  SidebarTrigger,
   useSidebar,
 } from '@/components/ui/sidebar';
 import {
   DropdownMenu,
   DropdownMenuContent,
   DropdownMenuItem,
-  DropdownMenuLabel,
-  DropdownMenuSeparator,
   DropdownMenuPortal,
   DropdownMenuSub,
   DropdownMenuTrigger,
@@ -131,6 +130,9 @@ function AppShellInner({ children }: AppShellProps) {
           />
         ) : (
           <div className="relative flex flex-col h-full">
+            <header className="flex items-center gap-2 p-2 md:hidden">
+              <SidebarTrigger />
+            </header>
             {children}
           </div>
         )}
@@ -163,13 +165,13 @@ function AppShellInner({ children }: AppShellProps) {
           <p className="text-xs text-muted-foreground">
             Your token is stored securely in the OS keychain.
             {hasTokenQuery.data === true && (
-              <span className="text-green-600 ml-1">A token is currently stored.</span>
+              <span className="text-green-600 dark:text-green-400 ml-1">A token is currently stored.</span>
             )}
           </p>
         </div>
         <DialogFooter>
           {saved && (
-            <span className="flex items-center gap-1 text-sm text-green-600 mr-auto">
+            <span className="flex items-center gap-1 text-sm text-green-600 dark:text-green-400 mr-auto">
               <Check size={14} />
               Saved
             </span>

src/renderer/components/projects/ProjectDetail.tsx

@@ -4,6 +4,7 @@ import { format } from 'date-fns';
 import { useNavigate } from '@tanstack/react-router';
 import { trpc } from '@/lib/trpc';
 import { Button } from '@/components/ui/button';
+import { Skeleton } from '@/components/ui/skeleton';
 import { Item, ItemMedia, ItemContent, ItemTitle, ItemDescription } from '@/components/ui/item';
 import {
   Breadcrumb,
@@ -167,8 +168,17 @@ export function ProjectDetail({ projectId }: ProjectDetailProps) {
 
   if (isLoading) {
     return (
-      <div className="flex items-center justify-center h-full text-sm text-muted-foreground">
-        Loading project...
+      <div className="p-6 flex flex-col gap-6">
+        <div className="flex flex-col gap-1">
+          <Skeleton className="h-4 w-24" />
+          <Skeleton className="h-8 w-56" />
+        </div>
+        <div className="grid grid-cols-3 gap-4">
+          <Skeleton className="h-20 rounded-lg" />
+          <Skeleton className="h-20 rounded-lg" />
+          <Skeleton className="h-20 rounded-lg" />
+        </div>
+        <Skeleton className="h-16 rounded-lg" />
       </div>
     );
   }

src/renderer/components/projects/ProjectSidebar.tsx

@@ -322,7 +322,7 @@ export function ProjectSidebar({ selectedProjectId, onSelectProject }: ProjectSi
     if (editCreatingClient && editNewClientName.trim()) {
       // Create a new client
       const result = await createClientMutation.mutateAsync({ name: editNewClientName.trim() });
-      let parentId = result.id;
+      const parentId = result.id;
 
       if (editCreatingSubClient && editNewSubClientName.trim()) {
         // Also create a sub-client under the new client

src/renderer/components/tasks/PriorityBadge.tsx

@@ -4,21 +4,21 @@ export function PriorityBadge({ priority }: { priority: string | null }) {
   switch (priority) {
     case 'high':
       return (
-        <span className="inline-flex items-center gap-1 text-xs">
+        <span className="inline-flex items-center gap-1 text-xs text-red-600 dark:text-red-400">
           <ArrowUp className="h-3 w-3" />
           High
         </span>
       );
     case 'medium':
       return (
-        <span className="inline-flex items-center gap-1 text-xs">
+        <span className="inline-flex items-center gap-1 text-xs text-amber-600 dark:text-amber-400">
           <ArrowRight className="h-3 w-3" />
           Medium
         </span>
       );
     case 'low':
       return (
-        <span className="inline-flex items-center gap-1 text-xs">
+        <span className="inline-flex items-center gap-1 text-xs text-muted-foreground">
           <ArrowDown className="h-3 w-3" />
           Low
         </span>

src/renderer/components/tasks/TaskRow.tsx

@@ -1,5 +1,7 @@
+import { Fragment } from 'react';
 import { motion } from 'framer-motion';
 import { Calendar, User, Pencil, Trash2 } from 'lucide-react';
+import { cn } from '@/lib/utils';
 import { Checkbox } from '@/components/ui/checkbox';
 import { Badge } from '@/components/ui/badge';
 import {
@@ -95,9 +97,13 @@ export function TaskRow({
       <ContextMenuTrigger asChild>
         <Wrapper
           {...wrapperProps}
-          className={`flex flex-col gap-1.5 px-4 py-3 rounded-md border select-none transition-colors ${
-            isDone ? 'bg-green-50 dark:bg-green-950/30 border-green-200 dark:border-green-900' : 'bg-card border-border'
-          } ${onClick ? 'cursor-pointer hover:bg-accent/50' : 'cursor-default'}`}
+          className={cn(
+            'flex flex-col gap-1.5 px-4 py-3 rounded-md border select-none transition-colors',
+            isDone
+              ? 'bg-green-50 dark:bg-green-950/30 border-green-200 dark:border-green-900'
+              : 'bg-card border-border',
+            onClick ? 'cursor-pointer hover:bg-accent/50' : 'cursor-default',
+          )}
           onClick={() => onClick?.(task)}
         >
           {/* Row 1: checkbox + title + description */}
@@ -109,7 +115,7 @@ export function TaskRow({
               className="mt-0.5 shrink-0"
             />
             <div className="flex-1 min-w-0">
-              <div className={`text-sm font-semibold ${isDone ? 'line-through text-muted-foreground' : ''}`}>
+              <div className={cn('text-sm font-medium', isDone && 'line-through text-muted-foreground')}>
                 {task.title}
               </div>
               {task.description && (
@@ -136,10 +142,12 @@ export function TaskRow({
                 <Breadcrumb className="shrink-0">
                   <BreadcrumbList>
                     {breadcrumb.map((part, i) => (
-                      <BreadcrumbItem key={i}>
+                      <Fragment key={i}>
                         {i > 0 && <BreadcrumbSeparator />}
+                        <BreadcrumbItem>
                           <span className="text-xs">{part}</span>
                         </BreadcrumbItem>
+                      </Fragment>
                     ))}
                   </BreadcrumbList>
                 </Breadcrumb>

src/renderer/components/ui/hover-card.tsx

@@ -1,42 +0,0 @@
-import * as React from "react"
-import { HoverCard as HoverCardPrimitive } from "radix-ui"
-
-import { cn } from "@/lib/utils"
-
-function HoverCard({
-  ...props
-}: React.ComponentProps<typeof HoverCardPrimitive.Root>) {
-  return <HoverCardPrimitive.Root data-slot="hover-card" {...props} />
-}
-
-function HoverCardTrigger({
-  ...props
-}: React.ComponentProps<typeof HoverCardPrimitive.Trigger>) {
-  return (
-    <HoverCardPrimitive.Trigger data-slot="hover-card-trigger" {...props} />
-  )
-}
-
-function HoverCardContent({
-  className,
-  align = "center",
-  sideOffset = 4,
-  ...props
-}: React.ComponentProps<typeof HoverCardPrimitive.Content>) {
-  return (
-    <HoverCardPrimitive.Portal data-slot="hover-card-portal">
-      <HoverCardPrimitive.Content
-        data-slot="hover-card-content"
-        align={align}
-        sideOffset={sideOffset}
-        className={cn(
-          "bg-popover text-popover-foreground data-[state=open]:animate-in data-[state=closed]:animate-out data-[state=closed]:fade-out-0 data-[state=open]:fade-in-0 data-[state=closed]:zoom-out-95 data-[state=open]:zoom-in-95 data-[side=bottom]:slide-in-from-top-2 data-[side=left]:slide-in-from-right-2 data-[side=right]:slide-in-from-left-2 data-[side=top]:slide-in-from-bottom-2 z-50 w-64 origin-(--radix-hover-card-content-transform-origin) rounded-md border p-4 shadow-md outline-hidden",
-          className
-        )}
-        {...props}
-      />
-    </HoverCardPrimitive.Portal>
-  )
-}
-
-export { HoverCard, HoverCardTrigger, HoverCardContent }

src/renderer/context/FloatingChatContext.tsx

@@ -2,7 +2,6 @@ import {
   createContext,
   useContext,
   useCallback,
-  useEffect,
   useState,
   useRef,
   type ReactNode,
@@ -11,7 +10,7 @@ import {
 
 // ---------- Types ----------
 
-export interface AISection {
+interface AISection {
   id: string; // e.g. "project-tasks", "tasks-list", "timeline-chart"
   label: string; // Human-readable, e.g. "Tasks", "Project Timeline"
   ref: RefObject<HTMLElement | null>;
@@ -19,7 +18,7 @@ export interface AISection {
   anchorMode?: 'top-right' | 'right-margin'; // default: 'top-right'
 }
 
-export interface SectionOpenOpts {
+interface SectionOpenOpts {
   clickY?: number; // For right-margin mode: Y-coordinate of the double-click
 }
 
@@ -52,15 +51,20 @@ interface FloatingChatContextValue {
 
 // ---------- Constants ----------
 
-export const CHAT_WIDTH = 380;
+/** Dynamic chat width: 35% of viewport, clamped between 320px and 520px. */
+export function getChatWidth(): number {
+  return Math.min(630, Math.max(320, Math.round(window.innerWidth * 0.35)));
+}
+
 export const CHAT_HEIGHT = 420;
 export const PADDING = 16;
 
 // ---------- Position computation ----------
 
 function clampPosition(x: number, y: number): { x: number; y: number } {
+  const w = getChatWidth();
   return {
-    x: Math.max(PADDING, Math.min(x, window.innerWidth - CHAT_WIDTH - PADDING)),
+    x: Math.max(PADDING, Math.min(x, window.innerWidth - w - PADDING)),
     y: Math.max(PADDING, Math.min(y, window.innerHeight - CHAT_HEIGHT - PADDING)),
   };
 }
@@ -70,7 +74,8 @@ function computeAnchorPosition(
   opts?: SectionOpenOpts,
 ): { x: number; y: number; width: number } {
   const el = section.ref.current;
-  if (!el) return { x: PADDING, y: PADDING, width: CHAT_WIDTH };
+  const w = getChatWidth();
+  if (!el) return { x: PADDING, y: PADDING, width: w };
 
   const rect = el.getBoundingClientRect();
   const mode = section.anchorMode ?? 'top-right';
@@ -80,14 +85,14 @@ function computeAnchorPosition(
     const rawX = rect.right + PADDING;
     const rawY = opts?.clickY ?? rect.top + PADDING;
     const { x, y } = clampPosition(rawX, rawY);
-    return { x, y, width: CHAT_WIDTH };
+    return { x, y, width: w };
   }
 
   // Default: top-right of section
-  const rawX = rect.right - CHAT_WIDTH - PADDING;
+  const rawX = rect.right - w - PADDING;
   const rawY = rect.top + PADDING;
   const { x, y } = clampPosition(rawX, rawY);
-  return { x, y, width: CHAT_WIDTH };
+  return { x, y, width: w };
 }
 
 /**
@@ -104,6 +109,7 @@ export function computeDualAnchor(
   if (section.anchorMode === 'right-margin') return null;
 
   const rect = el.getBoundingClientRect();
+  const w = getChatWidth();
 
   // Fully off-screen — freeze
   if (rect.bottom < 0 || rect.top > window.innerHeight) return null;
@@ -111,27 +117,27 @@ export function computeDualAnchor(
   // Primary anchor: top-right (when section top is visible)
   if (rect.top >= PADDING) {
     const { x, y } = clampPosition(
-      rect.right - CHAT_WIDTH - PADDING,
+      rect.right - w - PADDING,
       rect.top + PADDING,
     );
-    return { x, y, width: CHAT_WIDTH };
+    return { x, y, width: w };
   }
 
   // Fallback anchor: bottom-right (when section top scrolled off)
   if (rect.bottom > CHAT_HEIGHT) {
     const { x, y } = clampPosition(
-      rect.right - CHAT_WIDTH - PADDING,
+      rect.right - w - PADDING,
       rect.bottom - CHAT_HEIGHT - PADDING,
     );
-    return { x, y, width: CHAT_WIDTH };
+    return { x, y, width: w };
   }
 
   // Section visible but too small for fallback — clamp to top
   const { x, y } = clampPosition(
-    rect.right - CHAT_WIDTH - PADDING,
+    rect.right - w - PADDING,
     PADDING,
   );
-  return { x, y, width: CHAT_WIDTH };
+  return { x, y, width: w };
 }
 
 // ---------- Context ----------
@@ -145,15 +151,6 @@ export function useFloatingChat(): FloatingChatContextValue {
   return ctx;
 }
 
-// Convenience hook for pages to register a section
-export function useAISection(section: AISection): void {
-  const { registerSection, unregisterSection } = useFloatingChat();
-
-  useEffect(() => {
-    registerSection(section);
-    return () => unregisterSection(section.id);
-  }, [section.id, registerSection, unregisterSection]);
-}
 
 // ---------- Provider ----------
 
@@ -163,7 +160,7 @@ export function FloatingChatProvider({ children }: { children: ReactNode }) {
   const [state, setState] = useState<FloatingChatState>({
     isOpen: false,
     activeSectionId: null,
-    position: { x: 0, y: 0, width: CHAT_WIDTH },
+    position: { x: 0, y: 0, width: getChatWidth() },
     morphTargetId: null,
   });
 

src/renderer/globals.css

@@ -184,6 +184,78 @@ body {
   overflow: hidden;
 }
 
+/* ---- Glass Surface (ReactBits-style) ---- */
+/*
+ * Gradient border via padding-box/border-box background split —
+ * most reliable technique in Chromium/Electron; no pseudo-element mask needed.
+ */
+.glass-surface {
+  border: 1px solid transparent;
+  background:
+    /* glass fill — clips to padding-box (inside the border) */
+    rgba(255, 255, 255, 0.55) padding-box,
+    /* gradient border — clips to border-box (the 1px border strip) */
+    linear-gradient(
+      145deg,
+      rgba(255, 255, 255, 0.90) 0%,
+      rgba(200, 195, 205, 0.40) 40%,
+      rgba(200, 195, 205, 0.20) 100%
+    ) border-box;
+  backdrop-filter: blur(24px) saturate(180%);
+  -webkit-backdrop-filter: blur(24px) saturate(180%);
+  box-shadow:
+    0 4px 48px rgba(0, 0, 0, 0.10),
+    0 1px 2px rgba(0, 0, 0, 0.06),
+    inset 0 1px 0 rgba(255, 255, 255, 0.80);
+}
+
+.dark .glass-surface {
+  background:
+    rgba(255, 255, 255, 0.05) padding-box,
+    linear-gradient(
+      145deg,
+      rgba(255, 255, 255, 0.18) 0%,
+      rgba(255, 255, 255, 0.04) 40%,
+      rgba(255, 255, 255, 0.08) 100%
+    ) border-box;
+  box-shadow:
+    0 4px 48px rgba(0, 0, 0, 0.50),
+    0 1px 2px rgba(0, 0, 0, 0.20),
+    inset 0 1px 0 rgba(255, 255, 255, 0.10);
+}
+
+/* Subtle variant — same gradient border, much more transparent fill */
+.glass-surface-subtle {
+  border: 1px solid transparent;
+  background:
+    rgba(255, 255, 255, 0.20) padding-box,
+    linear-gradient(
+      145deg,
+      rgba(255, 255, 255, 0.70) 0%,
+      rgba(200, 195, 205, 0.25) 40%,
+      rgba(200, 195, 205, 0.10) 100%
+    ) border-box;
+  backdrop-filter: blur(16px) saturate(160%);
+  -webkit-backdrop-filter: blur(16px) saturate(160%);
+  box-shadow:
+    0 2px 12px rgba(0, 0, 0, 0.06),
+    inset 0 1px 0 rgba(255, 255, 255, 0.60);
+}
+
+.dark .glass-surface-subtle {
+  background:
+    rgba(255, 255, 255, 0.03) padding-box,
+    linear-gradient(
+      145deg,
+      rgba(255, 255, 255, 0.12) 0%,
+      rgba(255, 255, 255, 0.02) 40%,
+      rgba(255, 255, 255, 0.05) 100%
+    ) border-box;
+  box-shadow:
+    0 2px 12px rgba(0, 0, 0, 0.30),
+    inset 0 1px 0 rgba(255, 255, 255, 0.07);
+}
+
 /* Crepe editor layout */
 .milkdown-container {
   display: flex;

src/renderer/hooks/useAIChat.ts

@@ -1,7 +1,7 @@
 import { useState, useCallback, useRef } from 'react';
 import { trpc } from '@/lib/trpc';
 
-export interface ChatMessage {
+interface ChatMessage {
   id: string;
   role: 'user' | 'assistant';
   content: string;
@@ -14,7 +14,7 @@ export interface ChatContext {
   uiContext?: string;
 }
 
-export interface UseAIChatReturn {
+interface UseAIChatReturn {
   messages: ChatMessage[];
   input: string;
   setInput: (v: string) => void;
@@ -24,7 +24,7 @@ export interface UseAIChatReturn {
   clearMessages: () => void;
 }
 
-export interface UseAIChatOptions {
+interface UseAIChatOptions {
   onSectionTag?: (sectionId: string) => void;
 }
 
@@ -68,7 +68,7 @@ export function useAIChat(defaultContext: ChatContext, options?: UseAIChatOption
           const sectionMatch = finalContent.match(/^\[SECTION:([\w-]+)\]\s*/);
           if (sectionMatch) {
             finalContent = finalContent.slice(sectionMatch[0].length);
-            options?.onSectionTag?.(sectionMatch[1]);
+            options?.onSectionTag?.(sectionMatch[1]!);
           }
 
           setMessages((prev) => [

src/renderer/routes/tasks.tsx

@@ -4,7 +4,7 @@ import { useFloatingChat } from '@/context/FloatingChatContext';
 import {
   ClipboardCheck,
   ListTodo,
-  Loader2,
+  Clock,
   CheckCircle2,
   Plus,
   Search,
@@ -147,7 +147,7 @@ function TasksPage() {
         </Item>
         <Item variant="muted" className="bg-sky-50 dark:bg-sky-950/30">
           <ItemMedia variant="icon">
-            <Loader2 />
+            <Clock />
           </ItemMedia>
           <ItemContent>
             <ItemTitle>{stats.inProgress}</ItemTitle>

src/renderer/routes/timeline.tsx

@@ -1,12 +1,13 @@
 import { createFileRoute } from '@tanstack/react-router';
 import { useEffect, useRef, useState, useMemo } from 'react';
-import { Plus } from 'lucide-react';
+import { Plus, ChartGantt } from 'lucide-react';
 import { useFloatingChat } from '@/context/FloatingChatContext';
 import { trpc } from '@/lib/trpc';
 import { Button } from '@/components/ui/button';
 import { GanttChart, type GanttCheckpoint } from '@/components/timeline/GanttChart';
 import { AddCheckpointDialog } from '@/components/timeline/AddCheckpointDialog';
 import { EditCheckpointDialog } from '@/components/timeline/EditCheckpointDialog';
+import { Empty, EmptyHeader, EmptyMedia, EmptyTitle, EmptyDescription } from '@/components/ui/empty';
 
 export const Route = createFileRoute('/timeline')({
   component: TimelinePage,
@@ -107,9 +108,17 @@ function TimelinePage() {
 
       {/* Gantt Chart */}
       {ganttCheckpoints.length === 0 ? (
-        <div className="text-center text-muted-foreground text-sm py-12 border rounded-md bg-muted/30">
-          No checkpoints yet. Click "+ Add" to create your first milestone.
-        </div>
+        <Empty>
+          <EmptyHeader>
+            <EmptyMedia variant="icon">
+              <ChartGantt />
+            </EmptyMedia>
+            <EmptyTitle>No milestones yet</EmptyTitle>
+            <EmptyDescription>
+              Click "+ Add" to create your first project checkpoint.
+            </EmptyDescription>
+          </EmptyHeader>
+        </Empty>
       ) : (
         <div className="border rounded-md p-4 bg-card">
           <GanttChart