NomadArch

Optimize message handling to prevent UI freezing

Gemini AI · 2025-12-24 23:24:22 +04:00

8dddf4d0cf

Fix initialization order: Define filteredMessageIds before lastAssistantIndex

Fixed 'Cannot access filteredMessageIds before initialization' error by
reordering the declarations. Since lastAssistantIndex depends on
filteredMessageIds, it must be defined after it.

Gemini AI · 2025-12-24 22:54:20 +04:00

fb33e2ebe0

Fix UI freeze: Optimize reactive memos and remove trigger loops

Critical performance fixes for MULTIX chat mode:

1. isAgentThinking - Simplified to only check last message
   - Previously iterated ALL messages with .some() on every store update
   - Each getMessage() call created a reactive subscription
   - Now only checks the last message (O(1) instead of O(n))

2. lastAssistantIndex - Memoized with createMemo
   - Changed from function to createMemo for proper caching
   - Added early exit optimization for common case

3. Auto-scroll effect - Removed isAgentThinking dependency
   - The thinking-based scroll was firing on every reactive update
   - Now only triggers on message count changes
   - Streaming scroll is handled by the interval-based effect

These combined fixes prevent the cascading reactive loop that
was freezing the UI during message send.

Gemini AI · 2025-12-24 22:49:31 +04:00

6c63bb7d7d

Fix UI freeze: Remove high-frequency logging and throttle scroll effects

Performance optimizations to prevent UI freeze during streaming:

1. message-block-list.tsx:
   - Removed createEffect that logged on every messageIds change
   - Removed unused logger import (was causing IPC overload)

2. multi-task-chat.tsx:
   - Changed filteredMessageIds from function to createMemo for proper memoization
   - Throttled auto-scroll effect to only trigger when message COUNT changes
   - Previously it fired on every reactive store update during streaming

These changes prevent excessive re-renders and IPC calls during message streaming.

Gemini AI · 2025-12-24 22:27:27 +04:00

961c8743d3

Integrate Context-Engine RAG service for enhanced LLM responses

Backend:
- Created context-engine/client.ts - HTTP client for Context-Engine API
- Created context-engine/service.ts - Lifecycle management of Context-Engine sidecar
- Created context-engine/index.ts - Module exports
- Created server/routes/context-engine.ts - API endpoints for status/health/query

Integration:
- workspaces/manager.ts: Trigger indexing when workspace becomes ready (non-blocking)
- index.ts: Initialize ContextEngineService on server start (lazy mode)
- ollama-cloud.ts: Inject RAG context into chat requests when available

Frontend:
- model-selector.tsx: Added Context-Engine status indicator
  - Green dot = Ready (RAG enabled)
  - Blue pulsing dot = Indexing
  - Red dot = Error
  - Hidden when Context-Engine not running

All operations are non-blocking with graceful fallback when Context-Engine is unavailable.

Gemini AI · 2025-12-24 22:20:13 +04:00

743d0367e2

Fix TypeScript errors in mcp-manager and instance-shell2

Gemini AI · 2025-12-24 21:46:13 +04:00

fd6c563f71

Add custom agent creator, Zread MCP, fix model change context continuity

Features added:
- Custom Agent Creator dialog with AI generation support (up to 30k chars)
- Plus button next to agent selector to create new agents
- Zread MCP Server from Z.AI in marketplace (remote HTTP config)
- Extended MCP config types to support remote/http/sse servers

Bug fixes:
- Filter SDK Z.AI/GLM providers to ensure our custom routing with full message history
- This fixes the issue where changing models mid-chat lost conversationcontext

Gemini AI · 2025-12-24 21:34:16 +04:00

3501c20471

Backup before continuing from Codex 5.2 session - User storage, compaction suggestions, streaming improvements

Gemini AI · 2025-12-24 21:27:05 +04:00

e8c38b0add

Add skills catalog and sidebar tooling

Gemini AI · 2025-12-24 14:23:51 +04:00

f9748391a9

Add model offline badge and streaming safeguards

Gemini AI · 2025-12-24 13:52:33 +04:00

d153892bdf

feat: integrate Z.AI, Ollama Cloud, and OpenCode Zen free models

Added comprehensive AI model integrations:

Z.AI Integration:
- Client with Anthropic-compatible API (GLM Coding Plan)
- Routes for config, testing, and streaming chat
- Settings UI component with API key management

OpenCode Zen Integration:
- Free models client using 'public' API key
- Dynamic model fetching from models.dev
- Supports GPT-5 Nano, Big Pickle, Grok Code Fast 1, MiniMax M2.1
- No API key required for free tier!

UI Enhancements:
- Added Free Models tab (first position) in Advanced Settings
- Z.AI tab with GLM Coding Plan info
- OpenCode Zen settings with model cards and status

All integrations work standalone without opencode.exe dependency.

Gemini AI · 2025-12-23 14:26:03 +04:00

68b6c39934

feat: add APEX PRO mode combining SOLO + APEX

Combined autonomous and auto-approval modes into APEX PRO:
- Single toggle enables both functionalities
- Orange color scheme with gentle blinking animation
- Pulsing shadow effect when enabled
- Small glowing indicator dot
- Tooltip explains combined functionality
- SHIELD button remains separate for auto-approval only

Gemini AI · 2025-12-23 14:10:25 +04:00

cdd31feead

feat: add API Key Manager button, fix overflow, update branding

Changes:
1. Fixed MULTIX overflow issue - added max-h-full and overflow-hidden to prevent content from pushing interface out of frame

2. Added API Key Manager button in header:
   - Key icon with emerald hover effect
   - Opens modal with provider list (NomadArch Free, Ollama Cloud, OpenAI, Anthropic, OpenRouter)
   - Shows provider status and configuration

3. Updated branding:
   - Window title: 'NomadArch 1.0'
   - Loading screen: 'NomadArch 1.0 - A fork of OpenCode'
   - Updated page titles

4. Added Settings and Key icons to imports

Gemini AI · 2025-12-23 14:04:11 +04:00

3cd44dd0c2

feat: add hover preview tooltips to message sidebar

Enhanced YOU/ASST message navigation:
- Click scrolls to message (already implemented)
- Hover shows preview tooltip with:
  - Role label (You/Assistant)
  - Message number
  - First 100 chars of message content
- Smooth slide-in animation on hover
- Slightly larger buttons with scale effect on hover

Gemini AI · 2025-12-23 13:50:44 +04:00

37ff96f849

feat: add enhanced MULTIX UI features

Added all missing MULTIX enhancements matching the original screenshot:

1. STREAMING indicator:
   - Animated purple badge with sparkles icon
   - Shows live token count during streaming
   - Pulsing animation effect

2. Status badges:
   - PENDING/RUNNING/DONE badges for tasks
   - Color-coded based on status

3. APEX/SHIELD renamed:
   - 'Auto' -> 'APEX' with tooltip
   - 'Shield' -> 'SHIELD' with tooltip

4. THINKING indicator:
   - Bouncing dots animation (3 dots)
   - Shows THINKING or SENDING status

5. STOP button:
   - Red stop button appears during agent work
   - Calls cancel endpoint to interrupt

6. Detailed token stats bar:
   - INPUT/OUTPUT tokens
   - REASONING tokens (amber)
   - CACHE READ (emerald)
   - CACHE WRITE (cyan)
   - COST (violet)
   - MODEL (indigo)

7. Message navigation sidebar:
   - YOU/ASST labels for each message
   - Click to scroll to message
   - Appears on right side when viewing task

Gemini AI · 2025-12-23 13:49:17 +04:00

55f5945b61

feat: add enhanced MULTIX UI features

Added all missing MULTIX enhancements matching the original screenshot:

1. STREAMING indicator:
   - Animated purple badge with sparkles icon
   - Shows live token count during streaming
   - Pulsing animation effect

2. Status badges:
   - PENDING/RUNNING/DONE badges for tasks
   - Color-coded based on status

3. APEX/SHIELD renamed:
   - 'Auto' → 'APEX' with tooltip
   - 'Shield' → 'SHIELD' with tooltip

4. THINKING indicator:
   - Bouncing dots animation (3 dots)
   - Shows THINKING or SENDING status

5. STOP button:
   - Red stop button appears during agent work
   - Calls cancel endpoint to interrupt

6. Detailed token stats bar:
   - INPUT/OUTPUT tokens
   - REASONING tokens (amber)
   - CACHE READ (emerald)
   - CACHE WRITE (cyan)
   - COST (violet)
   - MODEL (indigo)

7. Message navigation sidebar:
   - YOU/ASST labels for each message
   - Click to scroll to message
   - Appears on right side when viewing task

Gemini AI · 2025-12-23 13:42:49 +04:00

00bee04867

feat: restore GLM 4.7 fixes - auto-scroll and retry logic

Changes from GLM 4.7 Progress Log:

1. Multi-task chat auto-scroll (multi-task-chat.tsx):
   - Added createEffect that monitors message count changes
   - Auto-scrolls using requestAnimationFrame + setTimeout(50ms)
   - Scrolls when new messages arrive or during streaming

2. Electron black screen fix (main.ts):
   - Added exponential backoff retry (1s, 2s, 4s, 8s, 16s max)
   - Added 30-second timeout for load operations
   - Added user-friendly error screen with retry button
   - Handles errno -3 network errors gracefully
   - Max 5 retry attempts before showing error

Gemini AI · 2025-12-23 13:33:39 +04:00

9c6d92efcd

restore: bring back all custom UI enhancements from checkpoint

Restored from commit 52be710 (checkpoint before qwen oauth + todo roller):

Enhanced UI Features:
- SMART FIX button with AI code analysis
- APEX (Autonomous Programming EXecution) mode
- SHIELD (Auto-approval) mode
- MULTIX MODE multi-task pipeline interface
- Live streaming token counter
- Thinking indicator with bouncing dots animation

Components restored:
- packages/ui/src/components/chat/multi-task-chat.tsx
- packages/ui/src/components/instance/instance-shell2.tsx
- packages/ui/src/components/settings/OllamaCloudSettings.tsx
- packages/ui/src/components/settings/QwenCodeSettings.tsx
- packages/ui/src/stores/solo-store.ts
- packages/ui/src/stores/task-actions.ts
- packages/ui/src/stores/session-events.ts (autonomous mode)
- packages/server/src/integrations/ollama-cloud.ts
- packages/server/src/server/routes/ollama.ts
- packages/server/src/server/routes/qwen.ts

This ensures all custom features are preserved in source control.

Gemini AI · 2025-12-23 13:18:37 +04:00

c4ac079660

fix: restore complete source code and fix launchers

- Copy complete source code packages from original CodeNomad project
- Add root package.json with npm workspace configuration
- Include electron-app, server, ui, tauri-app, and opencode-config packages
- Fix Launch-Windows.bat and Launch-Dev-Windows.bat to work with correct npm scripts
- Fix Launch-Unix.sh to work with correct npm scripts
- Launchers now correctly call npm run dev:electron which launches Electron app

Gemini AI · 2025-12-23 12:57:55 +04:00

b448d11991

19 Commits