6 Commits

• UI Debugging & Docs: Fix React error #130, update README, and cleanup dead backend logic
  Gemini AI · 2025-12-20 17:23:19 +04:00
  a4b12251fd
• feat: Add backend generation capability

  - Added 'Build Backend' button to Preview toolbar in Views.tsx
  - Defined BACKEND_GENERATOR_PROMPT in automationService.ts
  - Implemented specific prompt logic to infer API endpoints from frontend code

  Gemini AI · 2025-12-20 15:59:56 +04:00
  71c27fb060
• fix: Robust patch generation and safety timeouts

  - Condensed Canvas Isolation Architecture to streamline AI focus
  - Added robust JSON extraction (brace-finding) to handle conversational AI output
  - Implemented 90s safety timeout for patch generation to prevent infinite 'Generating' state
  - Throttled status updates to improve UI performance during streaming

  Gemini AI · 2025-12-20 15:03:13 +04:00
  7785feed1d
• feat: Implement Canvas Isolation Architecture for surgical code precision

  - Replaced old refinement protocol with technical Canvas Isolation Architecture
  - Integrated layered canvas logic (Base, Change, Merge, Validation)
  - Enforced isolation chamber and quarantine zone constraints in prompts
  - Updated QA self-check gate to strictly monitor for scope creep

  Gemini AI · 2025-12-20 14:43:03 +04:00
  0c76288d01
• fix: Enable Ollama models for code generation

  - Added getActiveModel() function to automationService for dynamic model selection
  - Replaced all hardcoded 'qwen-coder-plus' strings with getActiveModel() calls
  - Added localStorage sync when model is changed in orchestrator
  - This enables Ollama and other models to work in all automation tasks

  Gemini AI · 2025-12-20 13:56:21 +04:00
  4230159036
• Release v1.01 Enhanced: Vi Control, TUI Gen5, Core Stability
  Gemini AI · 2025-12-20 01:12:45 +04:00
  142aaeee1e