forge/TASKS.md
DJP b99d143b0f Add tasks documentation for remaining work
Documented:
- Critical bugs (downloads, Topaz errors)
- Provider-specific UI requirements
- Cross-tool integration needs
- Missing Mermaid/Markdown pages

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 (1M context) <noreply@anthropic.com>
2025-12-09 21:15:04 -05:00

3 KiB

FORGE AI - Remaining Tasks

Priority 1: Critical Bugs

Downloads Not Working

  • Issue: Downloads return error messages instead of files
  • Root Cause: Database was recreated, asset records exist but don't match orphaned files in storage/
  • Fix: Either re-import files to DB or regenerate content
  • Files: backend/app/api/v1/assets.py

Topaz Upscale Client-Side Exception

  • Issue: "Application error: a client-side exception has occurred"
  • Status: Added hydration guards but error persists
  • Need: Check browser console for actual error
  • Files: frontend/app/image/upscale/page.tsx, frontend/app/video/upscale/page.tsx

Priority 2: Feature Completeness

Provider-Specific UI

  • Image Generation: Show only relevant controls per provider

    • OpenAI: Quality, Background, Output format
    • Imagen: Aspect ratio, Image size, Enhance prompt
    • Nano Banana: Aspect ratio, Image size (1K/2K/4K)
    • Stability: Aspect ratio, Style presets, Seed
    • Leonardo: Width/Height, 30+ Style presets, Guidance/Steps
    • Bria: Aspect ratio, Medium, Prompt enhancement, Steps/Guidance
  • Video Generation: Provider-specific controls

    • Runway: Motion brush, Static camera, Resolution per model
    • Veo: Duration/resolution per model, Audio indicator, Reference images (3.1 only)
  • Backend API: /api/v1/modules/image/providers endpoint added

  • Files:

    • frontend/app/image/generate/page.tsx
    • frontend/app/video/generate/page.tsx

Cross-Tool Integration

  • Feature: Send assets/prompts between tools
  • Examples:
    • Send generated image to video first frame
    • Send prompt from Prompt Studio to Image Gen
    • Send image to Background Remover
  • Implementation: URL params or global state
  • Files: Add to all tool pages

Topaz API Features

  • Missing: Check Topaz API docs for all available parameters
  • Current: Basic scale, denoise, sharpen
  • Need: Full feature set from API documentation
  • Files:
    • backend/app/services/image_upscaler.py
    • backend/app/services/video_upscaler.py
    • frontend/app/image/upscale/page.tsx
    • frontend/app/video/upscale/page.tsx

Priority 3: Additional Features

Mermaid Diagram Tools

  • Backend: Service exists at backend/app/services/markdown_tools.py
  • Need: Frontend pages
    • /text/mermaid-generator
    • /text/mermaid-renderer
  • Features: Generate and render Mermaid diagrams

Markdown Tools

  • Backend: Service exists at backend/app/services/markdown_tools.py
  • Need: Frontend pages
    • /text/markdown-converter
    • /text/markdown-generator
  • Features: Convert and generate Markdown

Session Notes

What's Working:

  • Authentication with cookie-based sessions
  • All AI providers configured
  • Upload in asset library modal
  • Voice admin panel
  • Job tracking and history

Known Issues:

  • Downloads fail (orphaned files after DB recreation)
  • Some provider-specific features hidden in UI
  • Topaz pages have client errors
  • No cross-tool integration yet

Repository: bitbucket.org:zlalani/forge.git Test Login: test@forge.ai / password123