Files
slahiriandClaude Opus 4.5 bd3ceaa1e1 feat: add interrupt handling, increase token limits, add analysis report
Interrupt Handling:
- Add check_interrupt() using ComfyUI's throw_exception_if_processing_interrupted
- Nodes now properly stop when user clicks cancel button

Token/Word Limits (prevent truncation):
- Increase word limits from 400-500 to 800 words in all local clients
- Increase token buffer from 30% to 50% in PromptModifier
- Increase min tokens from 500 to 800 for prompt modification
- Increase default max_tokens from 2000 to 4000

PromptModifier Analysis Report:
- Add console report comparing original vs modified prompts
- Show word count changes and semantic differences
- Verify if requested modifications were applied

PromptGenerator:
- Remove prompt_metadata from outputs (was 3rd output)
- Save metadata to logs/prompt_generator/ folder
- Add logs/ to .gitignore

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-31 10:12:21 +05:30

80 lines
689 B
Plaintext

# Python
__pycache__/
*.py[cod]
*$py.class
*.so
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
*.egg-info/
.installed.cfg
*.egg
# Virtual Environment
.venv/
venv/
ENV/
env/
# IDE
.vscode/
.idea/
*.swp
*.swo
*~
# OS
.DS_Store
Thumbs.db
# API Keys and Secrets
.env
.env.local
secrets.json
api_keys.txt
# Logs
*.log
logs/
# Testing
.pytest_cache/
.coverage
htmlcov/
# ComfyUI specific
*.safetensors
*.ckpt
*.pt
models/
# Prompt cache
cache/
.cache/
# Claude Code
.claude/
# Test output directories
improvement_sessions/
test_results/
# Archives
*.zip
# Local test scripts
test_*.py
compare_results.py
download_test_images.py
nul