Add comprehensive documentation and examples

- docs/USAGE.md: Full usage guide with CLI options, Python API, troubleshooting
- docs/ATOMIZER_INTEGRATION.md: Guide for FEA/Atomizer integration
- examples/sample_config.toml: Annotated configuration example
- README.md: Expanded with installation, usage, architecture

README.md

@@ -2,61 +2,132 @@
 
 **One video → Complete engineering documentation.**
 
-Transform video walkthroughs of CAD models into comprehensive, structured documentation — ready for CDRs, FEA setups, and integration with the Atomaste engineering ecosystem.
+Transform video walkthroughs of CAD models into comprehensive, structured documentation — ready for CDRs, FEA setups, and client deliverables.
+
+[![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
 ## The Problem
 
-- Documentation is tedious — Engineers spend hours documenting CAD models manually
+- **Documentation is tedious** — Engineers spend hours documenting CAD models manually
-- Knowledge lives in heads — Verbal explanations during reviews aren't captured
+- **Knowledge lives in heads** — Verbal explanations during reviews aren't captured
-- CDR prep is painful — Gathering images, writing descriptions, creating BOMs
+- **CDR prep is painful** — Gathering images, writing descriptions, creating BOMs
-- FEA setup requires context — Atomizer needs model understanding that's often verbal
+- **FEA setup requires context** — Atomizer needs model understanding that's often verbal
 
 ## The Solution
 
-### Input
+Record yourself explaining your CAD model. CAD-Documenter:
-- 📹 Video of engineer explaining a CAD model
+
-- Optional: CAD file references, existing P/N databases
+1. **Extracts key frames** at scene changes (smart, not fixed intervals)
+2. **Transcribes your explanation** via Whisper
+3. **Analyzes visually** using GPT-4o or Claude vision
+4. **Correlates visual + verbal** to identify components
+5. **Generates documentation** with images, BOM, and Atomizer hints
 
 ### Output
+
 - 📄 **Markdown documentation** — Structured, version-controlled
-- 📊 **Bill of Materials** — With standardized P/N
+- 📊 **Bill of Materials** — CSV with components, materials, functions
-- 🔧 **Component registry** — Parts, functions, materials, specs
+- 🔧 **Component registry** — Detailed specs per component
-- 🎯 **Atomizer hints** — Parameters, constraints, objectives for FEA
+- 🎯 **Atomizer hints** — FEA objectives, constraints, parameters
-- 📑 **CDR-ready PDF** — Via Atomaste Report Standard
+- 📑 **PDF** — Professional output via Atomaste Report Standard
 
 ## Installation
 
 ```bash
-# Clone the repo
+# Clone
 git clone http://100.80.199.40:3000/Antoine/CAD-Documenter.git
 cd CAD-Documenter
 
-# Install dependencies (using uv)
+# Install with uv
 uv sync
+
+# Or with pip
+pip install -e .
 ```
 
 ### Requirements
+
 - Python 3.12+
 - ffmpeg (for video/audio processing)
-- Whisper (for transcription)
+- OpenAI or Anthropic API key (for vision analysis)
+
+```bash
+# macOS
+brew install ffmpeg
+
+# Ubuntu/Debian
+sudo apt install ffmpeg
+
+# Windows (with chocolatey)
+choco install ffmpeg
+```
+
+## Quick Start
+
+```bash
+# Set API key
+export OPENAI_API_KEY="sk-your-key"
+
+# Run
+uv run cad-doc walkthrough.mp4
+
+# With all features
+uv run cad-doc walkthrough.mp4 --bom --atomizer-hints --pdf
+```
 
 ## Usage
 
 ```bash
-# Basic documentation
+# Basic
 cad-doc video.mp4
 
-# Full pipeline with all integrations
+# Custom output directory
-cad-doc video.mp4 \
+cad-doc video.mp4 --output ./my_docs/
-  --output docs/my_assembly/ \
+
-  --atomizer-hints \
+# Full pipeline
-  --bom \
+cad-doc video.mp4 --bom --atomizer-hints --pdf
-  --pdf
 
 # Just extract frames
-cad-doc video.mp4 --frames-only --output frames/
+cad-doc video.mp4 --frames-only
+
+# Use Anthropic instead of OpenAI
+cad-doc video.mp4 --api-provider anthropic
+
+# Better transcription (slower)
+cad-doc video.mp4 --whisper-model medium
 ```
 
+## Configuration
+
+Create a config file:
+
+```bash
+cad-doc --init-config
+# Creates ~/.cad-documenter.toml
+```
+
+Or set environment variables:
+
+```bash
+export OPENAI_API_KEY="sk-..."      # Required for OpenAI
+export ANTHROPIC_API_KEY="sk-..."   # Required for Anthropic
+export CAD_DOC_PROVIDER="anthropic" # Override default provider
+```
+
+See [docs/USAGE.md](docs/USAGE.md) for full configuration options.
+
+## Recording Tips
+
+For best results when recording:
+
+1. **Spin slowly** — Give the AI time to see each angle
+2. **Name components** — "This is the main bracket..."
+3. **Mention materials** — "Made of 6061 aluminum"
+4. **Describe functions** — "This holds the motor"
+5. **Note constraints** — "Must fit within 200mm"
+6. **Point out features** — "These fillets reduce stress"
+
 ## Architecture
 
 ```
@@ -76,18 +147,77 @@ cad-doc video.mp4 --frames-only --output frames/
 └─────────────────────────────────────────────────────────────────────┘
 ```
 
-## Integrations
+## Atomizer Integration
 
-- **Atomizer** → FEA setup instructions from verbal explanations
+CAD-Documenter generates FEA optimization hints for Atomizer:
-- **Part Manager** → Standardized P/N lookup
-- **Atomaste Report Standard** → Professional PDF generation
 
-## Project Status
+```bash
+cad-doc walkthrough.mp4 --atomizer-hints
+```
 
-🚧 **Phase 1: Core Pipeline (MVP)** — In Progress
+Output `atomizer_hints.json`:
+```json
+{
+  "objectives": [{"name": "mass", "direction": "minimize"}],
+  "constraints": [{"type": "frequency", "value": ">100 Hz"}],
+  "parameters": ["thickness", "fillet_radius"],
+  "critical_regions": [{"feature": "fillet", "concern": "stress_concentration"}]
+}
+```
 
-See [ROADMAP.md](ROADMAP.md) for full implementation plan.
+See [docs/ATOMIZER_INTEGRATION.md](docs/ATOMIZER_INTEGRATION.md) for details.
+
+## Python API
+
+```python
+from cad_documenter.pipeline import DocumentationPipeline
+
+pipeline = DocumentationPipeline(
+    video_path="walkthrough.mp4",
+    output_dir="./docs"
+)
+
+results = pipeline.run_full_pipeline(
+    atomizer_hints=True,
+    bom=True,
+    pdf=True
+)
+```
+
+## Project Structure
+
+```
+CAD-Documenter/
+├── src/cad_documenter/
+│   ├── cli.py              # Command-line interface
+│   ├── pipeline.py         # Main orchestrator
+│   ├── config.py           # Configuration management
+│   ├── video_processor.py  # Frame extraction
+│   ├── audio_analyzer.py   # Whisper transcription
+│   ├── vision_analyzer.py  # AI vision analysis
+│   └── doc_generator.py    # Output generation
+├── prompts/                # AI prompts
+├── templates/              # Jinja2 templates
+├── tests/                  # Test suite
+├── docs/                   # Documentation
+└── examples/               # Example configs
+```
+
+## Roadmap
+
+- [x] Core pipeline (frames, transcription, vision)
+- [x] Configuration system
+- [x] Atomizer hints extraction
+- [x] BOM generation
+- [ ] Part Manager integration (P/N lookup)
+- [ ] Interactive review mode
+- [ ] Gitea auto-publish
+- [ ] SolidWorks add-in
 
 ## License
 
 MIT
+
+## Credits
+
+Built by [Atomaste](https://atomaste.ca) for the engineering community.

docs/ATOMIZER_INTEGRATION.md

@@ -0,0 +1,182 @@
+# Atomizer Integration Guide
+
+CAD-Documenter generates FEA optimization hints that integrate with Atomizer, the Atomaste optimization framework.
+
+## Overview
+
+When you explain your CAD model in a video walkthrough, CAD-Documenter extracts:
+
+1. **Optimization objectives** - What you want to minimize/maximize
+2. **Design constraints** - Limits and requirements
+3. **Design parameters** - Variables that could be optimized
+4. **Critical regions** - Areas requiring careful FEA attention
+
+## Verbal Cues → Atomizer Hints
+
+### Objectives
+
+| What You Say | Generated Objective |
+|--------------|---------------------|
+| "minimize the weight" | `{"name": "mass", "direction": "minimize"}` |
+| "maximize stiffness" | `{"name": "stiffness", "direction": "maximize"}` |
+| "reduce stress" | `{"name": "stress", "direction": "minimize"}` |
+| "keep the frequency high" | `{"name": "frequency", "direction": "maximize"}` |
+| "minimize deflection" | `{"name": "displacement", "direction": "minimize"}` |
+
+### Constraints
+
+| What You Say | Generated Constraint |
+|--------------|---------------------|
+| "must fit in 200mm" | `{"type": "envelope", "value": "200mm"}` |
+| "under 500 grams" | `{"type": "limit", "value": "500g"}` |
+| "frequency above 100 Hz" | `{"type": "minimum", "value": "100 Hz"}` |
+| "stress cannot exceed 150 MPa" | `{"type": "maximum", "value": "150 MPa"}` |
+
+### Parameters
+
+Mentioning these terms adds them to potential design parameters:
+
+- thickness, wall thickness
+- radius, fillet radius
+- diameter, hole size
+- length, width, height
+- angle, spacing, count
+- rib dimensions
+
+### Critical Regions
+
+| What You Mention | FEA Concern |
+|-----------------|-------------|
+| "this fillet is important" | Stress concentration |
+| "corner stress" | Stress concentration |
+| "bearing load here" | Contact stress |
+| "weld joint" | Fatigue concern |
+| "interface between parts" | Contact analysis |
+
+## Output Format
+
+### atomizer_hints.json
+
+```json
+{
+  "assembly_name": "Motor Bracket Assembly",
+  "generated": "2026-01-27T20:15:00",
+  
+  "model_understanding": {
+    "components": [
+      {
+        "name": "Main Bracket",
+        "material": "Aluminum 6061-T6",
+        "function": "Motor mounting",
+        "features": ["M6 holes", "fillet radii"]
+      }
+    ],
+    "materials_mentioned": ["Aluminum 6061-T6", "Steel"]
+  },
+  
+  "optimization_hints": {
+    "objectives": [
+      {"name": "mass", "direction": "minimize", "source": "Mentioned 'lightweight' in transcript"},
+      {"name": "stiffness", "direction": "maximize", "source": "Mentioned 'stiff' in transcript"}
+    ],
+    "constraints": [
+      {"type": "envelope", "value": "200mm", "raw_match": "must fit in (\\d+)"},
+      {"type": "minimum", "value": "100 Hz", "raw_match": "greater than (\\d+)"}
+    ],
+    "parameters": ["thickness", "fillet_radius", "rib_count"]
+  },
+  
+  "fea_hints": {
+    "critical_regions": [
+      {"feature": "fillet", "concern": "stress_concentration"},
+      {"feature": "interface", "concern": "contact_analysis"}
+    ],
+    "study_suggestions": [
+      "Modal analysis recommended - frequency/vibration mentioned",
+      "Topology optimization could reduce mass while maintaining performance"
+    ]
+  },
+  
+  "transcript_summary": "This assembly provides structural support for a NEMA 23 motor..."
+}
+```
+
+## Using with Atomizer
+
+### 1. Generate Hints
+
+```bash
+cad-doc walkthrough.mp4 --atomizer-hints
+```
+
+### 2. Load in Atomizer
+
+```python
+# In Atomizer study setup
+from atomizer import Study
+import json
+
+with open("walkthrough_docs/atomizer_hints.json") as f:
+    hints = json.load(f)
+
+study = Study.from_hints(hints)
+
+# Hints pre-populate:
+# - Objective functions
+# - Constraints
+# - Suggested parameters
+# - Critical regions for mesh refinement
+```
+
+### 3. Review and Refine
+
+The hints are suggestions, not final configurations:
+
+- Verify objectives match your actual goals
+- Add specific constraint values
+- Map parameters to CAD model variables
+- Adjust mesh refinement regions
+
+## Best Practices
+
+### During Recording
+
+1. **State objectives clearly**
+   - "The goal is to minimize weight while maintaining stiffness"
+   - "We need to keep the first natural frequency above 100 Hz"
+
+2. **Quantify constraints**
+   - "Maximum envelope is 200mm by 150mm by 100mm"
+   - "Weight budget is 500 grams"
+   - "Stress must stay below 150 MPa"
+
+3. **Point out critical features**
+   - "This fillet is critical for stress concentration"
+   - "The bearing surface here sees high contact stress"
+
+4. **Mention what could be optimized**
+   - "The wall thickness could potentially be reduced"
+   - "These rib dimensions are candidates for optimization"
+
+### After Generation
+
+1. Review `atomizer_hints.json` for accuracy
+2. Add missing numerical values
+3. Map parameters to your CAD model
+4. Use critical regions to guide mesh refinement
+5. Run initial FEA to validate hints
+
+## Example Workflow
+
+1. **Record walkthrough** explaining bracket design
+2. **Run CAD-Documenter** with `--atomizer-hints`
+3. **Review hints** in generated JSON
+4. **Import into Atomizer** for optimization study
+5. **Iterate** based on FEA results
+
+## Limitations
+
+- Hints are extracted from verbal/visual cues only
+- Numerical values may need refinement
+- Complex multi-objective problems need manual setup
+- Material properties should be verified against database

docs/USAGE.md

@@ -0,0 +1,220 @@
+# CAD-Documenter Usage Guide
+
+## Quick Start
+
+```bash
+# Install
+cd /path/to/CAD-Documenter
+uv sync
+
+# Set API key
+export OPENAI_API_KEY="sk-your-key"
+
+# Run
+uv run cad-doc your_video.mp4
+```
+
+## Basic Commands
+
+### Generate Documentation
+```bash
+cad-doc video.mp4
+```
+
+Creates `video_docs/` with:
+- `documentation.md` - Main documentation
+- `frames/` - Extracted keyframes
+
+### With All Features
+```bash
+cad-doc video.mp4 --bom --atomizer-hints --pdf
+```
+
+Creates additional:
+- `bom.csv` - Bill of Materials
+- `atomizer_hints.json` - FEA setup hints
+- `documentation.pdf` - PDF version
+
+### Custom Output Directory
+```bash
+cad-doc video.mp4 --output ./my_docs/
+```
+
+## Recording Tips
+
+For best results when recording your CAD walkthrough:
+
+### Video
+- Use 1080p or higher resolution
+- 30 FPS is sufficient
+- Record the CAD viewport directly (not your whole screen)
+- Spin the model slowly and steadily
+- Pause briefly when showing details
+
+### Audio
+- Use a decent microphone
+- Speak clearly and at normal pace
+- Name each component explicitly: "This is the main bracket..."
+- Mention materials: "Made of 6061 aluminum"
+- Describe functions: "This holds the motor in place"
+- Note constraints: "Must fit within 200mm envelope"
+- Call out features: "These fillets reduce stress concentration"
+
+### Structure
+1. Start with an overview (assembly name, purpose)
+2. Go through major components
+3. Show details and features
+4. Discuss assembly relationships
+5. Mention any constraints or requirements
+
+## Configuration
+
+### Create Config File
+```bash
+cad-doc --init-config
+```
+
+Creates `~/.cad-documenter.toml` with defaults.
+
+### Config Options
+
+```toml
+[api]
+provider = "openai"  # or "anthropic"
+# api_key = "sk-..."  # Or use env var
+
+[processing]
+whisper_model = "base"  # tiny/base/small/medium/large
+use_scene_detection = true
+max_frames = 15
+
+[output]
+include_bom = true
+include_atomizer_hints = true
+```
+
+### Environment Variables
+
+```bash
+export OPENAI_API_KEY="sk-..."      # For OpenAI
+export ANTHROPIC_API_KEY="sk-..."   # For Anthropic
+export CAD_DOC_PROVIDER="anthropic" # Override provider
+export CAD_DOC_WHISPER_MODEL="medium" # Override Whisper model
+```
+
+## CLI Options
+
+```
+Usage: cad-doc [OPTIONS] VIDEO
+
+Options:
+  -o, --output PATH           Output directory
+  --frames-only               Only extract frames, skip analysis
+  --atomizer-hints            Generate Atomizer FEA hints
+  --bom                       Generate Bill of Materials
+  --pdf                       Generate PDF output
+  --frame-interval FLOAT      Seconds between frames
+  --whisper-model [tiny|base|small|medium|large]
+                              Whisper model size
+  --api-provider [openai|anthropic]
+                              Vision API provider
+  --config PATH               Config file path
+  --init-config               Create default config file
+  -v, --verbose               Verbose output
+  --version                   Show version
+  --help                      Show this message
+```
+
+## Python API
+
+```python
+from cad_documenter.pipeline import DocumentationPipeline
+
+# Simple usage
+pipeline = DocumentationPipeline(
+    video_path="walkthrough.mp4",
+    output_dir="./docs"
+)
+
+results = pipeline.run_full_pipeline(
+    atomizer_hints=True,
+    bom=True,
+    pdf=True
+)
+
+print(f"Documentation: {results['documentation']}")
+print(f"Components: {results['components']}")
+```
+
+### With Progress Callback
+
+```python
+def on_progress(progress):
+    print(f"[{progress.stage.value}] {progress.message} ({progress.progress:.0%})")
+
+pipeline = DocumentationPipeline(
+    video_path="walkthrough.mp4",
+    output_dir="./docs",
+    progress_callback=on_progress
+)
+
+results = pipeline.run()
+```
+
+## Atomizer Integration
+
+The `atomizer_hints.json` output is designed for use with Atomizer FEA optimization:
+
+```json
+{
+  "assembly_name": "Motor Bracket Assembly",
+  "optimization_hints": {
+    "objectives": [
+      {"name": "mass", "direction": "minimize"},
+      {"name": "stiffness", "direction": "maximize"}
+    ],
+    "constraints": [
+      {"type": "envelope", "value": "200mm"},
+      {"type": "frequency", "value": ">100 Hz"}
+    ],
+    "parameters": ["thickness", "fillet_radius", "rib_count"]
+  },
+  "fea_hints": {
+    "critical_regions": [
+      {"feature": "fillet", "concern": "stress_concentration"}
+    ],
+    "study_suggestions": [
+      "Modal analysis recommended - frequency/vibration mentioned"
+    ]
+  }
+}
+```
+
+## Troubleshooting
+
+### "No API key found"
+Set your API key:
+```bash
+export OPENAI_API_KEY="sk-..."
+```
+Or add to config file.
+
+### "No frames extracted"
+- Check video file is valid
+- Try different frame_interval
+- Ensure ffmpeg is installed
+
+### "No components detected"
+- Ensure video clearly shows the model
+- Speak component names clearly
+- Try larger Whisper model: `--whisper-model medium`
+- Check API key has sufficient credits
+
+### "Transcription failed"
+- Video may have no audio track
+- Use `--frames-only` to skip transcription
+- Check ffmpeg can extract audio: `ffmpeg -i video.mp4 -vn audio.wav`
+
+### PDF generation fails
+- Install pandoc: `apt install pandoc texlive-xetex`
+- Or use Typst with Atomaste Report Standard

examples/sample_config.toml

@@ -0,0 +1,49 @@
+# CAD-Documenter Sample Configuration
+# Copy to ~/.cad-documenter.toml and customize
+
+[api]
+# Vision API provider: "openai" or "anthropic"
+provider = "openai"
+
+# API key - REQUIRED for vision analysis
+# Can also be set via OPENAI_API_KEY or ANTHROPIC_API_KEY environment variable
+# api_key = "sk-your-key-here"
+
+# Model overrides (optional - uses provider defaults if not set)
+# For OpenAI: gpt-4o (default), gpt-4o-mini
+# For Anthropic: claude-sonnet-4-20250514 (default), claude-3-haiku-20240307
+# vision_model = "gpt-4o"
+# text_model = "gpt-4o-mini"
+
+[processing]
+# Whisper model for transcription
+# Options: tiny (fastest), base (default), small, medium, large (most accurate)
+whisper_model = "base"
+
+# Seconds between frame extractions (used if scene detection disabled)
+frame_interval = 2.0
+
+# Use AI-powered scene change detection for smarter frame selection
+use_scene_detection = true
+
+# Maximum frames to analyze (limits API costs)
+max_frames = 15
+
+# Scene detection sensitivity (0.0-1.0, lower = more sensitive)
+scene_threshold = 0.3
+
+[output]
+# Include Bill of Materials table in documentation
+include_bom = true
+
+# Include Atomizer FEA hints section
+include_atomizer_hints = true
+
+# Include raw transcript at end of documentation
+include_raw_transcript = true
+
+# Keep extracted frames in output directory
+include_frames = true
+
+# PDF template name (for future template support)
+pdf_template = "default"

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "cad-documenter"
-version = "0.1.0"
+version = "0.2.0"
 description = "Video walkthrough → Complete engineering documentation"
 readme = "README.md"
 requires-python = ">=3.12"
@@ -8,26 +8,48 @@ license = {text = "MIT"}
 authors = [
     {name = "Antoine Letarte", email = "antoine.letarte@gmail.com"},
 ]
+keywords = ["cad", "documentation", "engineering", "video", "ai", "vision", "whisper"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Manufacturing",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering",
+    "Topic :: Multimedia :: Video",
+]
+
 dependencies = [
     "click>=8.1.0",
     "rich>=13.0.0",
-    "pydantic>=2.0.0",
     "jinja2>=3.1.0",
     "openai-whisper>=20231117",
     "pillow>=10.0.0",
-    "httpx>=0.27.0",
+    # Vision API clients
-    "tomli>=2.0.0;python_version<'3.11'",
+    "anthropic>=0.40.0",
+    "openai>=1.50.0",
 ]
 
 [project.optional-dependencies]
 dev = [
     "pytest>=8.0.0",
+    "pytest-cov>=4.0.0",
     "ruff>=0.1.0",
+    "mypy>=1.0.0",
+]
+pdf = [
+    "pandoc",  # For PDF generation fallback
 ]
 
 [project.scripts]
 cad-doc = "cad_documenter.cli:main"
 
+[project.urls]
+Homepage = "http://100.80.199.40:3000/Antoine/CAD-Documenter"
+Documentation = "http://100.80.199.40:3000/Antoine/CAD-Documenter"
+Repository = "http://100.80.199.40:3000/Antoine/CAD-Documenter"
+
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"
@@ -38,3 +60,17 @@ packages = ["src/cad_documenter"]
 [tool.ruff]
 line-length = 100
 target-version = "py312"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP"]
+ignore = ["E501"]  # Line length handled separately
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]
+
+[tool.mypy]
+python_version = "3.12"
+strict = false
+warn_return_any = true
+warn_unused_ignores = true

src/cad_documenter/__init__.py

@@ -1,3 +1,34 @@
-"""CAD-Documenter: Video walkthrough → Complete engineering documentation."""
+"""CAD-Documenter: Video walkthrough → Engineering documentation."""
 
-__version__ = "0.1.0"
+__version__ = "0.2.0"
+
+from .pipeline import DocumentationPipeline, create_pipeline, PipelineResult
+from .config import Config, load_config
+from .video_processor import VideoProcessor, FrameInfo, VideoMetadata
+from .audio_analyzer import AudioAnalyzer, Transcript, TranscriptSegment
+from .vision_analyzer import VisionAnalyzer, Component, ComponentAnalysis
+from .doc_generator import DocGenerator
+
+__all__ = [
+    # Main entry points
+    "DocumentationPipeline",
+    "create_pipeline",
+    "PipelineResult",
+    # Configuration
+    "Config",
+    "load_config",
+    # Video processing
+    "VideoProcessor",
+    "FrameInfo",
+    "VideoMetadata",
+    # Audio processing
+    "AudioAnalyzer",
+    "Transcript",
+    "TranscriptSegment",
+    # Vision analysis
+    "VisionAnalyzer",
+    "Component",
+    "ComponentAnalysis",
+    # Documentation
+    "DocGenerator",
+]

src/cad_documenter/cli.py

@@ -5,208 +5,379 @@ from pathlib import Path
 
 import click
 from rich.console import Console
-from rich.progress import Progress, SpinnerColumn, TextColumn
+from rich.progress import Progress, SpinnerColumn, TextColumn, BarColumn
 from rich.panel import Panel
+from rich.table import Table
 
-from .config import load_config, create_default_config
+from .pipeline import DocumentationPipeline, PipelineProgress, PipelineStage, create_pipeline
-from .pipeline import DocumentationPipeline
+from .config import Config, load_config
 
 console = Console()
 
 
 def print_banner():
-    """Print welcome banner."""
+    """Print the CAD-Documenter banner."""
     console.print(Panel.fit(
-        "[bold blue]CAD-Documenter[/bold blue] v0.1.0\n"
+        "[bold blue]CAD-Documenter[/bold blue] v0.2.0\n"
         "[dim]Video walkthrough → Engineering documentation[/dim]",
         border_style="blue"
     ))
 
 
-@click.command()
+def progress_handler(progress: PipelineProgress):
+    """Handle progress updates from pipeline."""
+    stage_icons = {
+        PipelineStage.INIT: "🔧",
+        PipelineStage.FRAMES: "🎬",
+        PipelineStage.TRANSCRIPTION: "🎤",
+        PipelineStage.ANALYSIS: "🔍",
+        PipelineStage.DOCUMENTATION: "📝",
+        PipelineStage.PDF: "📄",
+        PipelineStage.COMPLETE: "✅",
+    }
+    icon = stage_icons.get(progress.stage, "⏳")
+    
+    if progress.error:
+        console.print(f"  [red]✗[/red] {progress.message}")
+    else:
+        console.print(f"  {icon} {progress.message}")
+
+
+@click.group(invoke_without_command=True)
+@click.pass_context
+def cli(ctx):
+    """CAD-Documenter: Generate engineering documentation from video walkthroughs."""
+    if ctx.invoked_subcommand is None:
+        click.echo(ctx.get_help())
+
+
+@cli.command()
 @click.argument("video", type=click.Path(exists=True, path_type=Path))
 @click.option("-o", "--output", type=click.Path(path_type=Path), help="Output directory")
 @click.option("--frames-only", is_flag=True, help="Only extract frames, skip documentation")
+@click.option("--skip-transcription", is_flag=True, help="Skip audio transcription")
 @click.option("--atomizer-hints", is_flag=True, help="Generate Atomizer FEA hints")
 @click.option("--bom", is_flag=True, help="Generate Bill of Materials")
 @click.option("--pdf", is_flag=True, help="Generate PDF via Atomaste Report Standard")
-@click.option("--frame-interval", type=float, help="Seconds between frame extractions")
+@click.option("--frame-mode", type=click.Choice(["interval", "scene", "hybrid"]), 
-@click.option("--whisper-model", type=click.Choice(["tiny", "base", "small", "medium", "large"]), help="Whisper model size")
+              default="hybrid", help="Frame extraction mode")
-@click.option("--api-provider", type=click.Choice(["openai", "anthropic"]), help="Vision API provider")
+@click.option("--frame-interval", default=2.0, help="Seconds between frames (interval mode)")
-@click.option("--config", "config_path", type=click.Path(exists=True, path_type=Path), help="Config file path")
+@click.option("--whisper-model", default="base", 
-@click.option("--init-config", is_flag=True, help="Create default config file and exit")
+              help="Whisper model size (tiny/base/small/medium/large)")
-@click.option("-v", "--verbose", is_flag=True, help="Verbose output")
+@click.option("--vision-provider", type=click.Choice(["anthropic", "openai"]),
-@click.version_option()
+              default="anthropic", help="Vision API provider")
-def main(
+@click.option("--vision-model", default=None, help="Vision model name (provider-specific)")
+@click.option("--config", type=click.Path(path_type=Path), help="Config file path")
+@click.option("--verbose", "-v", is_flag=True, help="Verbose output")
+def process(
     video: Path,
     output: Path | None,
     frames_only: bool,
+    skip_transcription: bool,
     atomizer_hints: bool,
     bom: bool,
     pdf: bool,
-    frame_interval: float | None,
+    frame_mode: str,
-    whisper_model: str | None,
+    frame_interval: float,
-    api_provider: str | None,
+    whisper_model: str,
-    config_path: Path | None,
+    vision_provider: str,
-    init_config: bool,
+    vision_model: str | None,
+    config: Path | None,
     verbose: bool,
 ):
     """
-    Generate engineering documentation from a CAD walkthrough video.
+    Process a video walkthrough and generate documentation.
 
     VIDEO: Path to the video file (.mp4, .mov, .avi, etc.)
-
+    
     Examples:
-
+    
-        cad-doc walkthrough.mp4
+        cad-doc process video.mp4
-
+        
-        cad-doc video.mp4 --output ./docs --bom --atomizer-hints
+        cad-doc process video.mp4 --atomizer-hints --bom --pdf
-
+        
-        cad-doc video.mp4 --pdf --whisper-model medium
+        cad-doc process video.mp4 --frame-mode scene --vision-provider openai
     """
     print_banner()
-    
+    console.print(f"\n📹 Processing: [cyan]{video}[/cyan]")
-    # Handle --init-config
+
-    if init_config:
+    # Load or create config
-        default_path = Path.home() / ".cad-documenter.toml"
+    cfg = load_config(config)
-        create_default_config(default_path)
-        console.print(f"[green]✓[/green] Created config file: {default_path}")
-        console.print("[dim]Edit this file to configure API keys and defaults.[/dim]")
-        return
-    
-    # Load configuration
-    config = load_config(config_path)
     
     # Override config with CLI options
-    if frame_interval is not None:
+    cfg.frame_extraction.mode = frame_mode
-        config.processing.frame_interval = frame_interval
+    cfg.frame_extraction.interval_seconds = frame_interval
-    if whisper_model is not None:
+    cfg.transcription.model = whisper_model
-        config.processing.whisper_model = whisper_model
+    cfg.vision.provider = vision_provider
-    if api_provider is not None:
+    if vision_model:
-        config.api.provider = api_provider
+        cfg.vision.model = vision_model
-    
+
-    # Check API key
-    if not frames_only and not config.api.api_key:
-        provider = config.api.provider.upper()
-        console.print(f"[red]Error:[/red] No API key found for {config.api.provider}.")
-        console.print(f"Set [cyan]{provider}_API_KEY[/cyan] environment variable or add to config file.")
-        console.print(f"\nTo create a config file: [cyan]cad-doc --init-config[/cyan]")
-        sys.exit(1)
-    
-    console.print(f"Processing: [cyan]{video.name}[/cyan]")
-    if verbose:
-        console.print(f"  API: {config.api.provider} ({config.api.vision_model or 'default'})")
-        console.print(f"  Whisper: {config.processing.whisper_model}")
-    
     # Default output directory
     if output is None:
         output = video.parent / f"{video.stem}_docs"
-    
+
-    output.mkdir(parents=True, exist_ok=True)
+    console.print(f"📁 Output: [cyan]{output}[/cyan]\n")
-    console.print(f"Output: [cyan]{output}[/cyan]")
+
-    
+    # Create pipeline
-    # Initialize pipeline
+    pipeline = DocumentationPipeline(
+        video_path=video,
+        output_dir=output,
+        config=cfg,
+        progress_callback=progress_handler if verbose else None,
+    )
+
+    # Show video info
     try:
-        pipeline = DocumentationPipeline(
+        metadata = pipeline.get_video_metadata()
-            video_path=video,
+        console.print(f"  Duration: {metadata.duration:.1f}s | "
-            output_dir=output,
+                     f"Resolution: {metadata.width}x{metadata.height} | "
-            config=config,
+                     f"Audio: {'✓' if metadata.has_audio else '✗'}")
-        )
+    except Exception:
-    except ValueError as e:
+        pass
-        console.print(f"[red]Configuration error:[/red] {e}")
+
-        sys.exit(1)
+    console.print()
-    
+
-    # Frames only mode
+    # Run pipeline with progress
-    if frames_only:
-        with Progress(
-            SpinnerColumn(),
-            TextColumn("[progress.description]{task.description}"),
-            console=console,
-        ) as progress:
-            progress.add_task("Extracting frames...", total=None)
-            frames = pipeline.extract_frames()
-        
-        console.print(f"[green]✓[/green] Extracted {len(frames)} frames to {output / 'frames'}")
-        return
-    
-    # Full pipeline
     with Progress(
         SpinnerColumn(),
         TextColumn("[progress.description]{task.description}"),
+        BarColumn(),
+        TextColumn("[progress.percentage]{task.percentage:>3.0f}%"),
         console=console,
+        disable=verbose,  # Disable progress bar if verbose (use callback instead)
     ) as progress:
-        
+        task = progress.add_task("Processing...", total=100)
-        # Step 1: Extract frames
+
-        task1 = progress.add_task("[cyan]Step 1/4:[/cyan] Extracting frames...", total=None)
+        def update_progress(p: PipelineProgress):
-        frames = pipeline.extract_frames()
+            progress.update(task, completed=int(p.progress * 100), description=p.message)
-        progress.update(task1, description=f"[green]✓[/green] Extracted {len(frames)} frames")
+            if verbose:
-        progress.remove_task(task1)
+                progress_handler(p)
-        
+
-        # Step 2: Transcribe
+        pipeline.progress_callback = update_progress
-        task2 = progress.add_task("[cyan]Step 2/4:[/cyan] Transcribing audio...", total=None)
+
-        transcript = pipeline.transcribe_audio()
+        result = pipeline.run(
-        seg_count = len(transcript.segments) if transcript.segments else 0
+            frames_only=frames_only,
-        progress.update(task2, description=f"[green]✓[/green] Transcribed {seg_count} segments")
+            skip_transcription=skip_transcription,
-        progress.remove_task(task2)
+            atomizer_hints=atomizer_hints,
-        
+            bom=bom,
-        if verbose and transcript.full_text:
+            pdf=pdf,
-            console.print(Panel(
-                transcript.full_text[:500] + ("..." if len(transcript.full_text) > 500 else ""),
-                title="Transcript Preview",
-                border_style="dim"
-            ))
-        
-        # Step 3: Analyze
-        task3 = progress.add_task("[cyan]Step 3/4:[/cyan] Analyzing components...", total=None)
-        analysis = pipeline.analyze_components(frames, transcript)
-        comp_count = len(analysis.components)
-        progress.update(task3, description=f"[green]✓[/green] Identified {comp_count} components")
-        progress.remove_task(task3)
-        
-        if verbose and analysis.components:
-            console.print("\n[bold]Components found:[/bold]")
-            for c in analysis.components:
-                console.print(f"  • {c.name} ({c.material or 'material unknown'})")
-        
-        # Step 4: Generate documentation
-        task4 = progress.add_task("[cyan]Step 4/4:[/cyan] Generating documentation...", total=None)
-        doc_path = pipeline.generate_documentation(
-            analysis, 
-            atomizer_hints=atomizer_hints or config.output.include_atomizer_hints,
-            bom=bom or config.output.include_bom,
         )
-        progress.update(task4, description=f"[green]✓[/green] Documentation generated")
+
-        progress.remove_task(task4)
+    # Print results
-    
-    # Generate PDF if requested
-    if pdf:
-        console.print("[cyan]Generating PDF...[/cyan]")
-        try:
-            pdf_path = pipeline.generate_pdf(doc_path)
-            console.print(f"[green]✓[/green] PDF: {pdf_path}")
-        except Exception as e:
-            console.print(f"[yellow]Warning:[/yellow] PDF generation failed: {e}")
-    
-    # Summary
     console.print()
-    console.print(Panel.fit(
-        f"[bold green]Documentation complete![/bold green]\n\n"
-        f"📄 [cyan]{doc_path}[/cyan]\n"
-        f"📊 {len(analysis.components)} components documented\n"
-        f"🖼️  {len(frames)} frames extracted",
-        title="Summary",
-        border_style="green"
-    ))
     
-    # Show atomizer hints summary if generated
+    if result.success:
-    if (atomizer_hints or config.output.include_atomizer_hints) and analysis.atomizer_hints:
+        console.print(Panel.fit(
-        hints = analysis.atomizer_hints
+            f"[bold green]✓ Documentation generated successfully![/bold green]\n\n"
-        if hints.objectives or hints.constraints:
+            f"📊 Frames extracted: {result.frames_extracted}\n"
-            console.print("\n[bold]Atomizer Hints:[/bold]")
+            f"🔧 Components found: {result.components_found}\n"
-            for obj in hints.objectives[:3]:
+            f"🎤 Audio duration: {result.transcript_duration:.1f}s",
-                console.print(f"  🎯 {obj['direction'].capitalize()} {obj['name']}")
+            title="Results",
-            for constraint in hints.constraints[:3]:
+            border_style="green"
-                console.print(f"  📏 {constraint['type']}: {constraint['value']}")
+        ))
+        
+        # Show output files
+        table = Table(title="Output Files", show_header=True)
+        table.add_column("Type", style="cyan")
+        table.add_column("Path")
+        
+        if result.documentation_path:
+            table.add_row("Documentation", str(result.documentation_path))
+        if result.atomizer_hints_path:
+            table.add_row("Atomizer Hints", str(result.atomizer_hints_path))
+        if result.bom_path:
+            table.add_row("BOM", str(result.bom_path))
+        if result.pdf_path:
+            table.add_row("PDF", str(result.pdf_path))
+        
+        console.print(table)
+        
+        # Show warnings
+        if result.warnings:
+            console.print("\n[yellow]Warnings:[/yellow]")
+            for warning in result.warnings:
+                console.print(f"  ⚠️  {warning}")
+    else:
+        console.print(Panel.fit(
+            f"[bold red]✗ Pipeline failed[/bold red]\n\n" +
+            "\n".join(result.errors),
+            title="Error",
+            border_style="red"
+        ))
+        sys.exit(1)
+
+
+@cli.command()
+@click.argument("video", type=click.Path(exists=True, path_type=Path))
+@click.option("-o", "--output", type=click.Path(path_type=Path), help="Output directory")
+@click.option("--mode", type=click.Choice(["interval", "scene", "hybrid"]),
+              default="hybrid", help="Extraction mode")
+@click.option("--interval", default=2.0, help="Seconds between frames")
+@click.option("--threshold", default=0.3, help="Scene change threshold")
+def frames(video: Path, output: Path | None, mode: str, interval: float, threshold: float):
+    """
+    Extract frames from a video without full processing.
+    
+    Useful for previewing what frames will be analyzed.
+    """
+    from .video_processor import VideoProcessor
+    from .config import FrameExtractionConfig
+    
+    print_banner()
+    console.print(f"\n📹 Extracting frames from: [cyan]{video}[/cyan]")
+    
+    if output is None:
+        output = video.parent / f"{video.stem}_frames"
+    
+    config = FrameExtractionConfig(
+        mode=mode,
+        interval_seconds=interval,
+        scene_threshold=threshold,
+    )
+    
+    processor = VideoProcessor(video, output, config)
+    
+    with console.status("Extracting frames..."):
+        frames_list = processor.extract_frames()
+    
+    console.print(f"\n[green]✓[/green] Extracted {len(frames_list)} frames to {output}")
+    
+    # Show frame timestamps
+    table = Table(title="Extracted Frames")
+    table.add_column("#", style="dim")
+    table.add_column("Timestamp")
+    table.add_column("File")
+    table.add_column("Scene Score")
+    
+    for i, frame in enumerate(frames_list[:20]):  # Show first 20
+        table.add_row(
+            str(i + 1),
+            f"{frame.timestamp:.2f}s",
+            frame.path.name,
+            f"{frame.scene_score:.2f}" if frame.scene_score else "-"
+        )
+    
+    if len(frames_list) > 20:
+        table.add_row("...", f"({len(frames_list) - 20} more)", "", "")
+    
+    console.print(table)
+
+
+@cli.command()
+@click.argument("video", type=click.Path(exists=True, path_type=Path))
+@click.option("--model", default="base", help="Whisper model size")
+@click.option("--output", "-o", type=click.Path(path_type=Path), help="Output file")
+def transcribe(video: Path, model: str, output: Path | None):
+    """
+    Transcribe audio from a video file.
+    
+    Outputs transcript with timestamps.
+    """
+    from .audio_analyzer import AudioAnalyzer
+    from .config import TranscriptionConfig
+    
+    print_banner()
+    console.print(f"\n🎤 Transcribing: [cyan]{video}[/cyan]")
+    
+    config = TranscriptionConfig(model=model)
+    analyzer = AudioAnalyzer(video, config)
+    
+    with console.status(f"Transcribing with Whisper ({model})..."):
+        transcript = analyzer.transcribe()
+    
+    console.print(f"\n[green]✓[/green] Transcribed {len(transcript.segments)} segments")
+    console.print(f"   Duration: {transcript.duration:.1f}s")
+    console.print(f"   Language: {transcript.language}\n")
+    
+    # Save or display transcript
+    if output:
+        lines = []
+        for seg in transcript.segments:
+            lines.append(f"[{seg.start:.2f} - {seg.end:.2f}] {seg.text}")
+        output.write_text("\n".join(lines))
+        console.print(f"Saved to: {output}")
+    else:
+        for seg in transcript.segments[:10]:
+            console.print(f"[dim][{seg.start:.1f}s][/dim] {seg.text}")
+        if len(transcript.segments) > 10:
+            console.print(f"[dim]... ({len(transcript.segments) - 10} more segments)[/dim]")
+
+
+@cli.command()
+@click.option("--output", "-o", type=click.Path(path_type=Path), help="Output config file")
+def init(output: Path | None):
+    """
+    Create a default configuration file.
+    """
+    from .config import Config
+    
+    if output is None:
+        output = Path(".cad-documenter.json")
+    
+    config = Config()
+    config.to_file(output)
+    
+    console.print(f"[green]✓[/green] Created config file: {output}")
+    console.print("\nEdit this file to customize:")
+    console.print("  - Vision model and provider")
+    console.print("  - Whisper transcription settings")
+    console.print("  - Frame extraction parameters")
+
+
+@cli.command()
+@click.argument("video", type=click.Path(exists=True, path_type=Path))
+def info(video: Path):
+    """
+    Show information about a video file.
+    """
+    from .video_processor import VideoProcessor
+    
+    processor = VideoProcessor(video, Path("/tmp"))
+    metadata = processor.get_metadata()
+    
+    table = Table(title=f"Video Info: {video.name}")
+    table.add_column("Property", style="cyan")
+    table.add_column("Value")
+    
+    table.add_row("Duration", f"{metadata.duration:.2f}s ({metadata.duration/60:.1f} min)")
+    table.add_row("Resolution", f"{metadata.width}x{metadata.height}")
+    table.add_row("FPS", f"{metadata.fps:.2f}")
+    table.add_row("Codec", metadata.codec)
+    table.add_row("Has Audio", "✓" if metadata.has_audio else "✗")
+    table.add_row("File Size", f"{video.stat().st_size / 1024 / 1024:.1f} MB")
+    
+    console.print(table)
+
+
+# Legacy command for backwards compatibility
+@cli.command(name="main", hidden=True)
+@click.argument("video", type=click.Path(exists=True, path_type=Path))
+@click.option("-o", "--output", type=click.Path(path_type=Path))
+@click.option("--frames-only", is_flag=True)
+@click.option("--atomizer-hints", is_flag=True)
+@click.option("--bom", is_flag=True)
+@click.option("--pdf", is_flag=True)
+@click.option("--frame-interval", default=2.0)
+@click.option("--whisper-model", default="base")
+@click.pass_context
+def main_legacy(ctx, video, output, frames_only, atomizer_hints, bom, pdf, frame_interval, whisper_model):
+    """Legacy entry point - redirects to process command."""
+    ctx.invoke(
+        process,
+        video=video,
+        output=output,
+        frames_only=frames_only,
+        atomizer_hints=atomizer_hints,
+        bom=bom,
+        pdf=pdf,
+        frame_interval=frame_interval,
+        whisper_model=whisper_model,
+    )
+
+
+def main():
+    """Main entry point."""
+    cli()
 
 
 if __name__ == "__main__":