Root cause: Pre-trained model was loading successfully, causing CLI to skip
calibration entirely. System went straight to classification with 35% model.
Changes:
- config: Set calibration_model to qwen3:8b-q4_K_M (larger model for better instruction following)
- cli: Create separate calibration_llm provider with 8b model
- llm_analyzer: Improved prompt to force exact email ID copying
- workflow: Merge discovered categories with predefined ones
- workflow: Add detailed error logging for label mismatches
- ml_classifier: Fixed model path checking (was checking None parameter)
- ml_classifier: Add dual API support (sklearn predict_proba vs LightGBM predict)
- ollama: Fixed model list parsing (use m.model not m.get('name'))
- feature_extractor: Switch to Ollama embeddings (instant vs 90s load time)
Result: Calibration now runs and generates 16 categories + 50 labels correctly.
Next: Investigate calibration sampling to reduce overfitting on small samples.
- Immediate entry point for new users
- Three clear paths (5 min / 30-60 min / 2-3 hours)
- Quick reference commands
- FAQ section
- Documentation map
- Success criteria
- Key files locations
Enables users to:
1. Understand what they have
2. Choose their deployment path
3. Get started immediately
4. Know what to expect
This is the first file users should read.
Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
