Audit et corrections du Web Dashboard (port 5001) :
- Désactiver le bouton "Restaurer" (rollback) car la route /api/version/rollback
n'est pas implémentée côté serveur
- Corriger le parsing de /api/version : les données sont dans version.version (dict),
pas directement dans version (string)
- Corriger le parsing de /api/version/system-info : données imbriquées dans
system_info.system, pas directement à la racine
- Corriger le parsing de /api/backup/stats : utiliser stats.*.file_count au lieu
de categories.*.count qui n'existe pas
- Corriger le fallback correction packs pour utiliser le bon format de stats
- Corriger le parsing de faiss.total_vectors dans l'onglet Apprentissage
- Remplacer les données simulées dans loadActionTypeStats() par un placeholder honnête
- Corriger le HTML invalide (double attribut style sur configTestResults)
- Rendre switchTab() plus robuste avec event.target.closest('.tab')
- Réduire le polling services de 5s à 15s pour limiter la charge
- Mettre à jour SERVICES_CONFIG (ports corrects, .venv/ au lieu de venv_v3/)
- Ajouter le proxy streaming et 4 services manquants dans la config
- Ajouter 19 tests unitaires pour les routes du dashboard
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add CoachingDecision enum (ACCEPT, REJECT, CORRECT, EXECUTE_MANUAL, SKIP)
- Add CoachingResponse dataclass for user decisions
- Add WAITING_COACHING state to ExecutionState
- Implement _request_coaching_decision() with callback or polling support
- Implement submit_coaching_decision() for external API/UI submission
- Implement _apply_coaching_correction() for applying user corrections
- Implement _record_coaching_feedback() integrating with:
- TrainingDataCollector for session recording
- FeedbackProcessor for statistics
- CorrectionPackIntegration for automatic correction capture
- Add get_coaching_stats() for session statistics
- Add 17 unit tests for COACHING functionality
COACHING mode now:
1. Suggests actions to user
2. Waits for user decision (accept/reject/correct/manual/skip)
3. Applies corrections if provided
4. Records all feedback for learning
5. Propagates corrections to Correction Packs automatically
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add CorrectionPackIntegration class to bridge learning components
- Modify TrainingDataCollector to auto-propagate corrections to packs
- Modify FeedbackProcessor to capture corrections on INCORRECT/PARTIAL feedback
- Add convenience functions: get_correction_pack_integration(), capture_coaching_correction()
- Add 19 integration tests (all passing)
Corrections made during COACHING mode are now automatically captured
into a dedicated "auto_captured_corrections" pack for cross-workflow reuse.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement a complete system for capitalizing user corrections across multiple
workflows and sessions. This enables automatic application of learned fixes
when similar failures occur in different contexts.
New components:
- core/corrections/models.py: CorrectionKey, Correction, CorrectionPack models
- core/corrections/correction_repository.py: JSON storage with atomic writes
- core/corrections/aggregator.py: Aggregation by hash and quality filtering
- core/corrections/correction_pack_service.py: CRUD, export/import, versioning
- backend/api/correction_packs.py: REST API with 15 endpoints
Features:
- MD5-based key hashing for correction deduplication
- Export/import in JSON and YAML formats
- Version history with rollback support
- Cross-workflow pattern detection
- Integration with SelfHealingEngine for automatic application
- 29 unit tests (all passing)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
