feat: chat unifié, GestureCatalog, Copilot, Léa UI, extraction données, vérification replay

Refonte majeure du système Agent Chat et ajout de nombreux modules :

- Chat unifié : suppression du dual Workflows/Agent Libre, tout passe par /api/chat
  avec résolution en 3 niveaux (workflow → geste → "montre-moi")
- GestureCatalog : 38 raccourcis clavier universels Windows avec matching sémantique,
  substitution automatique dans les replays, et endpoint /api/gestures
- Mode Copilot : exécution pas-à-pas des workflows avec validation humaine via WebSocket
  (approve/skip/abort) avant chaque action
- Léa UI (agent_v0/lea_ui/) : interface PyQt5 pour Windows avec overlay transparent
  pour feedback visuel pendant le replay
- Data Extraction (core/extraction/) : moteur d'extraction visuelle de données
  (OCR + VLM → SQLite), avec schémas YAML et export CSV/Excel
- ReplayVerifier (agent_v0/server_v1/) : vérification post-action par comparaison
  de screenshots, avec logique de retry (max 3)
- IntentParser durci : meilleur fallback regex, type GREETING, patterns améliorés
- Dashboard : nouvelles pages gestures, streaming, extractions
- Tests : 63 tests GestureCatalog, 47 tests extraction, corrections tests existants
- Dépréciation : /api/agent/plan et /api/agent/execute retournent HTTP 410,
  suppression du code hardcodé _plan_to_replay_actions

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

core/models/__init__.py

@@ -92,6 +92,41 @@ def get_execution_result():
     from .execution_result import WorkflowExecutionResult
     return WorkflowExecutionResult
 
+# Lazy import via __getattr__ pour éviter les imports circulaires
+_LAZY_IMPORTS = {
+    "StateEmbedding": "core.models.state_embedding",
+    "EmbeddingComponent": "core.models.state_embedding",
+    "Workflow": "core.models.workflow_graph",
+    "WorkflowNode": "core.models.workflow_graph",
+    "WorkflowEdge": "core.models.workflow_graph",
+    "ScreenTemplate": "core.models.workflow_graph",
+    "Action": "core.models.workflow_graph",
+    "TargetSpec": "core.models.workflow_graph",
+    "ActionType": "core.models.workflow_graph",
+    "EdgeConstraints": "core.models.workflow_graph",
+    "PostConditions": "core.models.workflow_graph",
+    "LearningState": "core.models.workflow_graph",
+    "SelectionPolicy": "core.models.workflow_graph",
+    "WindowConstraint": "core.models.workflow_graph",
+    "TextConstraint": "core.models.workflow_graph",
+    "UIConstraint": "core.models.workflow_graph",
+    "EmbeddingPrototype": "core.models.workflow_graph",
+    "EdgeStats": "core.models.workflow_graph",
+    "SafetyRules": "core.models.workflow_graph",
+    "WorkflowStats": "core.models.workflow_graph",
+    "LearningConfig": "core.models.workflow_graph",
+    "WorkflowExecutionResult": "core.models.execution_result",
+    "PerformanceMetrics": "core.models.execution_result",
+}
+
+def __getattr__(name):
+    if name in _LAZY_IMPORTS:
+        import importlib
+        module = importlib.import_module(_LAZY_IMPORTS[name])
+        return getattr(module, name)
+    raise AttributeError(f"module 'core.models' has no attribute {name!r}")
+
+
 __all__ = [
     # Modèles de base standardisés (Tâche 4)
     "BBox",

core/models/base_models.py

@@ -45,6 +45,25 @@ class BBox(BaseModel):
             return int(v)
         raise ValueError("Dimensions must be numeric")
     
+    def __iter__(self):
+        """Permet le unpacking: x, y, w, h = bbox"""
+        return iter((self.x, self.y, self.width, self.height))
+
+    def __getitem__(self, index):
+        """Permet l'accès par index: bbox[0], bbox[1], etc."""
+        return (self.x, self.y, self.width, self.height)[index]
+
+    def __len__(self):
+        return 4
+
+    def __eq__(self, other):
+        if isinstance(other, BBox):
+            return (self.x == other.x and self.y == other.y and
+                    self.width == other.width and self.height == other.height)
+        if isinstance(other, (tuple, list)) and len(other) == 4:
+            return (self.x, self.y, self.width, self.height) == tuple(other)
+        return NotImplemented
+
     def to_tuple(self) -> Tuple[int, int, int, int]:
         """Conversion vers tuple (x, y, w, h)"""
         return (self.x, self.y, self.width, self.height)

core/models/workflow_graph.py

@@ -311,8 +311,8 @@ class ScreenTemplate:
         
         # Vérifier contraintes de texte
         if hasattr(screen_state, 'perception'):
-            detected_texts = getattr(screen_state.perception, 'detected_texts', [])
-            if not self.text.matches(detected_texts):
+            detected_text = getattr(screen_state.perception, 'detected_text', [])
+            if not self.text.matches(detected_text):
                 return False, 0.0
         
         # Vérifier contraintes UI