feat(analytics): normalise API + contrat explicite get_next_action (Lot A)

Contrat get_next_action() — suppression du None ambigu :
  {"status": "selected", "edge": ..., ...}
  {"status": "terminal"}
  {"status": "blocked", "reason": "no_valid_edge" | ...}

ExecutionLoop dispatche proprement : blocked -> PAUSED + _pause_requested,
terminal -> succès légitime. Rétrocompat défensive (None legacy -> blocked).

Analytics API normalisée (kwargs-only) :
  on_execution_complete(duration_ms, status, steps_total|completed|failed)
  on_step_complete(duration_ms, ...)
  on_recovery_attempt(duration_ms, ...)

Découverte critique : les anciens appels utilisaient des méthodes et champs
inexistants (ExecutionMetrics.duration, metrics_collector.record_execution).
Le code n'avait jamais tourné au runtime — zéro analytics remontée.
L'exception était avalée par le try/except englobant.

58 tests (18 analytics + 11 contrat + 20 ExecutionLoop + 12 edge_scorer
non-régression). Migration complète, pas de pont legacy.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

tests/integration/test_workflow_pipeline_enhanced.py

@@ -96,14 +96,16 @@ class TestWorkflowPipelineEnhanced:
             "confidence": 0.92
         }
         
-        # Mock de l'action suivante
+        # Mock de l'action suivante (contrat dict normalisé Lot A)
         mock_workflow_pipeline.get_next_action.return_value = {
+            "status": "selected",
             "edge_id": "edge_1",
             "action": {"type": "click", "target": "button"},
             "target_node": "node_2",
-            "confidence": 0.95
+            "confidence": 0.95,
+            "score": 0.95,
         }
-        
+
         # Mock du workflow
         mock_workflow = Mock(spec=Workflow)
         mock_edge = Mock(spec=WorkflowEdge)
@@ -112,7 +114,7 @@ class TestWorkflowPipelineEnhanced:
         mock_edge.to_node = "node_2"
         mock_workflow.edges = [mock_edge]
         mock_workflow_pipeline.load_workflow.return_value = mock_workflow
-        
+
         # Mock du résultat d'exécution
         mock_execution_result = Mock(spec=ExecutionResult)
         mock_execution_result.status = ExecutionStatus.SUCCESS
@@ -121,24 +123,24 @@ class TestWorkflowPipelineEnhanced:
         mock_execution_result.target_resolved = None
         mock_execution_result.error = None
         mock_workflow_pipeline.action_executor.execute_edge.return_value = mock_execution_result
-        
+
         # Créer l'instance enhanced
         enhanced = WorkflowPipelineEnhanced()
-        
+
         # Lier les méthodes du pipeline mock
         enhanced.match_current_state = mock_workflow_pipeline.match_current_state
         enhanced.get_next_action = mock_workflow_pipeline.get_next_action
         enhanced.load_workflow = mock_workflow_pipeline.load_workflow
         enhanced.action_executor = mock_workflow_pipeline.action_executor
         enhanced.error_handler = mock_workflow_pipeline.error_handler
-        
+
         # Act
         result = enhanced.execute_workflow_step_enhanced(
             workflow_id=workflow_id,
             current_state=mock_screen_state,
             context={"test_context": "value"}
         )
-        
+
         # Assert
         assert isinstance(result, WorkflowExecutionResult)
         assert result.success is True
@@ -242,7 +244,8 @@ class TestWorkflowPipelineEnhanced:
         }
         
         # Mock de l'action suivante (pas d'action = workflow terminé)
-        mock_workflow_pipeline.get_next_action.return_value = None
+        # Contrat dict normalisé Lot A : status="terminal" pour fin légitime
+        mock_workflow_pipeline.get_next_action.return_value = {"status": "terminal"}
         
         # Créer l'instance enhanced
         enhanced = WorkflowPipelineEnhanced()
@@ -347,14 +350,16 @@ class TestWorkflowPipelineEnhanced:
             "confidence": 0.92
         }
         
-        # Mock de l'action suivante
+        # Mock de l'action suivante (contrat dict normalisé Lot A)
         mock_workflow_pipeline.get_next_action.return_value = {
+            "status": "selected",
             "edge_id": "edge_1",
             "action": {"type": "click", "target": "button"},
             "target_node": "node_2",
-            "confidence": 0.95
+            "confidence": 0.95,
+            "score": 0.95,
         }
-        
+
         # Mock du workflow
         mock_workflow = Mock(spec=Workflow)
         mock_edge = Mock(spec=WorkflowEdge)
@@ -363,7 +368,7 @@ class TestWorkflowPipelineEnhanced:
         mock_edge.to_node = "node_2"
         mock_workflow.edges = [mock_edge]
         mock_workflow_pipeline.load_workflow.return_value = mock_workflow
-        
+
         # Mock du résultat d'exécution
         mock_execution_result = Mock(spec=ExecutionResult)
         mock_execution_result.status = ExecutionStatus.SUCCESS
@@ -372,17 +377,17 @@ class TestWorkflowPipelineEnhanced:
         mock_execution_result.target_resolved = None
         mock_execution_result.error = None
         mock_workflow_pipeline.action_executor.execute_edge.return_value = mock_execution_result
-        
+
         # Créer l'instance enhanced
         enhanced = WorkflowPipelineEnhanced()
-        
+
         # Lier les méthodes du pipeline mock
         enhanced.match_current_state = mock_workflow_pipeline.match_current_state
         enhanced.get_next_action = mock_workflow_pipeline.get_next_action
         enhanced.load_workflow = mock_workflow_pipeline.load_workflow
         enhanced.action_executor = mock_workflow_pipeline.action_executor
         enhanced.error_handler = mock_workflow_pipeline.error_handler
-        
+
         # Act
         result = enhanced.execute_workflow_step_enhanced(
             workflow_id=workflow_id,

tests/unit/test_analytics_vision_metrics.py

@@ -0,0 +1,520 @@
+"""
+Tests unitaires pour la remontée des champs vision-aware (C1) vers analytics.
+
+Couvre :
+  - StepMetrics.to_dict / from_dict avec les nouveaux champs
+  - AnalyticsExecutionIntegration.on_step_result passe bien les champs
+  - Persistance SQLite (schema + migration) des colonnes C1
+"""
+
+from __future__ import annotations
+
+import sqlite3
+import tempfile
+from datetime import datetime
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from core.analytics.collection.metrics_collector import StepMetrics
+
+
+# -----------------------------------------------------------------------------
+# StepMetrics : sérialisation des champs C1
+# -----------------------------------------------------------------------------
+
+
+def _make_step_metrics(**overrides) -> StepMetrics:
+    base = dict(
+        step_id="s1",
+        execution_id="exec1",
+        workflow_id="wf1",
+        node_id="n1",
+        action_type="click",
+        target_element="",
+        started_at=datetime(2026, 4, 13, 10, 0, 0),
+        completed_at=datetime(2026, 4, 13, 10, 0, 1),
+        duration_ms=1000.0,
+        status="completed",
+        confidence_score=0.9,
+        retry_count=0,
+        error_details=None,
+    )
+    base.update(overrides)
+    return StepMetrics(**base)
+
+
+class TestStepMetricsVisionFields:
+    def test_default_vision_fields(self):
+        m = _make_step_metrics()
+        assert m.ocr_ms == 0.0
+        assert m.ui_ms == 0.0
+        assert m.analyze_ms == 0.0
+        assert m.total_ms == 0.0
+        assert m.cache_hit is False
+        assert m.degraded is False
+
+    def test_to_dict_includes_vision_fields(self):
+        m = _make_step_metrics(
+            ocr_ms=120.5,
+            ui_ms=45.0,
+            analyze_ms=200.0,
+            total_ms=1050.0,
+            cache_hit=True,
+            degraded=True,
+        )
+        d = m.to_dict()
+        assert d["ocr_ms"] == 120.5
+        assert d["ui_ms"] == 45.0
+        assert d["analyze_ms"] == 200.0
+        assert d["total_ms"] == 1050.0
+        assert d["cache_hit"] is True
+        assert d["degraded"] is True
+
+    def test_from_dict_roundtrip(self):
+        original = _make_step_metrics(
+            ocr_ms=10.0, ui_ms=20.0, analyze_ms=30.0,
+            total_ms=100.0, cache_hit=True, degraded=False,
+        )
+        restored = StepMetrics.from_dict(original.to_dict())
+        assert restored.ocr_ms == 10.0
+        assert restored.ui_ms == 20.0
+        assert restored.analyze_ms == 30.0
+        assert restored.total_ms == 100.0
+        assert restored.cache_hit is True
+        assert restored.degraded is False
+
+    def test_from_dict_missing_vision_fields_defaults_to_zero(self):
+        """Rétrocompatibilité : un dict sans champs C1 doit produire 0/False."""
+        restored = StepMetrics.from_dict({
+            'step_id': 's1',
+            'execution_id': 'e1',
+            'workflow_id': 'w1',
+            'node_id': 'n1',
+            'action_type': 'click',
+            'target_element': '',
+            'started_at': datetime.now().isoformat(),
+            'completed_at': datetime.now().isoformat(),
+            'duration_ms': 100.0,
+            'status': 'completed',
+            'confidence_score': 0.5,
+        })
+        assert restored.ocr_ms == 0.0
+        assert restored.cache_hit is False
+        assert restored.degraded is False
+
+
+# -----------------------------------------------------------------------------
+# AnalyticsExecutionIntegration.on_step_result
+# -----------------------------------------------------------------------------
+
+
+class _FakeStepResult:
+    """Stand-in minimal pour core.execution.execution_loop.StepResult."""
+    def __init__(self, **kw):
+        self.success = kw.get("success", True)
+        self.node_id = kw.get("node_id", "n1")
+        self.edge_id = kw.get("edge_id", None)
+        self.action_result = kw.get("action_result", None)
+        self.match_confidence = kw.get("match_confidence", 0.9)
+        self.duration_ms = kw.get("duration_ms", 100.0)
+        self.message = kw.get("message", "")
+        self.ocr_ms = kw.get("ocr_ms", 0.0)
+        self.ui_ms = kw.get("ui_ms", 0.0)
+        self.analyze_ms = kw.get("analyze_ms", 0.0)
+        self.total_ms = kw.get("total_ms", 0.0)
+        self.cache_hit = kw.get("cache_hit", False)
+        self.degraded = kw.get("degraded", False)
+
+
+class TestAnalyticsOnStepResult:
+    def test_on_step_result_passes_vision_fields(self):
+        from core.analytics.integration.execution_integration import (
+            AnalyticsExecutionIntegration,
+        )
+
+        # Analytics system mocké
+        fake_system = MagicMock()
+        integration = AnalyticsExecutionIntegration(fake_system)
+
+        step = _FakeStepResult(
+            node_id="node_click",
+            success=True,
+            match_confidence=0.87,
+            duration_ms=1234.0,
+            ocr_ms=111.0,
+            ui_ms=222.0,
+            analyze_ms=333.0,
+            total_ms=1234.0,
+            cache_hit=True,
+            degraded=False,
+        )
+
+        integration.on_step_result(
+            execution_id="exec1",
+            workflow_id="wf1",
+            step_result=step,
+        )
+
+        # Vérifie qu'un StepMetrics avec les bons champs a été enregistré
+        record_calls = fake_system.metrics_collector.record_step.call_args_list
+        assert len(record_calls) == 1
+        recorded: StepMetrics = record_calls[0].args[0]
+        assert isinstance(recorded, StepMetrics)
+        assert recorded.node_id == "node_click"
+        assert recorded.workflow_id == "wf1"
+        assert recorded.execution_id == "exec1"
+        assert recorded.confidence_score == 0.87
+        assert recorded.duration_ms == 1234.0
+        assert recorded.ocr_ms == 111.0
+        assert recorded.ui_ms == 222.0
+        assert recorded.analyze_ms == 333.0
+        assert recorded.total_ms == 1234.0
+        assert recorded.cache_hit is True
+        assert recorded.degraded is False
+        assert recorded.status == "completed"
+
+    def test_on_step_result_failed_step(self):
+        from core.analytics.integration.execution_integration import (
+            AnalyticsExecutionIntegration,
+        )
+
+        fake_system = MagicMock()
+        integration = AnalyticsExecutionIntegration(fake_system)
+
+        step = _FakeStepResult(
+            success=False,
+            message="Click failed",
+            degraded=True,
+        )
+
+        integration.on_step_result("e1", "w1", step)
+
+        recorded: StepMetrics = fake_system.metrics_collector.record_step.call_args.args[0]
+        assert recorded.status == "failed"
+        assert recorded.error_details == "Click failed"
+        assert recorded.degraded is True
+
+    def test_on_step_result_disabled_integration_is_noop(self):
+        from core.analytics.integration.execution_integration import (
+            AnalyticsExecutionIntegration,
+        )
+
+        integration = AnalyticsExecutionIntegration(None)  # désactivé
+        assert integration.enabled is False
+
+        step = _FakeStepResult()
+        # Ne doit rien faire ni lever d'exception
+        integration.on_step_result("e1", "w1", step)
+
+
+# -----------------------------------------------------------------------------
+# AnalyticsExecutionIntegration.on_execution_complete (Lot A — avril 2026)
+# -----------------------------------------------------------------------------
+
+
+class TestAnalyticsOnExecutionComplete:
+    """Contrat normalisé : duration_ms (ms) + status (str), pas de magie."""
+
+    def _make_integration(self):
+        from core.analytics.integration.execution_integration import (
+            AnalyticsExecutionIntegration,
+        )
+
+        fake_system = MagicMock()
+        # Pas d'execution active : l'intégration doit emprunter le fallback
+        # "ExecutionMetrics synthétique pushé dans _buffer".
+        fake_system.metrics_collector._active_executions = {}
+        fake_system.metrics_collector._lock = MagicMock()
+        fake_system.metrics_collector._lock.__enter__ = MagicMock(
+            return_value=None
+        )
+        fake_system.metrics_collector._lock.__exit__ = MagicMock(
+            return_value=None
+        )
+        fake_system.metrics_collector._buffer = []
+        return AnalyticsExecutionIntegration(fake_system), fake_system
+
+    def test_fallback_builds_execution_metrics_with_correct_fields(self):
+        """Sans record_execution_start préalable, on construit un
+        ExecutionMetrics synthétique avec les bons noms de champs."""
+        from core.analytics.collection.metrics_collector import ExecutionMetrics
+
+        integration, fake_system = self._make_integration()
+
+        integration.on_execution_complete(
+            execution_id="exec1",
+            workflow_id="wf1",
+            duration_ms=1500.0,
+            status="completed",
+            steps_total=3,
+            steps_completed=3,
+            steps_failed=0,
+        )
+
+        # Un ExecutionMetrics a été pushé dans le buffer
+        buffer = fake_system.metrics_collector._buffer
+        assert len(buffer) == 1
+        metric: ExecutionMetrics = buffer[0]
+        assert isinstance(metric, ExecutionMetrics)
+        assert metric.execution_id == "exec1"
+        assert metric.workflow_id == "wf1"
+        assert metric.duration_ms == 1500.0
+        assert metric.status == "completed"
+        assert metric.steps_total == 3
+        assert metric.steps_completed == 3
+        assert metric.steps_failed == 0
+        # started_at / completed_at sont cohérents
+        delta_ms = (
+            metric.completed_at - metric.started_at
+        ).total_seconds() * 1000
+        assert abs(delta_ms - 1500.0) < 1.0
+
+    def test_uses_record_execution_complete_if_active(self):
+        """Si l'execution a été ouverte via on_execution_start, on délègue
+        à record_execution_complete (chemin nominal)."""
+        integration, fake_system = self._make_integration()
+        # Simuler une execution active
+        fake_system.metrics_collector._active_executions = {"exec1": object()}
+
+        integration.on_execution_complete(
+            execution_id="exec1",
+            workflow_id="wf1",
+            duration_ms=800.0,
+            status="failed",
+            steps_total=2,
+            steps_completed=1,
+            steps_failed=1,
+            error_message="timeout",
+        )
+
+        call = fake_system.metrics_collector.record_execution_complete.call_args
+        assert call is not None
+        kwargs = call.kwargs
+        assert kwargs["execution_id"] == "exec1"
+        assert kwargs["status"] == "failed"
+        assert kwargs["steps_total"] == 2
+        assert kwargs["steps_completed"] == 1
+        assert kwargs["steps_failed"] == 1
+        assert kwargs["error_message"] == "timeout"
+
+    def test_steps_total_derived_when_not_provided(self):
+        """steps_total déduit par somme si absent, pas d'erreur silencieuse."""
+        integration, fake_system = self._make_integration()
+
+        integration.on_execution_complete(
+            execution_id="exec1",
+            workflow_id="wf1",
+            duration_ms=500.0,
+            status="completed",
+            steps_completed=2,
+            steps_failed=1,
+        )
+
+        metric = fake_system.metrics_collector._buffer[0]
+        assert metric.steps_total == 3  # 2 + 1
+
+    def test_disabled_integration_is_noop(self):
+        from core.analytics.integration.execution_integration import (
+            AnalyticsExecutionIntegration,
+        )
+
+        integration = AnalyticsExecutionIntegration(None)
+        assert integration.enabled is False
+
+        # Ne doit rien faire ni lever d'exception
+        integration.on_execution_complete(
+            execution_id="exec1",
+            workflow_id="wf1",
+            duration_ms=100.0,
+            status="completed",
+        )
+
+    def test_realtime_complete_called(self):
+        """Le tracking temps réel est clos avec le bon status."""
+        integration, fake_system = self._make_integration()
+
+        integration.on_execution_complete(
+            execution_id="exec1",
+            workflow_id="wf1",
+            duration_ms=100.0,
+            status="stopped",
+        )
+
+        fake_system.realtime_analytics.complete_execution.assert_called_once_with(
+            execution_id="exec1",
+            status="stopped",
+        )
+
+
+# -----------------------------------------------------------------------------
+# AnalyticsExecutionIntegration.on_recovery_attempt (Lot A — avril 2026)
+# -----------------------------------------------------------------------------
+
+
+class TestAnalyticsOnRecoveryAttempt:
+    """Contrat normalisé : StepMetrics construit avec les vrais champs."""
+
+    def test_success_recovery_builds_valid_step_metrics(self):
+        from core.analytics.collection.metrics_collector import StepMetrics
+        from core.analytics.integration.execution_integration import (
+            AnalyticsExecutionIntegration,
+        )
+
+        fake_system = MagicMock()
+        integration = AnalyticsExecutionIntegration(fake_system)
+
+        integration.on_recovery_attempt(
+            execution_id="exec1",
+            workflow_id="wf1",
+            node_id="node_click",
+            strategy="retry_with_delay",
+            success=True,
+            duration_ms=250.0,
+        )
+
+        call = fake_system.metrics_collector.record_step.call_args
+        assert call is not None
+        recorded: StepMetrics = call.args[0]
+        assert isinstance(recorded, StepMetrics)
+        assert recorded.execution_id == "exec1"
+        assert recorded.workflow_id == "wf1"
+        assert recorded.node_id == "node_click_recovery"
+        assert recorded.action_type == "recovery_retry_with_delay"
+        assert recorded.duration_ms == 250.0
+        assert recorded.status == "completed"
+        assert recorded.error_details is None
+        # Champs obligatoires du dataclass
+        assert recorded.step_id  # non vide
+        assert recorded.target_element == ""
+        assert recorded.confidence_score == 0.0
+
+    def test_failed_recovery_sets_status_and_error_details(self):
+        from core.analytics.collection.metrics_collector import StepMetrics
+        from core.analytics.integration.execution_integration import (
+            AnalyticsExecutionIntegration,
+        )
+
+        fake_system = MagicMock()
+        integration = AnalyticsExecutionIntegration(fake_system)
+
+        integration.on_recovery_attempt(
+            execution_id="e1",
+            workflow_id="w1",
+            node_id="n1",
+            strategy="fallback_to_parent",
+            success=False,
+            duration_ms=80.0,
+        )
+
+        recorded: StepMetrics = (
+            fake_system.metrics_collector.record_step.call_args.args[0]
+        )
+        assert recorded.status == "failed"
+        assert recorded.error_details == "Recovery failed: fallback_to_parent"
+        assert recorded.duration_ms == 80.0
+
+    def test_disabled_integration_is_noop(self):
+        from core.analytics.integration.execution_integration import (
+            AnalyticsExecutionIntegration,
+        )
+
+        integration = AnalyticsExecutionIntegration(None)
+        integration.on_recovery_attempt(
+            execution_id="e1",
+            workflow_id="w1",
+            node_id="n1",
+            strategy="x",
+            success=True,
+            duration_ms=10.0,
+        )
+
+
+# -----------------------------------------------------------------------------
+# Persistance SQLite : schema + migration
+# -----------------------------------------------------------------------------
+
+
+class TestTimeSeriesStoreSchema:
+    def test_new_store_has_vision_columns(self, tmp_path):
+        from core.analytics.storage.timeseries_store import TimeSeriesStore
+
+        store = TimeSeriesStore(tmp_path)
+        with sqlite3.connect(str(store.db_path)) as conn:
+            cols = {row[1] for row in conn.execute(
+                "PRAGMA table_info(step_metrics)"
+            )}
+        # Colonnes legacy
+        assert "duration_ms" in cols
+        assert "confidence_score" in cols
+        # Colonnes C1
+        assert "ocr_ms" in cols
+        assert "ui_ms" in cols
+        assert "analyze_ms" in cols
+        assert "total_ms" in cols
+        assert "cache_hit" in cols
+        assert "degraded" in cols
+
+    def test_migration_adds_missing_columns(self, tmp_path):
+        """Base pré-existante sans les colonnes C1 — la migration doit les ajouter."""
+        from core.analytics.storage.timeseries_store import TimeSeriesStore
+
+        # Créer une base "legacy" manuellement, sans les nouvelles colonnes
+        storage_dir = tmp_path / "legacy"
+        storage_dir.mkdir()
+        legacy_db = storage_dir / "timeseries.db"
+        with sqlite3.connect(str(legacy_db)) as conn:
+            conn.executescript("""
+                CREATE TABLE step_metrics (
+                    step_id TEXT PRIMARY KEY,
+                    execution_id TEXT NOT NULL,
+                    workflow_id TEXT NOT NULL,
+                    node_id TEXT NOT NULL,
+                    action_type TEXT NOT NULL,
+                    target_element TEXT,
+                    started_at TIMESTAMP NOT NULL,
+                    completed_at TIMESTAMP NOT NULL,
+                    duration_ms REAL NOT NULL,
+                    status TEXT NOT NULL,
+                    confidence_score REAL,
+                    retry_count INTEGER DEFAULT 0,
+                    error_details TEXT
+                );
+            """)
+            conn.commit()
+
+        # Instancier TimeSeriesStore → doit migrer
+        _ = TimeSeriesStore(storage_dir)
+
+        with sqlite3.connect(str(legacy_db)) as conn:
+            cols = {row[1] for row in conn.execute(
+                "PRAGMA table_info(step_metrics)"
+            )}
+        assert "ocr_ms" in cols
+        assert "cache_hit" in cols
+        assert "degraded" in cols
+
+    def test_write_and_read_vision_metrics(self, tmp_path):
+        from core.analytics.storage.timeseries_store import TimeSeriesStore
+
+        store = TimeSeriesStore(tmp_path)
+        metric = _make_step_metrics(
+            ocr_ms=50.0, ui_ms=60.0, analyze_ms=110.0,
+            total_ms=500.0, cache_hit=True, degraded=True,
+        )
+        store.write_metrics([metric])
+
+        with sqlite3.connect(str(store.db_path)) as conn:
+            conn.row_factory = sqlite3.Row
+            row = conn.execute(
+                "SELECT * FROM step_metrics WHERE step_id = ?", (metric.step_id,)
+            ).fetchone()
+        assert row is not None
+        assert row["ocr_ms"] == 50.0
+        assert row["ui_ms"] == 60.0
+        assert row["analyze_ms"] == 110.0
+        assert row["total_ms"] == 500.0
+        # SQLite stocke les bool comme INTEGER
+        assert row["cache_hit"] == 1
+        assert row["degraded"] == 1

tests/unit/test_workflow_pipeline_get_next_action.py

@@ -0,0 +1,264 @@
+"""
+Tests de la sélection robuste d'edge dans WorkflowPipeline.get_next_action (C3).
+
+Vérifie que la nouvelle API utilise EdgeScorer et expose le contrat dict
+normalisé (Lot A — avril 2026) :
+  - status="selected"  → edge choisi
+  - status="terminal"  → aucun outgoing_edge (fin légitime)
+  - status="blocked"   → candidats rejetés (NE DOIT PAS être traité comme fin)
+"""
+
+from __future__ import annotations
+
+from datetime import datetime
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from core.models.screen_state import (
+    ContextLevel,
+    EmbeddingRef,
+    PerceptionLevel,
+    RawLevel,
+    ScreenState,
+    WindowContext,
+)
+from core.models.workflow_graph import (
+    Action,
+    EdgeConstraints,
+    EdgeStats,
+    PostConditions,
+    TargetSpec,
+    Workflow,
+    WorkflowEdge,
+    WorkflowNode,
+)
+
+
+def _edge(
+    edge_id: str,
+    required_window_title: str = "",
+    success_rate: float = 0.5,
+    execution_count: int = 10,
+    min_source_similarity: float = 0.80,
+) -> WorkflowEdge:
+    stats = EdgeStats()
+    if execution_count > 0:
+        stats.execution_count = execution_count
+        stats.success_count = int(round(success_rate * execution_count))
+        stats.failure_count = execution_count - stats.success_count
+
+    return WorkflowEdge(
+        edge_id=edge_id,
+        from_node="n1",
+        to_node="n2",
+        action=Action(type="mouse_click", target=TargetSpec()),
+        constraints=EdgeConstraints(
+            required_window_title=required_window_title,
+            min_source_similarity=min_source_similarity,
+        ),
+        post_conditions=PostConditions(),
+        stats=stats,
+    )
+
+
+def _state(window_title: str = "AppA") -> ScreenState:
+    return ScreenState(
+        screen_state_id="s",
+        timestamp=datetime.now(),
+        session_id="sess",
+        window=WindowContext(
+            app_name="app", window_title=window_title, screen_resolution=[1920, 1080]
+        ),
+        raw=RawLevel(screenshot_path="", capture_method="t", file_size_bytes=0),
+        perception=PerceptionLevel(
+            embedding=EmbeddingRef(provider="t", vector_id="v", dimensions=512),
+            detected_text=[],
+            text_detection_method="none",
+            confidence_avg=0.0,
+        ),
+        context=ContextLevel(),
+        ui_elements=[],
+    )
+
+
+@pytest.fixture
+def pipeline_with_workflow(tmp_path):
+    """Pipeline minimal avec un workflow en mémoire (Workflow mocké).
+
+    On évite la construction d'un vrai Workflow (ScreenTemplate trop lourd)
+    en utilisant un MagicMock configuré pour les méthodes utilisées par
+    `get_next_action` : `get_outgoing_edges`.
+    """
+    from core.pipeline.workflow_pipeline import WorkflowPipeline
+
+    # Stub pour éviter les lourds imports (mocks sur composants GPU)
+    with patch.multiple(
+        "core.pipeline.workflow_pipeline",
+        UIDetector=MagicMock(),
+        CLIPEmbedder=MagicMock(),
+        StateEmbeddingBuilder=MagicMock(),
+        FusionEngine=MagicMock(),
+        FAISSManager=MagicMock(),
+        GraphBuilder=MagicMock(),
+        NodeMatcher=MagicMock(),
+        HierarchicalMatcher=MagicMock(),
+        LearningManager=MagicMock(),
+        ActionExecutor=MagicMock(),
+        TargetResolver=MagicMock(),
+        ErrorHandler=MagicMock(),
+    ):
+        pipeline = WorkflowPipeline(data_dir=str(tmp_path), use_gpu=False)
+
+    workflow = MagicMock(spec=Workflow)
+    workflow.workflow_id = "wf1"
+    workflow.edges = []
+    workflow.get_outgoing_edges = lambda node_id: [
+        e for e in workflow.edges if e.from_node == node_id
+    ]
+    pipeline._workflows["wf1"] = workflow
+    return pipeline, workflow
+
+
+class TestGetNextActionC3:
+
+    def test_picks_highest_success_rate(self, pipeline_with_workflow):
+        pipeline, wf = pipeline_with_workflow
+        wf.edges = [
+            _edge("low", success_rate=0.1, execution_count=20),
+            _edge("high", success_rate=0.9, execution_count=20),
+        ]
+        result = pipeline.get_next_action("wf1", "n1", screen_state=_state())
+        assert result["status"] == "selected"
+        assert result["edge_id"] == "high"
+
+    def test_filters_out_invalid_preconditions(self, pipeline_with_workflow):
+        pipeline, wf = pipeline_with_workflow
+        wf.edges = [
+            _edge("bad", required_window_title="NopeApp", success_rate=0.99, execution_count=20),
+            _edge("ok", success_rate=0.50, execution_count=20),
+        ]
+        result = pipeline.get_next_action(
+            "wf1", "n1", screen_state=_state(window_title="AppA")
+        )
+        assert result["status"] == "selected"
+        assert result["edge_id"] == "ok"
+
+    def test_blocked_when_no_valid_edge(self, pipeline_with_workflow):
+        """Des candidats existent mais aucun ne passe les contraintes.
+
+        Lot A — cas critique : on NE DOIT PAS retourner "terminal" ici. Un
+        blocage doit remonter explicitement pour déclencher pause supervisée.
+        """
+        pipeline, wf = pipeline_with_workflow
+        wf.edges = [
+            _edge("e1", required_window_title="AppB"),
+            _edge("e2", required_window_title="AppC"),
+        ]
+        result = pipeline.get_next_action(
+            "wf1", "n1", screen_state=_state(window_title="AppA")
+        )
+        assert result["status"] == "blocked"
+        assert result["reason"] == "no_valid_edge"
+
+    def test_strategy_first_keeps_legacy_behavior(self, pipeline_with_workflow):
+        pipeline, wf = pipeline_with_workflow
+        wf.edges = [
+            _edge("e1", success_rate=0.1, execution_count=20),
+            _edge("e2", success_rate=0.9, execution_count=20),
+        ]
+        result = pipeline.get_next_action(
+            "wf1", "n1", screen_state=_state(), strategy="first"
+        )
+        # Mode legacy : premier edge sans tri
+        assert result["status"] == "selected"
+        assert result["edge_id"] == "e1"
+
+    def test_no_screen_state_still_works(self, pipeline_with_workflow):
+        """Sans ScreenState, le scorer ne peut pas filtrer mais peut ranker."""
+        pipeline, wf = pipeline_with_workflow
+        wf.edges = [
+            _edge("e1", success_rate=0.1, execution_count=20),
+            _edge("e2", success_rate=0.9, execution_count=20),
+        ]
+        result = pipeline.get_next_action("wf1", "n1", screen_state=None)
+        assert result["status"] == "selected"
+        # Le ranking par success_rate fonctionne toujours
+        assert result["edge_id"] == "e2"
+
+    def test_no_outgoing_edges_is_terminal(self, pipeline_with_workflow):
+        """Aucun outgoing_edge = fin légitime du workflow (status="terminal")."""
+        pipeline, wf = pipeline_with_workflow
+        wf.edges = []
+        result = pipeline.get_next_action("wf1", "n1", screen_state=_state())
+        assert result["status"] == "terminal"
+
+    def test_blocked_distinct_from_terminal(self, pipeline_with_workflow):
+        """Régression Lot A : blocked != terminal.
+
+        Le bug historique confondait ces deux cas. Un workflow bloqué
+        apparaissait comme "terminé avec succès" côté ExecutionLoop.
+        """
+        pipeline, wf = pipeline_with_workflow
+
+        # Cas terminal : pas d'outgoing
+        wf.edges = []
+        terminal = pipeline.get_next_action("wf1", "n1", screen_state=_state())
+
+        # Cas bloqué : outgoing présent mais rejetés
+        wf.edges = [_edge("bad", required_window_title="NopeApp")]
+        blocked = pipeline.get_next_action("wf1", "n1", screen_state=_state(window_title="AppA"))
+
+        assert terminal["status"] == "terminal"
+        assert blocked["status"] == "blocked"
+        # L'appelant doit pouvoir les distinguer sans ambiguïté
+        assert terminal["status"] != blocked["status"]
+
+    def test_workflow_not_found_is_blocked(self, pipeline_with_workflow):
+        """Workflow inexistant = blocked avec reason explicite (pas silencieux)."""
+        pipeline, _wf = pipeline_with_workflow
+        result = pipeline.get_next_action(
+            "wf_inexistant", "n1", screen_state=_state()
+        )
+        assert result["status"] == "blocked"
+        assert result["reason"] == "workflow_not_found"
+
+
+class TestGetNextActionSourceSimilarity:
+    """Lot B — propagation de source_similarity jusqu'à EdgeScorer."""
+
+    def test_high_similarity_passes_min_source_similarity(
+        self, pipeline_with_workflow
+    ):
+        """source_similarity élevée → edge accepté."""
+        pipeline, wf = pipeline_with_workflow
+        wf.edges = [_edge("e1", min_source_similarity=0.80)]
+        result = pipeline.get_next_action(
+            "wf1", "n1", screen_state=_state(), source_similarity=0.95
+        )
+        assert result["status"] == "selected"
+        assert result["edge_id"] == "e1"
+
+    def test_low_similarity_blocks_edge(self, pipeline_with_workflow):
+        """source_similarity < min_source_similarity → edge rejeté → blocked.
+
+        C'est la preuve que la précondition min_source_similarity est
+        redevenue effective (Lot B). Avant ce lot, l'EdgeScorer recevait
+        toujours 1.0 hardcodé et ne rejetait jamais l'edge pour ce motif.
+        """
+        pipeline, wf = pipeline_with_workflow
+        wf.edges = [_edge("e1", min_source_similarity=0.80)]
+        result = pipeline.get_next_action(
+            "wf1", "n1", screen_state=_state(), source_similarity=0.40
+        )
+        assert result["status"] == "blocked"
+        assert result["reason"] == "no_valid_edge"
+
+    def test_default_source_similarity_is_one(self, pipeline_with_workflow):
+        """Sans source_similarity fourni → défaut 1.0 → pas de rejet pour
+        ce motif (compat avec les call sites qui ne l'ont pas encore)."""
+        pipeline, wf = pipeline_with_workflow
+        # min_source_similarity très strict, mais défaut appelant = 1.0
+        wf.edges = [_edge("e1", min_source_similarity=0.99)]
+        result = pipeline.get_next_action("wf1", "n1", screen_state=_state())
+        assert result["status"] == "selected"