ML-007: add retraining pipeline and API

Closes #13

app/ml/__init__.py

@@ -1,5 +1,14 @@
 
 """Machine-Learning-Grundbausteine für SillyHome Next."""
-__all__ = ["FeatureStore", "FeatureVector", "TrainedArtifact", "TrainingPipeline"]
+__all__ = [
+    "FeatureStore",
+    "FeatureVector",
+    "RetrainingResult",
+    "RetrainingService",
+    "TrainedArtifact",
+    "TrainingPipeline",
+    "retrain_model",
+]
 from app.ml.feature_store import FeatureStore, FeatureVector
+from app.ml.retraining import RetrainingResult, RetrainingService, retrain_model
 from app.ml.training import TrainedArtifact, TrainingPipeline

app/ml/registry/model_registry.py

@@ -5,6 +5,7 @@ import logging
 import os
 from pathlib import Path
 import re
+from threading import RLock
 from collections.abc import Iterable
 
 from app.ml.training import TrainedArtifact
@@ -19,22 +20,31 @@ class ModelRegistry:
         self._root = Path(root).resolve()
         self._root.mkdir(parents=True, exist_ok=True)
         self._artifacts: dict[str, TrainedArtifact] = {}
+        self._lock = RLock()
         self._load_existing()
 
     def register(self, artifact: TrainedArtifact) -> TrainedArtifact:
+        registered, _ = self.register_with_status(artifact)
+        return registered
+
+    def register_with_status(self, artifact: TrainedArtifact) -> tuple[TrainedArtifact, bool]:
         self._validate_artifact_id(artifact.artifact_id)
-        self._persist(artifact)
-        self._artifacts[artifact.artifact_id] = artifact
-        return artifact
+        with self._lock:
+            replaced = artifact.artifact_id in self._artifacts
+            self._persist(artifact)
+            self._artifacts[artifact.artifact_id] = artifact
+        return artifact, replaced
 
     def load_artifact(self, artifact_id: str) -> TrainedArtifact:
         self._validate_artifact_id(artifact_id)
-        if artifact_id not in self._artifacts:
-            raise KeyError(f"Artifact '{artifact_id}' nicht registriert.")
-        return self._artifacts[artifact_id]
+        with self._lock:
+            if artifact_id not in self._artifacts:
+                raise KeyError(f"Artifact '{artifact_id}' nicht registriert.")
+            return self._artifacts[artifact_id]
 
     def list_models(self) -> Iterable[TrainedArtifact]:
-        return list(self._artifacts.values())
+        with self._lock:
+            return [self._artifacts[key] for key in sorted(self._artifacts)]
 
     def _load_existing(self) -> None:
         for source in sorted(self._root.glob("*.json")):

app/ml/retraining.py

@@ -0,0 +1,43 @@
+from __future__ import annotations
+
+from collections.abc import Iterable
+from dataclasses import dataclass
+
+from app.ml.feature_store import FeatureStore, FeatureVector
+from app.ml.registry.model_registry import ModelRegistry
+from app.ml.training import TrainedArtifact, TrainingPipeline
+
+
+@dataclass(frozen=True)
+class RetrainingResult:
+    artifact: TrainedArtifact
+    replaced: bool
+
+
+class RetrainingService:
+    """Runs one retraining cycle without owning scheduling or background threads."""
+
+    def __init__(self, registry: ModelRegistry) -> None:
+        self._registry = registry
+
+    def retrain(
+        self,
+        artifact_id: str,
+        vectors: Iterable[FeatureVector],
+    ) -> RetrainingResult:
+        store = FeatureStore()
+        store.add_batch(vectors)
+        pipeline = TrainingPipeline(store)
+        artifact = pipeline.run(artifact_id)
+        _, replaced = self._registry.register_with_status(artifact)
+        return RetrainingResult(artifact=artifact, replaced=replaced)
+
+
+def retrain_model(
+    registry: ModelRegistry,
+    artifact_id: str,
+    vectors: Iterable[FeatureVector],
+) -> RetrainingResult:
+    """Scheduler-compatible entry point for exactly one retraining run."""
+
+    return RetrainingService(registry).retrain(artifact_id, vectors)