harden delivery pipeline and production runtime

.dockerignore

@@ -12,6 +12,5 @@ node_modules
 .vscode
 .git
 .gitignore
-README.md
 .dockerignore
-docker-compose*.yml
+docker-compose*.yml

.env.example

@@ -1,2 +1,3 @@
 SILLYHOME_HA_URL=http://homeassistant.local:8123
-SILLYHOME_HA_TOKEN=REPLACE_ME_WITH_LONG_LIVED_TOKEN
+SILLYHOME_HA_TOKEN=REPLACE_ME_WITH_LONG_LIVED_TOKEN
+SILLYHOME_MODEL_STORE=.model_store

.gitea/workflows/quality.yml

@@ -0,0 +1,24 @@
+name: quality
+
+on:
+  push:
+    branches: ["main", "otto/**", "feature/**"]
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.11", "3.13"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
+      - run: python -m pip install --upgrade pip
+      - run: python -m pip install -e ".[dev]"
+      - run: python -m pytest
+      - run: ruff check .
+      - run: mypy

CHANGELOG.md

@@ -3,3 +3,8 @@
 ## Unreleased
 - Projektinitiierung
 - Architektur, ADRs und Roadmap
+- Einheitliche produktive FastAPI-App für HA- und ML-Routen
+- Funktionierende ENV-Konfiguration und sauberer HA-503-Zustand
+- Persistente, validierte und gegen Path Traversal gehärtete Model Registry
+- Reproduzierbares Packaging, CI-Gates und gehärteter non-root Container
+- Definierte API-Fehler und korrigierte Evaluationsmetriken

Dockerfile

@@ -1,15 +1,27 @@
 FROM python:3.13-slim
 
-ENV PYTHONDONTWRITEBYTECODE=1 PYTHONUNBUFFERED=1
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1 \
+    SILLYHOME_MODEL_STORE=/app/data/models
 
 WORKDIR /app
 
-COPY pyproject.toml ./
+RUN addgroup --system sillyhome && adduser --system --ingroup sillyhome sillyhome
-RUN python -m pip install --upgrade pip && \
-    pip install --no-cache-dir -e ".[dev]"
 
-COPY . .
+COPY pyproject.toml README.md ./
+COPY app ./app
+COPY backend ./backend
+RUN python -m pip install --upgrade pip && \
+    python -m pip install . && \
+    mkdir -p /app/data/models && \
+    chown -R sillyhome:sillyhome /app/data
 
 EXPOSE 8000
 
-CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
+USER sillyhome
+
+HEALTHCHECK --interval=30s --timeout=3s --start-period=10s --retries=3 \
+    CMD ["python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=2)"]
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]

README.md

@@ -1,6 +1,13 @@
 # SillyHome Next
 
-Modern, lokal-first und datenschutzfreundliches Smart-Home-Intelligenzsystem für Home Assistant.
+Lokaler, datenschutzfreundlicher API-Prototyp für Home Assistant.
+
+## Reifegrad
+
+Version `0.1.0` stellt eine gehärtete technische Basis bereit: Home-Assistant-Entities
+lesen, regelbasierte Bausteine und eine persistente Modell-Artefakt-Registry. Die
+aktuelle Trainings- und Vorhersagelogik ist noch eine deterministische
+Schnittstellen-Implementierung und **kein produktives Machine-Learning-Modell**.
 
 ## Motivation
 TheSillyHome zeigte die Idee: statt statischer Regeln das Zuhause aus Verhaltensmustern verstehen. Diese Architektur modernisiert den Ansatz in Richtung Explainable AI, hybride Intelligenzebenen und langlebige Wartbarkeit.
@@ -13,14 +20,12 @@ TheSillyHome zeigte die Idee: statt statischer Regeln das Zuhause aus Verhaltens
 - Lokal-first ohne Cloudpflicht
 - Erweiterbar, testbar, dokumentiert
 
-## APPENDIX
+## Quickstart
-
-### Quickstart
 1. Python-Venv anlegen und Abhängigkeiten installieren:
 ```bash
 python -m venv .venv
 source .venv/bin/activate
-pip install -e .
+pip install -e ".[dev]"
 ```
 
 2. Konfiguration aus `.env.example` übernehmen und anpassen:
@@ -37,17 +42,32 @@ uvicorn app.main:app --reload
 - `http://127.0.0.1:8000/health` - Health-Check
 - `http://127.0.0.1:8000/docs/` - OpenAPI-Dokumentation
 - `http://127.0.0.1:8000/v1/entities` - Home-Assistant-Entities
-- `http://127.0.0.1:8000/ml/health` - ML-Serving Health (ab ML-005)
+- `http://127.0.0.1:8000/ml/health` - Registry-/Serving-Health
+
+Ohne vollständige HA-Konfiguration liefert `/v1/entities` bewusst `503`.
+
+### Docker Compose
+
+```bash
+cp .env.example .env
+docker compose up --build -d
+curl --fail http://127.0.0.1:8000/health
+```
+
+Compose veröffentlicht die API standardmäßig nur auf `127.0.0.1`. Für Zugriff aus
+dem Netz muss ein authentifizierender Reverse Proxy vorgeschaltet werden.
 
 ### ENV-Konfiguration (`.env.example`)
 - `SILLYHOME_HA_URL` – Basis-URL deiner Home-Assistant-Instanz (z. B. `http://homeassistant.local:8123`)
-- `SILLYHOME_HA_TOKEN` – Long-Lived Access Token aus Home Assistant (nur lesen)
+- `SILLYHOME_HA_TOKEN` – Long-Lived Access Token eines dedizierten HA-Benutzers mit minimalen Rechten
+- `SILLYHOME_MODEL_STORE` – Verzeichnis für persistierte Modell-Metadaten
 
-Hinweis: Nutze ausschließlich Long-Lived Access Tokens mit Leserechten. Niemals Administrator-Tokens oder Passwörter eintragen. `.env` gehört nicht in Versionskontrollsysteme.
+Niemals Administrator-Tokens oder Passwörter eintragen. `.env` gehört nicht ins
+Versionskontrollsystem.
 
 ### Tests
 ```bash
-pytest -q
+pytest
 ruff check .
-mypy app tests
+mypy
-```
+```

app/api/v1/entities.py

@@ -2,38 +2,20 @@ from __future__ import annotations
 
 from typing import List
 
-from fastapi import APIRouter, HTTPException, Request
+from fastapi import APIRouter, Depends
 
+from app.dependencies import get_ha_reader
 from app.ha.models import HaEntitySummary
 from app.ha.reader import HaReader
-from app.rules.recommender import Recommender
 
 router = APIRouter(prefix="/v1", tags=["entities"])
 
 
-def _state_ha_reader(request: Request) -> HaReader:
-    try:
-        return request.app.state.ha_reader
-    except AttributeError as exc:
-        raise HTTPException(status_code=503, detail="HA-Reader nicht initialisiert.") from exc
-
-
-def _state_recommender(request: Request) -> Recommender:
-    try:
-        return request.app.state.recommender
-    except AttributeError as exc:
-        raise HTTPException(status_code=503, detail="Recommender nicht initialisiert.") from exc
-
-
 @router.get(
     "/entities",
     summary="Home-Assistant-Entities auflisten",
     description="Gibt eine kompakte Zusammenfassung aller erreichbaren HA-Entitäten zurück.",
     response_model=List[HaEntitySummary],
 )
-def list_entities(request: Request) -> List[HaEntitySummary]:
+def list_entities(ha_reader: HaReader = Depends(get_ha_reader)) -> List[HaEntitySummary]:
-    ha_reader = _state_ha_reader(request)
+    return list(ha_reader.read_entities())
-    recommender = _state_recommender(request)
-    entities = ha_reader.read_entities()
-    recommender.run(entities)
-    return entities

app/config.py

@@ -8,6 +8,7 @@ from dataclasses import dataclass
 class Settings:
     ha_url: str | None = None
     ha_token: str | None = None
+    model_store: str = ".model_store"
 
     @property
     def ha_configured(self) -> bool:
@@ -18,4 +19,5 @@ def load_settings() -> Settings:
     return Settings(
         ha_url=os.getenv("SILLYHOME_HA_URL") or os.getenv("HA_URL"),
         ha_token=os.getenv("SILLYHOME_HA_TOKEN") or os.getenv("HA_TOKEN"),
+        model_store=os.getenv("SILLYHOME_MODEL_STORE", ".model_store"),
     )

app/ha/client.py

@@ -31,10 +31,13 @@ class HaClient:
             "Content-Type": "application/json",
         })
 
+    def close(self) -> None:
+        self._session.close()
+
     def list_entities(self) -> list[dict[str, object]]:
         try:
             response = self._session.get(
-                f"{self._settings.url}/api/states",
+                f"{self._settings.url.rstrip('/')}/api/states",
                 timeout=self._settings.timeout_seconds,
             )
         except requests.Timeout as exc:
@@ -71,4 +74,4 @@ class HaClient:
                 "Antwort von Home Assistant hat unerwartetes Format."
             )
 
-        return payload
+        return payload

app/ha/reader.py

@@ -15,9 +15,10 @@ class HaReader:
         entities = self._client.list_entities()
         summaries: list[HaEntitySummary] = []
         for item in entities:
-            entity_id = item.get("entity_id", "")
+            raw_entity_id = item.get("entity_id")
-            if "." not in entity_id:
+            if not isinstance(raw_entity_id, str) or "." not in raw_entity_id:
                 continue
+            entity_id = raw_entity_id
             domain = entity_id.split(".", 1)[0]
             raw_attributes = item.get("attributes") or {}
             attributes: dict[str, Any] = raw_attributes if isinstance(raw_attributes, dict) else {}

app/main.py

@@ -1,34 +1,38 @@
 from contextlib import asynccontextmanager
+from collections.abc import AsyncIterator
+from typing import cast
 
 from fastapi import FastAPI
 
 from app.api.v1.entities import router as entities_router
+from app.config import load_settings
 from app.core.exception_handlers import register_exception_handlers
 from app.ha.client import HaClient, HaClientSettings
 from app.ha.reader import HaReader
-from app.rules.recommender import Recommender
+from app.ml.registry.model_registry import ModelRegistry
-from app.rules.heating import HeatingRule
+from backend.routes.ml import init_ml_routes
 
 
 @asynccontextmanager
-async def lifespan(app: FastAPI):
+async def lifespan(app: FastAPI) -> AsyncIterator[None]:
     settings = app.state.settings
-    ha_url = getattr(settings, "ha_url", None)
+    client: HaClient | None = None
-    ha_token = getattr(settings, "ha_token", None)
+    app.state.registry = ModelRegistry(settings.model_store)
-    client = HaClient(
+    if hasattr(app.state, "ha_reader"):
-        settings=HaClientSettings(
+        del app.state.ha_reader
-            url=ha_url or "",
+    if settings.ha_configured:
-            token=ha_token or "",
+        client = HaClient(
+            settings=HaClientSettings(
+                url=cast(str, settings.ha_url),
+                token=cast(str, settings.ha_token),
+            )
         )
-    )
+        app.state.ha_reader = HaReader(client=client)
-    app.state.ha_reader = HaReader(client=client)
+    try:
-    app.state.recommender = Recommender(rules=[HeatingRule()])
+        yield
-    yield
+    finally:
-
+        if client is not None:
-
+            client.close()
-class Settings:
-    ha_url: str = "http://localhost:8123"
-    ha_token: str = ""
 
 
 app = FastAPI(
@@ -37,9 +41,10 @@ app = FastAPI(
     version="0.1.0",
     lifespan=lifespan,
 )
-app.state.settings = Settings()
+app.state.settings = load_settings()
 register_exception_handlers(app)
 app.include_router(entities_router)
+init_ml_routes(app, model_store=app.state.settings.model_store)
 
 
 @app.get("/health")
@@ -49,4 +54,4 @@ def health() -> dict[str, str]:
 
 @app.get("/")
 def root() -> dict[str, str]:
-    return {"service": "sillyhome-next", "docs": "/docs"}
+    return {"service": "sillyhome-next", "docs": "/docs"}

app/ml/__init__.py

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

app/ml/evaluation.py

@@ -1,11 +1,10 @@
 from __future__ import annotations
 
 import logging
-from dataclasses import dataclass, field
+from collections.abc import Sequence
-from typing import Sequence
+from dataclasses import dataclass
 
-from app.ml.feature_store import FeatureVector
+from app.ml.training import TrainingPipeline
-from app.ml.training import TrainingPipeline, TrainedArtifact
 
 logger = logging.getLogger(__name__)
 
@@ -29,15 +28,16 @@ class Evaluator:
         self._pipeline = pipeline
 
     def evaluate(self, artifact_id: str, predictions: Sequence[str]) -> EvalReport:
-        artifacts = list(self._pipeline._artifacts)
+        try:
-        if not artifacts:
+            supported_sensors = set(self._pipeline.export(artifact_id).supported_sensors)
-            raise ValueError("Kein trainiertes Modell für Evaluation vorhanden.")
+        except KeyError as exc:
+            raise ValueError("Kein trainiertes Modell für Evaluation vorhanden.") from exc
 
-        supported_sensors = self._pipeline.export(artifact_id).supported_sensors
+        parsed_sensors = [_prediction_sensor(prediction) for prediction in predictions]
-        unknown_hits = sum(1 for prediction in predictions if ":" not in prediction)
+        supported_hits = sum(sensor in supported_sensors for sensor in parsed_sensors)
-        supported_references = sum(1 for sensor in supported_sensors for prediction in predictions if sensor in prediction)
+        unknown_hits = sum(sensor not in supported_sensors for sensor in parsed_sensors)
         sample_size = len(predictions)
-        coverage = supported_references / sample_size if sample_size else 0.0
+        coverage = supported_hits / sample_size if sample_size else 0.0
         unknown_rate = unknown_hits / sample_size if sample_size else 0.0
 
         coverage_metric = Metric(name="coverage", value=coverage, threshold=0.8)
@@ -54,4 +54,11 @@ class Evaluator:
             coverage,
             unknown_rate,
         )
-        return report
+        return report
+
+
+def _prediction_sensor(prediction: str) -> str | None:
+    parts = prediction.split(":", 2)
+    if len(parts) != 3 or not parts[0] or not parts[1]:
+        return None
+    return parts[1]

app/ml/feature_store.py

@@ -1,8 +1,8 @@
 from __future__ import annotations
 
 from collections import defaultdict
-from dataclasses import dataclass, field
+from collections.abc import Iterable
-from typing import Iterable
+from dataclasses import dataclass
 
 
 @dataclass(frozen=True)
@@ -28,4 +28,4 @@ class FeatureStore:
         return series[-1] if series else None
 
     def all(self) -> list[FeatureVector]:
-        return [vector for vectors in self._vectors.values() for vector in vectors]
+        return [vector for vectors in self._vectors.values() for vector in vectors]

app/ml/registry/model_registry.py

@@ -1,26 +1,34 @@
 from __future__ import annotations
 
+import json
 import logging
+import os
 from pathlib import Path
-from typing import Iterable
+import re
+from collections.abc import Iterable
 
 from app.ml.training import TrainedArtifact
 
 logger = logging.getLogger(__name__)
 
+_ARTIFACT_ID_PATTERN = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._-]{0,127}$")
+
 
 class ModelRegistry:
     def __init__(self, root: str | Path) -> None:
-        self._root = Path(root)
+        self._root = Path(root).resolve()
         self._root.mkdir(parents=True, exist_ok=True)
         self._artifacts: dict[str, TrainedArtifact] = {}
+        self._load_existing()
 
     def register(self, artifact: TrainedArtifact) -> TrainedArtifact:
-        self._artifacts[artifact.artifact_id] = artifact
+        self._validate_artifact_id(artifact.artifact_id)
         self._persist(artifact)
+        self._artifacts[artifact.artifact_id] = artifact
         return artifact
 
     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]
@@ -28,10 +36,45 @@ class ModelRegistry:
     def list_models(self) -> Iterable[TrainedArtifact]:
         return list(self._artifacts.values())
 
+    def _load_existing(self) -> None:
+        for source in sorted(self._root.glob("*.json")):
+            try:
+                raw = json.loads(source.read_text(encoding="utf-8"))
+                artifact_id = raw["artifact_id"]
+                supported_sensors = raw["supported_sensors"]
+                if not isinstance(artifact_id, str) or not isinstance(supported_sensors, list):
+                    raise ValueError("invalid artifact structure")
+                self._validate_artifact_id(artifact_id)
+                if source.name != f"{artifact_id}.json":
+                    raise ValueError("artifact id does not match filename")
+                if not all(isinstance(sensor, str) for sensor in supported_sensors):
+                    raise ValueError("supported_sensors must contain strings")
+            except (KeyError, TypeError, ValueError, json.JSONDecodeError) as exc:
+                raise ValueError(f"Ungültiges Modell-Artefakt: {source.name}") from exc
+
+            self._artifacts[artifact_id] = TrainedArtifact(
+                artifact_id=artifact_id,
+                supported_sensors=tuple(supported_sensors),
+            )
+
     def _persist(self, artifact: TrainedArtifact) -> None:
         target = self._root / f"{artifact.artifact_id}.json"
-        target.write_text(
+        temporary = target.with_suffix(".json.tmp")
-            f"{artifact.artifact_id}\t{','.join(artifact.supported_sensors)}\n",
+        payload = {
+            "artifact_id": artifact.artifact_id,
+            "supported_sensors": list(artifact.supported_sensors),
+        }
+        temporary.write_text(
+            json.dumps(payload, ensure_ascii=True, sort_keys=True) + "\n",
             encoding="utf-8",
         )
-        logger.info("Modell gespeichert: %s", target)
+        os.replace(temporary, target)
+        logger.info("Modell gespeichert: %s", target)
+
+    @staticmethod
+    def _validate_artifact_id(artifact_id: str) -> None:
+        if not _ARTIFACT_ID_PATTERN.fullmatch(artifact_id) or ".." in artifact_id:
+            raise ValueError(
+                "artifact_id darf nur Buchstaben, Ziffern, Punkt, Unterstrich "
+                "und Bindestrich enthalten."
+            )

app/ml/training.py

@@ -2,9 +2,8 @@ from __future__ import annotations
 
 import logging
 from dataclasses import dataclass
-from typing import Sequence
 
-from app.ml.feature_store import FeatureVector, FeatureStore
+from app.ml.feature_store import FeatureStore
 
 logger = logging.getLogger(__name__)
 
@@ -25,7 +24,7 @@ class TrainingPipeline:
         if not vectors:
             raise ValueError("FeatureStore enthält keine Trainingsdaten.")
 
-        sensors = tuple({vector.sensor_id for vector in vectors})
+        sensors = tuple(sorted({vector.sensor_id for vector in vectors}))
         artifact = TrainedArtifact(artifact_id=artifact_id, supported_sensors=sensors)
         self._artifacts[artifact_id] = artifact
         logger.info("Training abgeschlossen für %s mit %d Sensoren", artifact_id, len(sensors))
@@ -34,4 +33,4 @@ class TrainingPipeline:
     def export(self, artifact_id: str) -> TrainedArtifact:
         if artifact_id not in self._artifacts:
             raise KeyError(f"Artifact '{artifact_id}' nicht gefunden.")
-        return self._artifacts[artifact_id]
+        return self._artifacts[artifact_id]

backend/__init__.py

@@ -0,0 +1 @@
+"""Secondary application entry points for SillyHome Next."""

backend/app.py

@@ -1,4 +1,8 @@
+from collections.abc import AsyncIterator
+from contextlib import asynccontextmanager
+
 from fastapi import FastAPI
+from starlette.datastructures import State
 
 from backend.routes.ml import init_ml_routes
 from app.ml.registry.model_registry import ModelRegistry
@@ -6,18 +10,20 @@ from app.ml.training import TrainingPipeline
 from app.ml.feature_store import FeatureStore, FeatureVector
 
 
+@asynccontextmanager
+async def lifespan(application: FastAPI) -> AsyncIterator[None]:
+    application.state.registry = ModelRegistry(application.state.model_store)
+    _seed_default_model(application.state)
+    yield
+
+
 def create_app() -> FastAPI:
-    application = FastAPI(title="SillyHome Next ML")
+    application = FastAPI(title="SillyHome Next ML", lifespan=lifespan)
     init_ml_routes(application)
-    _seed_default_model(application.state if hasattr(application, "state") else application)
     return application
 
 
-def _app_state():  # noqa: ANN001
+def _seed_default_model(state: State) -> None:
-    return app.state
-
-
-def _seed_default_model(state) -> None:  # noqa: ANN001
     registry = getattr(state, "registry", None)
     if registry is None:
         registry = ModelRegistry(".model_store")
@@ -34,4 +40,4 @@ def _seed_default_model(state) -> None:  # noqa: ANN001
     registry.register(artifact)
 
 
-app = create_app()
+app = create_app()

backend/routes/__init__.py

@@ -0,0 +1 @@
+"""API route modules."""

backend/routes/ml.py

@@ -2,15 +2,14 @@ from __future__ import annotations
 
 import logging
 from datetime import datetime, timezone
-from typing import List, Sequence
+from collections.abc import Sequence
 
-from fastapi import APIRouter
+from fastapi import APIRouter, FastAPI, HTTPException, Request, status
 from pydantic import BaseModel, Field
 
 from app.ml.feature_store import FeatureVector
 from app.ml.predictor import Predictor
 from app.ml.registry.model_registry import ModelRegistry
-from app.ml.training import TrainedArtifact
 
 logger = logging.getLogger(__name__)
 
@@ -25,7 +24,7 @@ class HealthResponse(BaseModel):
 class PredictRequest(BaseModel):
     model_id: str = Field(..., alias="modelId")
     sensor_id: str
-    values: dict
+    values: dict[str, float]
 
 
 class PredictResponse(BaseModel):
@@ -43,7 +42,7 @@ class BatchResponse(BaseModel):
 
 
 class ModelsResponse(BaseModel):
-    models: List[str]
+    models: list[str]
 
 
 @router.get("/health", response_model=HealthResponse, status_code=200)
@@ -52,53 +51,66 @@ def health() -> HealthResponse:
 
 
 @router.get("/models", response_model=ModelsResponse, status_code=200)
-def list_models() -> ModelsResponse:
+def list_models(request: Request) -> ModelsResponse:
-    registry = _require_registry()
+    registry = _require_registry(request)
     models = [artifact.artifact_id for artifact in registry.list_models()]
     return ModelsResponse(models=models)
 
 
 @router.post("/predict", response_model=PredictResponse, status_code=200)
-def predict(request: PredictRequest) -> PredictResponse:
+def predict(payload: PredictRequest, request: Request) -> PredictResponse:
-    registry = _require_registry()
+    registry = _require_registry(request)
     predictor = Predictor(registry=registry)
-    vector = FeatureVector(sensor_id=request.sensor_id, values=request.values)
+    vector = FeatureVector(sensor_id=payload.sensor_id, values=payload.values)
     try:
-        prediction = predictor.predict(request.model_id, vector)
+        prediction = predictor.predict(payload.model_id, vector)
-    except KeyError as exc:  # unknown artifact
+    except KeyError as exc:
-        raise _not_found_error(str(exc)) from exc
+        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=str(exc)) from exc
-    return PredictResponse(model_id=request.model_id, sensor_id=request.sensor_id, prediction=prediction)
+    except ValueError as exc:
+        raise HTTPException(
+            status_code=status.HTTP_422_UNPROCESSABLE_CONTENT,
+            detail=str(exc),
+        ) from exc
+    return PredictResponse(
+        model_id=payload.model_id,
+        sensor_id=payload.sensor_id,
+        prediction=prediction,
+    )
 
 
 @router.post("/batch", response_model=BatchResponse, status_code=200)
-def predict_batch(request: BatchRequest) -> BatchResponse:
+def predict_batch(payload: BatchRequest, request: Request) -> BatchResponse:
-    registry = _require_registry()
+    registry = _require_registry(request)
     predictor = Predictor(registry=registry)
-    responses: List[PredictResponse] = []
+    responses: list[PredictResponse] = []
-    for item in request.requests:
+    for item in payload.requests:
         vector = FeatureVector(sensor_id=item.sensor_id, values=item.values)
         try:
             prediction = predictor.predict(item.model_id, vector)
         except KeyError as exc:
-            raise _not_found_error(str(exc)) from exc
+            raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=str(exc)) from exc
+        except ValueError as exc:
+            raise HTTPException(
+                status_code=status.HTTP_422_UNPROCESSABLE_CONTENT,
+                detail=str(exc),
+            ) from exc
         responses.append(
             PredictResponse(model_id=item.model_id, sensor_id=item.sensor_id, prediction=prediction)
         )
     return BatchResponse(predictions=responses)
 
 
-def _require_registry() -> ModelRegistry:
+def _require_registry(request: Request) -> ModelRegistry:
-    from backend.app import _app_state
+    registry = getattr(request.app.state, "registry", None)
-
+    if not isinstance(registry, ModelRegistry):
-    state_obj = _app_state()
+        raise HTTPException(
-    registry = getattr(state_obj, "registry", None)
+            status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
-    if registry is None:
+            detail="ML registry nicht initialisiert.",
-        raise RuntimeError("ML registry nicht initialisiert.")
+        )
     return registry
 
 
-def init_ml_routes(app) -> None:  # noqa: ANN001
+def init_ml_routes(app: FastAPI, model_store: str = ".model_store") -> None:
-    registry = ModelRegistry(".model_store")
+    app.state.model_store = model_store
-    app.state.registry = registry
     app.include_router(router)
-    logger.info("ML routes registered")
+    logger.info("ML routes registered")

docker-compose.yml

@@ -2,7 +2,22 @@ services:
   api:
     build: .
     ports:
-      - "8000:8000"
+      - "127.0.0.1:8000:8000"
     env_file:
-      - .env
+      - path: .env
-    restart: unless-stopped
+        required: false
+    environment:
+      SILLYHOME_MODEL_STORE: /app/data/models
+    volumes:
+      - model-data:/app/data/models
+    read_only: true
+    tmpfs:
+      - /tmp
+    security_opt:
+      - no-new-privileges:true
+    cap_drop:
+      - ALL
+    restart: unless-stopped
+
+volumes:
+  model-data:

docs/ml_api.md

@@ -1,6 +1,11 @@
 # ML-Serving-API
 
-Diese Dokumentation beschreibt die REST-Endpoints für ML-Vorhersagen in SillyHome Next.
+Diese Dokumentation beschreibt die REST-Endpunkte der aktuellen
+Modell-Artefakt- und Vorhersage-Schnittstelle.
+
+> Hinweis: Version 0.1.0 enthält noch kein statistisch trainiertes ML-Modell.
+> Die Vorhersage ist eine deterministische Referenzimplementierung für den
+> späteren Modellvertrag.
 
 ## Basis-URL
 
@@ -10,7 +15,8 @@ Diese Dokumentation beschreibt die REST-Endpoints für ML-Vorhersagen in SillyHo
 - Einzelvorhersage: `/predict`
 - Batchvorhersage: `/batch`
 
-Der Standard-Start erfolgt über `uvicorn backend.app:app --reload`, danach steht die API unter `/ml` bereit.
+Der Standard-Start erfolgt über `uvicorn app.main:app`, danach stehen HA- und
+ML-Routen in derselben Anwendung bereit.
 
 ## Endpoints
 
@@ -101,16 +107,18 @@ Batch-Vorhersage für mehrere Sensorwerte.
 
 ## Fehlerfälle
 
-- `400 Bad Request`: Fehlende oder ungültige Felder.
+- `404 Not Found`: Modell nicht registriert.
-- `404 Not Found`: Modell oder Sensor nicht registriert.
+- `422 Unprocessable Content`: Sensor wird vom Modell nicht unterstützt oder Eingabe ist ungültig.
-- `500 Internal Server Error`: Registry nicht initialisiert oder unerwarteter Fehler.
+- `503 Service Unavailable`: Registry ist nicht initialisiert.
 
 ## Betrieb
 
-Beim Start wird automatisch ein Default-Artefakt erstellt, falls noch kein Modell registriert ist. Neue Modelle müssen zusätzlich über `ModelRegistry.register(...)` eingetragen werden.
+Die produktive App lädt Artefakte aus `SILLYHOME_MODEL_STORE`. Neue Artefakte
+werden derzeit intern über `ModelRegistry.register(...)` registriert. Die
+Registry speichert validiertes JSON atomisch und lädt es beim Neustart.
 
 ## Verweise
 
 - `app/ml/predictor.py`
 - `app/ml/registry/model_registry.py`
-- `backend/routes/ml.py`
+- `backend/routes/ml.py`

docs/ml_training.md

@@ -0,0 +1,44 @@
+# ML Training- und Evaluations-Workflow
+
+Dieser Workflow beschreibt den aktuellen Platzhalter für Modell-Metadaten,
+Evaluation und Serving. Er trainiert in Version 0.1.0 noch kein statistisches
+Modell.
+
+## 1. Daten sammeln
+
+Alle Trainingsvektoren werden über `FeatureStore.add(...)` oder `add_batch(...)` eingepflegt. Jeder Vektor enthält eine Sensor-ID sowie ein Dictionary mit Merkmalen.
+
+## 2. Artefakt-Metadaten erzeugen
+
+```python
+store = FeatureStore()
+store.add(FeatureVector(sensor_id="sensor.kitchen", values={"temperature": 21.0}))
+pipeline = TrainingPipeline(store)
+artifact = pipeline.run("my_artifact")
+pipeline.export("my_artifact")
+```
+
+`TrainingPipeline.run(...)` erzeugt ein `TrainedArtifact` mit den unterstützten
+Sensor-IDs. Gewichte, Parameter oder ein echtes Modell werden noch nicht
+berechnet.
+
+## 3. Modell evaluieren
+
+```python
+evaluator = Evaluator(pipeline)
+report = evaluator.evaluate(artifact.artifact_id, predictions)
+```
+
+Der Report enthält:
+- `artifact_id`
+- `sample_size`
+- Metriken wie `coverage` und `unknown_rate` mit Default-Schwellenwerten
+
+## 4. Modell registrieren
+
+Das trainierte Artefakt kann anschließend über `ModelRegistry.register(artifact)` bereitgestellt werden. Die ML-Serving-API stellt es unter `/ml/predict` und `/ml/batch` zur Verfügung.
+
+## Hinweise
+- Für reproduzierbare Sensor-Reihenfolgen wird in `TrainingPipeline.run(...)` eine sortierte Sensor-Liste verwendet.
+- Fehlende Trainingsdaten lösen `ValueError` aus; nicht registrierte Artefakte lösen `KeyError` aus.
+- `coverage` zählt nur exakte Sensor-Referenzen und bleibt im Bereich 0 bis 1.

pyproject.toml

@@ -1,3 +1,7 @@
+[build-system]
+requires = ["setuptools>=69"]
+build-backend = "setuptools.build_meta"
+
 [project]
 name = "sillyhome-next"
 version = "0.1.0"
@@ -24,6 +28,10 @@ addopts = "-q"
 
 [tool.mypy]
 strict = true
+files = ["app", "backend", "tests"]
+
+[tool.setuptools.packages.find]
+include = ["app*", "backend*"]
 
 [tool.ruff]
 line-length = 100

tests/api/test_entities.py

@@ -49,8 +49,6 @@ def test_entities_returns_reader_data() -> None:
 
 def test_entities_returns_503_without_home_assistant_config() -> None:
     with TestClient(app) as client:
-        if hasattr(app.state, "ha_reader"):
-            delattr(app.state, "ha_reader")
         response = client.get("/v1/entities")
     assert response.status_code == 503
 

tests/api/test_ml_routes.py

@@ -0,0 +1,52 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+from fastapi.testclient import TestClient
+
+from app.main import app
+
+
+def test_ml_routes_are_exposed_by_production_app() -> None:
+    with TestClient(app) as client:
+        health = client.get("/ml/health")
+        models = client.get("/ml/models")
+
+    assert health.status_code == 200
+    assert models.status_code == 200
+    assert isinstance(models.json()["models"], list)
+
+
+def test_unknown_model_returns_404() -> None:
+    with TestClient(app) as client:
+        response = client.post(
+            "/ml/predict",
+            json={
+                "modelId": "missing",
+                "sensor_id": "sensor.kitchen",
+                "values": {"temperature": 21.0},
+            },
+        )
+
+    assert response.status_code == 404
+
+
+def test_unsupported_sensor_returns_422(tmp_path: Path) -> None:
+    from app.ml.registry.model_registry import ModelRegistry
+    from app.ml.training import TrainedArtifact
+
+    registry = ModelRegistry(tmp_path)
+    registry.register(TrainedArtifact("default", ("sensor.kitchen",)))
+
+    with TestClient(app) as client:
+        app.state.registry = registry
+        response = client.post(
+            "/ml/predict",
+            json={
+                "modelId": "default",
+                "sensor_id": "sensor.unknown",
+                "values": {"temperature": 21.0},
+            },
+        )
+
+    assert response.status_code == 422

tests/ml/test_evaluation.py

@@ -21,13 +21,35 @@ def evaluator_factory() -> Evaluator:
 
 def test_evaluate_returns_report_with_metrics() -> None:
     evaluator = evaluator_factory()
-    report = evaluator.evaluate("artifact_v1", ["artifact_v1:sensor.kitchen:{'temperature': 21.0}", "artifact_v1:sensor.bedroom:{'temperature': 18.5}"])
+    report = evaluator.evaluate(
+        "artifact_v1",
+        [
+            "artifact_v1:sensor.kitchen:{'temperature': 21.0}",
+            "artifact_v1:sensor.bedroom:{'temperature': 18.5}",
+        ],
+    )
     assert report.artifact_id == "artifact_v1"
     assert report.sample_size == 2
     assert {metric.name for metric in report.metrics} == {"coverage", "unknown_rate"}
+    assert next(metric.value for metric in report.metrics if metric.name == "coverage") == 1.0
 
 
 def test_evaluate_without_training_raises_value_error() -> None:
     evaluator = Evaluator(TrainingPipeline(FeatureStore()))
     with pytest.raises(ValueError):
-        evaluator.evaluate("artifact_v1", [])
+        evaluator.evaluate("artifact_v1", [])
+
+
+def test_coverage_is_bounded_and_requires_exact_sensor_match() -> None:
+    evaluator = evaluator_factory()
+    report = evaluator.evaluate(
+        "artifact_v1",
+        [
+            "artifact_v1:sensor.kitchen:{'note': 'sensor.bedroom'}",
+            "artifact_v1:sensor.kitchen_extra:{}",
+            "malformed",
+        ],
+    )
+
+    metrics = {metric.name: metric.value for metric in report.metrics}
+    assert metrics == {"coverage": pytest.approx(1 / 3), "unknown_rate": pytest.approx(2 / 3)}

tests/ml/test_feature_store.py

@@ -1,7 +1,5 @@
 from __future__ import annotations
 
-import pytest
-
 from app.ml.feature_store import FeatureStore, FeatureVector
 
 
@@ -31,12 +29,18 @@ def test_add_batch_appends_all_vectors() -> None:
     ]
     store.add_batch(vectors)
     assert len(store.all()) == 3
-    assert store.latest("sensor.kitchen").values["temperature"] == 20.0
+    latest = store.latest("sensor.kitchen")
+    assert latest is not None
+    assert latest.values["temperature"] == 20.0
 
 
 def test_different_sensors_are_stored_independently() -> None:
     store = FeatureStore()
     store.add(_vector("sensor.living_room", 21.0))
     store.add(_vector("sensor.bedroom", 18.5))
-    assert store.latest("sensor.living_room").values["temperature"] == 21.0
+    living_room = store.latest("sensor.living_room")
-    assert store.latest("sensor.bedroom").values["temperature"] == 18.5
+    bedroom = store.latest("sensor.bedroom")
+    assert living_room is not None
+    assert bedroom is not None
+    assert living_room.values["temperature"] == 21.0
+    assert bedroom.values["temperature"] == 18.5

tests/ml/test_model_registry.py

@@ -0,0 +1,39 @@
+from __future__ import annotations
+
+import json
+from pathlib import Path
+
+import pytest
+
+from app.ml.registry.model_registry import ModelRegistry
+from app.ml.training import TrainedArtifact
+
+
+def test_registry_loads_persisted_artifacts_after_restart(tmp_path: Path) -> None:
+    registry = ModelRegistry(tmp_path)
+    artifact = TrainedArtifact("model-v1", ("sensor.kitchen", "sensor.bedroom"))
+    registry.register(artifact)
+
+    restarted = ModelRegistry(tmp_path)
+
+    assert restarted.load_artifact("model-v1") == artifact
+
+
+@pytest.mark.parametrize("artifact_id", ["../escape", "nested/model", "..", ""])
+def test_registry_rejects_unsafe_artifact_ids(tmp_path: Path, artifact_id: str) -> None:
+    registry = ModelRegistry(tmp_path)
+
+    with pytest.raises(ValueError):
+        registry.register(TrainedArtifact(artifact_id, ("sensor.kitchen",)))
+
+    assert list(tmp_path.parent.glob("escape.json")) == []
+
+
+def test_registry_rejects_corrupt_persisted_artifact(tmp_path: Path) -> None:
+    (tmp_path / "broken.json").write_text(
+        json.dumps({"artifact_id": "../broken", "supported_sensors": []}),
+        encoding="utf-8",
+    )
+
+    with pytest.raises(ValueError, match="broken.json"):
+        ModelRegistry(tmp_path)

tests/ml/test_training.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 import pytest
 
 from app.ml.feature_store import FeatureStore, FeatureVector
-from app.ml.training import TrainingPipeline, TrainedArtifact
+from app.ml.training import TrainingPipeline
 
 
 def _vector(sensor_id: str, temperature: float, label: str | None = None) -> FeatureVector:
@@ -45,4 +45,4 @@ def test_export_returns_registered_artifact() -> None:
 def test_export_missing_artifact_raises_key_error() -> None:
     pipeline = store_with_data()
     with pytest.raises(KeyError):
-        pipeline.export("artifact_v1")
+        pipeline.export("artifact_v1")

tests/ml/test_training_evaluation.py

@@ -0,0 +1,33 @@
+from __future__ import annotations
+
+from app.ml.evaluation import Evaluator, EvalReport, Metric
+from app.ml.feature_store import FeatureStore, FeatureVector
+from app.ml.training import TrainingPipeline
+
+
+def _vector(sensor_id: str, temperature: float, label: str | None = None) -> FeatureVector:
+    return FeatureVector(sensor_id=sensor_id, values={"temperature": temperature}, label=label)
+
+
+def test_end_to_end_training_then_evaluation() -> None:
+    store = FeatureStore()
+    store.add_batch([_vector("sensor.kitchen", 19.0), _vector("sensor.bedroom", 18.5)])
+    pipeline = TrainingPipeline(store)
+    artifact = pipeline.run("artifact_v1")
+
+    evaluator = Evaluator(pipeline)
+    predictions = [
+        "artifact_v1:sensor.kitchen:{'temperature': 21.0}",
+        "artifact_v1:sensor.bedroom:{'temperature': 18.5}",
+    ]
+    report = evaluator.evaluate(artifact.artifact_id, predictions)
+    assert isinstance(report, EvalReport)
+    assert report.sample_size == len(predictions)
+    assert any(metric.name == "coverage" for metric in report.metrics)
+
+
+def test_metric_helpers_are_serializable() -> None:
+    metric = Metric(name="coverage", value=0.85, threshold=0.8)
+    assert metric.name == "coverage"
+    assert metric.value == 0.85
+    assert metric.threshold == 0.8

tests/test_config.py

@@ -0,0 +1,18 @@
+from __future__ import annotations
+
+from pytest import MonkeyPatch
+
+from app.config import load_settings
+
+
+def test_load_settings_reads_documented_environment(monkeypatch: MonkeyPatch) -> None:
+    monkeypatch.setenv("SILLYHOME_HA_URL", "http://ha.local:8123")
+    monkeypatch.setenv("SILLYHOME_HA_TOKEN", "secret")
+    monkeypatch.setenv("SILLYHOME_MODEL_STORE", "/tmp/models")
+
+    settings = load_settings()
+
+    assert settings.ha_url == "http://ha.local:8123"
+    assert settings.ha_token == "secret"
+    assert settings.model_store == "/tmp/models"
+    assert settings.ha_configured