Add anomaly and performance monitoring

CHANGELOG.md

@@ -1,5 +1,65 @@
 # Changelog
 
+## 1.2.0 - 2026-06-17
+- Automatische Sensor-Gewichtungsanpassung aus Nutzerfeedback:
+  korrektes Feedback staerkt aktuelle Kontextsignale leicht, falsches Feedback
+  wertet sie vorsichtig ab.
+- Modell-Snapshots mit aktivem Modellstand und Rollback-API ergaenzt.
+- Dashboard zeigt Modell-Snapshots, Rollback, Zeitprofile,
+  adaptive Gewichtungsupdates und Automation-Konflikte.
+- Automation-Refresh markiert Konflikte, wenn SillyHome aktiv ist und passende
+  HA-Automationen parallel aktiv bleiben.
+- Zeitprofile fuer Nacht, Morgen, Tag, Abend und Wochenende werden aus
+  gelernten Handlungen gebildet.
+
+## 1.1.0 - 2026-06-17
+- Dashboard als Einrichtungs- und Visualisierungszentrale erweitert:
+  Job-Queue, Sicherheitsprofil, Entscheidungsakte, Wissen/Annahmen/
+  Unsicherheiten und Beitragsfaktoren pro Aktor.
+- Lokales Safety-Profil pro Aktor eingefuehrt: manuelle Sperre,
+  Freigabestufe, Mindest-Confidence und optionaler Cooldown werden vor
+  autonomem Schalten ausgewertet.
+- Sofort-Schaltpfad bleibt schnell: Safety prueft nur lokale Daten; der
+  Home-Assistant-Serviceaufruf wird nicht durch Discovery, Training oder
+  Statistik blockiert.
+- Sichtbare Job-Queue fuer Discovery, Reconciliation, Training, Evaluation
+  und Automation-Refresh mit Status, Dauer, Fehler und Zusammenfassung.
+- Entscheidungsstatistik erweitert: Sensor-/Kontextfaktoren, aktive
+  Gewichtungen, Sample-/Confidence-Trends und Feedbackzaehler werden
+  persistiert.
+
+## 1.0.5 - 2026-06-17
+- Lange Friendly Names, Entity-IDs, Chips, Tabellenwerte und Metriken brechen
+  im Dashboard responsiv um und laufen nicht mehr aus Karten oder Boxen.
+- Automatisierter Performance-Budget-Test fuer Root-HTML und
+  `/v1/actuators/dashboard` gegen das 5-Sekunden-Limit ergaenzt.
+- HA-/Ingress-Verifikation mit Supervisor-Status, Backup, Watchdog,
+  Hard-Reload und Rollback im Operating Guide dokumentiert.
+
+## 1.0.4 - 2026-06-17
+- Sensor-Relevanz ist in der Aktor-Detailansicht sichtbar: automatische
+  Relevanz, aktive Gewichtung und Score werden pro verwendetem Sensor/Zustand
+  angezeigt.
+- Gewichtungen koennen im Dashboard korrigiert und per API unter
+  `/v1/actuators/{actuator_entity_id}/weights` gespeichert werden.
+- Gruppen-Gewichtungen buendeln mehrere Sensoren/Zustaende fuer einen Aktor,
+  damit verbundene Kontextsignale gemeinsam bewertet werden koennen.
+
+## 1.0.3 - 2026-06-17
+- Header-Menue als Pulldown umgesetzt; die separate Navigationsleiste entfaellt.
+- Geraetegruppen und manuelle Kontextbereiche sind standardmaessig geschlossen.
+- Dashboard startet in Phasen: leere Bedienoberflaeche, dann Status, danach
+  Geraetedaten.
+- Detailansicht oeffnet streamartiger: zuerst Basis-Shell, dann Aktorwerte,
+  danach Kontextvorschlaege.
+
+## 1.0.2 - 2026-06-17
+- v1.0-Abnahme als `docs/V1_0_ACCEPTANCE.md` dokumentiert: erledigte,
+  teilweise erledigte und offene v1.0.x-Punkte sind getrennt sichtbar.
+- Dashboard-Startstatistik erweitert: Freigabebereitschaft, Aktiv/Shadow,
+  Gelernt/Wartet und gelernte Handlungen werden direkt im Startbereich
+  zusammengefasst.
+
 ## 1.0.1 - 2026-06-17
 - Dashboard-UI nach v1-Korrektur neu strukturiert: feste Steuerungsleiste,
   separate Geräteübersicht, klare Freigabe-/Detailfläche und Statusbereich.

README.md

@@ -13,6 +13,14 @@ nach einer ausdrücklichen Freigabe ausführen.
   [`docs/OPERATIONS.md`](docs/OPERATIONS.md)
 - Version 1.0.0 bedienen und prüfen:
   [`docs/V1_0_0_OPERATING_GUIDE.md`](docs/V1_0_0_OPERATING_GUIDE.md)
+- Version 1.0.x Abnahme und offene Punkte:
+  [`docs/V1_0_ACCEPTANCE.md`](docs/V1_0_ACCEPTANCE.md)
+- Version 1.1.0 Safety, Transparenz und Job-Queue:
+  [`docs/V1_1_0_OPERATING_GUIDE.md`](docs/V1_1_0_OPERATING_GUIDE.md)
+- Version 1.2.0 adaptive Gewichtung, Rollback und Profile:
+  [`docs/V1_2_0_OPERATING_GUIDE.md`](docs/V1_2_0_OPERATING_GUIDE.md)
+- Version 1.3.0 Anomalie- und Performance-Überwachung:
+  [`docs/V1_3_0_OPERATING_GUIDE.md`](docs/V1_3_0_OPERATING_GUIDE.md)
 - Arbeitsregeln für Coding-Agenten: [`AGENTS.md`](AGENTS.md)
 
 ## Reifegrad

addon/config.yaml

@@ -1,5 +1,5 @@
 name: SillyHome Next
-version: "1.0.1"
+version: "1.3.0"
 slug: sillyhome_next
 description: Lernt automatisch aus deinem Verhalten und steuert freigegebene Aktoren
 url: http://192.168.6.31:3000/pino/sillyhome-next

app/actuators/lifecycle.py

@@ -16,6 +16,7 @@ from app.actuators.models import (
     ManualOverride,
     ModelLifecycleState,
     ReconciliationState,
+    SensorWeightGroup,
     model_id_for_actuator,
 )
 from app.actuators.store import ActuatorStore
@@ -239,6 +240,10 @@ class ActuatorReconciliationService:
         override = ManualOverride(
             numeric_entity_id=numeric_entity_id,
             context_entity_ids=selected_context_ids,
+            sensor_weights=record.manual_override.sensor_weights if record.manual_override else {},
+            sensor_weight_groups=(
+                record.manual_override.sensor_weight_groups if record.manual_override else []
+            ),
             updated_at=now,
             note=note,
         )
@@ -253,17 +258,23 @@ class ActuatorReconciliationService:
             update={
                 "assignment": assignment,
                 "manual_override": override,
-                "numeric_candidates": _merge_manual_candidates(
-                    record.numeric_candidates,
-                    entities,
-                    [numeric_entity_id] if numeric_entity_id else [],
-                    role=EntityRole.MEASUREMENT,
+                "numeric_candidates": _apply_weight_overrides(
+                    _merge_manual_candidates(
+                        record.numeric_candidates,
+                        entities,
+                        [numeric_entity_id] if numeric_entity_id else [],
+                        role=EntityRole.MEASUREMENT,
+                    ),
+                    override,
                 ),
-                "context_candidates": _merge_manual_candidates(
-                    record.context_candidates,
-                    entities,
-                    selected_context_ids,
-                    role=EntityRole.CONTEXT,
+                "context_candidates": _apply_weight_overrides(
+                    _merge_manual_candidates(
+                        record.context_candidates,
+                        entities,
+                        selected_context_ids,
+                        role=EntityRole.CONTEXT,
+                    ),
+                    override,
                 ),
                 "lifecycle": lifecycle,
                 "updated_at": now,
@@ -271,6 +282,65 @@ class ActuatorReconciliationService:
         )
         return self._store.upsert(updated)
 
+    def set_weight_overrides(
+        self,
+        actuator_entity_id: str,
+        *,
+        sensor_weights: dict[str, float],
+        sensor_weight_groups: list[SensorWeightGroup],
+        note: str | None = None,
+    ) -> ActuatorRecord:
+        now = datetime.now(timezone.utc)
+        record = self._store.get(actuator_entity_id)
+        selected_ids = {
+            entity_id
+            for entity_id in [
+                record.assignment.selected_numeric_entity_id,
+                *record.assignment.selected_context_entity_ids,
+            ]
+            if entity_id
+        }
+        selected_ids.update(sensor_weights)
+        for group in sensor_weight_groups:
+            selected_ids.update(group.entity_ids)
+        entities = {entity.entity_id: entity for entity in self._ha_reader.read_entities()}
+        missing = [entity_id for entity_id in selected_ids if entity_id not in entities]
+        if missing:
+            raise ValueError(f"Unbekannte Home-Assistant-Entity: {', '.join(sorted(missing))}")
+
+        previous = record.manual_override
+        override = ManualOverride(
+            numeric_entity_id=(
+                previous.numeric_entity_id
+                if previous is not None
+                else record.assignment.selected_numeric_entity_id
+            ),
+            context_entity_ids=(
+                previous.context_entity_ids
+                if previous is not None
+                else record.assignment.selected_context_entity_ids
+            ),
+            sensor_weights={entity_id: round(weight, 4) for entity_id, weight in sensor_weights.items()},
+            sensor_weight_groups=sensor_weight_groups,
+            updated_at=now,
+            note=note,
+        )
+        updated = record.model_copy(
+            update={
+                "manual_override": override,
+                "numeric_candidates": _apply_weight_overrides(
+                    record.numeric_candidates,
+                    override,
+                ),
+                "context_candidates": _apply_weight_overrides(
+                    record.context_candidates,
+                    override,
+                ),
+                "updated_at": now,
+            }
+        )
+        return self._store.upsert(updated)
+
     def reconcile_all(self, trigger: str = "manual") -> ReconciliationState:
         state = self._store.load_reconciliation_state().model_copy(
             update={
@@ -376,6 +446,9 @@ class ActuatorReconciliationService:
             ),
             context=True,
         )
+        if record.manual_override is not None:
+            numeric_candidates = _apply_weight_overrides(numeric_candidates, record.manual_override)
+            context_candidates = _apply_weight_overrides(context_candidates, record.manual_override)
         assignment = (
             self._manual_assignment(record.manual_override)
             if record.manual_override is not None
@@ -918,6 +991,41 @@ def _merge_manual_candidates(
     return sorted(by_id.values(), key=lambda item: (-item.confidence, item.entity_id))
 
 
+def _apply_weight_overrides(
+    candidates: list[AssignmentCandidate],
+    override: ManualOverride,
+) -> list[AssignmentCandidate]:
+    if not override.sensor_weights and not override.sensor_weight_groups:
+        return candidates
+    group_weights: dict[str, float] = {}
+    for group in override.sensor_weight_groups:
+        for entity_id in group.entity_ids:
+            group_weights[entity_id] = max(group_weights.get(entity_id, 0.0), group.weight)
+    weighted: list[AssignmentCandidate] = []
+    for candidate in candidates:
+        explicit = override.sensor_weights.get(candidate.entity_id)
+        group_weight = group_weights.get(candidate.entity_id)
+        manual_weight = explicit if explicit is not None else group_weight
+        effective_weight = manual_weight if manual_weight is not None else 1.0
+        evidence = [
+            item
+            for item in candidate.evidence
+            if not item.startswith("Manuelle Gewichtung:")
+        ]
+        if manual_weight is not None:
+            evidence.append(f"Manuelle Gewichtung: {round(manual_weight * 100)} %.")
+        weighted.append(
+            candidate.model_copy(
+                update={
+                    "manual_weight": manual_weight,
+                    "effective_weight": round(effective_weight, 4),
+                    "evidence": evidence,
+                }
+            )
+        )
+    return sorted(weighted, key=lambda item: (-item.confidence * item.effective_weight, item.entity_id))
+
+
 def _preferred_device_classes(domain: str, *, context: bool) -> frozenset[str]:
     if context:
         mapping = {

app/actuators/models.py

@@ -37,6 +37,21 @@ class BehaviorStatus(StrEnum):
     BLOCKED = "blocked"
 
 
+class SafetyStage(StrEnum):
+    OBSERVE = "observe"
+    SUGGEST = "suggest"
+    SHADOW = "shadow"
+    PARTIAL = "partial"
+    ACTIVE = "active"
+
+
+class JobStatus(StrEnum):
+    PENDING = "pending"
+    RUNNING = "running"
+    COMPLETED = "completed"
+    FAILED = "failed"
+
+
 class AssignmentCandidate(BaseModel):
     entity_id: str
     domain: str
@@ -49,6 +64,8 @@ class AssignmentCandidate(BaseModel):
     device_name: str | None = None
     score: float = Field(ge=0.0)
     confidence: float = Field(ge=0.0, le=1.0)
+    manual_weight: float | None = Field(default=None, ge=0.0, le=1.0)
+    effective_weight: float = Field(default=1.0, ge=0.0, le=1.0)
     auto_accepted: bool = False
     evidence: list[str] = Field(default_factory=list)
 
@@ -62,9 +79,18 @@ class AssignmentSelection(BaseModel):
     reason: str = "Noch keine Zuordnung vorhanden."
 
 
+class SensorWeightGroup(BaseModel):
+    group_id: str = Field(pattern=r"^[a-z0-9_-]{1,64}$")
+    name: str = Field(min_length=1, max_length=120)
+    entity_ids: list[str] = Field(default_factory=list)
+    weight: float = Field(default=1.0, ge=0.0, le=1.0)
+
+
 class ManualOverride(BaseModel):
     numeric_entity_id: str | None = None
     context_entity_ids: list[str] = Field(default_factory=list)
+    sensor_weights: dict[str, float] = Field(default_factory=dict)
+    sensor_weight_groups: list[SensorWeightGroup] = Field(default_factory=list)
     updated_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
     note: str | None = None
 
@@ -110,11 +136,111 @@ class BehaviorPrediction(BaseModel):
     execution_reason: str = "Vorhersage wurde noch nicht ausgeführt."
 
 
+class DecisionFactor(BaseModel):
+    entity_id: str | None = None
+    label: str
+    factor_type: str = Field(max_length=40)
+    state: str | None = None
+    weight: float = Field(default=1.0, ge=0.0, le=1.0)
+    contribution: float = Field(default=0.0, ge=0.0, le=1.0)
+    evidence: list[str] = Field(default_factory=list)
+
+
+class AdaptiveWeightUpdate(BaseModel):
+    entity_id: str
+    previous_weight: float = Field(ge=0.0, le=1.0)
+    new_weight: float = Field(ge=0.0, le=1.0)
+    reason: str = Field(max_length=300)
+    updated_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
+
+
+class SafetyRule(BaseModel):
+    rule_id: str = Field(pattern=r"^[a-z0-9_-]{1,64}$")
+    label: str = Field(min_length=1, max_length=160)
+    enabled: bool = True
+    blocking: bool = True
+    reason: str = Field(default="", max_length=300)
+
+
+def default_safety_rules() -> list[SafetyRule]:
+    return [
+        SafetyRule(
+            rule_id="activation_ready",
+            label="Nur nach Lernfreigabe aktiv schalten",
+            reason="Der Aktor muss genug eindeutiges Verhalten gelernt haben.",
+        ),
+        SafetyRule(
+            rule_id="confidence_threshold",
+            label="Mindest-Sicherheit einhalten",
+            reason="Vorhersagen unter der Schaltschwelle bleiben im Shadow-Modus.",
+        ),
+        SafetyRule(
+            rule_id="cooldown",
+            label="Sicherheits-Cooldown gegen Hin-und-her-Schalten",
+            reason="Gleiche Zielzustände werden nicht zu schnell wiederholt.",
+        ),
+        SafetyRule(
+            rule_id="manual_block",
+            label="Manuelle Sperre respektieren",
+            reason="Nutzer können jeden Aktor sofort blockieren.",
+        ),
+    ]
+
+
+class SafetyProfile(BaseModel):
+    stage: SafetyStage = SafetyStage.SHADOW
+    manual_block: bool = False
+    min_confidence: float = Field(default=0.82, ge=0.0, le=1.0)
+    min_confidence_on: float | None = Field(default=None, ge=0.0, le=1.0)
+    min_confidence_off: float | None = Field(default=None, ge=0.0, le=1.0)
+    cooldown_seconds: int | None = Field(default=None, ge=0)
+    rules: list[SafetyRule] = Field(default_factory=default_safety_rules)
+    updated_at: datetime | None = None
+    note: str | None = Field(default=None, max_length=500)
+
+
 class ExecutionEvent(BaseModel):
     target_state: str
     executed_at: datetime
 
 
+class ModelSnapshot(BaseModel):
+    version_id: str
+    created_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
+    sample_count: int = Field(default=0, ge=0)
+    high_confidence_sample_count: int = Field(default=0, ge=0)
+    average_confidence: float = Field(default=0.0, ge=0.0, le=1.0)
+    incorrect_feedback_count: int = Field(default=0, ge=0)
+    patterns: list[BehaviorPattern] = Field(default_factory=list)
+    reason: str = Field(default="", max_length=500)
+
+
+class AutomationConflict(BaseModel):
+    automation_entity_id: str = Field(pattern=r"^automation\.[a-z0-9_]+$")
+    severity: str = Field(default="info", max_length=20)
+    status: str = Field(default="open", max_length=40)
+    reason: str = Field(max_length=500)
+    updated_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
+
+
+class AnomalyEvent(BaseModel):
+    anomaly_id: str = Field(pattern=r"^[a-z0-9_.-]{1,120}$")
+    severity: str = Field(default="info", max_length=20)
+    category: str = Field(max_length=40)
+    title: str = Field(min_length=1, max_length=160)
+    detail: str = Field(min_length=1, max_length=500)
+    detected_at: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
+    resolved: bool = False
+
+
+class TimeProfile(BaseModel):
+    profile_id: str = Field(pattern=r"^[a-z0-9_-]{1,64}$")
+    label: str = Field(min_length=1, max_length=80)
+    sample_count: int = Field(default=0, ge=0)
+    dominant_state: str | None = None
+    confidence: float = Field(default=0.0, ge=0.0, le=1.0)
+
+
 class RelatedAutomation(BaseModel):
     entity_id: str = Field(pattern=r"^automation\.[a-z0-9_]+$")
     config_id: str = Field(min_length=1, max_length=120)
@@ -139,6 +265,22 @@ class BehaviorState(BaseModel):
     related_automations: list[RelatedAutomation] = Field(default_factory=list)
     paused_automation_entity_ids: list[str] = Field(default_factory=list)
     reason: str = "Historische Aktorhandlungen werden analysiert."
+    safety: SafetyProfile = Field(default_factory=SafetyProfile)
+    decision_factors: list[DecisionFactor] = Field(default_factory=list)
+    knowledge: list[str] = Field(default_factory=list)
+    assumptions: list[str] = Field(default_factory=list)
+    uncertainties: list[str] = Field(default_factory=list)
+    safety_blockers: list[str] = Field(default_factory=list)
+    sample_trend: list[int] = Field(default_factory=list)
+    confidence_trend: list[float] = Field(default_factory=list)
+    correct_feedback_count: int = Field(default=0, ge=0)
+    incorrect_feedback_count: int = Field(default=0, ge=0)
+    model_snapshots: list[ModelSnapshot] = Field(default_factory=list)
+    active_model_version: str | None = None
+    adaptive_weight_updates: list[AdaptiveWeightUpdate] = Field(default_factory=list)
+    automation_conflicts: list[AutomationConflict] = Field(default_factory=list)
+    time_profiles: list[TimeProfile] = Field(default_factory=list)
+    anomalies: list[AnomalyEvent] = Field(default_factory=list)
 
 
 class ActuatorRecord(BaseModel):
@@ -165,5 +307,22 @@ class ReconciliationState(BaseModel):
     last_summary: str = "Noch keine Reconciliation ausgeführt."
 
 
+class JobQueueItem(BaseModel):
+    job_id: str = Field(min_length=1, max_length=120)
+    kind: str = Field(min_length=1, max_length=40)
+    target: str | None = Field(default=None, max_length=160)
+    trigger: str = Field(default="manual", max_length=40)
+    status: JobStatus = JobStatus.PENDING
+    started_at: datetime | None = None
+    completed_at: datetime | None = None
+    duration_ms: int | None = Field(default=None, ge=0)
+    error: str | None = Field(default=None, max_length=500)
+    summary: str = Field(default="", max_length=500)
+
+
+class JobQueueState(BaseModel):
+    jobs: list[JobQueueItem] = Field(default_factory=list)
+
+
 def model_id_for_actuator(actuator_entity_id: str) -> str:
     return f"actuator.{actuator_entity_id}"

app/actuators/store.py

@@ -8,6 +8,9 @@ from threading import RLock
 
 from app.actuators.models import (
     ActuatorRecord,
+    JobQueueItem,
+    JobQueueState,
+    JobStatus,
     LifecycleStatus,
     ModelLifecycleState,
     ReconciliationState,
@@ -22,6 +25,7 @@ class ActuatorStore:
         self._actuators_root.mkdir(parents=True, exist_ok=True)
         self._lock = RLock()
         self._reconciliation_state_path = self._root / "reconciliation_state.json"
+        self._job_queue_path = self._root / "job_queue.json"
 
     def list(self) -> list[ActuatorRecord]:
         with self._lock:
@@ -85,6 +89,75 @@ class ActuatorStore:
             self._persist_reconciliation_state(state)
             return state
 
+    def load_job_queue(self) -> JobQueueState:
+        with self._lock:
+            if not self._job_queue_path.exists():
+                return JobQueueState()
+            try:
+                return JobQueueState.model_validate_json(
+                    self._job_queue_path.read_text(encoding="utf-8")
+                )
+            except ValueError as exc:
+                raise ValueError("Ungültiger Job-Queue-Status.") from exc
+
+    def start_job(
+        self,
+        *,
+        kind: str,
+        trigger: str,
+        target: str | None = None,
+        summary: str = "",
+    ) -> JobQueueItem:
+        now = datetime.now(timezone.utc)
+        job = JobQueueItem(
+            job_id=f"{now.strftime('%Y%m%d%H%M%S%f')}-{kind}-{target or 'all'}",
+            kind=kind,
+            target=target,
+            trigger=trigger,
+            status=JobStatus.RUNNING,
+            started_at=now,
+            summary=summary,
+        )
+        with self._lock:
+            queue = self.load_job_queue()
+            queue.jobs = [*queue.jobs, job][-50:]
+            self._persist_job_queue(queue)
+        return job
+
+    def finish_job(
+        self,
+        job_id: str,
+        *,
+        status: JobStatus,
+        summary: str = "",
+        error: str | None = None,
+    ) -> JobQueueItem | None:
+        now = datetime.now(timezone.utc)
+        with self._lock:
+            queue = self.load_job_queue()
+            updated_job: JobQueueItem | None = None
+            jobs: list[JobQueueItem] = []
+            for job in queue.jobs:
+                if job.job_id != job_id:
+                    jobs.append(job)
+                    continue
+                duration_ms = None
+                if job.started_at is not None:
+                    duration_ms = max(0, int((now - job.started_at).total_seconds() * 1000))
+                updated_job = job.model_copy(
+                    update={
+                        "status": status,
+                        "completed_at": now,
+                        "duration_ms": duration_ms,
+                        "summary": summary or job.summary,
+                        "error": error,
+                    }
+                )
+                jobs.append(updated_job)
+            queue.jobs = jobs[-50:]
+            self._persist_job_queue(queue)
+            return updated_job
+
     def _target(self, actuator_entity_id: str) -> Path:
         if "." not in actuator_entity_id:
             raise ValueError("Ungültige actuator_entity_id.")
@@ -108,6 +181,14 @@ class ActuatorStore:
         )
         os.replace(temporary, self._reconciliation_state_path)
 
+    def _persist_job_queue(self, state: JobQueueState) -> None:
+        temporary = self._job_queue_path.with_suffix(".json.tmp")
+        temporary.write_text(
+            json.dumps(state.model_dump(mode="json"), ensure_ascii=True, sort_keys=True) + "\n",
+            encoding="utf-8",
+        )
+        os.replace(temporary, self._job_queue_path)
+
     @staticmethod
     def _load(path: Path) -> ActuatorRecord:
         try:

app/api/v1/actuators.py

@@ -9,7 +9,8 @@ from fastapi import APIRouter, Depends, HTTPException, Query, Request, status
 from pydantic import BaseModel, Field
 
 from app.actuators.lifecycle import ActuatorReconciliationService
-from app.actuators.models import ActuatorRecord, ReconciliationState
+from app.actuators.models import ActuatorRecord, AnomalyEvent, ReconciliationState, SensorWeightGroup
+from app.actuators.models import JobQueueItem, JobQueueState, JobStatus, SafetyProfile
 from app.actuators.store import ActuatorStore
 from app.behavior.engine import BehaviorEngine
 from app.config import Settings
@@ -44,11 +45,25 @@ class ManualAssignmentRequest(BaseModel):
     note: str | None = Field(default=None, max_length=500)
 
 
+class WeightOverrideRequest(BaseModel):
+    sensor_weights: dict[str, float] = Field(default_factory=dict)
+    sensor_weight_groups: list[SensorWeightGroup] = Field(default_factory=list)
+    note: str | None = Field(default=None, max_length=500)
+
+
 class FeedbackRequest(BaseModel):
     correct: bool
     expected_state: str | None = Field(default=None, max_length=100)
 
 
+class SafetyProfileRequest(BaseModel):
+    safety: SafetyProfile
+
+
+class ModelRollbackRequest(BaseModel):
+    version_id: str = Field(min_length=1, max_length=120)
+
+
 class ActuatorSuggestion(BaseModel):
     entity_id: str
     domain: str
@@ -74,6 +89,8 @@ class ActuatorSummary(BaseModel):
     activation_ready: bool
     activation_reason: str
     sample_count: int
+    anomaly_count: int = 0
+    critical_anomaly_count: int = 0
     prediction_target_state: str | None = None
     prediction_confidence: float | None = None
     updated_at: str
@@ -93,6 +110,12 @@ class DashboardSystemStatus(BaseModel):
     configured_actuators: int = 0
     trained_models: int = 0
     review_required: int = 0
+    performance_budget_ms: int = 3000
+    job_p95_duration_ms: int | None = None
+    slow_job_count: int = 0
+    performance_status: str = "unknown"
+    anomaly_count: int = 0
+    critical_anomaly_count: int = 0
 
 
 class DashboardDiscoveryGroup(BaseModel):
@@ -106,6 +129,13 @@ class DashboardOverview(BaseModel):
     cache: EntityCacheStatus
     actuators: list[ActuatorSummary]
     discovery_groups: list[DashboardDiscoveryGroup]
+    jobs: JobQueueState = Field(default_factory=JobQueueState)
+
+
+class AnomalyOverview(BaseModel):
+    actuator_entity_id: str
+    friendly_name: str | None = None
+    anomalies: list[AnomalyEvent] = Field(default_factory=list)
 
 
 @router.get("/discovery", response_model=list[HaEntitySummary])
@@ -118,8 +148,19 @@ def discover_actuators(
     if cached_entities:
         entities = {entity.entity_id: entity for entity in cached_entities}
     else:
-        fresh_entities = list(ha_reader.read_entities())
-        _save_cached_entities(request, fresh_entities)
+        job = _start_job(
+            request,
+            kind="discovery",
+            trigger="manual" if refresh else "cache-miss",
+            summary="Home-Assistant-Entities werden gelesen und klassifiziert.",
+        )
+        try:
+            fresh_entities = list(ha_reader.read_entities())
+            _save_cached_entities(request, fresh_entities)
+        except Exception as exc:
+            _finish_job(job, request, status=JobStatus.FAILED, summary="Discovery fehlgeschlagen.", error=str(exc))
+            raise
+        _finish_job(job, request, status=JobStatus.COMPLETED, summary=f"{len(fresh_entities)} Entities klassifiziert.")
         entities = {entity.entity_id: entity for entity in fresh_entities}
     discovered = discover_entities(list(entities.values()))
     actuator_ids = _deduplicate_actuator_ids(
@@ -239,6 +280,14 @@ def list_configured_summary(request: Request) -> list[ActuatorSummary]:
             activation_ready=record.behavior.activation_ready,
             activation_reason=record.behavior.activation_reason,
             sample_count=record.behavior.sample_count,
+            anomaly_count=len([item for item in record.behavior.anomalies if not item.resolved]),
+            critical_anomaly_count=len(
+                [
+                    item
+                    for item in record.behavior.anomalies
+                    if not item.resolved and item.severity == "critical"
+                ]
+            ),
             prediction_target_state=(
                 record.behavior.prediction.target_state
                 if record.behavior.prediction is not None
@@ -272,6 +321,15 @@ def dashboard_overview(request: Request) -> DashboardOverview:
     reconciliation = _reconciliation_state_or_default(request)
     ws_status = getattr(request.app.state, "ws_status", None)
     actuators = list_configured_summary(request)
+    store = getattr(request.app.state, "actuator_store", None)
+    jobs = (
+        store.load_job_queue()
+        if isinstance(store, ActuatorStore)
+        else JobQueueState()
+    )
+    job_p95_duration_ms, slow_job_count, performance_status = _performance_status(jobs)
+    anomaly_count = sum(record.anomaly_count for record in actuators)
+    critical_anomaly_count = sum(record.critical_anomaly_count for record in actuators)
     return DashboardOverview(
         system=DashboardSystemStatus(
             websocket_status=getattr(ws_status, "status", "unavailable"),
@@ -284,6 +342,11 @@ def dashboard_overview(request: Request) -> DashboardOverview:
             configured_actuators=len(actuators),
             trained_models=reconciliation.trained_models,
             review_required=reconciliation.review_required,
+            job_p95_duration_ms=job_p95_duration_ms,
+            slow_job_count=slow_job_count,
+            performance_status=performance_status,
+            anomaly_count=anomaly_count,
+            critical_anomaly_count=critical_anomaly_count,
         ),
         cache=EntityCacheStatus(
             available=bool(raw_entities),
@@ -292,9 +355,33 @@ def dashboard_overview(request: Request) -> DashboardOverview:
         ),
         actuators=actuators,
         discovery_groups=cached_groups,
+        jobs=jobs,
     )
 
 
+@router.get("/anomalies", response_model=list[AnomalyOverview])
+def list_anomalies(request: Request) -> list[AnomalyOverview]:
+    records = _service(request).list_configured()
+    entity_map = _load_cached_entity_map(
+        request,
+        {record.actuator_entity_id for record in records},
+    )
+    overview: list[AnomalyOverview] = []
+    for record in records:
+        active = [item for item in record.behavior.anomalies if not item.resolved]
+        if not active:
+            continue
+        entity = entity_map.get(record.actuator_entity_id)
+        overview.append(
+            AnomalyOverview(
+                actuator_entity_id=record.actuator_entity_id,
+                friendly_name=entity.friendly_name if entity is not None else None,
+                anomalies=active,
+            )
+        )
+    return overview
+
+
 @router.get("", response_model=list[ActuatorRecord])
 def list_configured(request: Request) -> list[ActuatorRecord]:
     return _service(request).list_configured()
@@ -366,6 +453,32 @@ def record_feedback(
         raise HTTPException(status_code=404, detail=str(exc)) from exc
 
 
+@router.post("/{actuator_entity_id}/safety", response_model=ActuatorRecord)
+def set_safety_profile(
+    actuator_entity_id: str,
+    payload: SafetyProfileRequest,
+    request: Request,
+) -> ActuatorRecord:
+    try:
+        return _behavior(request).set_safety_profile(actuator_entity_id, profile=payload.safety)
+    except KeyError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+
+
+@router.post("/{actuator_entity_id}/model/rollback", response_model=ActuatorRecord)
+def rollback_model(
+    actuator_entity_id: str,
+    payload: ModelRollbackRequest,
+    request: Request,
+) -> ActuatorRecord:
+    try:
+        return _behavior(request).rollback_model(actuator_entity_id, version_id=payload.version_id)
+    except KeyError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+    except ValueError as exc:
+        raise HTTPException(status_code=422, detail=str(exc)) from exc
+
+
 @router.post("/{actuator_entity_id}/activation", response_model=ActuatorRecord)
 def set_activation(
     actuator_entity_id: str,
@@ -406,6 +519,27 @@ def set_manual_assignment(
         raise HTTPException(status_code=422, detail=str(exc)) from exc
 
 
+@router.post("/{actuator_entity_id}/weights", response_model=ActuatorRecord)
+def set_weight_overrides(
+    actuator_entity_id: str,
+    payload: WeightOverrideRequest,
+    request: Request,
+) -> ActuatorRecord:
+    try:
+        _validate_weight_payload(payload)
+        record = _service(request).set_weight_overrides(
+            actuator_entity_id,
+            sensor_weights=payload.sensor_weights,
+            sensor_weight_groups=payload.sensor_weight_groups,
+            note=payload.note,
+        )
+        return record
+    except KeyError as exc:
+        raise HTTPException(status_code=404, detail=str(exc)) from exc
+    except ValueError as exc:
+        raise HTTPException(status_code=422, detail=str(exc)) from exc
+
+
 @router.post(
     "/{actuator_entity_id}/related-automations/refresh",
     response_model=ActuatorRecord,
@@ -414,11 +548,27 @@ def refresh_related_automations(
     actuator_entity_id: str,
     request: Request,
 ) -> ActuatorRecord:
+    job = _start_job(
+        request,
+        kind="automation_refresh",
+        trigger="manual",
+        target=actuator_entity_id,
+        summary="Passende HA-Automationen werden gesucht.",
+    )
     try:
-        return _behavior(request).refresh_related_automations(actuator_entity_id)
+        record = _behavior(request).refresh_related_automations(actuator_entity_id)
+        _finish_job(
+            job,
+            request,
+            status=JobStatus.COMPLETED,
+            summary=f"{len(record.behavior.related_automations)} Automationen gefunden.",
+        )
+        return record
     except KeyError as exc:
+        _finish_job(job, request, status=JobStatus.FAILED, summary="Automation-Refresh fehlgeschlagen.", error=str(exc))
         raise HTTPException(status_code=404, detail=str(exc)) from exc
     except (ValueError, HaClientError) as exc:
+        _finish_job(job, request, status=JobStatus.FAILED, summary="Automation-Refresh fehlgeschlagen.", error=str(exc))
         raise HTTPException(status_code=409, detail=str(exc)) from exc
 
 
@@ -459,12 +609,105 @@ def run_reconciliation(
     request: Request,
     trigger: str = Query(default="manual", pattern=r"^[a-z0-9_-]{1,32}$"),
 ) -> ReconciliationState:
-    state = _service(request).reconcile_all(trigger=trigger)
-    _behavior(request).train_all()
-    _behavior(request).evaluate_all()
+    reconciliation_job = _start_job(
+        request,
+        kind="reconciliation",
+        trigger=trigger,
+        summary="Kontext, Zuordnung und Modelle werden abgeglichen.",
+    )
+    training_job: JobQueueItem | None = None
+    evaluation_job: JobQueueItem | None = None
+    try:
+        state = _service(request).reconcile_all(trigger=trigger)
+        _finish_job(reconciliation_job, request, status=JobStatus.COMPLETED, summary=state.last_summary)
+        reconciliation_job = None
+        training_job = _start_job(
+            request,
+            kind="training",
+            trigger=trigger,
+            summary="Gelernte Aktorhandlungen werden aktualisiert.",
+        )
+        _behavior(request).train_all()
+        _finish_job(training_job, request, status=JobStatus.COMPLETED, summary="Training abgeschlossen.")
+        training_job = None
+        evaluation_job = _start_job(
+            request,
+            kind="evaluation",
+            trigger=trigger,
+            summary="Aktuelle Vorhersagen werden neu berechnet.",
+        )
+        _behavior(request).evaluate_all()
+        _finish_job(evaluation_job, request, status=JobStatus.COMPLETED, summary="Evaluation abgeschlossen.")
+        evaluation_job = None
+    except Exception as exc:
+        for job in [reconciliation_job, training_job, evaluation_job]:
+            if isinstance(job, JobQueueItem) and job.status is JobStatus.RUNNING:
+                _finish_job(job, request, status=JobStatus.FAILED, summary="Job fehlgeschlagen.", error=str(exc))
+        raise
     return state
 
 
+@router.get("/job-queue/state", response_model=JobQueueState)
+def get_job_queue(request: Request) -> JobQueueState:
+    store = getattr(request.app.state, "actuator_store", None)
+    if not isinstance(store, ActuatorStore):
+        raise HTTPException(
+            status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
+            detail="Actuator Store nicht initialisiert.",
+        )
+    return store.load_job_queue()
+
+
+def _start_job(
+    request: Request,
+    *,
+    kind: str,
+    trigger: str,
+    target: str | None = None,
+    summary: str = "",
+) -> JobQueueItem | None:
+    store = getattr(request.app.state, "actuator_store", None)
+    if not isinstance(store, ActuatorStore):
+        return None
+    return store.start_job(kind=kind, trigger=trigger, target=target, summary=summary)
+
+
+def _finish_job(
+    job: JobQueueItem | None,
+    request: Request,
+    *,
+    status: JobStatus,
+    summary: str,
+    error: str | None = None,
+) -> None:
+    if job is None:
+        return
+    store = getattr(request.app.state, "actuator_store", None)
+    if not isinstance(store, ActuatorStore):
+        return
+    store.finish_job(job.job_id, status=status, summary=summary, error=error)
+
+
+def _performance_status(jobs: JobQueueState) -> tuple[int | None, int, str]:
+    budget_ms = 3000
+    durations = sorted(
+        job.duration_ms
+        for job in jobs.jobs
+        if job.status is JobStatus.COMPLETED and job.duration_ms is not None
+    )
+    slow_count = sum(1 for duration in durations if duration >= budget_ms)
+    if durations:
+        index = min(len(durations) - 1, int(round((len(durations) - 1) * 0.95)))
+        p95: int | None = durations[index]
+        status_value = "slow" if slow_count else "ok"
+    else:
+        p95 = None
+        status_value = "unknown"
+    if any(job.status is JobStatus.RUNNING for job in jobs.jobs):
+        status_value = "running" if status_value == "unknown" else status_value
+    return p95, slow_count, status_value
+
+
 def _service(request: Request) -> ActuatorReconciliationService:
     service = getattr(request.app.state, "actuator_service", None)
     if not isinstance(service, ActuatorReconciliationService):
@@ -485,6 +728,20 @@ def _behavior(request: Request) -> BehaviorEngine:
     return engine
 
 
+def _validate_weight_payload(payload: WeightOverrideRequest) -> None:
+    for entity_id, weight in payload.sensor_weights.items():
+        if "." not in entity_id:
+            raise ValueError(f"Ungültige Entity-ID: {entity_id}")
+        if not 0.0 <= weight <= 1.0:
+            raise ValueError(f"Ungültige Gewichtung für {entity_id}: {weight}")
+    for group in payload.sensor_weight_groups:
+        if not group.entity_ids:
+            raise ValueError(f"Gruppe {group.name} enthält keine Entities.")
+        for entity_id in group.entity_ids:
+            if "." not in entity_id:
+                raise ValueError(f"Ungültige Entity-ID in Gruppe {group.name}: {entity_id}")
+
+
 def _reconciliation_state_or_default(request: Request) -> ReconciliationState:
     store = getattr(request.app.state, "actuator_store", None)
     if not isinstance(store, ActuatorStore):

app/behavior/engine.py

@@ -7,13 +7,22 @@ from zoneinfo import ZoneInfo
 
 from app.actuators.models import (
     ActuatorRecord,
+    AdaptiveWeightUpdate,
+    AnomalyEvent,
+    AutomationConflict,
     BehaviorMode,
     BehaviorPattern,
     BehaviorPrediction,
     BehaviorState,
     BehaviorStatus,
+    DecisionFactor,
     ExecutionEvent,
+    ManualOverride,
+    ModelSnapshot,
     RelatedAutomation,
+    SafetyProfile,
+    SafetyStage,
+    TimeProfile,
 )
 from app.actuators.store import ActuatorStore
 from app.config import Settings
@@ -80,6 +89,16 @@ class BehaviorEngine:
                         ),
                         "last_trained_at": now,
                         "reason": "Noch kein geeigneter Kontext für Verhaltenslernen vorhanden.",
+                        "anomalies": _detect_anomalies(
+                            record,
+                            now=now,
+                            min_behavior_actions=self._settings.min_behavior_actions,
+                            stale_hours=self._settings.retrain_stale_hours,
+                            sample_count=0,
+                            trusted_actions=0,
+                            prediction=None,
+                            safety_blockers=[],
+                        ),
                     }
                 ),
             )
@@ -120,6 +139,16 @@ class BehaviorEngine:
                         "patterns": [],
                         "last_trained_at": now,
                         "reason": "Noch keine historischen Aktorhandlungen gefunden.",
+                        "anomalies": _detect_anomalies(
+                            record,
+                            now=now,
+                            min_behavior_actions=self._settings.min_behavior_actions,
+                            stale_hours=self._settings.retrain_stale_hours,
+                            sample_count=0,
+                            trusted_actions=0,
+                            prediction=None,
+                            safety_blockers=[],
+                        ),
                     }
                 ),
             )
@@ -165,6 +194,7 @@ class BehaviorEngine:
                 "eindeutig zugeordnete Handlungen fehlen."
             )
         )
+        model_version_id = f"model-{now.strftime('%Y%m%d%H%M%S')}"
         behavior = record.behavior.model_copy(
             update={
                 "status": status,
@@ -175,6 +205,32 @@ class BehaviorEngine:
                 "patterns": patterns[-_MAX_PATTERNS:],
                 "last_trained_at": now,
                 "reason": reason,
+                "sample_trend": [*record.behavior.sample_trend, len(patterns)][-30:],
+                "knowledge": _knowledge_lines(record, len(patterns), trusted_actions),
+                "assumptions": _assumption_lines(record),
+                "uncertainties": _uncertainty_lines(record, len(patterns), trusted_actions),
+                "time_profiles": _time_profiles(patterns),
+                "model_snapshots": _next_model_snapshots(
+                    record.behavior.model_snapshots,
+                    model_version_id,
+                    patterns[-_MAX_PATTERNS:],
+                    len(patterns),
+                    trusted_actions,
+                    _average(record.behavior.confidence_trend),
+                    record.behavior.incorrect_feedback_count,
+                    reason,
+                ),
+                "active_model_version": model_version_id,
+                "anomalies": _detect_anomalies(
+                    record,
+                    now=now,
+                    min_behavior_actions=self._settings.min_behavior_actions,
+                    stale_hours=self._settings.retrain_stale_hours,
+                    sample_count=len(patterns),
+                    trusted_actions=trusted_actions,
+                    prediction=record.behavior.prediction,
+                    safety_blockers=record.behavior.safety_blockers,
+                ),
             }
         )
         return self._save_behavior(record, behavior)
@@ -268,16 +324,25 @@ class BehaviorEngine:
             timezone_name=self._settings.timezone,
         )
         if prediction is not None:
+            safety_allowed, safety_blockers = self._assess_safety(
+                record,
+                actuator.state,
+                prediction,
+                now,
+            )
             prediction = prediction.model_copy(
                 update={
-                    "execution_reason": self._prediction_execution_reason(
-                        record,
-                        actuator.state,
-                        prediction,
-                        now,
+                    "execution_reason": (
+                        "Ausführung ist freigegeben."
+                        if safety_allowed
+                        else "Nicht ausgeführt: " + " ".join(safety_blockers)
                     )
                 }
             )
+        else:
+            safety_allowed = False
+            safety_blockers = ["Keine fällige Vorhersage."]
+        decision_factors = _decision_factors_for(record, current_context, prediction)
         behavior = record.behavior.model_copy(
             update={
                 "last_evaluated_at": now,
@@ -287,18 +352,31 @@ class BehaviorEngine:
                     if prediction is not None
                     else "Aktuell ist kein gelerntes Handlungsmuster fällig."
                 ),
+                "decision_factors": decision_factors,
+                "knowledge": _knowledge_lines(record, record.behavior.sample_count, record.behavior.high_confidence_sample_count),
+                "assumptions": _assumption_lines(record),
+                "uncertainties": _uncertainty_lines(record, record.behavior.sample_count, record.behavior.high_confidence_sample_count),
+                "safety_blockers": safety_blockers if prediction is not None else [],
+                "anomalies": _detect_anomalies(
+                    record,
+                    now=now,
+                    min_behavior_actions=self._settings.min_behavior_actions,
+                    stale_hours=self._settings.retrain_stale_hours,
+                    sample_count=record.behavior.sample_count,
+                    trusted_actions=record.behavior.high_confidence_sample_count,
+                    prediction=prediction,
+                    safety_blockers=safety_blockers if prediction is not None else [],
+                ),
+                "confidence_trend": (
+                    [*record.behavior.confidence_trend, round(prediction.confidence, 4)][-30:]
+                    if prediction is not None
+                    else record.behavior.confidence_trend
+                ),
             }
         )
         if (
             prediction is not None
-            and behavior.mode is BehaviorMode.ACTIVE
-            and prediction.confidence >= self._settings.prediction_confidence
-            and actuator.state != prediction.target_state
-            and self._cooldown_elapsed(
-                behavior,
-                now,
-                prediction.target_state,
-            )
+            and safety_allowed
         ):
             domain = actuator_entity_id.split(".", 1)[0]
             service = service_for_state(domain, prediction.target_state)
@@ -403,6 +481,8 @@ class BehaviorEngine:
                 )
             )
             reason = "Vorhersage wurde vom Nutzer als korrekt bestätigt."
+            correct_count = record.behavior.correct_feedback_count + 1
+            incorrect_count = record.behavior.incorrect_feedback_count
         else:
             target = prediction.target_state if prediction is not None else None
             if target:
@@ -431,6 +511,13 @@ class BehaviorEngine:
                     )
                 )
             reason = "Vorhersage wurde vom Nutzer als falsch markiert."
+            correct_count = record.behavior.correct_feedback_count
+            incorrect_count = record.behavior.incorrect_feedback_count + 1
+        adaptive_updates, manual_override = _adapt_sensor_weights(
+            record,
+            current_context,
+            correct=correct,
+        )
         behavior = record.behavior.model_copy(
             update={
                 "patterns": patterns[-_MAX_PATTERNS:],
@@ -441,6 +528,68 @@ class BehaviorEngine:
                 ),
                 "reason": reason,
                 "last_trained_at": now,
+                "correct_feedback_count": correct_count,
+                "incorrect_feedback_count": incorrect_count,
+                "adaptive_weight_updates": [
+                    *record.behavior.adaptive_weight_updates,
+                    *adaptive_updates,
+                ][-50:],
+                "anomalies": _detect_anomalies(
+                    record,
+                    now=now,
+                    min_behavior_actions=self._settings.min_behavior_actions,
+                    stale_hours=self._settings.retrain_stale_hours,
+                    sample_count=len(patterns),
+                    trusted_actions=record.behavior.high_confidence_sample_count,
+                    prediction=prediction,
+                    safety_blockers=record.behavior.safety_blockers,
+                    correct_feedback_count=correct_count,
+                    incorrect_feedback_count=incorrect_count,
+                ),
+            }
+        )
+        record_for_save = (
+            record.model_copy(update={"manual_override": manual_override})
+            if manual_override is not None
+            else record
+        )
+        return self._save_behavior(record_for_save, behavior)
+
+    def rollback_model(
+        self,
+        actuator_entity_id: str,
+        *,
+        version_id: str,
+    ) -> ActuatorRecord:
+        record = self._store.get(actuator_entity_id)
+        snapshot = next(
+            (item for item in record.behavior.model_snapshots if item.version_id == version_id),
+            None,
+        )
+        if snapshot is None:
+            raise ValueError("Modell-Snapshot nicht gefunden.")
+        behavior = record.behavior.model_copy(
+            update={
+                "patterns": snapshot.patterns,
+                "sample_count": snapshot.sample_count,
+                "high_confidence_sample_count": snapshot.high_confidence_sample_count,
+                "active_model_version": snapshot.version_id,
+                "reason": f"Rollback auf Modell-Snapshot {snapshot.version_id}.",
+            }
+        )
+        return self._save_behavior(record, behavior)
+
+    def set_safety_profile(
+        self,
+        actuator_entity_id: str,
+        *,
+        profile: SafetyProfile,
+    ) -> ActuatorRecord:
+        record = self._store.get(actuator_entity_id)
+        behavior = record.behavior.model_copy(
+            update={
+                "safety": profile.model_copy(update={"updated_at": datetime.now(timezone.utc)}),
+                "reason": "Sicherheitsprofil wurde manuell aktualisiert.",
             }
         )
         return self._save_behavior(record, behavior)
@@ -459,7 +608,24 @@ class BehaviorEngine:
             )
         ]
         behavior = record.behavior.model_copy(
-            update={"related_automations": related}
+            update={
+                "related_automations": related,
+                "automation_conflicts": _automation_conflicts(record, related),
+            }
+        )
+        behavior = behavior.model_copy(
+            update={
+                "anomalies": _detect_anomalies(
+                    record.model_copy(update={"behavior": behavior}),
+                    now=datetime.now(timezone.utc),
+                    min_behavior_actions=self._settings.min_behavior_actions,
+                    stale_hours=self._settings.retrain_stale_hours,
+                    sample_count=behavior.sample_count,
+                    trusted_actions=behavior.high_confidence_sample_count,
+                    prediction=behavior.prediction,
+                    safety_blockers=behavior.safety_blockers,
+                )
+            }
         )
         return self._save_behavior(record, behavior)
 
@@ -527,6 +693,9 @@ class BehaviorEngine:
                 update={
                     "mode": mode,
                     "approved_at": approved_at,
+                    "safety": record.behavior.safety.model_copy(
+                        update={"stage": SafetyStage.ACTIVE, "updated_at": now}
+                    ),
                     "reason": (
                         "Autonomes Lernen und Schalten wurde ausdrücklich freigegeben."
                     ),
@@ -607,6 +776,9 @@ class BehaviorEngine:
             update={
                 "mode": mode,
                 "approved_at": approved_at,
+                "safety": record.behavior.safety.model_copy(
+                    update={"stage": SafetyStage.SHADOW, "updated_at": now}
+                ),
                 "related_automations": [
                     automation.model_copy(update={"enabled": True})
                     if (
@@ -651,6 +823,51 @@ class BehaviorEngine:
             return "Nicht ausgeführt: Sicherheits-Cooldown ist noch aktiv."
         return "Ausführung ist freigegeben."
 
+    def _assess_safety(
+        self,
+        record: ActuatorRecord,
+        current_state: str | None,
+        prediction: BehaviorPrediction,
+        now: datetime,
+    ) -> tuple[bool, list[str]]:
+        profile = record.behavior.safety
+        blockers: list[str] = []
+        domain = record.actuator_entity_id.split(".", 1)[0]
+        if not record.enabled:
+            blockers.append("Aktor ist in SillyHome deaktiviert.")
+        if domain not in _SAFE_ACTIVE_DOMAINS:
+            blockers.append(f"Domain {domain} ist nicht für autonomes Schalten freigegeben.")
+        if profile.manual_block:
+            blockers.append("Manuelle Sicherheitssperre ist aktiv.")
+        stage = profile.stage
+        if (
+            record.behavior.mode is BehaviorMode.ACTIVE
+            and profile.updated_at is None
+            and stage is SafetyStage.SHADOW
+        ):
+            stage = SafetyStage.ACTIVE
+        if stage not in {SafetyStage.ACTIVE, SafetyStage.PARTIAL}:
+            blockers.append(f"Safety-Stufe {stage.value} erlaubt noch kein Schalten.")
+        if record.behavior.mode is not BehaviorMode.ACTIVE:
+            blockers.append("SillyHome ist im Shadow-Modus.")
+        if not record.behavior.activation_ready:
+            blockers.append(record.behavior.activation_reason)
+        threshold = _confidence_threshold_for(profile, prediction.target_state)
+        if prediction.confidence < threshold:
+            blockers.append(
+                f"Sicherheit {prediction.confidence:.0%} liegt unter der Schwelle {threshold:.0%}."
+            )
+        if current_state == prediction.target_state:
+            blockers.append("Zielzustand ist bereits erreicht.")
+        if not self._cooldown_elapsed(
+            record.behavior,
+            now,
+            prediction.target_state,
+            cooldown_seconds=profile.cooldown_seconds,
+        ):
+            blockers.append("Sicherheits-Cooldown ist noch aktiv.")
+        return not blockers, blockers
+
     def _build_patterns(
         self,
         *,
@@ -701,6 +918,8 @@ class BehaviorEngine:
         behavior: BehaviorState,
         now: datetime,
         target_state: str,
+        *,
+        cooldown_seconds: int | None = None,
     ) -> bool:
         if behavior.last_executed_at is None:
             return True
@@ -708,7 +927,9 @@ class BehaviorEngine:
         if last_event is not None and last_event.target_state != target_state:
             return True
         return (now - behavior.last_executed_at) >= timedelta(
-            seconds=self._settings.execution_cooldown_seconds
+            seconds=cooldown_seconds
+            if cooldown_seconds is not None
+            else self._settings.execution_cooldown_seconds
         )
 
     def _save_behavior(
@@ -791,6 +1012,378 @@ def _event_changed_at(new_state: dict[str, object] | None) -> datetime | None:
     return parsed
 
 
+def _confidence_threshold_for(profile: SafetyProfile, target_state: str) -> float:
+    if target_state == "on" and profile.min_confidence_on is not None:
+        return profile.min_confidence_on
+    if target_state in {"off", "closed"} and profile.min_confidence_off is not None:
+        return profile.min_confidence_off
+    return profile.min_confidence
+
+
+def _decision_factors_for(
+    record: ActuatorRecord,
+    current_context: dict[str, str | None],
+    prediction: BehaviorPrediction | None,
+) -> list[DecisionFactor]:
+    factors: list[DecisionFactor] = []
+    candidates = {
+        candidate.entity_id: candidate
+        for candidate in [*record.numeric_candidates, *record.context_candidates]
+    }
+    for entity_id, state in current_context.items():
+        candidate = candidates.get(entity_id)
+        weight = candidate.effective_weight if candidate is not None else 1.0
+        relevance = candidate.confidence if candidate is not None else 0.5
+        contribution = round(min(1.0, weight * relevance), 4)
+        factors.append(
+            DecisionFactor(
+                entity_id=entity_id,
+                label=(
+                    candidate.friendly_name
+                    if candidate is not None and candidate.friendly_name
+                    else entity_id
+                ),
+                factor_type="context",
+                state=state,
+                weight=round(weight, 4),
+                contribution=contribution,
+                evidence=(
+                    candidate.evidence[:4]
+                    if candidate is not None
+                    else ["Aktuell ausgewähltes Kontextsignal."]
+                ),
+            )
+        )
+    if prediction is not None:
+        factors.append(
+            DecisionFactor(
+                label=f"Vorhersage {prediction.target_state}",
+                factor_type="prediction",
+                state=prediction.target_state,
+                weight=1.0,
+                contribution=prediction.confidence,
+                evidence=[prediction.reason],
+            )
+        )
+    return sorted(factors, key=lambda item: (-item.contribution, item.label))[:12]
+
+
+def _knowledge_lines(
+    record: ActuatorRecord,
+    sample_count: int,
+    trusted_actions: int,
+) -> list[str]:
+    lines = [
+        f"{sample_count} historische Aktorhandlungen sind ausgewertet.",
+        f"{trusted_actions} Handlungen stammen eindeutig von Nutzer oder HA-Automationen.",
+    ]
+    if record.assignment.selected_numeric_entity_id:
+        lines.append(f"Hauptsensor: {record.assignment.selected_numeric_entity_id}.")
+    if record.assignment.selected_context_entity_ids:
+        lines.append(
+            f"{len(record.assignment.selected_context_entity_ids)} Kontextsignale sind verbunden."
+        )
+    return lines
+
+
+def _assumption_lines(record: ActuatorRecord) -> list[str]:
+    lines = [
+        "Ähnliche Zeitfenster und ähnliche Kontextzustände deuten auf ähnliche Nutzerabsicht hin."
+    ]
+    if record.manual_override is not None:
+        lines.append("Manuelle Sensor-/Kontextkorrekturen werden höher gewichtet.")
+    if record.behavior.related_automations:
+        lines.append("Passende HA-Automationen gelten als starker Hinweis auf vorhandene Logik.")
+    return lines
+
+
+def _uncertainty_lines(
+    record: ActuatorRecord,
+    sample_count: int,
+    trusted_actions: int,
+) -> list[str]:
+    lines: list[str] = []
+    if sample_count < trusted_actions + 3:
+        lines.append("Noch wenig Varianz in den gelernten Handlungen.")
+    if trusted_actions < sample_count:
+        lines.append("Ein Teil der Handlungen ist nicht eindeutig Nutzer oder Automation zugeordnet.")
+    if record.assignment.review_required:
+        lines.append("Die automatische Kontextzuordnung verlangt noch Prüfung.")
+    if record.behavior.incorrect_feedback_count:
+        lines.append(
+            f"{record.behavior.incorrect_feedback_count} negative Feedbacks senken Vertrauen."
+        )
+    return lines or ["Keine kritische Unsicherheit aus den lokalen Daten erkannt."]
+
+
+def _next_model_snapshots(
+    existing: list[ModelSnapshot],
+    version_id: str,
+    patterns: list[BehaviorPattern],
+    sample_count: int,
+    trusted_actions: int,
+    average_confidence: float,
+    incorrect_feedback_count: int,
+    reason: str,
+) -> list[ModelSnapshot]:
+    snapshot = ModelSnapshot(
+        version_id=version_id,
+        sample_count=sample_count,
+        high_confidence_sample_count=trusted_actions,
+        average_confidence=round(average_confidence, 4),
+        incorrect_feedback_count=incorrect_feedback_count,
+        patterns=patterns,
+        reason=reason,
+    )
+    return [*existing, snapshot][-10:]
+
+
+def _average(values: list[float]) -> float:
+    return sum(values) / len(values) if values else 0.0
+
+
+def _time_profiles(patterns: list[BehaviorPattern]) -> list[TimeProfile]:
+    buckets = {
+        "night": ("Nacht", range(0, 360)),
+        "morning": ("Morgen", range(360, 720)),
+        "day": ("Tag", range(720, 1080)),
+        "evening": ("Abend", range(1080, 1440)),
+    }
+    profiles: list[TimeProfile] = []
+    for profile_id, (label, minutes) in buckets.items():
+        selected = [pattern for pattern in patterns if pattern.minute_of_day in minutes]
+        if not selected:
+            profiles.append(TimeProfile(profile_id=profile_id, label=label))
+            continue
+        by_state: dict[str, int] = {}
+        for pattern in selected:
+            by_state[pattern.target_state] = by_state.get(pattern.target_state, 0) + 1
+        dominant_state, count = max(by_state.items(), key=lambda item: (item[1], item[0]))
+        profiles.append(
+            TimeProfile(
+                profile_id=profile_id,
+                label=label,
+                sample_count=len(selected),
+                dominant_state=dominant_state,
+                confidence=round(count / len(selected), 4),
+            )
+        )
+    weekend = [pattern for pattern in patterns if pattern.weekday >= 5]
+    profiles.append(
+        TimeProfile(
+            profile_id="weekend",
+            label="Wochenende",
+            sample_count=len(weekend),
+            dominant_state=(
+                max(
+                    {pattern.target_state: 0 for pattern in weekend},
+                    key=lambda state: sum(pattern.target_state == state for pattern in weekend),
+                )
+                if weekend
+                else None
+            ),
+            confidence=round(len(weekend) / len(patterns), 4) if patterns else 0.0,
+        )
+    )
+    return profiles
+
+
+def _adapt_sensor_weights(
+    record: ActuatorRecord,
+    current_context: dict[str, str | None],
+    *,
+    correct: bool,
+) -> tuple[list[AdaptiveWeightUpdate], ManualOverride | None]:
+    if not current_context:
+        return [], record.manual_override
+    candidates = {
+        candidate.entity_id: candidate
+        for candidate in [*record.numeric_candidates, *record.context_candidates]
+    }
+    previous = record.manual_override
+    weights = dict(previous.sensor_weights if previous is not None else {})
+    updates: list[AdaptiveWeightUpdate] = []
+    delta = 0.03 if correct else -0.08
+    for entity_id in current_context:
+        candidate = candidates.get(entity_id)
+        base = weights.get(
+            entity_id,
+            candidate.effective_weight if candidate is not None else 1.0,
+        )
+        new_weight = round(min(1.0, max(0.1, base + delta)), 4)
+        if new_weight == base:
+            continue
+        weights[entity_id] = new_weight
+        updates.append(
+            AdaptiveWeightUpdate(
+                entity_id=entity_id,
+                previous_weight=round(base, 4),
+                new_weight=new_weight,
+                reason=(
+                    "Feedback korrekt: Kontextsignal leicht höher gewichtet."
+                    if correct
+                    else "Feedback falsch: Kontextsignal vorsichtig abgewertet."
+                ),
+            )
+        )
+    if not updates:
+        return [], previous
+    return updates, ManualOverride(
+        numeric_entity_id=(
+            previous.numeric_entity_id
+            if previous is not None
+            else record.assignment.selected_numeric_entity_id
+        ),
+        context_entity_ids=(
+            previous.context_entity_ids
+            if previous is not None
+            else record.assignment.selected_context_entity_ids
+        ),
+        sensor_weights=weights,
+        sensor_weight_groups=previous.sensor_weight_groups if previous is not None else [],
+        note="Sensor-Gewichtungen automatisch aus Feedback angepasst.",
+    )
+
+
+def _automation_conflicts(
+    record: ActuatorRecord,
+    related: list[RelatedAutomation],
+) -> list[AutomationConflict]:
+    conflicts: list[AutomationConflict] = []
+    for automation in related:
+        if record.behavior.mode is BehaviorMode.ACTIVE and automation.enabled:
+            conflicts.append(
+                AutomationConflict(
+                    automation_entity_id=automation.entity_id,
+                    severity="warning",
+                    status="open",
+                    reason=(
+                        "SillyHome ist aktiv, aber diese passende HA-Automation "
+                        "ist ebenfalls aktiv. Das kann zu konkurrierenden Schaltungen führen."
+                    ),
+                )
+            )
+        elif automation.entity_id in record.behavior.paused_automation_entity_ids:
+            conflicts.append(
+                AutomationConflict(
+                    automation_entity_id=automation.entity_id,
+                    severity="info",
+                    status="controlled",
+                    reason="Automation ist durch SillyHome pausiert.",
+                )
+            )
+    return conflicts
+
+
+def _detect_anomalies(
+    record: ActuatorRecord,
+    *,
+    now: datetime,
+    min_behavior_actions: int,
+    stale_hours: int,
+    sample_count: int,
+    trusted_actions: int,
+    prediction: BehaviorPrediction | None,
+    safety_blockers: list[str],
+    correct_feedback_count: int | None = None,
+    incorrect_feedback_count: int | None = None,
+) -> list[AnomalyEvent]:
+    anomalies: list[AnomalyEvent] = []
+
+    def add(category: str, severity: str, title: str, detail: str) -> None:
+        anomalies.append(
+            AnomalyEvent(
+                anomaly_id=f"{record.actuator_entity_id}.{category}",
+                category=category,
+                severity=severity,
+                title=title,
+                detail=detail,
+                detected_at=now,
+            )
+        )
+
+    if not record.assignment.selected_context_entity_ids and not record.assignment.selected_numeric_entity_id:
+        add(
+            "missing_context",
+            "warning",
+            "Kein Kontext verbunden",
+            "Der Aktor hat keine Sensor-/Kontextbasis. Entscheidungen bleiben unsicher.",
+        )
+    if sample_count < min_behavior_actions:
+        add(
+            "low_samples",
+            "info",
+            "Zu wenig Lernbeispiele",
+            f"{sample_count} von {min_behavior_actions} benoetigten Handlungen gelernt.",
+        )
+    if trusted_actions < sample_count:
+        add(
+            "unclear_sources",
+            "info",
+            "Unklare Aktorhandlungen",
+            "Ein Teil der gelernten Handlungen stammt nicht eindeutig von Nutzer oder Automation.",
+        )
+    if record.behavior.last_trained_at is not None:
+        age = now - record.behavior.last_trained_at
+        if age > timedelta(hours=stale_hours):
+            add(
+                "stale_training",
+                "warning",
+                "Training ist veraltet",
+                f"Letztes Training liegt mehr als {stale_hours} Stunden zurueck.",
+            )
+    if prediction is not None and prediction.matching_patterns and prediction.confidence < record.behavior.safety.min_confidence:
+        add(
+            "low_confidence_prediction",
+            "warning",
+            "Vorhersage unter Sicherheitsgrenze",
+            (
+                f"Confidence {prediction.confidence:.0%} liegt unter "
+                f"{record.behavior.safety.min_confidence:.0%}."
+            ),
+        )
+    if record.behavior.safety.manual_block:
+        add(
+            "manual_block",
+            "info",
+            "Manuelle Sicherheitssperre aktiv",
+            "Der Aktor ist bewusst gegen automatisches Schalten gesperrt.",
+        )
+    if safety_blockers:
+        add(
+            "safety_blockers",
+            "info",
+            "Safety blockiert aktuelle Aktion",
+            " ".join(safety_blockers)[:500],
+        )
+    if any(conflict.severity == "warning" for conflict in record.behavior.automation_conflicts):
+        add(
+            "automation_conflict",
+            "critical",
+            "Parallele Automation erkannt",
+            "SillyHome und mindestens eine passende HA-Automation koennen parallel schalten.",
+        )
+    correct = (
+        record.behavior.correct_feedback_count
+        if correct_feedback_count is None
+        else correct_feedback_count
+    )
+    incorrect = (
+        record.behavior.incorrect_feedback_count
+        if incorrect_feedback_count is None
+        else incorrect_feedback_count
+    )
+    total = correct + incorrect
+    if total >= 3 and incorrect / total >= 0.35:
+        add(
+            "feedback_error_rate",
+            "critical",
+            "Viele falsche Vorhersagen",
+            f"{incorrect} von {total} Feedbacks waren negativ. Modell pruefen oder Rollback nutzen.",
+        )
+    return anomalies[-30:]
+
+
 def predict_behavior(
     patterns: list[BehaviorPattern],
     *,

app/main.py

@@ -105,7 +105,7 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]:
 app = FastAPI(
     title="SillyHome Next API",
     description="Lokales Smart-Home-Intelligenzsystem für Home Assistant.",
-    version="1.0.1",
+    version="1.3.0",
     lifespan=lifespan,
 )
 app.state.settings = load_settings()

app/static/index.html

@@ -25,6 +25,7 @@
       --bad:#8fb8ff;
     }
     * { box-sizing:border-box; }
+    html, body { max-width:100%; overflow-x:hidden; }
     body { margin:0; font-size:15px; background:var(--panel-quiet); }
     h1,h2,h3 { margin:0 0 10px; letter-spacing:0; }
     p { margin:6px 0; }
@@ -34,11 +35,10 @@
     .brand-row { display:flex; align-items:center; gap:10px; flex-wrap:wrap; }
     .brand-mark { width:34px; height:34px; border-radius:8px; display:grid; place-items:center; background:var(--accent); color:#201204; font-weight:900; }
     header p { color:var(--text-soft); max-width:820px; }
+    .header-actions { display:grid; gap:8px; min-width:230px; }
+    .header-actions label { margin:0; font-size:.82rem; }
     .status-pill { display:flex; align-items:center; gap:8px; padding:8px 10px; border:1px solid var(--border); border-radius:8px; background:#101722; color:#d9e6f0; white-space:nowrap; }
     .dot { width:9px; height:9px; border-radius:50%; background:var(--complement); box-shadow:0 0 0 3px rgba(28,199,255,.15); }
-    .quick-nav { position:sticky; top:0; z-index:10; display:flex; gap:8px; overflow-x:auto; padding:10px 18px; background:rgba(14,18,24,.96); border-bottom:1px solid var(--border); backdrop-filter:blur(8px); }
-    .quick-nav a { flex:0 0 auto; min-height:36px; display:grid; place-items:center; padding:8px 12px; border-radius:8px; background:#151c25; border:1px solid var(--border); color:#f3f7fb; text-decoration:none; font-weight:750; font-size:.92rem; }
-    .quick-nav a.primary { background:var(--accent); border-color:var(--accent); color:#211204; }
     main { display:grid; grid-template-columns:minmax(270px,.72fr) minmax(0,1.58fr); grid-template-areas:"control board" "control detail" "status status" "guide guide"; gap:12px; padding:12px; max-width:1480px; margin:0 auto; }
     section { background:var(--panel); border:1px solid var(--border); border-radius:8px; padding:12px; min-width:0; }
     section:target { outline:2px solid var(--complement); outline-offset:2px; }
@@ -72,31 +72,40 @@
     .bad { color: var(--bad); }
     label { display:block; margin:9px 0 4px; color:#c3d2df; font-weight:700; }
     select,input,button { width:100%; border-radius:8px; border:1px solid #3b4b5b; padding:10px; background:#111821; color:#fff; font:inherit; min-width:0; }
+    input[type="checkbox"] { width:auto; min-width:0; vertical-align:middle; margin-right:8px; }
     select[multiple] { min-height:150px; }
     button { min-height:42px; margin-top:10px; background:var(--accent); color:#211204; border:0; font-weight:850; cursor:pointer; }
     button.secondary { background:var(--complement-soft); color:#dff6ff; border:1px solid #22607c; }
     button.danger { background:#2a3441; color:#f2f6fb; border:1px solid #536273; }
     button.compact { width:auto; min-width:112px; margin-right:8px; padding:8px 10px; min-height:36px; }
-    table { width: 100%; border-collapse: collapse; font-size: .92rem; }
-    td,th { padding: 8px; border-bottom: 1px solid #2d3a47; text-align: left; vertical-align: top; }
+    table { width: 100%; border-collapse: collapse; table-layout:fixed; font-size: .92rem; }
+    td,th { padding: 8px; border-bottom: 1px solid #2d3a47; text-align: left; vertical-align: top; overflow-wrap:anywhere; word-break:break-word; }
     ul { margin: 8px 0; padding-left: 18px; }
     .notice { border-left:4px solid var(--complement); padding-left:10px; }
     .grid-two { display:grid; grid-template-columns:repeat(auto-fit,minmax(240px,1fr)); gap:12px; }
     .chips { display:flex; flex-wrap:wrap; gap:6px; margin-top:8px; }
-    .chip { padding:4px 8px; border-radius:8px; background:#222b36; border:1px solid var(--border); font-size:.85rem; }
+    .chip { padding:4px 8px; border-radius:8px; background:#222b36; border:1px solid var(--border); font-size:.85rem; max-width:100%; overflow-wrap:anywhere; word-break:break-word; }
     .muted { color:var(--text-soft); }
     .card-list { display:grid; grid-template-columns:repeat(auto-fit,minmax(250px,1fr)); gap:10px; }
     .actuator-card { background:#121922; border:1px solid var(--border); border-radius:8px; padding:10px; min-width:0; }
     .actuator-card.selected { border-color:var(--complement); box-shadow:0 0 0 1px rgba(28,199,255,.35); }
-    .card-title { display:flex; justify-content:space-between; gap:10px; align-items:flex-start; margin-bottom:8px; }
-    .entity-id { overflow-wrap:anywhere; font-weight:800; }
+    .card-title { display:flex; flex-wrap:wrap; justify-content:space-between; gap:10px; align-items:flex-start; margin-bottom:8px; min-width:0; }
+    .card-title > div { min-width:0; flex:1 1 160px; overflow-wrap:anywhere; word-break:break-word; }
+    .card-title .chip { flex:0 1 auto; white-space:normal; text-align:center; }
+    .actuator-card strong { overflow-wrap:anywhere; word-break:break-word; }
+    .entity-id { overflow-wrap:anywhere; word-break:break-word; font-weight:800; }
     .metric-grid { display:grid; grid-template-columns:repeat(auto-fit,minmax(120px,1fr)); gap:6px; margin:8px 0; }
-    .metric { background:var(--panel-soft); border:1px solid var(--border); border-radius:8px; padding:8px; min-width:0; }
+    .metric { background:var(--panel-soft); border:1px solid var(--border); border-radius:8px; padding:8px; min-width:0; overflow-wrap:anywhere; word-break:break-word; }
     .metric strong { display:block; margin-bottom:4px; color:#cfe0ec; font-size:.84rem; }
+    .decision-list { display:grid; gap:8px; margin:10px 0; }
+    .decision-row { background:#121922; border:1px solid var(--border); border-radius:8px; padding:9px; min-width:0; overflow-wrap:anywhere; }
+    .decision-row.slow,
+    .decision-row.critical { border-color:var(--warn); box-shadow:0 0 0 1px rgba(243,201,105,.25); }
+    .decision-row header { padding:0; border:0; background:transparent; display:flex; justify-content:space-between; gap:10px; flex-wrap:wrap; }
     .actions { display:flex; flex-wrap:wrap; gap:8px; margin-top:10px; }
     .actions button { flex:1 1 180px; margin-top:0; }
     .detail-header { display:flex; justify-content:space-between; gap:12px; align-items:flex-start; flex-wrap:wrap; }
-    .manual-context { margin-top:12px; background:#121922; border:1px solid var(--border); border-radius:8px; padding:10px; }
+    .manual-context { margin-top:12px; background:#121922; border:1px solid var(--border); border-radius:8px; padding:10px; min-width:0; overflow-wrap:anywhere; word-break:break-word; }
     .inline-controls { display:grid; grid-template-columns:repeat(auto-fit,minmax(160px,1fr)); gap:8px; margin:8px 0; }
     .manual-entry { min-height:80px; resize:vertical; }
     textarea { width:100%; border-radius:8px; border:1px solid #3b4b5b; padding:12px; background:#101820; color:#fff; font:inherit; }
@@ -107,7 +116,8 @@
       header { padding:16px 12px; }
       header h1 { font-size:1.55rem; }
       .topbar { display:grid; }
-      .status-pill { width:max-content; }
+      .header-actions { min-width:0; }
+      .status-pill { width:max-content; max-width:100%; white-space:normal; }
       main { display:block; padding:8px; }
       .control-panel { position:static; }
       section { margin-bottom:10px; padding:10px; border-radius:8px; }
@@ -117,8 +127,6 @@
       .card-list { grid-template-columns:1fr; }
       .actions { display:grid; grid-template-columns:1fr; }
       .actions button, button.compact { width:100%; min-width:0; margin-right:0; }
-      .quick-nav { padding:8px 10px; }
-      .quick-nav a { padding:10px 11px; }
     }
     @media (max-width: 430px) {
       .metric-grid { grid-template-columns:1fr; }
@@ -137,16 +145,19 @@
       <p>Arbeitsdashboard für gelernte Home-Assistant-Bedienung: Geräte auswählen, Lernstand prüfen, Freigaben steuern.</p>
       <p class="notice">Sicherer Start: Zuerst wird nur beobachtet und vorhergesagt. Ohne deine spätere Freigabe wird nichts geschaltet.</p>
     </div>
-    <div class="status-pill"><span class="dot"></span><span id="load-budget">Startdaten laden ...</span></div>
+    <div class="header-actions">
+      <label for="section-jump">Menü</label>
+      <select id="section-jump" onchange="jumpToSection(this.value)">
+        <option value="#choose">Steuerung</option>
+        <option value="#observed">Geräte</option>
+        <option value="#detail">Freigabe</option>
+        <option value="#status-section">System</option>
+        <option value="#guide">Ablauf</option>
+      </select>
+      <div class="status-pill"><span class="dot"></span><span id="load-budget">Seite bereit, Status folgt ...</span></div>
+    </div>
   </div>
 </header>
-<nav class="quick-nav" aria-label="Schnellnavigation">
-  <a class="primary" href="#choose">Steuerung</a>
-  <a href="#observed">Geräte</a>
-  <a href="#detail">Freigabe</a>
-  <a href="#status-section">System</a>
-  <a href="#guide">Ablauf</a>
-</nav>
 <main>
   <section class="control-panel" id="choose">
     <div class="panel-title">
@@ -227,6 +238,7 @@
     <div id="status">Prüfung läuft ...</div>
     <div class="chips" id="status-chips"></div>
     <div id="dashboard-stats" class="metric-grid"></div>
+    <div id="job-queue" class="decision-list"></div>
   </section>
 
   <section class="guide-panel" id="guide">
@@ -270,9 +282,15 @@ let cachedActuators = null;
 let cachedEntities = null;
 let cachedDiscovery = null;
 let discoveryLoadPromise = null;
+let currentSensorWeightGroups = [];
 const ACTUATOR_RESULT_LIMIT = 50;
 const STATUS_TIMEOUT_MS = 2000;
-const DASHBOARD_TIMEOUT_MS = 4500;
+const DASHBOARD_TIMEOUT_MS = 3000;
+
+function jumpToSection(target) {
+  if (!target) return;
+  document.querySelector(target)?.scrollIntoView({behavior: "smooth", block: "start"});
+}
 
 function uniqueValues(values) {
   return [...new Set(values.filter(Boolean))];
@@ -423,11 +441,17 @@ async function loadOverview() {
   document.getElementById("configured-actuators").innerHTML = "<p class='muted'>Beobachtete Geräte werden geladen ...</p>";
   try {
     const dashboard = await apiWithTimeout("v1/actuators/dashboard", DASHBOARD_TIMEOUT_MS);
+    dashboard._load_elapsed_ms = Math.round(performance.now() - startedAt);
     cachedActuators = dashboard.actuators || [];
     cachedEntities = [];
     renderDashboardStatus(dashboard);
     renderConfiguredActuators();
-    if (budget) budget.textContent = `Bereit in ${Math.round(performance.now() - startedAt)} ms`;
+    if (budget) {
+      const loadMs = dashboard._load_elapsed_ms;
+      budget.textContent = loadMs <= DASHBOARD_TIMEOUT_MS
+        ? `Bereit in ${loadMs} ms`
+        : `Langsam: ${loadMs} ms`;
+    }
   } catch (error) {
     document.getElementById("configured-actuators").innerHTML = `<p class="bad">${escapeHtml(error.message)}</p>`;
     if (budget) budget.textContent = "Startdaten verzögert";
@@ -445,17 +469,16 @@ async function loadStatus() {
   const chips = document.getElementById("status-chips");
   status.innerHTML = "<p class='muted'>Status wird geprüft ...</p>";
   try {
-    const [health, websocket, ml, reconciliation, actuators] = await Promise.allSettled([
+    const [health, websocket, ml, reconciliation] = await Promise.allSettled([
       apiWithTimeout("health"),
       apiWithTimeout("health/websocket"),
       apiWithTimeout("ml/health"),
       apiWithTimeout("v1/actuators/reconciliation/state"),
-      apiWithTimeout("v1/actuators/summary"),
     ]);
-    const values = [health, websocket, ml, reconciliation, actuators].map(result =>
+    const values = [health, websocket, ml, reconciliation].map(result =>
       result.status === "fulfilled" ? result.value : null
     );
-    const [healthValue, websocketValue, mlValue, reconciliationValue, actuatorValue] = values;
+    const [healthValue, websocketValue, mlValue, reconciliationValue] = values;
     const hasError = values.some(value => value === null);
     status.innerHTML = hasError
       ? "<p class='warn'>Status teilweise verfügbar. Das Dashboard bleibt bedienbar.</p>"
@@ -464,7 +487,6 @@ async function loadStatus() {
       `<span class="chip">API: ${escapeHtml(healthValue?.status || "offen")}</span>`,
       `<span class="chip">WebSocket: ${escapeHtml(websocketValue?.status || "offen")}</span>`,
       `<span class="chip">Lernsystem: ${escapeHtml(mlValue?.status || "offen")}</span>`,
-      `<span class="chip">Aktoren: ${Array.isArray(actuatorValue) ? actuatorValue.length : "offen"}</span>`,
       `<span class="chip">Lernbereite Geräte: ${escapeHtml(reconciliationValue?.trained_models ?? "offen")}</span>`,
     ].join("");
   } catch (error) {
@@ -477,16 +499,39 @@ function renderDashboardStatus(dashboard) {
   const status = document.getElementById("status");
   const chips = document.getElementById("status-chips");
   const stats = document.getElementById("dashboard-stats");
+  const jobsBox = document.getElementById("job-queue");
   const system = dashboard.system || {};
   const cache = dashboard.cache || {};
+  const actuators = dashboard.actuators || [];
   const discoveryGroups = dashboard.discovery_groups || [];
+  const activeCount = actuators.filter(record => record.behavior_mode === "active").length;
+  const shadowCount = actuators.filter(record => record.behavior_mode !== "active").length;
+  const readyCount = actuators.filter(record => record.activation_ready).length;
+  const pendingCount = actuators.filter(record =>
+    ["pending_history", "pending_assignment", "archived"].includes(record.lifecycle_status)
+  ).length;
+  const trainedCount = actuators.filter(record => record.behavior_status === "trained").length;
+  const sampleTotal = actuators.reduce((sum, record) => sum + Number(record.sample_count || 0), 0);
+  const anomalyTotal = Number(system.anomaly_count || 0);
+  const criticalAnomalyTotal = Number(system.critical_anomaly_count || 0);
+  const loadMs = Number(dashboard._load_elapsed_ms || 0);
+  const jobs = dashboard.jobs?.jobs || [];
+  const runningJobs = jobs.filter(job => job.status === "running").length;
+  const slowJobs = Number(system.slow_job_count || 0);
+  const p95 = system.job_p95_duration_ms == null ? "offen" : `${system.job_p95_duration_ms} ms`;
+  const performanceClass = (
+    loadMs > DASHBOARD_TIMEOUT_MS
+    || slowJobs > 0
+    || system.performance_status === "slow"
+  ) ? "warn" : "ok";
   const cacheLabel = cache.available
     ? `Cache aktuell mit ${cache.entity_count} Entities`
     : "Cache wird nach Discovery aufgebaut";
   status.innerHTML = `
-    <p class="${system.websocket_status === "connected" ? "ok" : "warn"}">
-      Dashboard bereit. WebSocket: ${escapeHtml(system.websocket_status || "unbekannt")}
+    <p class="${performanceClass}">
+      Dashboard bereit in ${escapeHtml(loadMs || "offen")} ms. Budget: ${escapeHtml(system.performance_budget_ms || DASHBOARD_TIMEOUT_MS)} ms.
     </p>
+    <p class="${system.websocket_status === "connected" ? "ok" : "warn"}">WebSocket: ${escapeHtml(system.websocket_status || "unbekannt")}</p>
     <p class="muted">Letzte automatische Prüfung: ${escapeHtml(system.reconciliation_last_completed_at || "noch nicht abgeschlossen")}</p>
   `;
   chips.innerHTML = [
@@ -495,12 +540,38 @@ function renderDashboardStatus(dashboard) {
     `<span class="chip">Aktoren: ${escapeHtml(system.configured_actuators ?? 0)}</span>`,
     `<span class="chip">Lernbereit: ${escapeHtml(system.trained_models ?? 0)}</span>`,
     `<span class="chip">Prüfen: ${escapeHtml(system.review_required ?? 0)}</span>`,
+    `<span class="chip">Jobs aktiv: ${escapeHtml(runningJobs)}</span>`,
+    `<span class="chip">Anomalien: ${escapeHtml(anomalyTotal)}</span>`,
+    `<span class="chip">Kritisch: ${escapeHtml(criticalAnomalyTotal)}</span>`,
   ].join("");
   stats.innerHTML = [
-    `<div class="metric"><strong>Geladene Startdaten</strong>${escapeHtml((dashboard.actuators || []).length)} Geräte</div>`,
+    `<div class="metric"><strong>Geladene Startdaten</strong>${escapeHtml(actuators.length)} Geräte</div>`,
+    `<div class="metric"><strong>Freigabebereit</strong>${escapeHtml(readyCount)} Geräte</div>`,
+    `<div class="metric"><strong>Aktiv / Shadow</strong>${escapeHtml(activeCount)} / ${escapeHtml(shadowCount)}</div>`,
+    `<div class="metric"><strong>Gelernt / Wartet</strong>${escapeHtml(trainedCount)} / ${escapeHtml(pendingCount)}</div>`,
+    `<div class="metric"><strong>Gelernte Handlungen</strong>${escapeHtml(sampleTotal)}</div>`,
+    `<div class="metric"><strong>Performance-Budget</strong>${escapeHtml(system.performance_budget_ms || 3000)} ms</div>`,
+    `<div class="metric"><strong>Job p95</strong>${escapeHtml(p95)}</div>`,
+    `<div class="metric"><strong>Langsame Jobs</strong>${escapeHtml(slowJobs)}</div>`,
+    `<div class="metric"><strong>Anomalien</strong>${escapeHtml(anomalyTotal)} offen</div>`,
     `<div class="metric"><strong>Discovery-Gruppen</strong>${escapeHtml(discoveryGroups.length)} Kategorien</div>`,
     `<div class="metric"><strong>Cache-Zeitpunkt</strong>${escapeHtml(cache.updated_at || "noch offen")}</div>`,
   ].join("");
+  jobsBox.innerHTML = jobs.length ? `
+    <h3>Job-Queue</h3>
+    ${jobs.slice(-6).reverse().map(job => `
+      <div class="decision-row ${Number(job.duration_ms || 0) >= DASHBOARD_TIMEOUT_MS ? "slow" : ""}">
+        <header>
+          <strong>${escapeHtml(job.kind)}${job.target ? `: ${escapeHtml(job.target)}` : ""}</strong>
+          <span class="chip">${escapeHtml(job.status)}${Number(job.duration_ms || 0) >= DASHBOARD_TIMEOUT_MS ? " · langsam" : ""}</span>
+        </header>
+        <p class="muted">${escapeHtml(job.summary || "Keine Zusammenfassung")}</p>
+        <p class="muted">Start: ${escapeHtml(job.started_at || "offen")} · Dauer: ${escapeHtml(job.duration_ms == null ? "läuft/offen" : `${job.duration_ms} ms`)}</p>
+        ${job.error ? `<p class="bad">${escapeHtml(job.error)}</p>` : ""}
+        ${job.status === "failed" ? "<p class='warn'>Retry: Aktion im Dashboard erneut starten; der nächste Lauf schreibt einen neuen Queue-Eintrag.</p>" : ""}
+      </div>
+    `).join("")}
+  ` : "";
 }
 
 async function loadSummaryData() {
@@ -734,7 +805,7 @@ function renderConfiguredActuators() {
     const groupedRows = [...groups.entries()].sort(([left], [right]) => left.localeCompare(right));
     box.innerHTML = rows.length ? `
       ${groupedRows.map(([group, items]) => `
-        <details class="group-panel" open>
+        <details class="group-panel">
         <summary>${escapeHtml(group)} (${items.length})</summary>
         <div class="card-list">
         ${items.map(({record}) => `
@@ -774,9 +845,10 @@ function renderConfiguredActuators() {
 async function showActuator(actuatorId, evaluationMessage = "") {
   currentActuatorId = actuatorId;
   const box = document.getElementById("actuator-detail");
+  renderActuatorDetailShell(actuatorId);
   try {
     const record = await api(`v1/actuators/${encodeURIComponent(actuatorId)}`);
-    await loadContextOptions(actuatorId);
+    contextOptions = [];
     const contexts = [
       record.assignment.selected_numeric_entity_id,
       ...record.assignment.selected_context_entity_ids,
@@ -785,6 +857,62 @@ async function showActuator(actuatorId, evaluationMessage = "") {
       .filter(candidate => contexts.includes(candidate.entity_id))
       .map(candidate => `<li><strong>${escapeHtml(candidate.friendly_name || candidate.entity_id)}</strong>: ${uniqueValues(candidate.evidence).map(escapeHtml).join(", ") || "statistisch relevanter Kandidat"}</li>`)
       .join("");
+    const weightedCandidates = [...record.numeric_candidates, ...record.context_candidates]
+      .filter(candidate => contexts.includes(candidate.entity_id));
+    const weightGroups = record.manual_override?.sensor_weight_groups || [];
+    currentSensorWeightGroups = weightGroups;
+    const weightControls = weightedCandidates.length ? `
+      <div class="card-list">
+        ${weightedCandidates.map(candidate => {
+          const relevance = Math.round((candidate.confidence ?? 0) * 100);
+          const effective = Math.round((candidate.effective_weight ?? 1) * 100);
+          const manual = candidate.manual_weight == null ? effective : Math.round(candidate.manual_weight * 100);
+          return `
+            <article class="actuator-card">
+              <div class="card-title">
+                <div>
+                  <div><strong>${escapeHtml(candidate.friendly_name || candidate.entity_id)}</strong></div>
+                  <div class="entity-id">${escapeHtml(candidate.entity_id)}</div>
+                </div>
+                <span class="chip">${relevance} % relevant</span>
+              </div>
+              <div class="metric-grid">
+                <div class="metric"><strong>Automatische Relevanz</strong>${relevance} %</div>
+                <div class="metric"><strong>Aktive Gewichtung</strong>${effective} %</div>
+                <div class="metric"><strong>Score</strong>${escapeHtml(candidate.score)}</div>
+              </div>
+              <label for="weight-${escapeHtml(candidate.entity_id)}">Gewichtung korrigieren</label>
+              <input id="weight-${escapeHtml(candidate.entity_id)}" data-weight-entity="${escapeHtml(candidate.entity_id)}" type="number" min="0" max="100" step="5" value="${manual}">
+            </article>
+          `;
+        }).join("")}
+      </div>
+      <div class="actions">
+        <button onclick="saveWeightOverrides('${escapeHtml(record.actuator_entity_id)}')">Gewichtungen speichern</button>
+      </div>
+    ` : "<p class='muted'>Noch keine verwendeten Sensoren oder Zustände für eine Gewichtung ausgewählt.</p>";
+    const weightGroupControls = `
+      <details class="manual-context">
+        <summary>Gruppen-Gewichtung</summary>
+        ${weightGroups.length ? `<ul>${weightGroups.map(group => `
+          <li><strong>${escapeHtml(group.name)}</strong>: ${Math.round(group.weight * 100)} %
+          <span class="muted">${group.entity_ids.map(escapeHtml).join(", ")}</span></li>
+        `).join("")}</ul>` : "<p class='muted'>Noch keine Gruppe gespeichert.</p>"}
+        <div class="inline-controls">
+          <div>
+            <label for="weight-group-name">Gruppenname</label>
+            <input id="weight-group-name" placeholder="z. B. Flur Bewegung + Helligkeit">
+          </div>
+          <div>
+            <label for="weight-group-value">Gruppen-Gewicht in %</label>
+            <input id="weight-group-value" type="number" min="0" max="100" step="5" value="100">
+          </div>
+        </div>
+        <label for="weight-group-entities">Entity-IDs der Gruppe</label>
+        <textarea id="weight-group-entities" class="manual-entry" placeholder="Eine oder mehrere Entity-IDs">${escapeHtml(contexts.join("\n"))}</textarea>
+        <button class="secondary" onclick="saveWeightOverrides('${escapeHtml(record.actuator_entity_id)}', true)">Als Gruppe speichern</button>
+      </details>
+    `;
     const currentContextControls = contexts.length
       ? `<ul>${contexts.map(entityId => `
           <li>
@@ -794,6 +922,131 @@ async function showActuator(actuatorId, evaluationMessage = "") {
         `).join("")}</ul>`
       : "<p class='muted'>Noch keine Kontext-Entity ausgewählt.</p>";
     const prediction = record.behavior.prediction;
+    const safety = record.behavior.safety || {};
+    const blockers = record.behavior.safety_blockers || [];
+    const decisionFactors = record.behavior.decision_factors || [];
+    const knowledge = record.behavior.knowledge || [];
+    const assumptions = record.behavior.assumptions || [];
+    const uncertainties = record.behavior.uncertainties || [];
+    const snapshots = record.behavior.model_snapshots || [];
+    const activeModelVersion = record.behavior.active_model_version || "";
+    const adaptiveUpdates = record.behavior.adaptive_weight_updates || [];
+    const automationConflicts = record.behavior.automation_conflicts || [];
+    const timeProfiles = record.behavior.time_profiles || [];
+    const anomalies = (record.behavior.anomalies || []).filter(item => !item.resolved);
+    const safetyControls = `
+      <details class="manual-context" open>
+        <summary>Sicherheit und manuelles Gegensteuern</summary>
+        <div class="inline-controls">
+          <div>
+            <label for="safety-stage">Freigabestufe</label>
+            <select id="safety-stage">
+              ${["observe", "suggest", "shadow", "partial", "active"].map(stage => `
+                <option value="${stage}" ${safety.stage === stage ? "selected" : ""}>${stage}</option>
+              `).join("")}
+            </select>
+          </div>
+          <div>
+            <label for="safety-confidence">Mindest-Sicherheit in %</label>
+            <input id="safety-confidence" type="number" min="0" max="100" step="1" value="${Math.round((safety.min_confidence ?? 0.82) * 100)}">
+          </div>
+          <div>
+            <label for="safety-cooldown">Cooldown Sekunden</label>
+            <input id="safety-cooldown" type="number" min="0" step="10" value="${safety.cooldown_seconds ?? ""}" placeholder="Standard">
+          </div>
+        </div>
+        <label>
+          <input id="safety-manual-block" type="checkbox" ${safety.manual_block ? "checked" : ""}>
+          Manuelle Sicherheitssperre aktiv
+        </label>
+        ${blockers.length ? `<p class="warn">Aktuelle Blocker: ${blockers.map(escapeHtml).join(" ")}</p>` : "<p class='ok'>Keine lokalen Sicherheitsblocker für die aktuelle Vorhersage.</p>"}
+        <button class="secondary" onclick="saveSafetyProfile('${escapeHtml(record.actuator_entity_id)}')">Sicherheitsprofil speichern</button>
+      </details>
+    `;
+    const decisionArchive = `
+      <details class="manual-context" open>
+        <summary>Entscheidungsakte</summary>
+        <div class="grid-two">
+          <div>
+            <h3>Wissen</h3>
+            <ul>${knowledge.map(item => `<li>${escapeHtml(item)}</li>`).join("") || "<li>Keine gesicherten Punkte gespeichert.</li>"}</ul>
+          </div>
+          <div>
+            <h3>Annahmen</h3>
+            <ul>${assumptions.map(item => `<li>${escapeHtml(item)}</li>`).join("") || "<li>Keine Annahmen gespeichert.</li>"}</ul>
+          </div>
+        </div>
+        <h3>Unsicherheit</h3>
+        <ul>${uncertainties.map(item => `<li>${escapeHtml(item)}</li>`).join("") || "<li>Keine Unsicherheit gespeichert.</li>"}</ul>
+        <h3>Beitragsfaktoren</h3>
+        <div class="decision-list">
+          ${decisionFactors.length ? decisionFactors.map(factor => `
+            <div class="decision-row">
+              <header>
+                <strong>${escapeHtml(factor.label)}</strong>
+                <span class="chip">${Math.round((factor.contribution || 0) * 100)} % Beitrag</span>
+              </header>
+              <p class="muted">${escapeHtml(factor.entity_id || factor.factor_type)} · Zustand: ${escapeHtml(factor.state || "offen")} · Gewicht: ${Math.round((factor.weight || 0) * 100)} %</p>
+              <p>${(factor.evidence || []).map(escapeHtml).join(" ")}</p>
+            </div>
+          `).join("") : "<p class='muted'>Noch keine aktuelle Entscheidungsfaktoren berechnet.</p>"}
+        </div>
+      </details>
+    `;
+    const adaptivePanel = `
+      <details class="manual-context">
+        <summary>v1.2 Lernen, Rollback und Konflikte</summary>
+        <h3>Zeitprofile</h3>
+        <div class="metric-grid">
+          ${timeProfiles.length ? timeProfiles.map(profile => `
+            <div class="metric">
+              <strong>${escapeHtml(profile.label)}</strong>
+              ${escapeHtml(profile.sample_count)} Samples · ${escapeHtml(profile.dominant_state || "offen")}
+              <p class="muted">${Math.round((profile.confidence || 0) * 100)} % Profilklarheit</p>
+            </div>
+          `).join("") : "<div class='metric'><strong>Zeitprofile</strong>Noch keine Daten</div>"}
+        </div>
+        <h3>Modell-Snapshots</h3>
+        <div class="decision-list">
+          ${snapshots.length ? snapshots.slice(-5).reverse().map(snapshot => `
+            <div class="decision-row">
+              <header>
+                <strong>${escapeHtml(snapshot.version_id)}</strong>
+                <span class="chip">${snapshot.version_id === activeModelVersion ? "aktiv" : "Rollback möglich"}</span>
+              </header>
+              <p class="muted">${escapeHtml(snapshot.sample_count)} Samples · ${escapeHtml(snapshot.high_confidence_sample_count)} eindeutig · Ø ${Math.round((snapshot.average_confidence || 0) * 100)} %</p>
+              <p>${escapeHtml(snapshot.reason || "Kein Kommentar")}</p>
+              ${snapshot.version_id !== activeModelVersion ? `<button class="secondary compact" onclick="rollbackModel('${escapeHtml(record.actuator_entity_id)}', '${escapeHtml(snapshot.version_id)}')">Rollback</button>` : ""}
+            </div>
+          `).join("") : "<p class='muted'>Noch kein Modell-Snapshot gespeichert.</p>"}
+        </div>
+        <h3>Automatische Gewichtsanpassungen</h3>
+        <ul>${adaptiveUpdates.length ? adaptiveUpdates.slice(-8).reverse().map(update => `
+          <li><code>${escapeHtml(update.entity_id)}</code>: ${Math.round(update.previous_weight * 100)} % → ${Math.round(update.new_weight * 100)} %. ${escapeHtml(update.reason)}</li>
+        `).join("") : "<li>Noch keine automatische Gewichtsanpassung.</li>"}</ul>
+        <h3>Automation-Konflikte</h3>
+        <ul>${automationConflicts.length ? automationConflicts.map(conflict => `
+          <li><code>${escapeHtml(conflict.automation_entity_id)}</code>: <span class="${conflict.severity === "warning" ? "warn" : "muted"}">${escapeHtml(conflict.status)}</span> ${escapeHtml(conflict.reason)}</li>
+        `).join("") : "<li>Keine aktiven Automation-Konflikte erkannt.</li>"}</ul>
+      </details>
+    `;
+    const anomalyPanel = `
+      <details class="manual-context" ${anomalies.length ? "open" : ""}>
+        <summary>v1.3 Anomalie- und Performance-Hinweise</summary>
+        <div class="decision-list">
+          ${anomalies.length ? anomalies.map(anomaly => `
+            <div class="decision-row ${anomaly.severity === "critical" ? "critical" : ""}">
+              <header>
+                <strong>${escapeHtml(anomaly.title)}</strong>
+                <span class="chip">${escapeHtml(anomaly.severity)} · ${escapeHtml(anomaly.category)}</span>
+              </header>
+              <p>${escapeHtml(anomaly.detail)}</p>
+              <p class="muted">Erkannt: ${escapeHtml(anomaly.detected_at || "offen")}</p>
+            </div>
+          `).join("") : "<p class='ok'>Keine offenen Anomalien fuer diesen Aktor.</p>"}
+        </div>
+      </details>
+    `;
     const learnedAutomationActions = record.behavior.patterns.filter(
       pattern => pattern.source === "automation",
     ).length;
@@ -814,7 +1067,7 @@ async function showActuator(actuatorId, evaluationMessage = "") {
       selected: manualContextIds,
     };
     const manualAssignment = `
-      <details class="manual-context" open>
+      <details class="manual-context">
         <summary>Kontext selbst festlegen</summary>
         <p class="muted">Die Vorschläge sind aktorbezogen vorsortiert. Wenn etwas fehlt, trage die Entity-ID unten manuell ein, z. B. PIR, Helligkeit außen, Luftfeuchtigkeit oder Lichtzustände.</p>
         <label for="manual-numeric-select">Optionaler Haupt-Messsensor</label>
@@ -843,7 +1096,7 @@ async function showActuator(actuatorId, evaluationMessage = "") {
         <textarea id="manual-context-freeform" class="manual-entry" placeholder="Eine oder mehrere Entity-IDs, getrennt durch Komma, Leerzeichen oder neue Zeilen">${escapeHtml(manualOnlyIds.join("\n"))}</textarea>
         <div class="actions">
           <button onclick="saveManualAssignment('${escapeHtml(record.actuator_entity_id)}')">Diese Kontext-Auswahl speichern</button>
-          <button class="secondary" onclick="loadContextOptions('${escapeHtml(record.actuator_entity_id)}').then(() => showActuator('${escapeHtml(record.actuator_entity_id)}'))">Vorschläge neu laden</button>
+          <button class="secondary" onclick="hydrateCurrentContextOptions('${escapeHtml(record.actuator_entity_id)}')">Vorschläge neu laden</button>
         </div>
       </details>
     `;
@@ -903,22 +1156,118 @@ async function showActuator(actuatorId, evaluationMessage = "") {
         <button class="secondary" onclick="sendFeedback('${escapeHtml(record.actuator_entity_id)}', true)">Vorhersage korrekt</button>
         <button class="secondary" onclick="sendFeedback('${escapeHtml(record.actuator_entity_id)}', false)">Vorhersage falsch</button>
       </div>
+      ${safetyControls}
+      ${decisionArchive}
+      ${adaptivePanel}
+      ${anomalyPanel}
       <h3>Passende Home-Assistant-Automationen</h3>
       <p class="muted">Bei einer Übernahme pausiert SillyHome diese Automationen. Beim Stoppen können sie gezielt fortgesetzt werden.</p>
       <button class="secondary compact" onclick="refreshRelatedAutomations('${escapeHtml(record.actuator_entity_id)}')">Automationen neu suchen</button>
       ${automationControls}
       <h3>Welche Zusammenhänge automatisch verwendet werden</h3>
       ${evidence ? `<ul>${evidence}</ul>` : "<p class='warn'>Noch kein geeigneter Kontext erkannt. SillyHome prüft bei neuen HA-Daten erneut.</p>"}
+      <h3>Sensor-Gewichtung</h3>
+      <p class="muted">Automatische Relevanz kommt aus der Zuordnung. Die aktive Gewichtung kannst du korrigieren; Gruppen bündeln mehrere Sensoren/Zustände.</p>
+      ${weightControls}
+      ${weightGroupControls}
       <h3>Verwendete Sensoren/Zustände ändern</h3>
       ${currentContextControls}
       ${manualAssignment}
     `;
+    void hydrateContextOptions(record);
     document.getElementById("detail").scrollIntoView({behavior: "smooth", block: "start"});
   } catch (error) {
     box.textContent = error.message;
   }
 }
 
+function renderActuatorDetailShell(actuatorId) {
+  document.getElementById("actuator-detail").innerHTML = `
+    <div class="detail-header">
+      <div>
+        <h3>${escapeHtml(actuatorId)}</h3>
+        <p class="muted">Basisdaten werden geladen ...</p>
+      </div>
+    </div>
+    <div class="metric-grid">
+      <div class="metric"><strong>Phase 1</strong>Aktuelle Einstellung</div>
+      <div class="metric"><strong>Phase 2</strong>Lernstand</div>
+      <div class="metric"><strong>Phase 3</strong>Kontextvorschläge</div>
+    </div>
+  `;
+}
+
+async function hydrateContextOptions(record) {
+  await loadContextOptions(record.actuator_entity_id);
+  const manualContextSelect = document.getElementById("manual-context-select");
+  const numericSelect = document.getElementById("manual-numeric-select");
+  const categorySelect = document.getElementById("manual-context-category");
+  if (!manualContextSelect || !numericSelect || !categorySelect) return;
+  const manualContextIds = new Set(record.assignment.selected_context_entity_ids || []);
+  const numericOptions = contextOptions.filter(entity => entity.domain === "sensor");
+  const contextCategories = [...new Set(contextOptions
+    .filter(entity => entity.entity_id !== record.actuator_entity_id)
+    .map(categoryForEntity))]
+    .sort();
+  manualContextState = {
+    options: contextOptions.filter(entity => entity.entity_id !== record.actuator_entity_id),
+    selected: manualContextIds,
+  };
+  numericSelect.innerHTML = `
+    <option value="">Keinen numerischen Hauptsensor verwenden</option>
+    ${optionGroups(numericOptions, new Set([record.assignment.selected_numeric_entity_id].filter(Boolean)))}
+  `;
+  categorySelect.innerHTML = `
+    <option value="">Alle relevanten Vorschläge</option>
+    ${contextCategories.map(category => `<option value="${escapeHtml(category)}">${escapeHtml(category)}</option>`).join("")}
+  `;
+  renderManualContextSelect();
+}
+
+async function hydrateCurrentContextOptions(actuatorId) {
+  const record = await api(`v1/actuators/${encodeURIComponent(actuatorId)}`);
+  await hydrateContextOptions(record);
+}
+
+async function saveWeightOverrides(actuatorId, includeNewGroup = false) {
+  const sensorWeights = {};
+  for (const input of document.querySelectorAll("[data-weight-entity]")) {
+    const value = Number(input.value);
+    if (Number.isFinite(value)) {
+      sensorWeights[input.dataset.weightEntity] = Math.max(0, Math.min(100, value)) / 100;
+    }
+  }
+  const groups = [...currentSensorWeightGroups];
+  if (includeNewGroup) {
+    const name = document.getElementById("weight-group-name")?.value.trim();
+    const value = Number(document.getElementById("weight-group-value")?.value || 100);
+    const entityIds = parseEntityIds(document.getElementById("weight-group-entities")?.value || "");
+    if (name && entityIds.length) {
+      groups.push({
+        group_id: name.toLowerCase().replace(/[^a-z0-9]+/g, "_").replace(/^_+|_+$/g, "").slice(0, 64) || "gruppe",
+        name,
+        entity_ids: entityIds,
+        weight: Math.max(0, Math.min(100, Number.isFinite(value) ? value : 100)) / 100,
+      });
+    }
+  }
+  try {
+    await api(`v1/actuators/${encodeURIComponent(actuatorId)}/weights`, {
+      method: "POST",
+      body: JSON.stringify({
+        sensor_weights: sensorWeights,
+        sensor_weight_groups: groups,
+        note: "Gewichtung im Dashboard korrigiert",
+      }),
+    });
+    invalidateDashboardCache();
+    await loadConfiguredActuators();
+    await showActuator(actuatorId, "Sensor-Gewichtung gespeichert.");
+  } catch (error) {
+    alert(error.message);
+  }
+}
+
 async function saveManualAssignment(actuatorId) {
   const numericEntityId = document.getElementById("manual-numeric-select").value || null;
   const selectedContextIds = Array.from(
@@ -1013,6 +1362,51 @@ async function sendFeedback(actuatorId, correct) {
   }
 }
 
+async function saveSafetyProfile(actuatorId) {
+  const confidence = Number(document.getElementById("safety-confidence")?.value || 82);
+  const cooldownRaw = document.getElementById("safety-cooldown")?.value || "";
+  const cooldown = cooldownRaw === "" ? null : Math.max(0, Number(cooldownRaw));
+  const profile = {
+    stage: document.getElementById("safety-stage")?.value || "shadow",
+    manual_block: Boolean(document.getElementById("safety-manual-block")?.checked),
+    min_confidence: Math.max(0, Math.min(100, Number.isFinite(confidence) ? confidence : 82)) / 100,
+    cooldown_seconds: Number.isFinite(cooldown) ? cooldown : null,
+    rules: [
+      {rule_id: "activation_ready", label: "Nur nach Lernfreigabe aktiv schalten", enabled: true, blocking: true, reason: "Der Aktor muss genug eindeutiges Verhalten gelernt haben."},
+      {rule_id: "confidence_threshold", label: "Mindest-Sicherheit einhalten", enabled: true, blocking: true, reason: "Vorhersagen unter der Schaltschwelle bleiben im Shadow-Modus."},
+      {rule_id: "cooldown", label: "Sicherheits-Cooldown gegen Hin-und-her-Schalten", enabled: true, blocking: true, reason: "Gleiche Zielzustände werden nicht zu schnell wiederholt."},
+      {rule_id: "manual_block", label: "Manuelle Sperre respektieren", enabled: true, blocking: true, reason: "Nutzer können jeden Aktor sofort blockieren."},
+    ],
+    note: "Sicherheitsprofil im Dashboard gespeichert",
+  };
+  try {
+    await api(`v1/actuators/${encodeURIComponent(actuatorId)}/safety`, {
+      method: "POST",
+      body: JSON.stringify({safety: profile}),
+    });
+    invalidateDashboardCache();
+    await loadConfiguredActuators();
+    await showActuator(actuatorId, "Sicherheitsprofil gespeichert.");
+  } catch (error) {
+    alert(error.message);
+  }
+}
+
+async function rollbackModel(actuatorId, versionId) {
+  if (!confirm(`${actuatorId}: wirklich auf Modell ${versionId} zurückrollen?`)) return;
+  try {
+    await api(`v1/actuators/${encodeURIComponent(actuatorId)}/model/rollback`, {
+      method: "POST",
+      body: JSON.stringify({version_id: versionId}),
+    });
+    invalidateDashboardCache();
+    await loadConfiguredActuators();
+    await showActuator(actuatorId, `Rollback auf ${versionId} ausgeführt.`);
+  } catch (error) {
+    alert(error.message);
+  }
+}
+
 async function setActivation(actuatorId, active, pauseMatchingAutomations, restorePausedAutomations) {
   const question = active
     ? pauseMatchingAutomations
@@ -1083,7 +1477,16 @@ async function removeActuator(actuatorId) {
   }
 }
 
-loadOverview();
+async function startDashboard() {
+  document.getElementById("status").innerHTML = "<p class='muted'>Status lädt nach ...</p>";
+  document.getElementById("configured-actuators").innerHTML = "<div class='empty-state'>Geräte werden nach dem Status geladen.</div>";
+  document.getElementById("actuator-detail").innerHTML = "<div class='empty-state'>Wähle später ein Gerät aus der Übersicht.</div>";
+  await new Promise(resolve => requestAnimationFrame(resolve));
+  await loadStatus();
+  await loadOverview();
+}
+
+void startDashboard();
 </script>
 </body>
 </html>

docs/V1_0_0_OPERATING_GUIDE.md

@@ -4,6 +4,10 @@ Diese Version stabilisiert den produktiven Kern: schnelle Dashboard-Nutzung,
 lokales Caching, klare Aktor-/Sensor-Kategorien und nachvollziehbare Freigabe
 gelernter Aktionen.
 
+Die detaillierte Abnahme steht in
+[`V1_0_ACCEPTANCE.md`](V1_0_ACCEPTANCE.md). Dort sind erledigte, teilweise
+erledigte und fuer v1.0.x offene Punkte getrennt dokumentiert.
+
 ## Grundprinzip
 
 - Home Assistant bleibt die Quelle fuer aktuelle States und Services.
@@ -97,6 +101,21 @@ wget -qO /tmp/summary.json http://58adbe1e-sillyhome-next:8000/v1/actuators/summ
 wget -qO /tmp/dashboard.json http://58adbe1e-sillyhome-next:8000/v1/actuators/dashboard
 ```
 
+Wenn der Add-on-Container aus dem Agent-Host nicht direkt routbar ist, gilt der
+Home-Assistant-Supervisor als Verifikationsquelle:
+
+- Add-on-Info pruefen: Version, `version_latest`, `update_available`, `state`,
+  `boot` und `watchdog`.
+- Vor Updates eine Home-Assistant-Teil-Sicherung fuer **SillyHome Next**
+  erstellen.
+- Nach einem Store-Reload und Update muss `version == version_latest`,
+  `update_available == false`, `state == started`, `boot == auto` und
+  `watchdog == true` gelten.
+- Den HA-/Ingress-Tab nach jedem Update hart neu laden, weil Home Assistant
+  sonst alte HTML-/JavaScript-Ressourcen aus dem bestehenden Tab verwenden kann.
+- Rollback erfolgt ueber die vorherige Add-on-Teil-Sicherung oder den letzten
+  Git-Tag; beide Referenzen im Release-/Abnahmeprotokoll notieren.
+
 ## Rollback
 
 Der stabile Vor-1.0-Stand ist `v0.7.21`. Vor dem 1.0.0-Umbau wurde ein

docs/V1_0_ACCEPTANCE.md

@@ -0,0 +1,82 @@
+# SillyHome Next v1.0 Acceptance
+
+Stand: 2026-06-17
+
+Diese Abnahme trennt belegte Umsetzung von offenen v1.0.x-Nacharbeiten. Der
+Funktionskern bleibt aktorzentriert: Nutzer waehlen Aktoren, SillyHome lernt
+Kontext und Verhalten, laeuft zuerst im Shadow-Modus und schaltet erst nach
+expliziter Freigabe.
+
+## Erfuellt
+
+- Versioniert, gepusht und installiert:
+  - `v1.0.0`: API-/Cache-Umbau
+  - `v1.0.1`: Dashboard-/Performance-Korrektur
+- Startpfad:
+  - `/v1/actuators/dashboard` liefert lokale Startdaten aus Store und Cache.
+  - Dashboard blockiert nicht mehr auf Discovery, Vorschlaegen oder
+    Automation-Refresh.
+  - Frontend bricht den Startdaten-Request nach 4,5 Sekunden ab und bleibt
+    bedienbar.
+- Cache:
+  - HA-Entity-Metadaten werden als `ha_entity_cache.json` gespeichert.
+  - Summary und Dashboard verwenden Friendly Name, Area und Device aus Cache.
+- Keine externen Abfragen im Dashboard-Startpfad:
+  - Kein Cloud-Ping, keine Fremd-API.
+  - HA-Zugriffe bleiben lokal gegen Home Assistant.
+- Dashboard:
+  - Orange ist Primaerfarbe.
+  - Cyan ist sichtbare Komplementaerfarbe.
+  - Rote UI-Flaechen wurden entfernt.
+  - Steuerung, beobachtete Geraete, Lernfortschritt/Freigabe und Systemstatus
+    sind getrennte Bereiche.
+  - Discovery, Vorschlaege und Automation-Suche laden erst bei Nutzeraktion.
+- Lernfortschritt und Freigabe:
+  - Karten zeigen Modus, Status, Handlungen, Vorhersage und Freigabestatus.
+  - Detailansicht zeigt Zuordnung, Sicherheit, Lernstand, Vorhersage,
+    Feedback, passende HA-Automationen und verwendete Sensoren/Zustaende.
+- Direkte HA-Nutzung:
+  - Aktor-Schaltungen laufen ueber Home-Assistant-Serviceaufrufe.
+  - Automation-Steuerung nutzt Home-Assistant-Endpunkte und gecachte
+    Automation-Metadaten.
+- Qualitaet:
+  - `pytest -q`
+  - `ruff check .`
+  - `mypy app backend tests`
+  - `git diff --check`
+- Performance-Budget:
+  - Automatisierter Test prueft Root-HTML und `/v1/actuators/dashboard` gegen
+    das 5-Sekunden-Budget mit kontrollierten Fake-HA-/Cache-Daten.
+- HA-/Ingress-Verifikation:
+  - Supervisor-Update, Add-on-Status, Watchdog, Backup, Ingress-Hard-Reload
+    und Rollback sind im Operating Guide dokumentiert.
+
+## Teilweise Erfuellt
+
+- Bessere Statistik:
+  - Startbereich zeigt Aktoren, Freigabebereitschaft, Aktiv/Shadow,
+    Gelernt/Wartet, gelernte Handlungen, Discovery-Gruppen und Cache-Zeitpunkt.
+  - Noch offen: Verlaufsgrafiken, p95-Latenzen und Trendstatistik je Aktor.
+- Kontrollierte Abarbeitung und Queue:
+  - Reconciliation/Training laufen kontrolliert im Prozess und sind testbar.
+  - Noch offen: sichtbare Job-Queue mit Laufzeit, Fehlern und Retry-Status im
+    Dashboard.
+- Saubere Issues:
+  - v1.0.0-Issues #41 bis #47 wurden geschlossen.
+  - Rueckblickend waren sie zu grob; v1.0.x bekommt feinere Folgeissues fuer
+    Statistik, Queue-Sichtbarkeit und Performance-Budgets.
+
+## Offen Fuer v1.0.x
+
+- Dashboard-Jobstatus fuer Reconciliation, Training, Discovery und
+  Automation-Refresh.
+- Mehr Entscheidungsstatistik pro Aktor: welche Sensoren wie stark
+  beigetragen haben, wie sich Confidence und Sample Count entwickeln.
+
+## Rollback
+
+- Git-Bundle-Backups liegen unter
+  `/root/.openclaw/workspace/backups/sillyhome-next/`.
+- Vor `v1.0.1` wurde ein Home-Assistant-Teilbackup des Add-ons angelegt.
+  Referenz: `18a5b387`.
+- Letzter Vor-1.0-Stand: `v0.7.21`.

docs/V1_1_0_OPERATING_GUIDE.md

@@ -0,0 +1,72 @@
+# SillyHome Next v1.1.0 Operating Guide
+
+## Ziel
+
+v1.1.0 macht das Dashboard zur Zentrale fuer Visualisierung, Einrichtung,
+Sicherheit und manuelles Gegensteuern. Autonomes Schalten bleibt ein kurzer
+lokaler Pfad: Vorhersage und Safety-Profil werden aus bereits vorhandenen Daten
+bewertet, danach folgt direkt der Home-Assistant-Serviceaufruf.
+
+## Sicherheitsmodell
+
+Jeder Aktor hat ein Safety-Profil:
+
+- `stage`: Beobachten, Vorschlagen, Shadow, Teilaktiv oder Aktiv.
+- `manual_block`: harte manuelle Sperre.
+- `min_confidence`: Mindest-Sicherheit fuer autonomes Schalten.
+- `cooldown_seconds`: optionaler Aktor-Cooldown gegen schnelles Hin-und-her.
+- Safety-Regeln: Freigabe, Confidence, Cooldown und manuelle Sperre.
+
+Ein Aktor schaltet nur, wenn alle lokalen Safety-Regeln frei sind, der
+Behavior-Modus aktiv ist, die Freigabe bereit ist, die Confidence passt, der
+Zielzustand noch nicht erreicht ist und der Cooldown abgelaufen ist.
+
+## Transparenz
+
+Die Aktor-Detailansicht trennt:
+
+- Wissen: belegte Fakten aus Historie, Zuordnung und Automationen.
+- Annahmen: heuristische Schluesse wie Zeit-/Kontext-Aehnlichkeit.
+- Unsicherheiten: geringe Datenmenge, unklare Quellen, Review-Bedarf oder
+  negatives Feedback.
+- Beitragsfaktoren: Sensoren, Kontextsignale, aktive Gewichtung und Beitrag.
+- Safety-Blocker: Gruende, warum nicht geschaltet wird.
+
+## Job-Queue
+
+Das Dashboard zeigt die letzten Jobs mit Status, Dauer, Fehler und
+Zusammenfassung. Sichtbar sind:
+
+- Discovery
+- Reconciliation
+- Training
+- Evaluation
+- Automation-Refresh
+
+Die Queue ist persistent in `job_queue.json` und dient als Betriebsanzeige. Sie
+blockiert nicht den Startpfad und nicht den Schaltpfad.
+
+## Manuelles Gegensteuern
+
+Im Dashboard koennen pro Aktor gesetzt werden:
+
+- manuelle Sicherheitssperre
+- Freigabestufe
+- Mindest-Confidence
+- optionaler Cooldown
+- Sensor-Gewichtungen und Gruppen-Gewichtungen
+- Kontextauswahl
+- Feedback: Vorhersage korrekt/falsch
+- HA-Automationen pausieren/fortsetzen
+
+## Qualitaetspruefung
+
+Vor Release:
+
+```bash
+.venv/bin/pytest -q
+.venv/bin/ruff check .
+.venv/bin/mypy app backend tests
+git diff --check
+node --check /tmp/sillyhome-dashboard.js
+```

docs/V1_2_0_OPERATING_GUIDE.md

@@ -0,0 +1,62 @@
+# SillyHome Next v1.2.0 Operating Guide
+
+## Ziel
+
+v1.2.0 erweitert die sichere v1.1-Grundlage um adaptive Lernfunktionen. Diese
+Funktionen laufen bei Feedback, Training oder Automation-Refresh und blockieren
+nicht den direkten Schaltpfad.
+
+## Adaptive Gewichtung
+
+Feedback passt die Gewichtung aktuell beteiligter Kontextsignale vorsichtig an:
+
+- korrektes Feedback: +3 Prozentpunkte bis maximal 100 %
+- falsches Feedback: -8 Prozentpunkte bis minimal 10 %
+
+Die Aenderungen werden als `adaptive_weight_updates` gespeichert und im
+Dashboard angezeigt. Manuelle Gewichtungen bleiben weiter direkt korrigierbar.
+
+## Modell-Snapshots und Rollback
+
+Bei jedem Training wird ein Snapshot gespeichert:
+
+- Version-ID
+- Sample Count
+- eindeutig zugeordnete Handlungen
+- durchschnittliche Confidence
+- negative Feedbacks
+- Musterliste
+- Begruendung
+
+Ueber das Dashboard kann auf einen frueheren Snapshot zurueckgerollt werden.
+
+## Automation-Konflikte
+
+Beim Automation-Refresh markiert SillyHome Konflikte, wenn:
+
+- SillyHome fuer einen Aktor aktiv ist
+- eine passende Home-Assistant-Automation ebenfalls aktiv bleibt
+
+Pausierte Automationen werden als kontrolliert markiert.
+
+## Zeitprofile
+
+SillyHome bildet Profile fuer:
+
+- Nacht
+- Morgen
+- Tag
+- Abend
+- Wochenende
+
+Diese Profile zeigen Sample Count, dominanten Zielzustand und Profilklarheit.
+
+## Performance-Grenze
+
+v1.2-Funktionen duerfen den Schaltmoment nicht verlangsamen. Der direkte
+Schaltpfad bleibt:
+
+1. vorhandene aktuelle States nutzen
+2. lokale Safety-Pruefung
+3. direkter Home-Assistant-Serviceaufruf
+4. Persistenz der Entscheidung

docs/V1_3_0_OPERATING_GUIDE.md

@@ -0,0 +1,68 @@
+# SillyHome Next v1.3.0 Operating Guide
+
+v1.3.0 ergänzt die v1.2-Lernfunktionen um Anomalie-Erkennung und
+Performance-Überwachung. Das Dashboard bleibt Visualisierung und Einrichtung;
+der direkte Schaltpfad bleibt kurz und führt vor dem Home-Assistant-Service-Call
+keine Discovery, kein Training und keine Modellanalyse aus.
+
+## Performance-Budget
+
+- Dashboard-Start und `/v1/actuators/dashboard` haben ein Budget von 3000 ms.
+- Das Dashboard zeigt die eigene Ladezeit, das aktive Budget, Job-p95 und die
+  Anzahl langsamer Jobs.
+- Jobs ab 3000 ms werden in der Job-Queue als langsam markiert.
+- Der automatisierte API-Test prüft den Root- und Dashboard-Startpfad gegen das
+  3-Sekunden-Budget.
+
+## Anomalie-Erkennung
+
+Anomalien werden pro Aktor gespeichert und im Aktor-Detail angezeigt. Erkannt
+werden aktuell:
+
+- fehlender Sensor-/Kontextbezug
+- zu wenige Lernbeispiele
+- unklare Quellen historischer Schaltungen
+- veraltetes Training
+- Vorhersagen unter der Sicherheitsgrenze
+- aktive manuelle Sicherheitssperren
+- Safety-Blocker
+- parallele HA-Automationen bei aktivem SillyHome
+- hohe negative Feedbackquote
+
+Die Anomalien sind Hinweise für Setup und manuelles Gegensteuern. Sie lösen
+keine automatische Eskalation und keine langsamere Schaltung aus.
+
+## API
+
+- `GET /v1/actuators/dashboard` liefert jetzt zusätzlich:
+  - `performance_budget_ms`
+  - `job_p95_duration_ms`
+  - `slow_job_count`
+  - `performance_status`
+  - `anomaly_count`
+  - `critical_anomaly_count`
+- `GET /v1/actuators/anomalies` liefert offene Anomalien gruppiert nach Aktor.
+
+## Betrieb
+
+Bei Ladezeiten ab 3 Sekunden gilt die Seite als nicht performant. Dann zuerst
+prüfen:
+
+1. Dashboard-Statistik: Ladezeit, Job-p95, langsame Jobs.
+2. Job-Queue: welche Aktion langsam war.
+3. Aktor-Detail: Anomalien, Safety-Blocker und Automation-Konflikte.
+4. Falls Discovery oder Training langsam war: nicht in den Startpfad ziehen,
+   sondern geplant, manuell oder über Queue laufen lassen.
+
+## Qualität
+
+Vor Release/Installation ausführen:
+
+```bash
+pytest -q
+ruff check .
+mypy app backend tests
+git diff --check
+```
+
+Zusätzlich das eingebettete Dashboard-JavaScript mit `node --check` prüfen.

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "sillyhome-next"
-version = "1.0.1"
+version = "1.3.0"
 description = "Lokales Smart-Home-Intelligenzsystem für Home Assistant"
 requires-python = ">=3.11"
 dependencies = [

tests/api/test_actuators.py

@@ -1,11 +1,13 @@
 from __future__ import annotations
 
-from datetime import datetime, timedelta
+from time import perf_counter
+from datetime import datetime, timedelta, timezone
 from pathlib import Path
 
 from fastapi.testclient import TestClient
 
 from app.actuators.lifecycle import ActuatorReconciliationService
+from app.actuators.models import JobStatus, ModelSnapshot
 from app.actuators.store import ActuatorStore
 from app.behavior.engine import BehaviorEngine
 from app.config import Settings
@@ -29,6 +31,7 @@ class FakeHaReader(HaReader):
         self._entities = entities
         self._history = history
         self.read_entities_calls = 0
+        self.service_calls: list[tuple[str, str, dict[str, object]]] = []
 
     def read_entities(self) -> list[HaEntitySummary]:
         self.read_entities_calls += 1
@@ -85,6 +88,7 @@ class FakeHaReader(HaReader):
         service: str,
         service_data: dict[str, object],
     ) -> list[object]:
+        self.service_calls.append((domain, service, service_data))
         return []
 
     def find_automations_for_entity(
@@ -110,6 +114,7 @@ def _install_service(tmp_path: Path) -> None:
             unit_of_measurement="lx",
             friendly_name="Abstellkammer Helligkeit",
             area_name="Abstellkammer",
+            state="12",
         ),
         HaEntitySummary(
             entity_id="binary_sensor.abstellkammer_motion",
@@ -117,6 +122,7 @@ def _install_service(tmp_path: Path) -> None:
             device_class="motion",
             friendly_name="Abstellkammer Bewegung",
             area_name="Abstellkammer",
+            state="off",
         ),
         HaEntitySummary(
             entity_id="sensor.pfsense_interface_vpn_inbytes",
@@ -215,6 +221,136 @@ def test_manual_assignment_endpoint_updates_context(tmp_path: Path) -> None:
     ]
 
 
+def test_weight_override_endpoint_updates_sensor_relevance(tmp_path: Path) -> None:
+    with TestClient(app) as client:
+        _install_service(tmp_path)
+        client.post("/v1/actuators", json={"actuator_entity_id": "light.abstellkammer"})
+        client.post(
+            "/v1/actuators/light.abstellkammer/assignment",
+            json={
+                "numeric_entity_id": "sensor.abstellkammer_illuminance",
+                "context_entity_ids": ["binary_sensor.abstellkammer_motion"],
+            },
+        )
+
+        response = client.post(
+            "/v1/actuators/light.abstellkammer/weights",
+            json={
+                "sensor_weights": {
+                    "sensor.abstellkammer_illuminance": 0.75,
+                    "binary_sensor.abstellkammer_motion": 0.5,
+                },
+                "sensor_weight_groups": [
+                    {
+                        "group_id": "abstellkammer_context",
+                        "name": "Abstellkammer Kontext",
+                        "entity_ids": [
+                            "sensor.abstellkammer_illuminance",
+                            "binary_sensor.abstellkammer_motion",
+                        ],
+                        "weight": 0.8,
+                    }
+                ],
+                "note": "Gewichtung korrigiert",
+            },
+        )
+
+    assert response.status_code == 200
+    payload = response.json()
+    assert payload["manual_override"]["sensor_weights"]["sensor.abstellkammer_illuminance"] == 0.75
+    assert payload["manual_override"]["sensor_weight_groups"][0]["group_id"] == (
+        "abstellkammer_context"
+    )
+    numeric = {
+        candidate["entity_id"]: candidate
+        for candidate in payload["numeric_candidates"]
+    }
+    assert numeric["sensor.abstellkammer_illuminance"]["manual_weight"] == 0.75
+    assert numeric["sensor.abstellkammer_illuminance"]["effective_weight"] == 0.75
+
+
+def test_safety_profile_can_block_actuator_manually(tmp_path: Path) -> None:
+    with TestClient(app) as client:
+        _install_service(tmp_path)
+        client.post("/v1/actuators", json={"actuator_entity_id": "light.abstellkammer"})
+
+        response = client.post(
+            "/v1/actuators/light.abstellkammer/safety",
+            json={
+                "safety": {
+                    "stage": "shadow",
+                    "manual_block": True,
+                    "min_confidence": 0.9,
+                    "cooldown_seconds": 120,
+                    "rules": [
+                        {
+                            "rule_id": "manual_block",
+                            "label": "Manuelle Sperre respektieren",
+                            "enabled": True,
+                            "blocking": True,
+                            "reason": "Test",
+                        }
+                    ],
+                    "note": "Test",
+                }
+            },
+        )
+
+    assert response.status_code == 200
+    payload = response.json()
+    assert payload["behavior"]["safety"]["manual_block"] is True
+    assert payload["behavior"]["safety"]["min_confidence"] == 0.9
+    assert payload["behavior"]["safety"]["cooldown_seconds"] == 120
+
+
+def test_feedback_adapts_sensor_weights_and_model_can_rollback(tmp_path: Path) -> None:
+    with TestClient(app) as client:
+        _install_service(tmp_path)
+        client.post(
+            "/v1/actuators",
+            json={"actuator_entity_id": "light.abstellkammer"},
+        )
+        record = app.state.actuator_store.get("light.abstellkammer")
+        version_id = "model-test"
+        snapshot = ModelSnapshot(
+            version_id=version_id,
+            sample_count=1,
+            high_confidence_sample_count=1,
+            average_confidence=0.9,
+            patterns=[],
+            reason="Test-Snapshot",
+        )
+        app.state.actuator_store.upsert(
+            record.model_copy(
+                update={
+                    "behavior": record.behavior.model_copy(
+                        update={
+                            "model_snapshots": [snapshot],
+                            "active_model_version": "model-current",
+                            "sample_count": 2,
+                        }
+                    )
+                }
+            )
+        )
+
+        feedback = client.post(
+            "/v1/actuators/light.abstellkammer/feedback",
+            json={"correct": False, "expected_state": "off"},
+        )
+        rollback = client.post(
+            "/v1/actuators/light.abstellkammer/model/rollback",
+            json={"version_id": version_id},
+        )
+
+    assert feedback.status_code == 200
+    feedback_payload = feedback.json()
+    assert feedback_payload["behavior"]["adaptive_weight_updates"]
+    assert feedback_payload["manual_override"]["sensor_weights"]
+    assert rollback.status_code == 200
+    assert rollback.json()["behavior"]["active_model_version"] == version_id
+
+
 def test_summary_is_lightweight_and_uses_cached_entity_metadata(tmp_path: Path) -> None:
     with TestClient(app) as client:
         _install_service(tmp_path)
@@ -249,6 +385,76 @@ def test_dashboard_overview_uses_cache_without_ha_roundtrip(tmp_path: Path) -> N
     assert payload["cache"]["entity_count"] == 4
     assert payload["actuators"][0]["friendly_name"] == "Abstellkammer Licht"
     assert payload["discovery_groups"]
+    assert payload["jobs"]["jobs"][-1]["kind"] == "discovery"
+
+
+def test_reconciliation_run_records_visible_job_queue(tmp_path: Path) -> None:
+    with TestClient(app) as client:
+        _install_service(tmp_path)
+        client.post("/v1/actuators", json={"actuator_entity_id": "light.abstellkammer"})
+
+        response = client.post("/v1/actuators/reconciliation/run")
+        jobs = client.get("/v1/actuators/job-queue/state")
+
+    assert response.status_code == 200
+    assert jobs.status_code == 200
+    payload = jobs.json()
+    assert [job["kind"] for job in payload["jobs"][-3:]] == [
+        "reconciliation",
+        "training",
+        "evaluation",
+    ]
+    assert payload["jobs"][-1]["status"] == "completed"
+
+
+def test_dashboard_start_path_stays_within_three_second_budget(tmp_path: Path) -> None:
+    with TestClient(app) as client:
+        _install_service(tmp_path)
+        client.get("/v1/actuators/discovery")
+        client.post("/v1/actuators", json={"actuator_entity_id": "light.abstellkammer"})
+
+        root_started_at = perf_counter()
+        root_response = client.get("/")
+        root_elapsed = perf_counter() - root_started_at
+
+        dashboard_started_at = perf_counter()
+        dashboard_response = client.get("/v1/actuators/dashboard")
+        dashboard_elapsed = perf_counter() - dashboard_started_at
+
+    assert root_response.status_code == 200
+    assert dashboard_response.status_code == 200
+    assert root_elapsed < 3.0
+    assert dashboard_elapsed < 3.0
+
+
+def test_dashboard_reports_performance_budget_and_anomalies(tmp_path: Path) -> None:
+    with TestClient(app) as client:
+        _install_service(tmp_path)
+        client.get("/v1/actuators/discovery")
+        client.post("/v1/actuators", json={"actuator_entity_id": "light.abstellkammer"})
+        store = app.state.actuator_store
+        job = store.start_job(kind="training", trigger="test", summary="Langsamer Testjob")
+        queue = store.load_job_queue()
+        queue.jobs = [
+            item.model_copy(update={"started_at": datetime.now(timezone.utc) - timedelta(seconds=4)})
+            if item.job_id == job.job_id
+            else item
+            for item in queue.jobs
+        ]
+        store._persist_job_queue(queue)
+        store.finish_job(job.job_id, status=JobStatus.COMPLETED, summary="Fertig")
+
+        dashboard_response = client.get("/v1/actuators/dashboard")
+        anomalies_response = client.get("/v1/actuators/anomalies")
+
+    assert dashboard_response.status_code == 200
+    system = dashboard_response.json()["system"]
+    assert system["performance_budget_ms"] == 3000
+    assert system["slow_job_count"] == 1
+    assert system["performance_status"] == "slow"
+    assert system["anomaly_count"] >= 1
+    assert anomalies_response.status_code == 200
+    assert anomalies_response.json()
 
 
 def test_discovery_reads_entities_once_and_reuses_them(tmp_path: Path) -> None: