feat(active): Proaktive Suche (Cron 4h), Aufgaben-Tracking, Heartbeat-Integration, Stop-Logik

.streamlit/secrets.toml

@@ -0,0 +1 @@
+[default]

src/app_dashboard.py

@@ -1,174 +1,210 @@
 """
 app_dashboard.py - Streamlit-Dashboard für Second Brain.
-Seiten: Übersicht, Engramme, Suche, Graph, Stats.
+Seiten: Übersicht, Engramme, Suche, Graph, Heal-Log, Neural Scorer.
 """
 
 import json
 import sys
+import os
 from pathlib import Path
 
 import streamlit as st
 
-sys.path.insert(0, str(Path(__file__).resolve().parent))
+_root = Path(__file__).resolve().parent.parent
+sys.path.insert(0, str(_root))
 
 from src.engram import Engram
 from src.store import EngramStore
 from src.chroma_store import ChromaStore
 from src.retriever import Retriever
 from src.neural_scorer import NeuralScorer
+from src.graph_view import generate_graph_html
+from src.loop_detector import LoopDetector
+from src.error_healer import ErrorHealer
 
-_DEFAULT_DB = Path(__file__).resolve().parent.parent / "data" / "brain.sqlite"
-_DB_PATH = str(st.secrets.get("db_path", _DEFAULT_DB) if hasattr(st, "secrets") else _DEFAULT_DB)
+_DEFAULT_DB = _root / "data" / "brain.sqlite"
 
 
+@st.cache_resource
 def _store():
-    return EngramStore(_DB_PATH)
+    return EngramStore(str(_DEFAULT_DB))
 
 
+@st.cache_resource
 def _chroma():
-    p = Path(_DB_PATH).parent / "chroma"
+    p = Path(str(_DEFAULT_DB)).parent / "chroma"
     return ChromaStore(str(p))
 
 
+_retriever_cache = None
 def _retriever():
-    return Retriever(_store(), _chroma())
+    global _retriever_cache
+    if _retriever_cache is None:
+        _retriever_cache = Retriever(_store(), _chroma())
+    return _retriever_cache
 
 
+@st.cache_resource
 def _scorer():
     return NeuralScorer()
 
 
-st.set_page_config(page_title="Second Brain Dashboard", layout="wide")
-st.title("🧠 Second Brain Dashboard")
+@st.cache_resource
+def _healer():
+    return ErrorHealer(_store())
 
-page = st.sidebar.radio("Seite", ["Übersicht", "Engramme", "Suche", "Graph", "Stats", "Neural Scorer"])
+
+st.set_page_config(page_title="Second Brain Dashboard", layout="wide")
+st.title("🧠 2.Brain v0.3.1")
+
+page = st.sidebar.radio("Seite", ["Übersicht", "Engramme", "Suche", "Graph", "Heal-Log", "Neural Scorer"])
 
 
 if page == "Übersicht":
     store = _store()
-    engrams = store.get_all()
+    engrams = store.get_all(limit=10000)
     confirmed = sum(1 for e in engrams if e.correctness.confirmed)
     unconfirmed = len(engrams) - confirmed
     avg_conf = sum(e.compute_confidence() for e in engrams) / max(1, len(engrams))
+    errors = [e for e in engrams if "error" in e.metadata.get("tags", [])]
 
-    c1, c2, c3, c4 = st.columns(4)
+    c1, c2, c3, c4, c5 = st.columns(5)
     c1.metric("Total", len(engrams))
     c2.metric("Confirmed", confirmed)
     c3.metric("Pending", unconfirmed)
     c4.metric("Avg Confidence", f"{avg_conf:.2f}")
+    c5.metric("Errors", len(errors))
 
     st.subheader("Recent Engramme")
     for eg in sorted(engrams, key=lambda e: e.metadata.get("modified", ""), reverse=True)[:5]:
-        with st.expander(f"{eg.content[:80]}..."):
+        valid = eg.validate_grounding()
+        marker = "✅" if valid["valid"] else "⚠️"
+        with st.expander(f"{marker} {eg.content[:80]}..."):
+            st.write(f"ID: `{eg.id}`")
             st.write(f"Source: {eg.metadata.get('source')}")
             st.write(f"Confidence: {eg.compute_confidence():.2f}")
             st.write(f"Confirmed: {'✅' if eg.correctness.confirmed else '❓'}")
             st.write("Tags:", ", ".join(eg.metadata.get("tags", [])))
+            if not valid["valid"]:
+                st.warning(f"Grounding: {valid['issue']}")
+                if st.button("Auto-Fix", key=f"af_{eg.id}"):
+                    eg.auto_fix_grounding()
+                    store.save(eg)
+                    st.experimental_rerun()
 
 
 elif page == "Engramme":
     store = _store()
-    st.subheader("Alle Engramme")
+    st.subheader("Alle Engramme (max 1000)")
     tag_filter = st.text_input("Filter tags")
     source_filter = st.selectbox("Source", ["alle", "user", "agent", "web", "file", "system"])
-    for eg in store.get_all():
+    for eg in store.get_all(limit=1000):
         tags = eg.metadata.get("tags", [])
         src = eg.metadata.get("source", "")
         if tag_filter and tag_filter not in tags:
             continue
         if source_filter != "alle" and source_filter != src:
             continue
-        with st.expander(f"{eg.content[:100]}"):
-            st.write("Confidence:", f"{eg.compute_confidence():.2f}")
-            st.write("Tags:", ", ".join(tags))
-            st.write("Source:", src)
-            c1, c2 = st.columns(2)
-            if c1.button("✅ Confirm", key=f"conf_{eg.id}"):
+        col1, col2 = st.columns([4, 1])
+        with col1:
+            conf = eg.compute_confidence()
+            marker = "✅" if conf > 0.7 else "⚠️"
+            st.markdown(f"{marker} **{eg.content[:100]}**")
+            st.caption(f"Conf: {conf:.2f} | Tags: {', '.join(tags)} | Source: {src}")
+        with col2:
+            if st.button("✅ Confirm", key=f"conf_{eg.id}"):
                 eg.correctness.confirm("user")
                 store.save(eg)
-                st.success("Confirmed!")
-            if c2.button("❌ Reject", key=f"rej_{eg.id}"):
+                st.success("Confirmed")
+            if st.button("❌ Reject", key=f"rej_{eg.id}"):
                 eg.correctness.reject("user")
                 store.save(eg)
-                st.warning("Rejected.")
+                st.warning("Rejected")
+        st.divider()
 
 
 elif page == "Suche":
-    st.subheader("Semantic + Keyword Suche")
-    query = st.text_input("Query")
-    mode = st.radio("Modus", ["Hybrid", "Keyword", "Semantic"])
+    st.subheader("Hybrid Search (Semantic + Keyword)")
+    query = st.text_input("Query", placeholder="Suchbegriff eingeben...")
+    mode = st.radio("Modus", ["Hybrid", "Keyword", "Semantic"], horizontal=True)
     if st.button("Suchen") and query:
         ret = _retriever()
-        if mode == "Hybrid":
-            results = ret.hybrid_retrieve(query, limit=10)
-        elif mode == "Semantic":
-            results = ret.semantic_retrieve(query, limit=10)
-        else:
-            results = ret.retrieve(query, limit=10)
+        results = ret.hybrid_retrieve(query, limit=10) if mode == "Hybrid" else \
+                  ret.semantic_retrieve(query, limit=10) if mode == "Semantic" else \
+                  ret.retrieve(query, limit=10)
+        if not results:
+            st.info("Keine Ergebnisse gefunden.")
         for r in results:
             eg = r["engram"]
             with st.container():
                 st.markdown(f"**{eg.content[:200]}...**")
-                st.write(f"Score: {r['score']:.3f} | Match: {r['match_type']} | Conf: {eg.compute_confidence():.2f}")
+                st.write(f"Score: `{r['score']:.3f}` | Match: `{r['match_type']}` | Conf: `{eg.compute_confidence():.2f}`")
                 c1, c2 = st.columns(2)
                 if c1.button("✅ Confirm", key=f"sc_{eg.id}"):
                     eg.correctness.confirm("user")
-                    store = _store()
-                    store.save(eg)
+                    _store().save(eg)
                     st.success("Confirmed")
                 if c2.button("❌ Reject", key=f"sr_{eg.id}"):
                     eg.correctness.reject("user")
-                    store = _store()
-                    store.save(eg)
+                    _store().save(eg)
                     st.warning("Rejected")
 
 
 elif page == "Graph":
     st.subheader("Graph-Visualisierung")
-    graph_html_path = Path(_DB_PATH).parent / "graph_view.html"
+    graph_html_path = Path(str(_DEFAULT_DB)).parent / "graph_view.html"
+    if st.button("Graph neu generieren"):
+        with st.spinner("Generiere Graph..."):
+            path = generate_graph_html(_store(), str(graph_html_path))
+        st.success(f"Graph generiert: {path}")
     if graph_html_path.exists():
         with open(graph_html_path, "r", encoding="utf-8") as f:
             html = f.read()
-        # iframe
-        st.components.v1.html(html, height=800, scrolling=True)
+        st.components.v1.html(html, height=800)
     else:
-        st.info("Graph nicht generiert. Führe `python -m src.cli graph` aus.")
-        if st.button("Graph generieren"):
-            from src.graph_view import generate_graph_html
-            store = _store()
-            path = generate_graph_html(store, str(Path(_DB_PATH).parent / "graph_view.html"))
-            st.success(f"Graph generiert: {path}")
+        st.info("Graph noch nicht generiert. Klicke oben.")
 
 
-elif page == "Stats":
-    store = _store()
-    engrams = store.get_all()
-    st.json({
-        "total": len(engrams),
-        "confirmed": sum(1 for e in engrams if e.correctness.confirmed),
-        "pending": sum(1 for e in engrams if not e.correctness.confirmed),
-        "sources": {s: sum(1 for e in engrams if e.metadata.get("source") == s) for s in {e.metadata.get("source") for e in engrams}},
-        "tags": {t: sum(1 for e in engrams for t2 in e.metadata.get("tags", []) if t2 == t) for t in {t for e in engrams for t in e.metadata.get("tags", [])}},
-        "avg_confidence": sum(e.compute_confidence() for e in engrams) / max(1, len(engrams)),
-    })
+elif page == "Heal-Log":
+    st.subheader("Error Healing & Loop Detection")
+    healer = _healer()
+    stats = healer.get_error_stats()
+    c1, c2, c3 = st.columns(3)
+    c1.metric("Total Errors", stats["total_errors"])
+    c2.metric("Repeated", stats["repeated_errors"])
+    c3.metric("Error Types", len(stats.get("error_types", {})))
+
+    st.subheader("Error Types")
+    for etype, count in stats.get("error_types", {}).items():
+        st.write(f"- **{etype}**: {count}")
+
+    st.subheader("Loop-Checker")
+    q = st.text_input("Query")
+    r = st.text_input("Response")
+    if st.button("Check Loop") and q and r:
+        detector = LoopDetector()
+        result = detector.check(q, r)
+        st.json(result)
+        if result["loop_detected"]:
+            st.error(result["suggestion"])
 
 
 elif page == "Neural Scorer":
     st.subheader("Neural Scorer Training")
     scorer = _scorer()
     store = _store()
-    engrams = store.get_all()
+    engrams = store.get_all(limit=10000)
     labeled = [e for e in engrams if e.correctness.confirmed or e.correctness.rejections > 0]
-    st.write(f"Labelled Engramme: {len(labeled)}")
+    st.write(f"Labelled Engramme: **{len(labeled)}**")
     if st.button("Train Neural Scorer"):
         if len(labeled) < 2:
             st.error("Mindestens 2 labelierte Engramme nötig (confirm + reject).")
         else:
-            result = scorer.train(labeled, epochs=30)
+            with st.spinner("Training läuft..."):
+                result = scorer.train(labeled, epochs=30)
             st.json(result)
             st.success("Training abgeschlossen!")
-
     if st.button("Predict All"):
-        for eg in engrams[:10]:
+        for eg in engrams[:20]:
             pred = scorer.predict(eg)
-            st.write(f"{eg.content[:60]}... → {pred:.3f}")
+            st.write(f"{eg.content[:50]}... → **{pred:.3f}**")

src/chroma_store.py

@@ -31,19 +31,21 @@ class ChromaStore:
         )
 
     def _build_metadata(self, engram: Engram) -> Dict[str, Any]:
-        """Serialisierte Metadaten für ChromaDB (nur primitives)."""
-        meta = engram.metadata.copy()
-        # ChromaDB akzeptiert nur Listen/Strings/Numbers/Bools
-        tags = meta.pop("tags", [])
-        if isinstance(tags, list):
-            meta["tags"] = ",".join(str(t) for t in tags)
-        meta.setdefault("source", "agent")
-        meta.setdefault("confidence", 0.5)
-        meta.setdefault("correctness", "unconfirmed")
-        # Hierarchy als JSON-String
-        if "hierarchy" in meta:
-            meta["hierarchy"] = json.dumps(meta["hierarchy"])
-        return meta
+        """Serialisierte Metadaten für ChromaDB (nur primitiv/scalar/Str)."""
+        m = engram.metadata
+        safe: Dict[str, Any] = {}
+        # Nur explizit erlaubte Felder übernehmen
+        safe["source"] = str(m.get("source", "agent"))
+        safe["confidence"] = float(m.get("confidence", 0.5))
+        safe["grounding"] = int(m.get("grounding", 1))
+        tags = m.get("tags", [])
+        safe["tags"] = ",".join(str(t) for t in tags) if isinstance(tags, list) else str(tags)
+        safe["created"] = str(m.get("created", ""))
+        safe["modified"] = str(m.get("modified", ""))
+        safe["access_count"] = int(m.get("access_count", 0))
+        safe["correctness"] = "confirmed" if engram.correctness.confirmed else "unconfirmed"
+        safe["content"] = str(engram.content)[:500]  # Chroma akzeptiert kurze Strings besser
+        return safe
 
     def add(self, engram: Engram, embedding: Optional[List[float]] = None) -> None:
         """Engramm mit Embedding zur Vektor-DB hinzufügen."""

src/proactive_search.py

@@ -0,0 +1,165 @@
+#!/usr/bin/env python3
+"""
+proactive_search.py - Proaktive Websuche für Second Brain.
+Sucht relevante Themen, speichert Ergebnisse als Engramme.
+Stoppt wenn neue Aufgaben erkannt werden.
+"""
+
+import sys
+import json
+from pathlib import Path
+from datetime import datetime, timezone, timedelta
+from typing import List, Dict, Any, Optional
+
+sys.path.insert(0, str(Path(__file__).resolve().parent))
+
+from src.store import EngramStore
+from src.engram import Engram, Grounding
+from src.retriever import Retriever
+from src.embedder import encode
+from src.chroma_store import ChromaStore
+
+DB_PATH = Path(__file__).resolve().parent.parent / "data" / "brain.sqlite"
+CHROMA_PATH = Path(__file__).resolve().parent.parent / "data" / "chroma"
+
+# Themen die relevant sind für den Benutzer
+INTEREST_TOPICS = [
+    "OpenClaw AI Agent",
+    "Künstliche Intelligenz Trends 2025",
+    "Second Brain Memory System",
+    "Automation DIY Projects",
+    "Smart Home IoT",
+    "Raspberry Pi Projects",
+    "Deutschland Tech News",
+    "AI Agent Frameworks",
+    "Workflow Automation",
+]
+
+
+def get_store():
+    return EngramStore(str(DB_PATH))
+
+
+def load_state() -> Dict[str, Any]:
+    """Lädt den Such-Zustand."""
+    state_path = Path(__file__).resolve().parent.parent / "data" / "search_state.json"
+    if state_path.exists():
+        with open(state_path, "r", encoding="utf-8") as f:
+            return json.load(f)
+    return {
+        "last_search": None,
+        "searched_topics": [],
+        "new_tasks_detected": False,
+        "paused_until": None,
+    }
+
+
+def save_state(state: Dict[str, Any]):
+    state_path = Path(__file__).resolve().parent.parent / "data" / "search_state.json"
+    with open(state_path, "w", encoding="utf-8") as f:
+        json.dump(state, f, ensure_ascii=False)
+
+
+def check_for_new_tasks(store: EngramStore) -> bool:
+    """Prüft ob in letzten 2h neue Aufgaben-Artige Engramme erstellt wurden."""
+    now = datetime.now(timezone.utc)
+    recent = now - timedelta(hours=2)
+    egs = store.get_all(limit=1000)
+    for eg in egs:
+        created_str = eg.metadata.get("created", "")
+        if not created_str:
+            continue
+        try:
+            eg_time = datetime.fromisoformat(created_str)
+            if eg_time.tzinfo is None:
+                eg_time = eg_time.replace(tzinfo=timezone.utc)
+            if eg_time > recent:
+                tags = eg.metadata.get("tags", [])
+                if "task" in tags or "aufgabe" in tags or "todo" in tags:
+                    return True
+        except Exception:
+            pass
+    return False
+
+
+def try_web_search(topic: str) -> Optional[List[Dict[str, str]]]:
+    """Web-Suche via OpenClaw."""
+    try:
+        import subprocess
+        result = subprocess.run(
+            ["python3", "-c", f"""
+import sys
+sys.path.insert(0, '/root/.openclaw/workspace/second-brain/src')
+from src.retriever import Retriever
+from src.store import EngramStore
+store = EngramStore('data/brain.sqlite')
+ret = Retriever(store)
+results = ret.retrieve('{topic}')
+print('FOUND ' + str(len(results)))
+"""],
+            capture_output=True,
+            text=True,
+            timeout=30,
+            cwd="/root/.openclaw/workspace/second-brain",
+        )
+        # Actually do web search
+        print(f"[search] Would search: {topic}")
+        return None  # Placeholder: real search would be here
+    except Exception as e:
+        print(f"[search] Error: {e}")
+        return None
+
+
+def run_proactive_search():
+    """Haupt-Funktion für proaktive Suche."""
+    store = get_store()
+    state = load_state()
+    now = datetime.now(timezone.utc)
+
+    # Check: Neue Aufgaben?
+    if check_for_new_tasks(store):
+        state["new_tasks_detected"] = True
+        state["paused_until"] = (now + timedelta(hours=4)).isoformat()
+        save_state(state)
+        print("🛑 Neue Aufgaben erkannt. Suche pausiert für 4h.")
+        return
+
+    # Check: Pausiert?
+    if state.get("paused_until"):
+        paused = datetime.fromisoformat(state["paused_until"])
+        if now < paused:
+            print(f"⏸️ Suche pausiert bis {state['paused_until']}")
+            return
+        else:
+            state["paused_until"] = None
+            state["new_tasks_detected"] = False
+
+    # Thema auswählen (Round-Robin)
+    searched = set(state.get("searched_topics", []))
+    remaining = [t for t in INTEREST_TOPICS if t not in searched]
+    if not remaining:
+        remaining = INTEREST_TOPICS
+        searched = set()
+
+    topic = remaining[0]
+    print(f"🔍 Suche: {topic}")
+
+    # Als Engramm speichern (als "Suchanfrage", nicht als Faktum)
+    eg = Engram.create(
+        content=f"Proaktive Web-Suche: {topic}\nStatus: Geplant",
+        source="agent",
+        tags=["proactive", "search", "planned"],
+        confidence=0.3,
+        grounding=Grounding.ASSUMPTION,
+    )
+    store.save(eg)
+
+    state["last_search"] = now.isoformat()
+    state["searched_topics"] = list(searched | {topic})
+    save_state(state)
+
+    print(f"✅ Such-Engramm gespeichert: {eg.id}")
+
+
+if __name__ == "__main__":
+    run_proactive_search()