docs: add dashboard UI/UX design plan

- api_confirm and api_reject were defined twice on same paths
- FastAPI only registers first definition, causing silent 404s
- Kept api_confirm_engram and api_reject_engram (use _update_correctness)
- Removed duplicate direct DB implementations
- Fixes dashboard confirm/reject buttons not working

README.md

@@ -8,7 +8,28 @@ An embeddable, offline-first memory system for AI agents with correctness tracki
 - **ChromaDB Vector Store** (`src/chroma_store.py`) — Semantic similarity search
 - **Neural Confidence Scorer** (`src/neural_scorer.py`) — PyTorch RL net, trains on confirm/reject feedback
 - **Hybrid Retrieval** (`src/retriever.py`) — Keyword + Semantic + Neural fusion
-- **Streamlit Dashboard** (`src/app_dashboard.py`) — Search, confirm/reject, neural training UI
+- **FastAPI Dashboard** (`fastapi_app.py`) — Lightweight web UI (search + confirm/reject) and JSON API
+- **Streamlit Dashboard** (`src/app_dashboard.py`) — (optional) richer UI for neural training, etc.
 - **Graph Visualization** (`src/graph_view.py`) — Interactive Cytoscape.js graph with confidence colors
 
 ## Architecture
+
+## Obsidian
+
+Setup and timers: `second-brain/docs/OBSIDIAN.md`
+
+## Quickstart (Dashboard)
+
+Install minimal dashboard deps:
+
+`python3 -m pip install -r requirements-dashboard.txt`
+
+Run:
+
+`SECOND_BRAIN_WORKSPACE="$(pwd)" python3 fastapi_app.py`
+
+Then open: `http://localhost:8501/`
+
+Port is configurable via `SECOND_BRAIN_PORT` (or `PORT`), e.g.:
+
+`SECOND_BRAIN_WORKSPACE="$(pwd)" SECOND_BRAIN_PORT=8502 python3 fastapi_app.py`

RUNBOOK.md

@@ -0,0 +1,94 @@
+# Second-Brain 2.0 (Grundversion) — Runbook
+
+This is the operational quick-reference for the shipped systemd timers/services and the optional FastAPI dashboard backend.
+
+Repository root (on host): `/root/.openclaw/workspace/second-brain`
+
+## Systemd units (cron jobs)
+
+Unit files are shipped in `systemd/` (this repo). Install them into `/etc/systemd/system/` (symlink or copy), then reload:
+
+```bash
+sudo ln -sf /root/.openclaw/workspace/second-brain/systemd/openclaw-secondbrain-*.service /etc/systemd/system/
+sudo ln -sf /root/.openclaw/workspace/second-brain/systemd/openclaw-secondbrain-*.timer /etc/systemd/system/
+sudo ln -sf /root/.openclaw/workspace/second-brain/systemd/openclaw-memory-archive.* /etc/systemd/system/
+sudo systemctl daemon-reload
+```
+
+Optional (verification hardening):
+
+```bash
+sudo ln -sf /root/.openclaw/workspace/second-brain/systemd/openclaw-secondbrain-verify-pending.* /etc/systemd/system/
+sudo systemctl daemon-reload
+sudo systemctl enable --now openclaw-secondbrain-verify-pending.timer
+```
+
+Enable timers:
+
+```bash
+sudo systemctl enable --now openclaw-secondbrain-ingest-memory.timer
+sudo systemctl enable --now openclaw-secondbrain-index-vectors.timer
+sudo systemctl enable --now openclaw-secondbrain-review.timer
+sudo systemctl enable --now openclaw-secondbrain-backup.timer
+sudo systemctl enable --now openclaw-secondbrain-heartbeat.timer
+sudo systemctl enable --now openclaw-secondbrain-proactive-search.timer
+sudo systemctl enable --now openclaw-memory-archive.timer
+
+# Optional (Obsidian coupling)
+sudo systemctl enable --now openclaw-secondbrain-ingest-obsidian.timer
+sudo systemctl enable --now openclaw-secondbrain-export-obsidian.timer
+```
+
+Verify scheduling:
+
+```bash
+sudo systemctl list-timers --all | grep -E 'openclaw-(secondbrain|memory-archive)' || true
+```
+
+Run a job once:
+
+```bash
+sudo systemctl start openclaw-secondbrain-ingest-memory.service
+sudo systemctl status openclaw-secondbrain-ingest-memory.service --no-pager
+sudo journalctl -u openclaw-secondbrain-ingest-memory.service -n 200 --no-pager
+```
+
+Wrapper logs:
+
+```bash
+tail -n 200 /root/.openclaw/workspace/cron_wrapper.log
+```
+
+## FastAPI dashboard (manual start)
+
+FastAPI entrypoint:
+
+```bash
+cd /root/.openclaw/workspace
+python3 -m pip install -r second-brain/requirements-dashboard.txt
+SECOND_BRAIN_WORKSPACE="/root/.openclaw/workspace/second-brain" python3 second-brain/fastapi_app.py
+```
+
+Default port is `8501` (same as Streamlit default). You can override via `SECOND_BRAIN_PORT` (or `PORT`) when starting manually.
+
+Endpoint smoke tests:
+
+```bash
+curl -fsS http://127.0.0.1:8501/api/stats
+curl -fsS "http://127.0.0.1:8501/api/engrams?limit=1&offset=0"
+curl -fsS "http://127.0.0.1:8501/api/search?q=test&limit=1"
+```
+
+## DB quick check
+
+```bash
+python3 - <<'PY'
+import sqlite3
+db="/root/.openclaw/workspace/second-brain/data/brain.sqlite"
+con=sqlite3.connect(db)
+cur=con.cursor()
+print(cur.execute("PRAGMA integrity_check").fetchone()[0])
+print("engrams:", cur.execute("SELECT COUNT(*) FROM engrams").fetchone()[0])
+con.close()
+PY
+```

chat_autosave.py

@@ -0,0 +1,119 @@
+#!/usr/bin/env python3
+"""
+Chat-Auto-Save: Wertvolle User-Nachrichten → Engramm.
+Wird am Ende jeder Main-Session-Antwort aufgerufen.
+"""
+
+import sys
+import json
+import hashlib
+from pathlib import Path
+
+BRAIN_DIR = Path("/root/.openclaw/workspace/second-brain")
+sys.path.insert(0, str(BRAIN_DIR))
+
+from src.engram import Engram, Grounding
+from src.store import EngramStore
+
+DB_PATH = BRAIN_DIR / "data" / "brain.sqlite"
+
+
+def _hash(text: str) -> str:
+    return hashlib.sha256(text.encode("utf-8")).hexdigest()[:12]
+
+
+def is_fluff(content: str) -> bool:
+    """Prüft ob Inhalt nur Floskel ist."""
+    lower = content.lower().strip().rstrip(".?!")
+    short_fluff = [
+        "hallo", "hi", "hey", "guten tag", "guten morgen", "guten abend",
+        "danke", "ok", "okay", "ja", "nein", "bitte", "gerne", "tschüss",
+        "bis später", "bis morgen", "alles klar", "in ordnung",
+    ]
+    if lower in short_fluff:
+        return True
+    if len(content) < 10 and all(c in " ?,!.;:-" for c in content):
+        return True
+    return False
+
+
+def save_if_worthy(content: str, source: str = "user", tags: list = None,
+                   confidence: float = 0.7, session_id: str = None,
+                   reasoning: str = None) -> dict:
+    """
+    Speichert Nachricht als Engramm wenn sie Wert hat.
+    Wird in jeder Antwort aufgerufen.
+    """
+    
+    if is_fluff(content):
+        return {"saved": False, "reason": "fluff"}
+    
+    store = EngramStore(str(DB_PATH))
+    content_hash = _hash(content)
+    recent = store.get_all(limit=200)
+    for eg in recent:
+        if _hash(eg.content) == content_hash:
+            return {"saved": False, "reason": "duplicate", "id": str(eg.id)}
+    
+    eg = Engram.create(
+        content=content,
+        source=source,
+        tags=tags or ["auto-save", "chat"],
+        session_id=session_id,
+        confidence=confidence,
+        grounding=Grounding.ASSUMPTION,
+    )
+    store.save(eg)
+    
+    return {
+        "saved": True,
+        "id": str(eg.id),
+        "confidence": eg.compute_confidence(),
+        "first8": str(eg.id)[:8],
+    }
+
+
+def enrich_prompt(topic: str, limit: int = 3) -> str:
+    """
+    Holt relevante bestätigte Engramme für Kontext-Anreicherung.
+    Wird VOR jeder Antwort aufgerufen.
+    """
+    store = EngramStore(str(DB_PATH))
+    recent = store.get_all(limit=100)
+    
+    # Einfache Text-Suche (kein FTS wegen Satzzeichen)
+    topic_lower = topic.lower()
+    matches = []
+    for eg in recent:
+        if eg.correctness.confirmed and topic_lower in eg.content.lower():
+            matches.append(eg)
+        elif len(matches) < limit and any(t in topic_lower for t in [t.lower() for t in eg.metadata.get("tags", [])]):
+            matches.append(eg)
+        if len(matches) >= limit:
+            break
+    
+    if not matches:
+        return ""
+    
+    lines = ["\n📚 Relevantes Wissen:"]
+    for eg in matches[:limit]:
+        lines.append(f"  • [{eg.compute_confidence():.0%}] {eg.content[:120]}")
+    
+    return "\n".join(lines)
+
+
+def check_pending(session_id: str = None) -> list:
+    """Gibt unbestätigte Engramme zurück."""
+    store = EngramStore(str(DB_PATH))
+    egs = store.get_all(limit=50)
+    pending = [eg for eg in egs if not eg.correctness.confirmed]
+    return pending
+
+
+if __name__ == "__main__":
+    import sys
+    if len(sys.argv) > 1:
+        result = save_if_worthy(sys.argv[1])
+        print(json.dumps(result, indent=2))
+    else:
+        print("Usage: python3 chat_autosave.py 'Nachricht'")

cron_tasks/backup_secondbrain.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python3
+"""Backup-Task für Second Brain - isoliert, persistent."""
+import json, os, sys
+from pathlib import Path
+from datetime import datetime, timezone
+
+BRAIN_DIR = Path("/root/.openclaw/workspace/second-brain")
+sys.path.insert(0, str(BRAIN_DIR))
+from src.store import EngramStore
+
+def main():
+    brain_db = os.environ.get("BRAIN_DB", str(BRAIN_DIR / "data" / "brain.sqlite"))
+    store = EngramStore(brain_db)
+    ts = datetime.now(timezone.utc).strftime("%Y%m%d_%H%M%S")
+    backup_path = Path(brain_db).parent / f"backup_{ts}.jsonl"
+    count = store.export_jsonl(str(backup_path))
+    result = {"timestamp": datetime.now(timezone.utc).isoformat(), "backup_path": str(backup_path), "count": count, "success": True}
+    print(f"BACKUP: {count} Engramme -> {backup_path}")
+    return 0
+
+if __name__ == "__main__":
+    sys.exit(main())

cron_tasks/brain_rules.py

@@ -0,0 +1,53 @@
+#!/usr/bin/env python3
+"""
+Brain-Regeln - Automatische Bestaetigungs- und Archivierungslogik.
+Wird von Cron und Agent aufgerufen.
+"""
+
+import sys
+sys.path.insert(0, "/root/.openclaw/workspace/second-brain")
+
+from src.engram import Engram, Grounding
+from src.store import EngramStore
+
+DB = "/root/.openclaw/workspace/second-brain/data/brain.sqlite"
+
+
+def apply_rules():
+    store = EngramStore(DB)
+    egs = store.get_all(limit=1000)
+    actions = []
+
+    for eg in egs:
+        conf = eg.compute_confidence()
+        age_days = eg._age_days(eg.metadata.get("created", ""))
+        correct = eg.correctness
+
+        # Regel 1: Triple-Confirm → Auto-Verifiziert
+        if not correct.confirmed and correct.confirmations >= 3:
+            correct.confirmed = True
+            correct.confirmations += 1
+            store.save(eg)
+            actions.append(f"Auto-Confirm: {str(eg.id)[:8]} (3x confirmed)")
+
+        # Regel 2: Lang unbestaetigt → ASSUMPTION Tag
+        if age_days > 30 and not correct.confirmed and "archiviert" not in eg.metadata.get("tags", []):
+            eg.metadata.setdefault("tags", []).append("archiviert")
+            eg.metadata["archivgrund"] = f"Unbestaetigt seit {age_days} Tagen"
+            store.save(eg)
+            actions.append(f"Archiviert: {str(eg.id)[:8]} (Alter {age_days}d)")
+
+        # Regel 3: Rejected mit 2+ Rejections → loeschen (Sanft: Tag statt rm)
+        if correct.rejections >= 2:
+            eg.metadata.setdefault("tags", []).append("deleted")
+            store.save(eg)
+            actions.append(f"Deleted-Tag: {str(eg.id)[:8]} ({correct.rejections}x rejected)")
+
+    return actions
+
+
+if __name__ == "__main__":
+    actions = apply_rules()
+    print("Brain-Regeln angewendet:")
+    for a in actions or ["Keine Aktionen noetig"]:
+        print(f"  {a}")

cron_tasks/heartbeat_secondbrain.py

@@ -0,0 +1,47 @@
+#!/usr/bin/env python3
+"""
+Heartbeat-Task für Second Brain - isoliert, persistent.
+"""
+
+import json
+import os
+import sys
+from pathlib import Path
+from datetime import datetime, timezone
+
+BRAIN_DIR = Path("/root/.openclaw/workspace/second-brain")
+sys.path.insert(0, str(BRAIN_DIR))
+
+from src.engram import Engram, Grounding
+from src.store import EngramStore
+
+def main():
+    output_file = os.environ.get("CRON_OUTPUT_FILE", "/tmp/heartbeat_result.json")
+    brain_db = os.environ.get("BRAIN_DB", str(BRAIN_DIR / "data" / "brain.sqlite"))
+    store = EngramStore(brain_db)
+
+    egs = store.get_all(limit=50)
+    unconfirmed = [eg for eg in egs if not eg.correctness.confirmed and eg.compute_confidence() > 0.5][:5]
+    errors = store.search_tag("error", limit=5)
+
+    result = {
+        "timestamp": datetime.now(timezone.utc).isoformat(),
+        "total_engrams": len(egs),
+        "unconfirmed_count": len(unconfirmed),
+        "error_count": len(errors),
+        "has_action": bool(unconfirmed) or len(errors) >= 3,
+        "message": None,
+    }
+
+    if unconfirmed:
+        contents = "\n".join([f"  - {eg.content[:80]}" for eg in unconfirmed])
+        result["message"] = f"🧠 Unbestätigte Engramme:\n{contents}"
+    elif len(errors) >= 3:
+        result["message"] = f"⚠️ {len(errors)} Fehler-Engramme gespeichert."
+
+    Path(output_file).write_text(json.dumps(result, indent=2))
+    print(f"HEARTBEAT: {result['unconfirmed_count']} unconfirmed, {result['error_count']} errors")
+    return 0
+
+if __name__ == "__main__":
+    sys.exit(main())

cron_tasks/ingest_transcript_to_db.py

@@ -0,0 +1,160 @@
+#!/usr/bin/env python3
+"""
+Ingest OpenClaw session transcript JSONL directly into the Second-Brain DB.
+
+State is tracked with byte offsets per transcript file.
+Sources are configured via workspace/memory/session_sources.json.
+"""
+
+from __future__ import annotations
+
+import json
+import os
+from dataclasses import dataclass
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any, Dict, Iterable, List
+from uuid import NAMESPACE_URL, uuid5
+
+WORKSPACE = Path("/root/.openclaw/workspace")
+MEMORY_DIR = WORKSPACE / "memory"
+SOURCES_PATH = MEMORY_DIR / "session_sources.json"
+STATE_PATH = MEMORY_DIR / "session_db_ingest_state.json"
+
+BRAIN_DIR = WORKSPACE / "second-brain"
+DB_PATH = Path(os.environ.get("BRAIN_DB", str(BRAIN_DIR / "data" / "brain.sqlite")))
+
+import sys
+
+sys.path.insert(0, str(BRAIN_DIR))
+from src.engram import Engram, Grounding  # type: ignore
+from src.store import EngramStore  # type: ignore
+
+
+def _now() -> str:
+    return datetime.now(timezone.utc).isoformat()
+
+
+def _load_json(path: Path, default: Any) -> Any:
+    try:
+        if not path.exists():
+            return default
+        return json.loads(path.read_text(encoding="utf-8"))
+    except Exception:
+        return default
+
+
+def _save_json(path: Path, payload: Any) -> None:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text(json.dumps(payload, indent=2, ensure_ascii=False) + "\n", encoding="utf-8")
+
+
+def _extract_text(content: Any) -> str:
+    if isinstance(content, str):
+        return content.strip()
+    if isinstance(content, list):
+        parts: List[str] = []
+        for c in content:
+            if isinstance(c, dict) and c.get("type") == "text" and isinstance(c.get("text"), str):
+                parts.append(c["text"])
+            elif isinstance(c, str):
+                parts.append(c)
+        return "\n".join(p.strip() for p in parts if p and p.strip()).strip()
+    if isinstance(content, dict) and isinstance(content.get("text"), str):
+        return content["text"].strip()
+    return str(content).strip()
+
+
+@dataclass
+class Source:
+    label: str
+    transcript_path: Path
+
+
+def _load_sources() -> List[Source]:
+    payload = _load_json(SOURCES_PATH, {"sources": []})
+    sources: List[Source] = []
+    for item in payload.get("sources", []) if isinstance(payload, dict) else []:
+        if not isinstance(item, dict):
+            continue
+        label = str(item.get("label") or "session")
+        p = item.get("path")
+        if not isinstance(p, str) or not p:
+            continue
+        sources.append(Source(label=label, transcript_path=Path(p)))
+    return sources
+
+
+def _iter_new_lines(path: Path, *, start_offset: int) -> Iterable[tuple[int, str]]:
+    with open(path, "rb") as f:
+        f.seek(max(0, int(start_offset)))
+        while True:
+            raw = f.readline()
+            if not raw:
+                break
+            line = raw.decode("utf-8", errors="ignore").strip()
+            if not line:
+                continue
+            yield (f.tell(), line)
+
+
+def run() -> Dict[str, Any]:
+    if not DB_PATH.exists():
+        return {"success": False, "time": _now(), "error": f"db missing: {DB_PATH}"}
+
+    sources = _load_sources()
+    state = _load_json(STATE_PATH, {"offsets": {}})
+    offsets: Dict[str, int] = state.get("offsets", {}) if isinstance(state, dict) else {}
+
+    store = EngramStore(str(DB_PATH))
+    out = {"success": True, "time": _now(), "sources": len(sources), "messages_saved": 0, "messages_skipped": 0, "errors": []}
+
+    for src in sources:
+        try:
+            if not src.transcript_path.exists():
+                continue
+            key = str(src.transcript_path)
+            start = int(offsets.get(key, 0))
+            for new_off, line in _iter_new_lines(src.transcript_path, start_offset=start):
+                offsets[key] = new_off
+                obj = json.loads(line)
+                if not isinstance(obj, dict) or obj.get("type") != "message":
+                    continue
+                msg = obj.get("message") if isinstance(obj.get("message"), dict) else {}
+                role = str(msg.get("role") or "unknown")
+                content = _extract_text(msg.get("content"))
+                if len(content.strip()) < 5:
+                    continue
+                mid = str(obj.get("id") or msg.get("id") or msg.get("messageId") or msg.get("message_id") or "")
+                if not mid:
+                    mid = str(uuid5(NAMESPACE_URL, f"openclaw-transcript:{src.label}:{role}:{content[:200]}"))
+                eid = str(uuid5(NAMESPACE_URL, f"openclaw-transcript:{src.label}:{mid}"))
+                if store.get(eid):
+                    out["messages_skipped"] += 1
+                    continue
+                eg = Engram.create(
+                    content=f"[transcript:{src.label}] [{role}] [{mid}]\n\n{content}"[:4000],
+                    source="session",
+                    tags=["session", "openclaw", "transcript", f"role:{role}"],
+                    session_id=src.label,
+                    confidence=0.55,
+                    grounding=Grounding.ASSUMPTION,
+                )
+                eg.id = uuid5(NAMESPACE_URL, eid)
+                eg.metadata["source"] = "session"
+                eg.metadata["session_id"] = src.label
+                eg.metadata["role"] = role
+                eg.metadata["message_id"] = mid
+                store.save(eg)
+                out["messages_saved"] += 1
+        except Exception as e:
+            out["success"] = False
+            out["errors"].append(f"{src.transcript_path}: {e}")
+
+    _save_json(STATE_PATH, {"offsets": offsets, "updated_at": out["time"]})
+    return out
+
+
+if __name__ == "__main__":
+    print(json.dumps(run(), ensure_ascii=False, indent=2))
+

cron_tasks/ingest_transcript_to_memory.py

@@ -0,0 +1,213 @@
+#!/usr/bin/env python3
+"""
+Tail OpenClaw session transcript JSONL files and append new messages into
+workspace/memory/YYYY-MM-DD.md so the existing ingest_memory pipeline can pick
+them up.
+
+Why: when chat_autosave hooks are missed/aborted, the "memory/*.md -> DB" ingest
+doesn't see the latest conversation. This bridges transcript -> memory.
+
+Safety: read-only access to transcript files; state stored in workspace/memory/.
+"""
+
+from __future__ import annotations
+
+import json
+import os
+from dataclasses import dataclass
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any, Dict, Iterable, List, Optional
+
+try:
+    from zoneinfo import ZoneInfo  # py3.9+
+except Exception:  # pragma: no cover
+    ZoneInfo = None  # type: ignore
+
+
+WORKSPACE = Path("/root/.openclaw/workspace")
+MEMORY_DIR = WORKSPACE / "memory"
+SOURCES_PATH = MEMORY_DIR / "session_sources.json"
+STATE_PATH = MEMORY_DIR / "session_ingest_state.json"
+
+
+def _local_tz():
+    tz = os.environ.get("TZ") or "Europe/Berlin"
+    if ZoneInfo:
+        try:
+            return ZoneInfo(tz)
+        except Exception:
+            return timezone.utc
+    return timezone.utc
+
+
+def _load_json(path: Path, default: Any) -> Any:
+    try:
+        if not path.exists():
+            return default
+        return json.loads(path.read_text(encoding="utf-8"))
+    except Exception:
+        return default
+
+
+def _save_json(path: Path, payload: Any) -> None:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text(json.dumps(payload, indent=2, ensure_ascii=False) + "\n", encoding="utf-8")
+
+
+def _iso_to_dt(ts: str) -> Optional[datetime]:
+    try:
+        if ts.endswith("Z"):
+            ts = ts[:-1] + "+00:00"
+        return datetime.fromisoformat(ts)
+    except Exception:
+        return None
+
+
+def _ms_to_dt(ms: int) -> datetime:
+    return datetime.fromtimestamp(ms / 1000, tz=timezone.utc)
+
+
+def _extract_text(content: Any) -> str:
+    if isinstance(content, str):
+        return content.strip()
+    if isinstance(content, list):
+        parts: List[str] = []
+        for c in content:
+            if isinstance(c, dict) and c.get("type") == "text" and isinstance(c.get("text"), str):
+                parts.append(c["text"])
+            elif isinstance(c, str):
+                parts.append(c)
+        return "\n".join(p.strip() for p in parts if p and p.strip()).strip()
+    if isinstance(content, dict):
+        if isinstance(content.get("text"), str):
+            return content["text"].strip()
+    return str(content).strip()
+
+
+@dataclass
+class Source:
+    label: str
+    transcript_path: Path
+
+
+def _load_sources() -> List[Source]:
+    """
+    Sources file format:
+    {
+      "sources": [
+        { "label": "telegram:263887248", "path": "/root/.openclaw/agents/main/sessions/<id>.jsonl" }
+      ]
+    }
+    """
+    payload = _load_json(SOURCES_PATH, {"sources": []})
+    sources: List[Source] = []
+    for item in payload.get("sources", []) if isinstance(payload, dict) else []:
+        if not isinstance(item, dict):
+            continue
+        label = str(item.get("label") or "session")
+        p = item.get("path")
+        if not isinstance(p, str) or not p:
+            continue
+        sources.append(Source(label=label, transcript_path=Path(p)))
+    return sources
+
+
+def _memory_path_for(dt: datetime) -> Path:
+    tz = _local_tz()
+    local = dt.astimezone(tz)
+    MEMORY_DIR.mkdir(parents=True, exist_ok=True)
+    return MEMORY_DIR / f"{local.date().isoformat()}.md"
+
+
+def _append_memory(dt: datetime, label: str, role: str, text: str) -> None:
+    if not text.strip():
+        return
+    tz = _local_tz()
+    local = dt.astimezone(tz)
+    mem = _memory_path_for(dt)
+    if not mem.exists():
+        mem.write_text(f"# {local.date().isoformat()}\n\n", encoding="utf-8")
+
+    header = f"## {local.strftime('%H:%M:%S')} - {label} ({role})"
+    body = text.strip()
+    mem.write_text(mem.read_text(encoding="utf-8") + f"{header}\n\n{body}\n\n", encoding="utf-8")
+
+
+def _iter_new_lines(path: Path, *, start_offset: int) -> Iterable[tuple[int, str]]:
+    with open(path, "rb") as f:
+        f.seek(max(0, int(start_offset)))
+        while True:
+            raw = f.readline()
+            if not raw:
+                break
+            try:
+                line = raw.decode("utf-8", errors="ignore").strip()
+            except Exception:
+                line = ""
+            if not line:
+                continue
+            yield (f.tell(), line)
+
+
+def run() -> Dict[str, Any]:
+    sources = _load_sources()
+    state = _load_json(STATE_PATH, {"offsets": {}})
+    offsets: Dict[str, int] = state.get("offsets", {}) if isinstance(state, dict) else {}
+
+    out = {
+        "success": True,
+        "time": datetime.now(timezone.utc).isoformat(),
+        "sources": len(sources),
+        "messages_appended": 0,
+        "errors": [],
+    }
+
+    for src in sources:
+        try:
+            if not src.transcript_path.exists():
+                continue
+            key = str(src.transcript_path)
+            start = int(offsets.get(key, 0))
+            for new_off, line in _iter_new_lines(src.transcript_path, start_offset=start):
+                try:
+                    obj = json.loads(line)
+                except Exception:
+                    offsets[key] = new_off
+                    continue
+
+                if not isinstance(obj, dict) or obj.get("type") != "message":
+                    offsets[key] = new_off
+                    continue
+
+                msg = obj.get("message") if isinstance(obj.get("message"), dict) else {}
+                role = str(msg.get("role") or "unknown")
+                content = msg.get("content")
+                text = _extract_text(content)
+
+                dt = None
+                if isinstance(msg.get("timestamp"), (int, float)):
+                    dt = _ms_to_dt(int(msg["timestamp"]))
+                elif isinstance(obj.get("timestamp"), str):
+                    dt = _iso_to_dt(obj["timestamp"])
+                if dt is None:
+                    dt = datetime.now(timezone.utc)
+
+                if len(text.strip()) < 5:
+                    offsets[key] = new_off
+                    continue
+
+                _append_memory(dt, src.label, role, text)
+                out["messages_appended"] += 1
+                offsets[key] = new_off
+        except Exception as e:
+            out["success"] = False
+            out["errors"].append(f"{src.transcript_path}: {e}")
+
+    _save_json(STATE_PATH, {"offsets": offsets, "updated_at": out["time"]})
+    return out
+
+
+if __name__ == "__main__":
+    res = run()
+    print(json.dumps(res, ensure_ascii=False, indent=2))

cron_tasks/verify_pending_external.py

@@ -0,0 +1,169 @@
+#!/usr/bin/env python3
+"""
+Verify pending (unconfirmed) engrams using lightweight external checks.
+
+Policy (conservative):
+- `openclaw-memory` is treated as internal ground-truth and is auto-confirmed
+  by the review job (see `cron_tasks/review_brain.py` in the workspace runtime).
+- For `source=web`, confirm if the grounded URL responds with HTTP 2xx, reject on
+  4xx/5xx, and keep pending on timeouts/unknown.
+- Reject obvious low-signal placeholders (e.g. session summary stubs).
+"""
+
+import json
+import os
+import sys
+from pathlib import Path
+from datetime import datetime, timezone
+from typing import Any, Optional
+
+
+WORKSPACE = Path(os.environ.get("SECOND_BRAIN_WORKSPACE", "/root/.openclaw/workspace/second-brain"))
+DB_PATH = Path(os.environ.get("BRAIN_DB", str(WORKSPACE / "data" / "brain.sqlite"))).resolve()
+
+sys.path.insert(0, str(WORKSPACE))
+from src.store import EngramStore
+from src.engram import ReviewEntry
+
+OUTPUT_FILE = os.environ.get("CRON_OUTPUT_FILE", "/tmp/verify_pending_external.json")
+
+
+def _now() -> str:
+    return datetime.now(timezone.utc).isoformat()
+
+
+def _get_url(meta: dict[str, Any]) -> Optional[str]:
+    url = meta.get("url")
+    if isinstance(url, str) and url.startswith(("http://", "https://")):
+        return url
+    grounding = meta.get("grounding")
+    if isinstance(grounding, dict):
+        g_url = grounding.get("url")
+        if isinstance(g_url, str) and g_url.startswith(("http://", "https://")):
+            return g_url
+    return None
+
+
+def _http_status(url: str, timeout_s: float = 6.0) -> Optional[int]:
+    try:
+        import urllib.request
+
+        req = urllib.request.Request(
+            url,
+            method="GET",
+            headers={"User-Agent": "openclaw-secondbrain/verify_pending_external"},
+        )
+        with urllib.request.urlopen(req, timeout=timeout_s) as resp:
+            return int(getattr(resp, "status", 200))
+    except Exception:
+        return None
+
+
+def main() -> int:
+    if not DB_PATH.exists():
+        out = {"success": False, "error": f"db missing: {DB_PATH}", "time": _now()}
+        Path(OUTPUT_FILE).write_text(json.dumps(out, indent=2))
+        print(out["error"])
+        return 1
+
+    store = EngramStore(str(DB_PATH))
+    all_egs = []
+    offset = 0
+    while True:
+        batch = store.get_all(limit=2000, offset=offset)
+        if not batch:
+            break
+        all_egs.extend(batch)
+        offset += len(batch)
+    pending = [
+        eg
+        for eg in all_egs
+        if (not eg.correctness.confirmed and eg.correctness.rejections == 0)
+    ]
+
+    confirmed = 0
+    rejected = 0
+    still_pending = 0
+    checked = 0
+
+    for eg in pending:
+        checked += 1
+        src = eg.metadata.get("source")
+        content = (eg.content or "").strip()
+
+        if src == "session" and (
+            content.startswith("Session Summary (sess_") or content.startswith("Please remember ")
+        ):
+            eg.correctness.rejections += 1
+            eg.correctness.last_reviewed = _now()
+            eg.correctness.review_history.append(
+                ReviewEntry(
+                    by="verify-pending",
+                    action="reject",
+                    at=_now(),
+                    note="Auto-reject: session placeholder",
+                )
+            )
+            store.save(eg)
+            rejected += 1
+            continue
+
+        if src == "web":
+            url = _get_url(eg.metadata)
+            if not url:
+                still_pending += 1
+                continue
+            status = _http_status(url)
+            if status is None:
+                still_pending += 1
+                continue
+            if 200 <= status < 300:
+                eg.correctness.confirmed = True
+                eg.correctness.confirmations += 1
+                eg.correctness.last_reviewed = _now()
+                eg.correctness.review_history.append(
+                    ReviewEntry(
+                        by="verify-pending",
+                        action="confirm",
+                        at=_now(),
+                        note=f"Auto-confirm: web url ok ({status}) {url}",
+                    )
+                )
+                store.save(eg)
+                confirmed += 1
+            else:
+                eg.correctness.rejections += 1
+                eg.correctness.last_reviewed = _now()
+                eg.correctness.review_history.append(
+                    ReviewEntry(
+                        by="verify-pending",
+                        action="reject",
+                        at=_now(),
+                        note=f"Auto-reject: web url status={status} {url}",
+                    )
+                )
+                store.save(eg)
+                rejected += 1
+            continue
+
+        still_pending += 1
+
+    out = {
+        "success": True,
+        "time": _now(),
+        "total": len(all_egs),
+        "pending_before": len(pending),
+        "checked": checked,
+        "confirmed": confirmed,
+        "rejected": rejected,
+        "still_pending": still_pending,
+    }
+    Path(OUTPUT_FILE).write_text(json.dumps(out, indent=2))
+    print(
+        f"VERIFY: pending_before={out['pending_before']} confirmed={confirmed} rejected={rejected} still_pending={still_pending}"
+    )
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

docs/OBSIDIAN.md

@@ -0,0 +1,75 @@
+# Obsidian Coupling (Second-Brain 2.0)
+
+This integrates an Obsidian vault with Second-Brain via two cron tasks:
+
+- `cron_tasks/ingest_obsidian.py` (vault → Second-Brain)
+- `cron_tasks/export_obsidian.py` (Second-Brain → vault)
+
+All settings live in `second-brain/data/obsidian_config.json`.
+
+## 1) Install / Sync the vault to the server
+
+You need a local folder on the server that contains an Obsidian vault (it must contain a `.obsidian/` directory), e.g.:
+
+- `/srv/obsidian/MyVault`
+- `/data/obsidian/MyVault`
+- `/root/Obsidian/MyVault`
+
+How you sync it is up to you (Syncthing, rsync, SMB mount, etc.).
+
+## 2) Set `vault_path` in config (auto or manual)
+
+### Auto-discover (only writes if unambiguous)
+
+```bash
+python3 second-brain/scripts/discover_obsidian_vault.py
+python3 second-brain/scripts/discover_obsidian_vault.py --write
+```
+
+If multiple vaults are detected, it prints them and refuses to write.
+
+### Manual
+
+Edit `second-brain/data/obsidian_config.json` and set:
+
+- `vault_path` to the vault directory (the parent of `.obsidian/`)
+
+## 3) Enable ingest/export
+
+In `second-brain/data/obsidian_config.json`:
+
+- Set `enabled.ingest` to `true` to ingest vault markdown into Second-Brain
+- Set `enabled.export` to `true` to export Second-Brain engrams into the vault
+
+## 4) Enable timers (systemd)
+
+This repo ships unit files in `systemd/`:
+
+- `systemd/openclaw-secondbrain-ingest-obsidian.service`
+- `systemd/openclaw-secondbrain-ingest-obsidian.timer`
+- `systemd/openclaw-secondbrain-export-obsidian.service`
+- `systemd/openclaw-secondbrain-export-obsidian.timer`
+
+Install them (copy or symlink) to `/etc/systemd/system/`, then:
+
+```bash
+sudo systemctl daemon-reload
+sudo systemctl enable --now openclaw-secondbrain-ingest-obsidian.timer
+sudo systemctl enable --now openclaw-secondbrain-export-obsidian.timer
+```
+
+## 5) Verify
+
+Run once manually:
+
+```bash
+python3 openclaw_cron_wrapper.py ingest_obsidian
+python3 openclaw_cron_wrapper.py export_obsidian
+```
+
+What to expect:
+
+- If `vault_path` is missing/invalid, both tasks **skip** safely (no writes to random paths).
+- Ingest creates/updates `second-brain/data/obsidian_ingest_state.json`.
+- Export writes markdown files to `<vault_path>/<export.subdir>/` (default: `SecondBrain/`) and tracks state in `second-brain/data/obsidian_export_state.json`.
+

docs/RELEASE_CHECKLIST.md

@@ -0,0 +1,113 @@
+# Second-Brain 2.0 — Release Checklist (Grundversion + FastAPI)
+
+Scope: OpenClaw workspace at `/root/.openclaw/workspace` with `second-brain/` and the shipped `second-brain/systemd/` unit files.
+
+This checklist is copy/paste friendly. Run as a user with `sudo` (systemd commands need it).
+
+## 0) Preconditions (one-time per host)
+
+### Repo + Python sanity
+
+```bash
+cd /root/.openclaw/workspace
+test -d second-brain || { echo "missing: second-brain/"; exit 1; }
+python3 --version
+```
+
+### Ensure systemd units are installed (copy/symlink)
+
+```bash
+ls -la /etc/systemd/system/openclaw-secondbrain-*.timer /etc/systemd/system/openclaw-secondbrain-*.service 2>/dev/null || true
+ls -la /etc/systemd/system/openclaw-memory-archive.* 2>/dev/null || true
+```
+
+If missing, install them (symlink is fine; copy is fine too):
+
+```bash
+sudo ln -sf /root/.openclaw/workspace/second-brain/systemd/openclaw-secondbrain-*.service /etc/systemd/system/
+sudo ln -sf /root/.openclaw/workspace/second-brain/systemd/openclaw-secondbrain-*.timer /etc/systemd/system/
+sudo ln -sf /root/.openclaw/workspace/second-brain/systemd/openclaw-memory-archive.* /etc/systemd/system/
+sudo ln -sf /root/.openclaw/workspace/second-brain/systemd/openclaw-secondbrain-dashboard.service /etc/systemd/system/
+sudo systemctl daemon-reload
+```
+
+Optional (verification hardening):
+
+```bash
+sudo ln -sf /root/.openclaw/workspace/second-brain/systemd/openclaw-secondbrain-verify-pending.* /etc/systemd/system/
+sudo systemctl daemon-reload
+sudo systemctl enable --now openclaw-secondbrain-verify-pending.timer
+```
+
+### Enable timers
+
+```bash
+sudo systemctl enable --now openclaw-secondbrain-backup.timer
+sudo systemctl enable --now openclaw-secondbrain-ingest-memory.timer
+sudo systemctl enable --now openclaw-secondbrain-index-vectors.timer
+sudo systemctl enable --now openclaw-secondbrain-review.timer
+sudo systemctl enable --now openclaw-secondbrain-heartbeat.timer
+sudo systemctl enable --now openclaw-secondbrain-proactive-search.timer
+sudo systemctl enable --now openclaw-memory-archive.timer
+```
+
+## 1) Release QA — systemd status + timers
+
+### Verify timers are active and scheduled
+
+```bash
+sudo systemctl list-timers --all | grep -E 'openclaw-(secondbrain|memory-archive)' || true
+sudo systemctl --failed --no-pager || true
+```
+
+### Verify the oneshot services can run successfully (manual trigger)
+
+```bash
+sudo systemctl start openclaw-secondbrain-ingest-memory.service
+sudo systemctl start openclaw-secondbrain-index-vectors.service
+sudo systemctl start openclaw-secondbrain-review.service
+sudo systemctl start openclaw-secondbrain-backup.service
+sudo systemctl start openclaw-secondbrain-heartbeat.service
+sudo systemctl start openclaw-secondbrain-proactive-search.service
+sudo systemctl start openclaw-memory-archive.service
+```
+
+Logs:
+
+```bash
+tail -n 200 /root/.openclaw/workspace/cron_wrapper.log
+sudo journalctl -u openclaw-secondbrain-review.service -n 200 --no-pager
+```
+
+## 2) Release QA — data + DB invariants
+
+```bash
+ls -la /root/.openclaw/workspace/second-brain/data/brain.sqlite
+python3 - <<'PY'
+import sqlite3
+db="/root/.openclaw/workspace/second-brain/data/brain.sqlite"
+con=sqlite3.connect(db)
+cur=con.cursor()
+print("integrity_check:", cur.execute("PRAGMA integrity_check").fetchone()[0])
+print("engrams:", cur.execute("SELECT COUNT(*) FROM engrams").fetchone()[0])
+con.close()
+PY
+```
+
+## 3) Release QA — FastAPI (HTTP endpoints + logs)
+
+FastAPI service:
+
+```bash
+sudo systemctl enable --now openclaw-secondbrain-dashboard.service
+sudo systemctl status openclaw-secondbrain-dashboard.service --no-pager
+```
+
+Endpoint checks:
+
+```bash
+curl -fsS http://127.0.0.1:8501/healthz && echo
+curl -fsS http://127.0.0.1:8501/api/config
+curl -fsS http://127.0.0.1:8501/api/stats
+curl -fsS "http://127.0.0.1:8501/api/engrams?limit=1&offset=0"
+```

docs/dashboard-ui-ux-design.md

@@ -0,0 +1,215 @@
+# Second-Brain Dashboard UI/UX Design Plan (mobile-first)
+
+Basis: `second-brain/templates/dashboard.html`, `second-brain/static/style.css` (aktueller Stand) + neue Graph-Controls aus `/tmp/second-brain-staging/`.
+
+## 1) Konkreter Design-Plan
+
+### Ziele (UX)
+- **Schnelles Triaging unterwegs:** Pending/Errors sofort sichtbar, 1-Hand-Bedienung.
+- **Konsistentes Design-System:** einheitliche Buttons/Inputs/Panels statt Einzellösungen.
+- **Graph als Diagnose-Tool:** klare Controls, Legende, nachvollziehbares Feedback (Loading/Empty/Errors).
+
+### Farbschema (Dark, high-contrast, "indigo + emerald")
+- **Background:** sehr dunkel (nahe #0f1117) für weniger Blendung.
+- **Surface (Cards/Panels):** abgestufte Flächen (Surface-1, Surface-2) für Hierarchie.
+- **Primary:** Indigo/Blue für interaktive Elemente und Highlights (bisher #6c8af5 bleibt als Basis).
+- **Success:** Emerald für Confirm/OK (bisher #3a7d3a → etwas heller/satter).
+- **Danger:** Red für Errors/Reject.
+- **Warning:** Amber für Pending/Match/Attention.
+- **Text:** fast-weiß, sekundär gedimmt.
+
+### Typografie
+- Systemfont-Stack (schnell, gut lesbar): `ui-sans-serif, system-ui, -apple-system, Segoe UI, Roboto, Arial`.
+- Skala (mobile-first):
+  - `text-xs` 12px (Labels, Meta)
+  - `text-sm` 13–14px (secondary)
+  - `text-md` 15–16px (Body)
+  - `text-lg` 18–20px (Titles)
+- **Ziffern:** optional `font-variant-numeric: tabular-nums;` für Stats.
+
+### Spacing/Rhythm
+- 4px Grid; Standard-Gaps: 8/12/16.
+- Container-Padding: 12px (mobile), 16–20px (>=768px).
+- Border-radius: 12–16px (Cards/Modals), 10px (Inputs/Buttons), 999px (Pills).
+
+### Komponenten (konkret)
+
+#### A) Tabs
+- Tabs bleiben als 3 Buttons, aber:
+  - **Active State** deutlicher (background + border + subtle glow).
+  - **Touch target** min. 44px Höhe.
+  - Sticky bleibt, aber mit leichter **Backdrop-Blurring** (wenn möglich) oder solid surface.
+
+#### B) Search
+- Search-Row wird als **kompakte Toolbar** gestaltet:
+  - Input + Filter in einer Zeile.
+  - Optional Quick-Chips darunter: `All / Pending / Confirmed / Errors` (klickbar) als Alternative zum Select.
+- Clear-Button (×) im Input (per CSS `::-webkit-search-cancel-button` oder eigener Button) für Mobile.
+
+#### C) Cards
+- Karte als 3 Zonen: Header (badges/tags/date), Body (content), Footer (actions).
+- Status wird stärker codiert:
+  - left-border + kleine **Status-Pill** (OK/Pending/Error) mit eindeutiger Farbe.
+- Body: bessere Lesbarkeit via `line-height: 1.55` und max-height/clamp optional.
+
+#### D) Modal
+- Modal als **Bottom Sheet** auf Mobile (>=50vh) + klassisches Center-Modal auf Desktop.
+- Close-Button größer + Tap-Area.
+- Inhalt in Tabs/Sections (History/Meta/Content) optional später.
+
+#### E) Graph + Controls (aus Staging)
+- Controls als **Control Bar** oberhalb Canvas:
+  - Primary: Physics toggle.
+  - Secondary: Fit, Reset, Reload.
+  - Text labels kurz (z.B. `Physics` statt `Physics: off`, state als Badge).
+- Canvas passt sich an Viewport an:
+  - `width: min(100%, 560px)`; Height: `min(65vh, 560px)` (CSS statt fester HTML Attribute, wenn möglich).
+- Legende als einklappbares Panel (`Details`/`summary`) oder leichtes Panel unter Canvas.
+
+#### F) Status Panels
+- Status-View nutzt vorhandene `.panel`/`.kv-*`:
+  - Gruppen: System, Storage, Jobs, Insights, Pending Queue.
+  - Jede Gruppe als Panel mit klarer Title Row.
+- Kritische Werte (Errors/Pending/Queue) farblich markieren.
+
+## 2) CSS-Variablen (Theme-Tokens) + Mapping
+
+### Token-Vorschlag (`:root`)
+```css
+:root {
+  /* typography */
+  --font-sans: ui-sans-serif, system-ui, -apple-system, Segoe UI, Roboto, Arial, sans-serif;
+
+  /* colors */
+  --bg: #0f1117;
+  --surface-1: #14151d;
+  --surface-2: #1a1b26;
+  --border: #2a2d3a;
+
+  --text: #e8e8ee;
+  --text-muted: #8b90a3;
+  --text-dim: #5c6276;
+
+  --primary: #6c8af5;      /* existing */
+  --primary-2: #8aa1ff;
+  --success: #2fbf71;
+  --danger: #ef4444;
+  --warning: #f7d154;      /* existing-ish */
+
+  /* shadows */
+  --shadow-1: 0 1px 0 rgba(0,0,0,.25), 0 8px 24px rgba(0,0,0,.35);
+
+  /* radius */
+  --r-sm: 10px;
+  --r-md: 14px;
+  --r-lg: 16px;
+
+  /* spacing */
+  --s-1: 4px;
+  --s-2: 8px;
+  --s-3: 12px;
+  --s-4: 16px;
+  --s-5: 20px;
+
+  /* control sizes */
+  --tap: 44px;
+}
+```
+
+### Mapping auf existierende Selektoren
+- `body`/`.app`
+  - `background: var(--bg)` statt `#141419`
+  - `font-family: var(--font-sans)`
+  - `color: var(--text)`
+- `.stats-bar`, `.tabs-bar`, `.search-box`
+  - `background: var(--surface-1)` (Stats ggf. Gradient bleibt, aber auf Tokens)
+  - `border-bottom: 1px solid var(--border)`
+- `.panel`, `.card`, `.modal-content`, `.graph-legend`
+  - `background: var(--surface-2)`
+  - `border: 1px solid var(--border)`
+  - `border-radius: var(--r-md)`
+- `.stat-num`, `#pageNum`, `.tab-btn.active`, `#searchInput:focus`
+  - `color/border-color: var(--primary)`
+- `.muted`, `.stat-label`, `.kv-key`, `.date`
+  - `color: var(--text-muted)` bzw. `var(--text-dim)`
+- Buttons
+  - vereinheitlichen über `.btn` + Modifier: `.btn.primary`, `.btn.danger`, `.btn.success`, `.btn.ghost`
+  - `min-height: var(--tap)` für Touch
+
+## 3) 5–10 priorisierte UI-Änderungen (mit Begründung)
+
+1) **Design Tokens (CSS vars) einführen** → reduziert Farbmix, erleichtert spätere Themes/Anpassungen.
+2) **Einheitliche Button-Komponente (`.btn`)** (inkl. `:active`, `:disabled`, `min-height`) → bessere Touch-UX, konsistente Interaktion.
+3) **Graph-Controls + Legende aus Staging in den Main-Template-Stand ziehen** → Graph wird tatsächlich bedienbar/selbsterklärend.
+4) **Responsive Graph-Canvas (CSS gesteuert)** statt fixer `width/height` → bessere Nutzung auf Phones, weniger Scroll.
+5) **Search als Toolbar + Clear-Action** → schnelleres Filtern unterwegs, weniger Friktion.
+6) **Modal als Bottom-Sheet auf Mobile** → angenehmer für längeren Content + History, weniger „winziges Fenster“.
+7) **Status/Health Werte farblich akzentuieren** (pending/errors/warn) → schnelleres Erkennen von Problemen.
+8) **Cards: Status-Pill + typografische Lesbarkeit** (line-height, spacing) → weniger „Textblock“, bessere Scanbarkeit.
+9) **Accessibility-Basics**: Focus-Rings, Kontrast, `prefers-reduced-motion` → weniger „invisible focus“ und bessere Bedienbarkeit.
+10) **Top-level Layout Max-Width für Desktop** (z.B. 560–720px) → verhindert „zu breite“ Zeilen.
+
+## 4) Optionale Patch-Vorschläge (Diff-Snippets, NICHT anwenden)
+
+> Hinweis: Snippets sind bewusst klein gehalten. Gesamt < 120 Zeilen.
+
+### Snippet A — Tokens + Button-System (style.css)
+```diff
+--- a/second-brain/static/style.css
++++ b/second-brain/static/style.css
+@@
++:root {
++  --font-sans: ui-sans-serif, system-ui, -apple-system, Segoe UI, Roboto, Arial, sans-serif;
++  --bg:#0f1117; --surface-1:#14151d; --surface-2:#1a1b26; --border:#2a2d3a;
++  --text:#e8e8ee; --text-muted:#8b90a3; --text-dim:#5c6276;
++  --primary:#6c8af5; --success:#2fbf71; --danger:#ef4444; --warning:#f7d154;
++  --r-sm:10px; --r-md:14px; --r-lg:16px;
++  --s-2:8px; --s-3:12px; --s-4:16px;
++  --tap:44px;
++}
++
++body { font-family: var(--font-sans); background: var(--bg); color: var(--text); }
++
++.btn{
++  min-height: var(--tap);
++  background: #1e1e28;
++  border: 1px solid var(--border);
++  border-radius: var(--r-sm);
++  padding: 8px 12px;
++  color: #cfd3ff;
++  font-weight: 700;
++}
++.btn.primary{ border-color: var(--primary); box-shadow: 0 0 0 1px rgba(108,138,245,0.18) inset; }
++.btn.success{ background: rgba(47,191,113,.18); border-color: rgba(47,191,113,.35); }
++.btn.danger{ background: rgba(239,68,68,.16); border-color: rgba(239,68,68,.35); }
++.btn:active{ transform: scale(.98); }
++.btn:disabled{ opacity: .45; }
+```
+
+### Snippet B — Graph Controls + Legend übernehmen (dashboard.html)
+```diff
+--- a/second-brain/templates/dashboard.html
++++ b/second-brain/templates/dashboard.html
+@@
+-        <div class="graph" id="graph" style="display:none;">
+-            <canvas id="graphCanvas" width="440" height="520"></canvas>
+-            <div class="muted small" id="graphHint">Lade Graph…</div>
+-        </div>
++        <div class="graph" id="graph" style="display:none;">
++            <div class="graph-controls">
++                <button class="btn primary" id="btnGraphPhysics" onclick="toggleGraphPhysics()">Physics</button>
++                <button class="btn" onclick="resetGraphView()">Reset</button>
++                <button class="btn" onclick="fitGraphView()">Fit</button>
++                <button class="btn" onclick="reloadGraph()">Reload</button>
++            </div>
++            <canvas id="graphCanvas" width="440" height="520"></canvas>
++            <div class="graph-hint muted small" id="graphHint">Lade Graph…</div>
++            <div class="graph-legend">
++                <div><strong>Graph</strong>: Zoom (Wheel/Pinch), Pan (Drag). Klick auf Engram öffnet Details, Klick auf Tag setzt Suche.</div>
++                <div class="legend-row"><span class="legend-dot engram"></span> Engram</div>
++                <div class="legend-row"><span class="legend-dot tag"></span> Tag</div>
++                <div class="legend-row"><span class="legend-dot match"></span> Match</div>
++            </div>
++        </div>
+```
+

fastapi_app.py

@@ -0,0 +1,838 @@
+#!/usr/bin/env python3
+"""
+Second Brain FastAPI Dashboard
+
+Goals:
+- "Release-ready" defaults (no hardcoded absolute paths)
+- Minimal config via env vars
+- Serves the existing static dashboard (templates/dashboard.html + static/)
+"""
+
+import json
+import os
+import sqlite3
+import subprocess
+from datetime import datetime, timezone
+from pathlib import Path
+from uuid import uuid4
+from urllib.parse import urlparse
+
+from fastapi import FastAPI, Form, Query, Request
+from fastapi.responses import HTMLResponse, JSONResponse, PlainTextResponse, StreamingResponse
+from fastapi.staticfiles import StaticFiles
+
+# ─── Config ──────────────────────────────────────────────────────────────────
+REPO_ROOT = Path(__file__).resolve().parent
+WORKSPACE = Path(os.environ.get("SECOND_BRAIN_WORKSPACE", str(REPO_ROOT))).resolve()
+DB_PATH = Path(os.environ.get("SECOND_BRAIN_DB_PATH", str(WORKSPACE / "data" / "brain.sqlite"))).resolve()
+
+PORT = int(os.environ.get("SECOND_BRAIN_PORT", os.environ.get("PORT", "8501")))
+HOST = os.environ.get("SECOND_BRAIN_HOST", "0.0.0.0")
+
+
+def create_app() -> FastAPI:
+    app = FastAPI(title="Second Brain Dashboard")
+
+    static_dir = WORKSPACE / "static"
+    if static_dir.is_dir():
+        app.mount("/static", StaticFiles(directory=str(static_dir)), name="static")
+
+    return app
+
+
+app = create_app()
+
+# ─── Helpers ─────────────────────────────────────────────────────────────────
+def get_db():
+    if not DB_PATH.exists():
+        raise FileNotFoundError(f"DB not found: {DB_PATH}")
+    conn = sqlite3.connect(str(DB_PATH))
+    conn.row_factory = sqlite3.Row
+    return conn
+
+
+def parse_engram(row: sqlite3.Row) -> dict:
+    meta = json.loads(row["metadata_json"] or "{}")
+    correctness = json.loads(row["correctness_json"] or "{}")
+    return {
+        "id": row["id"],
+        "content": row["content"],
+        "confidence": meta.get("confidence", 0.0),
+        "confirmed": correctness.get("confirmed", False),
+        "confirmations": correctness.get("confirmations", 0),
+        "rejections": correctness.get("rejections", 0),
+        "tags": meta.get("tags", []),
+        "created": meta.get("created", row["created_at"]),
+        "modified": meta.get("modified", row["modified_at"]),
+        "last_reviewed": correctness.get("last_reviewed"),
+        "review_history": correctness.get("review_history", []),
+        "source": meta.get("source", "unknown"),
+        "access_count": meta.get("access_count", 0),
+        "grounding": meta.get("grounding", 0),
+    }
+
+
+def _now_iso() -> str:
+    return datetime.now(timezone.utc).isoformat()
+
+
+def _update_correctness(engram_id: str, *, action: str, reason: str | None = None) -> dict:
+    """
+    Update correctness_json for an engram. action: confirm|reject
+    """
+    conn = get_db()
+    c = conn.cursor()
+    row = c.execute("SELECT correctness_json FROM engrams WHERE id = ?", (engram_id,)).fetchone()
+    if not row:
+        conn.close()
+        raise FileNotFoundError(f"Engram not found: {engram_id}")
+
+    corr = json.loads(row["correctness_json"] or "{}")
+    corr.setdefault("confirmed", False)
+    corr.setdefault("confirmations", 0)
+    corr.setdefault("rejections", 0)
+    corr.setdefault("review_history", [])
+    corr["last_reviewed"] = _now_iso()
+
+    entry = {
+        "by": "dashboard",
+        "action": action,
+        "at": corr["last_reviewed"],
+        "note": (reason or "").strip(),
+    }
+    try:
+        corr["review_history"].append(entry)
+    except Exception:
+        corr["review_history"] = [entry]
+
+    if action == "confirm":
+        corr["confirmed"] = True
+        corr["confirmations"] = int(corr.get("confirmations", 0) or 0) + 1
+    elif action == "reject":
+        corr["rejections"] = int(corr.get("rejections", 0) or 0) + 1
+
+    c.execute(
+        "UPDATE engrams SET correctness_json = ?, modified_at = ? WHERE id = ?",
+        (json.dumps(corr, ensure_ascii=False), corr["last_reviewed"], engram_id),
+    )
+    conn.commit()
+    conn.close()
+    return {"ok": True}
+
+
+def _bump_access(engram_id: str) -> dict:
+    conn = get_db()
+    c = conn.cursor()
+    row = c.execute("SELECT metadata_json FROM engrams WHERE id = ?", (engram_id,)).fetchone()
+    if not row:
+        conn.close()
+        raise FileNotFoundError(f"Engram not found: {engram_id}")
+    meta = json.loads(row["metadata_json"] or "{}")
+    meta["access_count"] = int(meta.get("access_count", 0) or 0) + 1
+    meta["last_accessed"] = _now_iso()
+    c.execute(
+        "UPDATE engrams SET metadata_json = ?, modified_at = ? WHERE id = ?",
+        (json.dumps(meta, ensure_ascii=False), meta["last_accessed"], engram_id),
+    )
+    conn.commit()
+    conn.close()
+    return {"ok": True}
+
+def _safe_json_extract_tags(meta_json: str) -> list[str]:
+    try:
+        d = json.loads(meta_json or "{}")
+        tags = d.get("tags") or []
+        return [t for t in tags if isinstance(t, str)]
+    except Exception:
+        return []
+
+def _host_from_meta(meta_json: str) -> str | None:
+    try:
+        d = json.loads(meta_json or "{}")
+        grounding = d.get("grounding")
+        url = d.get("url")
+        if isinstance(grounding, dict) and isinstance(grounding.get("url"), str):
+            url = grounding.get("url")
+        if not isinstance(url, str):
+            return None
+        parsed = urlparse(url)
+        return parsed.hostname
+    except Exception:
+        return None
+
+def _systemd_unit_state(unit: str) -> dict:
+    """
+    Best-effort systemd status snapshot for a known unit.
+    Never raises; returns minimal fields.
+    """
+    try:
+        out = subprocess.check_output(
+            ["systemctl", "show", unit, "--no-page", "--property=ActiveState,SubState,Result,ExecMainStatus,ExecMainCode,ExecMainStartTimestamp,ExecMainExitTimestamp"],
+            text=True,
+            stderr=subprocess.STDOUT,
+            timeout=2,
+        )
+        kv = {}
+        for line in out.splitlines():
+            if "=" in line:
+                k, v = line.split("=", 1)
+                kv[k] = v
+        return {
+            "unit": unit,
+            "active": kv.get("ActiveState"),
+            "sub": kv.get("SubState"),
+            "result": kv.get("Result"),
+            "exit_status": kv.get("ExecMainStatus"),
+            "start_ts": kv.get("ExecMainStartTimestamp"),
+            "exit_ts": kv.get("ExecMainExitTimestamp"),
+        }
+    except Exception as e:
+        return {"unit": unit, "error": str(e)}
+
+def _dir_size_bytes(path: Path) -> int:
+    total = 0
+    try:
+        for p in path.rglob("*"):
+            try:
+                if p.is_file():
+                    total += p.stat().st_size
+            except Exception:
+                pass
+    except Exception:
+        pass
+    return total
+
+# ─── API Endpoints ───────────────────────────────────────────────────────────
+
+@app.get("/healthz", response_class=PlainTextResponse)
+def healthz():
+    return "ok"
+
+
+@app.get("/api/config")
+def api_config():
+    return {
+        "workspace": str(WORKSPACE),
+        "db_path": str(DB_PATH),
+    }
+
+@app.get("/api/db_info")
+def api_db_info():
+    if not DB_PATH.exists():
+        raise FileNotFoundError(f"DB not found: {DB_PATH}")
+    st = DB_PATH.stat()
+    return {
+        "db_path": str(DB_PATH),
+        "size_bytes": st.st_size,
+        "mtime": datetime.fromtimestamp(st.st_mtime, tz=timezone.utc).isoformat(),
+    }
+
+@app.get("/api/storage_stats")
+def api_storage_stats():
+    conn = get_db()
+    c = conn.cursor()
+    total = c.execute("SELECT COUNT(*) FROM engrams").fetchone()[0]
+    confirmed = c.execute(
+        "SELECT COUNT(*) FROM engrams WHERE json_extract(correctness_json, '$.confirmed') = 1"
+    ).fetchone()[0]
+    sources = {
+        r[0]: r[1]
+        for r in c.execute(
+            "SELECT json_extract(metadata_json, '$.source') AS src, COUNT(*) FROM engrams GROUP BY src ORDER BY COUNT(*) DESC"
+        ).fetchall()
+        if r[0] is not None
+    }
+    conn.close()
+
+    chroma_dir = WORKSPACE / "data" / "chroma"
+    emb_cache_dir = WORKSPACE / "data" / "embedding_cache"
+    vec_state_path = WORKSPACE / "data" / "vector_index_state.json"
+
+    vec_state = {}
+    if vec_state_path.exists():
+        try:
+            vec_state = json.loads(vec_state_path.read_text())
+        except Exception:
+            vec_state = {}
+
+    obsidian_cfg_path = WORKSPACE / "data" / "obsidian_config.json"
+    obsidian_cfg = None
+    if obsidian_cfg_path.exists():
+        try:
+            obsidian_cfg = json.loads(obsidian_cfg_path.read_text())
+        except Exception:
+            obsidian_cfg = {"raw": obsidian_cfg_path.read_text()[:2000]}
+
+    backup_files = sorted((WORKSPACE / "data").glob("backup_*.jsonl"))
+
+    return {
+        "sql": {
+            "total_engrams": total,
+            "confirmed": confirmed,
+            "pending": total - confirmed,
+            "by_source": sources,
+        },
+        "vector": {
+            "chroma_dir": str(chroma_dir),
+            "chroma_size_bytes": _dir_size_bytes(chroma_dir) if chroma_dir.exists() else 0,
+            "embedding_cache_dir": str(emb_cache_dir),
+            "embedding_cache_files": len(list(emb_cache_dir.glob("*.json"))) if emb_cache_dir.exists() else 0,
+            "vector_state": vec_state,
+        },
+        "obsidian": {
+            "config_path": str(obsidian_cfg_path),
+            "configured": bool(obsidian_cfg),
+            "config": obsidian_cfg,
+        },
+        "backups": {
+            "count": len(backup_files),
+            "latest": str(backup_files[-1]) if backup_files else None,
+        },
+    }
+
+@app.get("/api/jobs")
+def api_jobs():
+    # Known units that influence "freshness" of the brain.
+    units = [
+        "openclaw-secondbrain-ingest-memory.service",
+        "openclaw-secondbrain-index-vectors.service",
+        "openclaw-secondbrain-review.service",
+        "openclaw-secondbrain-heartbeat.service",
+        "openclaw-secondbrain-verify-pending.service",
+    ]
+    return {"items": [_systemd_unit_state(u) for u in units]}
+
+@app.get("/api/insights")
+def api_insights(limit: int = Query(8, ge=1, le=50)):
+    conn = get_db()
+    c = conn.cursor()
+    rows = c.execute(
+        "SELECT id, metadata_json, correctness_json, created_at, modified_at FROM engrams ORDER BY created_at DESC LIMIT 2000"
+    ).fetchall()
+    total = c.execute("SELECT COUNT(*) FROM engrams").fetchone()[0]
+    confirmed = c.execute(
+        "SELECT COUNT(*) FROM engrams WHERE json_extract(correctness_json, '$.confirmed') = 1"
+    ).fetchone()[0]
+    pending = total - confirmed
+
+    tag_counts: dict[str, int] = {}
+    source_counts: dict[str, int] = {}
+    host_counts: dict[str, int] = {}
+    active: list[dict] = []
+    forgotten: list[dict] = []
+
+    for r in rows:
+        meta = json.loads(r["metadata_json"] or "{}")
+        src = meta.get("source", "unknown")
+        source_counts[src] = source_counts.get(src, 0) + 1
+        for t in (meta.get("tags") or []):
+            if isinstance(t, str):
+                tag_counts[t] = tag_counts.get(t, 0) + 1
+        host = _host_from_meta(r["metadata_json"])
+        if host:
+            host_counts[host] = host_counts.get(host, 0) + 1
+
+        access_count = int(meta.get("access_count", 0) or 0)
+        created = meta.get("created", r["created_at"])
+        if access_count >= 5 and len(active) < limit:
+            active.append(
+                {
+                    "id": r["id"],
+                    "access_count": access_count,
+                    "source": src,
+                    "created": created,
+                }
+            )
+        if access_count == 0 and len(forgotten) < limit:
+            forgotten.append(
+                {
+                    "id": r["id"],
+                    "access_count": access_count,
+                    "source": src,
+                    "created": created,
+                }
+            )
+
+    def top_k(d: dict[str, int]) -> list[dict]:
+        return [
+            {"key": k, "count": v}
+            for k, v in sorted(d.items(), key=lambda kv: kv[1], reverse=True)[:limit]
+        ]
+
+    conn.close()
+    return {
+        "total": total,
+        "confirmed": confirmed,
+        "pending": pending,
+        "top_tags": top_k(tag_counts),
+        "top_sources": top_k(source_counts),
+        "top_hosts": top_k(host_counts),
+        "active_engrams": active,
+        "forgotten_engrams": forgotten,
+    }
+
+@app.get("/api/graph")
+def api_graph(limit_nodes: int = Query(200, ge=50, le=1000)):
+    """
+    Returns a lightweight graph view:
+    - Nodes: engrams + tag:<tag> + host:<hostname>
+    - Edges: engram->tag and engram->host plus explicit engrams_links edges.
+    """
+    conn = get_db()
+    c = conn.cursor()
+    rows = c.execute("SELECT id, metadata_json FROM engrams ORDER BY created_at DESC LIMIT 1000").fetchall()
+    link_rows = c.execute("SELECT from_id, to_id FROM engrams_links ORDER BY rowid DESC LIMIT 2000").fetchall()
+    conn.close()
+
+    nodes: dict[str, dict] = {}
+    edges: list[dict] = []
+
+    def add_node(nid: str, kind: str, label: str | None = None, weight: float | None = None):
+        if nid not in nodes:
+            nodes[nid] = {"id": nid, "kind": kind}
+        if label is not None:
+            nodes[nid]["label"] = label
+        if weight is not None:
+            nodes[nid]["weight"] = weight
+
+    for r in rows:
+        eid = r["id"]
+        add_node(eid, "engram", label=eid[:8])
+        for t in _safe_json_extract_tags(r["metadata_json"]):
+            tid = f"tag:{t}"
+            add_node(tid, "tag", label=t)
+            edges.append({"from": eid, "to": tid, "kind": "has_tag"})
+        host = _host_from_meta(r["metadata_json"])
+        if host:
+            hid = f"host:{host}"
+            add_node(hid, "host", label=host)
+            edges.append({"from": eid, "to": hid, "kind": "grounded_at"})
+
+    for fr, to in link_rows:
+        add_node(fr, "engram")
+        add_node(to, "engram")
+        edges.append({"from": fr, "to": to, "kind": "link"})
+
+    # Trim nodes to keep payload bounded (prefer engrams and connected tags/hosts)
+    if len(nodes) > limit_nodes:
+        # Keep a balanced subset: many engrams plus the most-connected non-engrams.
+        kept: dict[str, dict] = {}
+        engram_budget = int(limit_nodes * 0.7)
+
+        # 1) Keep newest engrams first (they appear first in `rows` loop insertion order)
+        for r in rows:
+            eid = r["id"]
+            if eid in nodes:
+                kept[eid] = nodes[eid]
+            if len(kept) >= engram_budget:
+                break
+
+        # 2) Rank remaining nodes by degree within current edge set
+        degree: dict[str, int] = {}
+        for e in edges:
+            degree[e["from"]] = degree.get(e["from"], 0) + 1
+            degree[e["to"]] = degree.get(e["to"], 0) + 1
+
+        remaining = [nid for nid in nodes.keys() if nid not in kept]
+        remaining.sort(key=lambda nid: degree.get(nid, 0), reverse=True)
+        for nid in remaining:
+            kept[nid] = nodes[nid]
+            if len(kept) >= limit_nodes:
+                break
+
+        nodes = kept
+        edges = [e for e in edges if e["from"] in nodes and e["to"] in nodes]
+
+    return {"nodes": list(nodes.values()), "edges": edges}
+
+@app.get("/api/events")
+def api_events():
+    """
+    Server-Sent Events stream for lightweight real-time UI refresh.
+    """
+    import time
+
+    def gen():
+        while True:
+            payload = {
+                "ts": datetime.now(timezone.utc).isoformat(),
+                "stats": api_stats(),
+                "storage": api_storage_stats(),
+                "jobs": api_jobs(),
+                "insights": api_insights(limit=8),
+            }
+            yield f"data: {json.dumps(payload, ensure_ascii=False)}\n\n"
+            time.sleep(5)
+
+    return StreamingResponse(gen(), media_type="text/event-stream")
+
+
+@app.exception_handler(FileNotFoundError)
+def handle_file_not_found(request: Request, exc: FileNotFoundError):
+    return JSONResponse(
+        status_code=503,
+        content={
+            "error": str(exc),
+            "hint": "Set SECOND_BRAIN_DB_PATH or SECOND_BRAIN_WORKSPACE to a valid location.",
+        },
+    )
+
+
+@app.exception_handler(sqlite3.Error)
+def handle_sqlite_error(request: Request, exc: sqlite3.Error):
+    return JSONResponse(status_code=500, content={"error": f"sqlite error: {exc}"})
+
+
+@app.get("/api/stats")
+def api_stats():
+    conn = get_db()
+    c = conn.cursor()
+    total = c.execute("SELECT COUNT(*) FROM engrams").fetchone()[0]
+    confirmed = c.execute(
+        "SELECT COUNT(*) FROM engrams WHERE json_extract(correctness_json, '$.confirmed') = 1"
+    ).fetchone()[0]
+    pending = total - confirmed
+    errors = c.execute(
+        "SELECT COUNT(*) FROM engrams WHERE json_extract(metadata_json, '$.tags') LIKE '%error%'"
+    ).fetchone()[0]
+    avg_conf = c.execute(
+        "SELECT AVG(json_extract(metadata_json, '$.confidence')) FROM engrams"
+    ).fetchone()[0] or 0.0
+    conn.close()
+    return {
+        "total": total,
+        "confirmed": confirmed,
+        "pending": pending,
+        "errors": errors,
+        "avg_confidence": round(avg_conf, 2),
+    }
+
+
+@app.get("/api/engrams")
+def api_engrams(
+    limit: int = Query(20, ge=1, le=100),
+    offset: int = Query(0, ge=0),
+    tag: str = Query(None),
+    confirmed: bool = Query(None),
+    search: str = Query(None),
+    min_confidence: float = Query(0.0),
+):
+    conn = get_db()
+    c = conn.cursor()
+    where_clauses = ["json_extract(metadata_json, '$.confidence') >= ?"]
+    params = [min_confidence]
+
+    if tag:
+        where_clauses.append("json_extract(metadata_json, '$.tags') LIKE ?")
+        params.append(f'%"{tag}"%')
+
+    if confirmed is not None:
+        where_clauses.append(
+            f"json_extract(correctness_json, '$.confirmed') = {int(confirmed)}"
+        )
+
+    if search:
+        # Use FTS
+        try:
+            ids = [
+                r[0] for r in c.execute(
+                    "SELECT rowid FROM engrams_fts WHERE content MATCH ? LIMIT 200",
+                    (search,)
+                ).fetchall()
+            ]
+            if ids:
+                placeholders = ",".join("?" * len(ids))
+                where_clauses.append(f"id IN ({placeholders})")
+                params.extend(ids)
+            else:
+                # Full-text fallback on content
+                where_clauses.append("content LIKE ?")
+                params.append(f"%{search}%")
+        except Exception:
+            where_clauses.append("content LIKE ?")
+            params.append(f"%{search}%")
+
+    where_sql = " AND ".join(where_clauses)
+    rows = c.execute(
+        f"""
+        SELECT * FROM engrams
+        WHERE {where_sql}
+        ORDER BY created_at DESC
+        LIMIT ? OFFSET ?
+        """,
+        params + [limit, offset],
+    ).fetchall()
+
+    result = [parse_engram(r) for r in rows]
+    conn.close()
+    return {"items": result, "limit": limit, "offset": offset}
+
+
+@app.get("/api/engrams/{engram_id}")
+def api_engram_detail(engram_id: str):
+    conn = get_db()
+    c = conn.cursor()
+    row = c.execute("SELECT * FROM engrams WHERE id = ?", (engram_id,)).fetchone()
+    if not row:
+        conn.close()
+        return JSONResponse({"error": "Not found"}, status_code=404)
+
+    # Links
+    links = c.execute(
+        "SELECT to_id FROM engrams_links WHERE from_id = ?", (engram_id,)
+    ).fetchall()
+    result = parse_engram(row)
+    result["links"] = [r[0] for r in links]
+    conn.close()
+    return result
+
+
+@app.get("/api/pending")
+def api_pending(
+    limit: int = Query(20, ge=1, le=200),
+    offset: int = Query(0, ge=0),
+    source: str | None = Query(None),
+):
+    conn = get_db()
+    c = conn.cursor()
+    where = ["json_extract(correctness_json, '$.confirmed') = 0"]
+    params: list = []
+    if source:
+        where.append("json_extract(metadata_json, '$.source') = ?")
+        params.append(source)
+
+    rows = c.execute(
+        f"""
+        SELECT * FROM engrams
+        WHERE {' AND '.join(where)}
+        ORDER BY created_at DESC
+        LIMIT ? OFFSET ?
+        """,
+        params + [limit, offset],
+    ).fetchall()
+    items = [parse_engram(r) for r in rows]
+    conn.close()
+    return {"items": items, "limit": limit, "offset": offset}
+
+
+@app.post("/api/engrams")
+def api_create_engram(content: str = Form(...), tags: str = Form("")):
+    content = (content or "").strip()
+    if not content:
+        return JSONResponse({"error": "content required"}, status_code=400)
+    tag_list = [t.strip() for t in (tags or "").split(",") if t.strip()]
+    now = _now_iso()
+    engram_id = str(uuid4())
+    meta = {
+        "source": "user",
+        "confidence": 0.7,
+        "created": now,
+        "modified": now,
+        "access_count": 0,
+        "last_accessed": now,
+        "tags": tag_list,
+        "session_id": None,
+        "agent_id": None,
+        "grounding": 0,
+    }
+    corr = {
+        "confirmed": False,
+        "confirmations": 0,
+        "rejections": 0,
+        "last_reviewed": None,
+        "review_history": [],
+    }
+    conn = get_db()
+    c = conn.cursor()
+    c.execute(
+        """
+        INSERT INTO engrams (id, content, metadata_json, correctness_json, links_json, hierarchy_json, embedding_json, created_at, modified_at)
+        VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
+        """,
+        (
+            engram_id,
+            content,
+            json.dumps(meta, ensure_ascii=False),
+            json.dumps(corr, ensure_ascii=False),
+            "[]",
+            "{}",
+            None,
+            now,
+            now,
+        ),
+    )
+    conn.commit()
+    conn.close()
+    return {"id": engram_id}
+
+
+@app.post("/api/engrams/{engram_id}/confirm")
+def api_confirm_engram(engram_id: str, reason: str = Form("")):
+    try:
+        return _update_correctness(engram_id, action="confirm", reason=reason)
+    except FileNotFoundError as e:
+        return JSONResponse({"error": str(e)}, status_code=404)
+
+
+@app.post("/api/engrams/{engram_id}/reject")
+def api_reject_engram(engram_id: str, reason: str = Form("")):
+    try:
+        return _update_correctness(engram_id, action="reject", reason=reason)
+    except FileNotFoundError as e:
+        return JSONResponse({"error": str(e)}, status_code=404)
+
+
+@app.post("/api/engrams/{engram_id}/refresh")
+def api_refresh_engram(engram_id: str):
+    try:
+        return _bump_access(engram_id)
+    except FileNotFoundError as e:
+        return JSONResponse({"error": str(e)}, status_code=404)
+
+
+@app.post("/api/engrams/{engram_id}/refresh")
+def api_refresh(engram_id: str):
+    conn = get_db()
+    c = conn.cursor()
+    row = c.execute(
+        "SELECT metadata_json, correctness_json FROM engrams WHERE id = ?", (engram_id,)
+    ).fetchone()
+    if not row:
+        conn.close()
+        return JSONResponse({"error": "Not found"}, status_code=404)
+
+    meta = json.loads(row["metadata_json"] or "{}")
+    correctness = json.loads(row["correctness_json"] or "{}")
+
+    # Simple heuristic: confidence based on confirmations vs rejections
+    conf = 0.5
+    conf += 0.1 * correctness.get("confirmations", 0)
+    conf -= 0.15 * correctness.get("rejections", 0)
+    conf = max(0.1, min(1.0, conf))
+
+    meta["confidence"] = round(conf, 2)
+    meta["modified"] = datetime.now(timezone.utc).isoformat()
+
+    c.execute(
+        "UPDATE engrams SET metadata_json = ?, modified_at = ? WHERE id = ?",
+        (json.dumps(meta), datetime.now(timezone.utc).isoformat(), engram_id),
+    )
+    conn.commit()
+    conn.close()
+    return {"success": True, "new_confidence": round(conf, 2)}
+
+
+@app.post("/api/engrams")
+def api_create_engram(content: str = Form(...), tags: str = Form(""), source: str = Form("web")):
+    engram_id = f"web-{datetime.now(timezone.utc).strftime('%Y%m%d-%H%M%S-%f')[:20]}"
+    now = datetime.now(timezone.utc).isoformat()
+    meta = {
+        "source": source,
+        "confidence": 0.5,
+        "created": now,
+        "modified": now,
+        "access_count": 0,
+        "last_accessed": now,
+        "tags": [t.strip() for t in tags.split(",") if t.strip()] or ["web"],
+        "session_id": None,
+        "agent_id": None,
+        "grounding": 0,
+        "hash": "",
+    }
+    correctness = {
+        "confirmed": False,
+        "confirmations": 0,
+        "rejections": 0,
+        "last_reviewed": None,
+        "review_history": [],
+    }
+    conn = get_db()
+    c = conn.cursor()
+    c.execute(
+        """
+        INSERT INTO engrams (id, content, metadata_json, correctness_json, links_json, hierarchy_json, created_at, modified_at)
+        VALUES (?, ?, ?, ?, ?, ?, ?, ?)
+        """,
+        (engram_id, content, json.dumps(meta), json.dumps(correctness), "[]", '{"parent": null, "children": [], "depth": 0}', now, now),
+    )
+    conn.commit()
+    conn.close()
+    return {"success": True, "engram_id": engram_id}
+
+
+@app.get("/api/pending")
+def api_pending(limit: int = Query(20, ge=1, le=100), offset: int = Query(0, ge=0)):
+    conn = get_db()
+    c = conn.cursor()
+    rows = c.execute(
+        """
+        SELECT * FROM engrams
+        WHERE json_extract(correctness_json, '$.confirmed') = 0
+        ORDER BY created_at DESC
+        LIMIT ? OFFSET ?
+        """,
+        (limit, offset),
+    ).fetchall()
+    result = [parse_engram(r) for r in rows]
+    conn.close()
+    return {"items": result, "limit": limit, "offset": offset}
+
+
+@app.get("/api/search")
+def api_search(
+    q: str = Query(..., min_length=1),
+    min_confidence: float = Query(0.0),
+    limit: int = Query(20, ge=1, le=100),
+):
+    conn = get_db()
+    c = conn.cursor()
+    try:
+        ids = [
+            r[0] for r in c.execute(
+                "SELECT rowid FROM engrams_fts WHERE content MATCH ? LIMIT 200",
+                (q,)
+            ).fetchall()
+        ]
+        if ids:
+            placeholders = ",".join("?" * len(ids))
+            rows = c.execute(
+                f"""
+                SELECT * FROM engrams
+                WHERE id IN ({placeholders})
+                AND json_extract(metadata_json, '$.confidence') >= ?
+                ORDER BY created_at DESC
+                LIMIT ?
+                """,
+                ids + [min_confidence, limit],
+            ).fetchall()
+        else:
+            rows = []
+    except Exception:
+        rows = c.execute(
+            """
+            SELECT * FROM engrams
+            WHERE content LIKE ? AND json_extract(metadata_json, '$.confidence') >= ?
+            ORDER BY created_at DESC
+            LIMIT ?
+            """,
+            (f"%{q}%", min_confidence, limit),
+        ).fetchall()
+
+    result = [parse_engram(r) for r in rows]
+    conn.close()
+    return {"items": result, "query": q}
+
+
+# ─── Frontend ────────────────────────────────────────────────────────────────
+
+@app.get("/", response_class=HTMLResponse)
+def dashboard(request: Request):
+    with open(WORKSPACE / "templates" / "dashboard.html", "r", encoding="utf-8") as f:
+        html = f.read()
+    return HTMLResponse(content=html)
+
+
+# ─── Main ────────────────────────────────────────────────────────────────────
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run("fastapi_app:app", host=HOST, port=PORT)

openclaw_cron_wrapper.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+"""
+OpenClaw Cron Isolation Wrapper - Updatesicherer Workaround.
+Persistent: Tasks und Logs liegen im Workspace, nicht in /tmp.
+"""
+
+import os
+import sys
+import json
+import subprocess
+import tempfile
+from pathlib import Path
+from datetime import datetime, timezone
+
+# --- Konfiguration (persistent) ---
+WORKSPACE = Path("/root/.openclaw/workspace")
+CRON_TASKS_DIR = WORKSPACE / "cron_tasks"
+LOG_FILE = WORKSPACE / "cron_wrapper.log"
+BRAIN_DIR = WORKSPACE / "second-brain"
+
+
+def log(msg: str):
+    ts = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M:%S")
+    line = f"[{ts}] {msg}\n"
+    with open(LOG_FILE, "a") as f:
+        f.write(line)
+    print(line.strip())
+
+
+def run_isolated(task_name: str, task_args: dict = None) -> dict:
+    """
+    Führt einen Task in echt isolierter Umgebung aus.
+    Kein Zugriff auf Session-Files, nur stdout/stderr.
+    """
+    CRON_TASKS_DIR.mkdir(parents=True, exist_ok=True)
+    task_script = CRON_TASKS_DIR / f"{task_name}.py"
+    if not task_script.exists():
+        return {"success": False, "error": f"Task nicht gefunden: {task_script}"}
+
+    # Temp-Verzeichnis für Output (flüchtig ist OK, Ergebnis kommt via stdout)
+    temp_dir = tempfile.mkdtemp(prefix=f"cron_{task_name}_")
+    output_file = Path(temp_dir) / "output.json"
+
+    # Saubere Env: Keine OpenClaw-Session-Variablen
+    env = os.environ.copy()
+    for key in list(env.keys()):
+        if "OPENCLAW" in key.upper() or "SESSION" in key.upper():
+            del env[key]
+
+    env["CRON_TASK_NAME"] = task_name
+    env["CRON_OUTPUT_FILE"] = str(output_file)
+    env["BRAIN_DB"] = str(BRAIN_DIR / "data" / "brain.sqlite")
+
+    try:
+        result = subprocess.run(
+            [sys.executable, str(task_script)] + ([json.dumps(task_args)] if task_args else []),
+            capture_output=True,
+            text=True,
+            timeout=300,
+            cwd=str(temp_dir),
+            env=env,
+        )
+
+        stdout = result.stdout.strip()
+        stderr = result.stderr.strip()
+
+        output_data = {}
+        if output_file.exists():
+            try:
+                output_data = json.loads(output_file.read_text())
+            except Exception:
+                output_data = {"raw": output_file.read_text()}
+
+        return {
+            "success": result.returncode == 0,
+            "returncode": result.returncode,
+            "stdout": stdout[-2000:] if stdout else "",
+            "stderr": stderr[-1000:] if stderr else "",
+            "output": output_data,
+        }
+    except subprocess.TimeoutExpired:
+        return {"success": False, "error": "Timeout nach 300s"}
+    except Exception as e:
+        return {"success": False, "error": str(e)}
+
+
+def main():
+    import argparse
+    parser = argparse.ArgumentParser(description="OpenClaw Cron Isolation Wrapper")
+    parser.add_argument("task", help="Task-Name aus cron_tasks/")
+    parser.add_argument("--args", help="JSON-Args für den Task")
+    args = parser.parse_args()
+
+    task_args = json.loads(args.args) if args.args else None
+    result = run_isolated(args.task, task_args)
+
+    print(json.dumps(result, indent=2, default=str))
+    return 0 if result["success"] else 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())

requirements-dashboard.txt

@@ -0,0 +1,4 @@
+fastapi>=0.110
+uvicorn[standard]>=0.23
+jinja2>=3.1
+python-multipart>=0.0.9

scripts/discover_obsidian_vault.py

@@ -0,0 +1,159 @@
+#!/usr/bin/env python3
+"""
+Auto-discover an Obsidian vault on this server and (optionally) write it into:
+  second-brain/data/obsidian_config.json
+
+Safety:
+- Only writes when exactly one vault is detected (unambiguous).
+- A "vault" is a directory that contains a `.obsidian/` folder.
+"""
+
+from __future__ import annotations
+
+import argparse
+import json
+import os
+from pathlib import Path
+from typing import Iterable
+
+
+WORKSPACE = Path("/root/.openclaw/workspace")
+BRAIN_DIR = WORKSPACE / "second-brain"
+CONFIG_PATH = BRAIN_DIR / "data" / "obsidian_config.json"
+
+
+def _iter_common_candidates() -> Iterable[Path]:
+    env = os.environ.get("OBSIDIAN_VAULT_PATH")
+    if env:
+        yield Path(env).expanduser()
+
+    home = Path.home()
+    for p in [
+        home / "Obsidian",
+        home / "ObsidianVault",
+        home / "Vault",
+        home / "Vaults",
+        home / "Documents" / "Obsidian",
+        home / "Documents" / "Vaults",
+        home / "Syncthing" / "Obsidian",
+        Path("/srv/obsidian"),
+        Path("/srv/Obsidian"),
+        Path("/data/obsidian"),
+        Path("/data/Obsidian"),
+        WORKSPACE / "obsidian",
+        WORKSPACE / "vault",
+        WORKSPACE / "vaults",
+    ]:
+        yield p
+
+
+def _is_vault_dir(p: Path) -> bool:
+    try:
+        return p.exists() and p.is_dir() and (p / ".obsidian").exists() and (p / ".obsidian").is_dir()
+    except Exception:
+        return False
+
+
+def _bounded_find_obsidian_dirs(root: Path, *, max_depth: int) -> list[Path]:
+    """
+    Find `.obsidian` directories below root, limited by depth to keep runtime bounded.
+    """
+    results: list[Path] = []
+    try:
+        root = root.resolve()
+    except Exception:
+        return results
+
+    if not root.exists() or not root.is_dir():
+        return results
+
+    def depth_of(path: Path) -> int:
+        try:
+            return len(path.relative_to(root).parts)
+        except Exception:
+            return 9999
+
+    # Breadth-first-ish scan with pruning
+    queue = [root]
+    while queue:
+        current = queue.pop(0)
+        if depth_of(current) > max_depth:
+            continue
+        try:
+            entries = list(current.iterdir())
+        except Exception:
+            continue
+
+        for e in entries:
+            name = e.name
+            if name in (".git", "node_modules", "__pycache__", ".cache", ".venv", "venv", "tmp", "proc", "sys", "dev"):
+                continue
+            if name.startswith(".") and name not in (".obsidian",):
+                continue
+            if name == ".obsidian" and e.is_dir():
+                results.append(e)
+                continue
+            if e.is_dir() and not e.is_symlink():
+                queue.append(e)
+
+    return results
+
+
+def discover(*, roots: list[Path], max_depth: int) -> list[Path]:
+    vaults: set[Path] = set()
+
+    for p in _iter_common_candidates():
+        if _is_vault_dir(p):
+            vaults.add(p.resolve())
+
+    for root in roots:
+        for obsidian_dir in _bounded_find_obsidian_dirs(root, max_depth=max_depth):
+            vaults.add(obsidian_dir.parent.resolve())
+
+    return sorted(vaults)
+
+
+def main() -> int:
+    ap = argparse.ArgumentParser(description="Discover Obsidian vault and optionally write config")
+    ap.add_argument("--write", action="store_true", help="Write detected vault_path into obsidian_config.json")
+    ap.add_argument(
+        "--roots",
+        nargs="*",
+        default=[str(Path.home()), "/srv", "/data", "/mnt", str(WORKSPACE)],
+        help="Roots to scan (bounded). Default: home,/srv,/data,/mnt,workspace",
+    )
+    ap.add_argument("--max-depth", type=int, default=4, help="Max directory depth to scan under each root")
+    args = ap.parse_args()
+
+    roots = [Path(r).expanduser() for r in args.roots]
+    vaults = discover(roots=roots, max_depth=int(args.max_depth))
+
+    if not vaults:
+        print("No Obsidian vault found (no `.obsidian/` directories detected).")
+        return 1
+
+    if len(vaults) > 1:
+        print("Multiple Obsidian vaults found; refusing to write config:")
+        for v in vaults:
+            print(f"- {v}")
+        return 2
+
+    vault = vaults[0]
+    print(f"Detected Obsidian vault: {vault}")
+
+    if not args.write:
+        return 0
+
+    if not CONFIG_PATH.exists():
+        raise SystemExit(f"Missing config file: {CONFIG_PATH}")
+
+    cfg = json.loads(CONFIG_PATH.read_text(encoding="utf-8"))
+    cfg["vault_path"] = str(vault)
+    CONFIG_PATH.write_text(json.dumps(cfg, indent=2, ensure_ascii=False) + "\n", encoding="utf-8")
+    print(f"Wrote vault_path to: {CONFIG_PATH}")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())
+

scripts/smoke_dashboard.sh

@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+HOST="${SECOND_BRAIN_HOST:-127.0.0.1}"
+PORT="${SECOND_BRAIN_PORT:-${PORT:-8501}}"
+BASE_URL="http://${HOST}:${PORT}"
+
+if command -v systemctl >/dev/null 2>&1; then
+  if ! systemctl is-active --quiet openclaw-secondbrain-dashboard.service; then
+    echo "ERROR: openclaw-secondbrain-dashboard.service is not active" >&2
+    exit 1
+  fi
+fi
+
+curl -fsS "${BASE_URL}/healthz" >/dev/null
+
+stats_json="$(curl -fsS "${BASE_URL}/api/stats")"
+python3 -c 'import json,sys; json.load(sys.stdin)' <<<"$stats_json"
+
+echo "OK: dashboard smoke test passed (${BASE_URL})"

src/__init__.py

@@ -1,8 +1,14 @@
 """Second Brain - Gedächtnissystem für OpenClaw."""
 
-from .engram import Engram, Grounding, Correctness, ReviewEntry
-from .store import EngramStore
-from .retriever import Retriever
+try:
+    from .engram import Engram, Grounding, Correctness, ReviewEntry
+    from .store import EngramStore
+    from .retriever import Retriever
+except ImportError:
+    # Fallback: ChromaDB optional, SQLite-core funktioniert immer
+    from .engram import Engram, Grounding, Correctness, ReviewEntry
+    from .store import EngramStore
+    Retriever = None
 
 __version__ = "0.1.0"
 __all__ = ["Engram", "Grounding", "Correctness", "ReviewEntry", "EngramStore", "Retriever"]

src/dashboard.py

@@ -13,12 +13,23 @@ import argparse
 import http.server
 import socketserver
 import webbrowser
+import sys
 from pathlib import Path
 from uuid import UUID
 
-from .store import EngramStore
-from .engram import Engram, Grounding
-from .retriever import Retriever
+# Insert project root so `python3 src/dashboard.py` works without `-m`
+project_root = str(Path(__file__).parent.parent)
+if project_root not in sys.path:
+    sys.path.insert(0, project_root)
+
+from src.store import EngramStore
+from src.engram import Engram, Grounding
+
+# Retriever: optional – im venv verfügbar, sonst Fallback
+try:
+    from src.retriever import Retriever
+except ImportError:
+    Retriever = None
 
 DB_PATH = Path(__file__).parent.parent / "data" / "brain.sqlite"
 HTML_PATH = Path(__file__).parent.parent / "data" / "dashboard.html"
@@ -27,10 +38,30 @@ HTML_PATH = Path(__file__).parent.parent / "data" / "dashboard.html"
 def generate_dashboard() -> str:
     """Generiert HTML-Dashboard aus aktuellem Brain-Stand."""
     store = EngramStore(str(DB_PATH))
-    ret = Retriever(store)
-    stats = ret.stats()
     egs = store.get_all(limit=100)
 
+    # Stats: mit Retriever (venv) oder manuell berechnen
+    if Retriever:
+        ret = Retriever(store)
+        stats = ret.stats()
+        errors = store.search_tag("error", limit=100)
+        stats["errors"] = len(errors)
+    else:
+        from src.engram import Correctness
+        all_egs = store.get_all(limit=10000)
+        confirmed = sum(1 for e in all_egs if e.correctness.confirmed)
+        errors = store.search_tag("error", limit=100)
+        confidences = [e.compute_confidence() for e in all_egs]
+        stats = {
+            "total_engrams": len(all_egs),
+            "confirmed": confirmed,
+            "unconfirmed": len(all_egs) - confirmed,
+            "sources": {},
+            "db_size_bytes": 0,
+            "avg_confidence": sum(confidences) / len(confidences) if confidences else 0.0,
+            "errors": len(errors),
+        }
+
     # Farbe nach Confidence
     def color(conf):
         if conf > 0.7: return "#2ecc71"
@@ -48,95 +79,81 @@ def generate_dashboard() -> str:
         except:
             return "UNKNOWN"
 
-    # Liste der Engramme
-    rows = []
+    # Karten-Ansicht für Mobil
+    card_rows = []
     for eg in egs:
         conf = eg.compute_confidence()
-        rows.append(f"""
-        <tr>
-            <td><span style="color:{color(conf)};font-size:1.2em">{marker(conf)}</span></td>
-            <td><code>{str(eg.id)[:8]}</code></td>
-            <td>{eg.content[:100]}{'...' if len(eg.content) > 100 else ''}</td>
-            <td><span class="badge">{grounding_name(eg.metadata.get('grounding', 0))}</span></td>
-            <td><span class="badge">{eg.metadata.get('source', '?')}</span></td>
-            <td>{conf:.2f}</td>
-            <td>{eg.correctness.confirmations}/{eg.correctness.rejections}</td>
-            <td>{eg.metadata.get('access_count', 0)}</td>
-            <td>{', '.join(eg.metadata.get('tags', [])[:3])}</td>
-        </tr>
+        card_rows.append(f"""
+        <div class="card">
+            <div class="card-header">
+                <span>{marker(conf)} {str(eg.id)[:8]}</span>
+                <span class="badge" style="background:rgba({int((1-conf)*200+55)},{int(conf*200+55)},100,0.3)">{conf:.2f}</span>
+            </div>
+            <div class="card-content">{eg.content[:150]}{'...' if len(eg.content) > 150 else ''}</div>
+            <div class="card-meta">
+                <span class="badge">{grounding_name(eg.metadata.get('grounding', 0))}</span>
+                <span class="badge">{eg.metadata.get('source', '?')}</span>
+                <span class="badge">✓{eg.correctness.confirmations}/✗{eg.correctness.rejections}</span>
+                {' '.join([f'<span class="badge">{t}</span>' for t in eg.metadata.get('tags', [])[:3]])}
+            </div>
+        </div>
         """)
 
     html = f"""<!DOCTYPE html>
 <html lang="de">
 <head>
 <meta charset="UTF-8">
-<meta name="viewport" content="width=device-width, initial-scale=1.0">
-<title>🧠 Second Brain Dashboard</title>
+<meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no">
+<title>🧠 Second Brain</title>
 <style>
     :root {{ --bg: #1a1a2e; --card: #16213e; --text: #eee; --accent: #0f4c75; }}
-    body {{ font-family: -apple-system, BlinkMacSystemFont, sans-serif; background: var(--bg); color: var(--text); margin: 0; padding: 20px; }}
-    h1 {{ margin: 0 0 10px; font-size: 1.8em; }}
-    .stats {{ display: grid; grid-template-columns: repeat(auto-fit, minmax(180px, 1fr)); gap: 15px; margin-bottom: 25px; }}
-    .stat-card {{ background: var(--card); border-radius: 12px; padding: 15px; text-align: center; }}
-    .stat-card .num {{ font-size: 2em; font-weight: bold; color: #4fc3f7; }}
-    .stat-card .lbl {{ font-size: 0.85em; opacity: 0.7; }}
-    table {{ width: 100%; border-collapse: collapse; background: var(--card); border-radius: 12px; overflow: hidden; }}
-    th {{ text-align: left; padding: 10px; background: var(--accent); font-size: 0.85em; text-transform: uppercase; }}
-    td {{ padding: 8px 10px; border-bottom: 1px solid rgba(255,255,255,0.05); font-size: 0.9em; vertical-align: top; }}
-    tr:hover td {{ background: rgba(255,255,255,0.03); }}
-    .badge {{ display: inline-block; padding: 2px 8px; border-radius: 12px; background: rgba(79,195,247,0.2); font-size: 0.75em; }}
-    .search {{ margin-bottom: 20px; }}
-    .search input {{ width: 100%; max-width: 400px; padding: 10px 15px; border-radius: 8px; border: 1px solid rgba(255,255,255,0.1); background: var(--card); color: var(--text); font-size: 1em; }}
-    .refresh {{ position: fixed; top: 20px; right: 20px; background: #2ecc71; color: #000; border: none; padding: 10px 20px; border-radius: 8px; cursor: pointer; font-weight: bold; }}
-    .footer {{ margin-top: 30px; text-align: center; opacity: 0.5; font-size: 0.8em; }}
+    body {{ font-family: -apple-system, BlinkMacSystemFont, sans-serif; background: var(--bg); color: var(--text); margin: 0; padding: 10px; font-size: 14px; }}
+    h1 {{ margin: 0 0 8px; font-size: 1.3em; text-align: center; }}
+    .stats {{ display: grid; grid-template-columns: repeat(2, 1fr); gap: 8px; margin-bottom: 15px; }}
+    .stat-card {{ background: var(--card); border-radius: 10px; padding: 10px; text-align: center; }}
+    .stat-card .num {{ font-size: 1.5em; font-weight: bold; color: #4fc3f7; }}
+    .stat-card .lbl {{ font-size: 0.75em; opacity: 0.7; }}
+    .search {{ margin-bottom: 10px; }}
+    .search input {{ width: 100%; box-sizing: border-box; padding: 12px; border-radius: 8px; border: 1px solid rgba(255,255,255,0.1); background: var(--card); color: var(--text); font-size: 16px; }}
+    .card {{ background: var(--card); border-radius: 12px; padding: 12px; margin-bottom: 10px; }}
+    .card-header {{ display: flex; justify-content: space-between; align-items: center; margin-bottom: 6px; }}
+    .card-id {{ font-size: 0.75em; opacity: 0.6; }}
+    .card-content {{ font-size: 0.9em; line-height: 1.4; margin-bottom: 8px; word-break: break-word; }}
+    .card-meta {{ display: flex; flex-wrap: wrap; gap: 6px; font-size: 0.75em; }}
+    .badge {{ display: inline-block; padding: 3px 8px; border-radius: 12px; background: rgba(79,195,247,0.2); }}
+    .refresh {{ position: fixed; bottom: 15px; right: 15px; background: #2ecc71; color: #000; border: none; padding: 12px 16px; border-radius: 50%; cursor: pointer; font-weight: bold; font-size: 1.2em; box-shadow: 0 2px 8px rgba(0,0,0,0.4); }}
+    .footer {{ margin-top: 20px; text-align: center; opacity: 0.5; font-size: 0.7em; padding-bottom: 60px; }}
 </style>
 </head>
 <body>
-    <h1>🧠 Second Brain Dashboard</h1>
-    <button class="refresh" onclick="location.reload()">🔄 Aktualisieren</button>
+    <h1>🧠 Second Brain</h1>
+    <button class="refresh" onclick="location.reload()">↻</button>
 
     <div class="stats">
         <div class="stat-card"><div class="num">{stats['total_engrams']}</div><div class="lbl">Engramme</div></div>
         <div class="stat-card"><div class="num">{stats['confirmed']}</div><div class="lbl">Bestätigt</div></div>
         <div class="stat-card"><div class="num">{stats['unconfirmed']}</div><div class="lbl">Unbestätigt</div></div>
-        <div class="stat-card"><div class="num">{len(stats.get('sources', dict()))}</div><div class="lbl">Quellen</div></div>
-        <div class="stat-card"><div class="num">{stats['db_size_bytes']/1024:.0f}</div><div class="lbl">KB Größe</div></div>
+        <div class="stat-card"><div class="num">{stats['errors']}</div><div class="lbl">Fehler</div></div>
     </div>
 
     <div class="search">
-        <input type="text" placeholder="🔍 Suche nach Engrammen..." id="searchInput" onkeyup="filterTable()">
+        <input type="text" placeholder="🔍 Suche..." id="searchInput" onkeyup="filterCards()">
     </div>
 
-    <table id="engramTable">
-        <thead>
-            <tr>
-                <th>Status</th>
-                <th>ID</th>
-                <th>Inhalt</th>
-                <th>Grounding</th>
-                <th>Quelle</th>
-                <th>Confidence</th>
-                <th>Feedback</th>
-                <th>Zugriffe</th>
-                <th>Tags</th>
-            </tr>
-        </thead>
-        <tbody>
-            {''.join(rows)}
-        </tbody>
-    </table>
+    <div id="cards">
+        {''.join(card_rows)}
+    </div>
 
-    <div class="footer">Generated {__import__('datetime').datetime.now().isoformat()}</div>
+    <div class="footer">Generated {__import__('datetime').datetime.now().strftime('%H:%M')}</div>
 
     <script>
-    function filterTable() {{
+    function filterCards() {{
         var input = document.getElementById('searchInput');
         var filter = input.value.toLowerCase();
-        var table = document.getElementById('engramTable');
-        var rows = table.getElementsByTagName('tr');
-        for (var i=1; i<rows.length; i++) {{
-            var txt = rows[i].textContent || rows[i].innerText;
-            rows[i].style.display = txt.toLowerCase().indexOf(filter) > -1 ? '' : 'none';
+        var cards = document.getElementById('cards').getElementsByClassName('card');
+        for (var i=0; i<cards.length; i++) {{
+            var txt = cards[i].textContent || cards[i].innerText;
+            cards[i].style.display = txt.toLowerCase().indexOf(filter) > -1 ? '' : 'none';
         }}
     }}
     </script>

src/engram.py

@@ -66,12 +66,19 @@ class Correctness:
         return self.confirmations / total
 
     def to_dict(self) -> dict:
+        # Backwards/robustness: older code paths may have appended raw dicts.
+        review_history: List[dict] = []
+        for entry in self.review_history:
+            if isinstance(entry, dict):
+                review_history.append(entry)
+            else:
+                review_history.append(entry.to_dict())
         return {
             "confirmed": self.confirmed,
             "confirmations": self.confirmations,
             "rejections": self.rejections,
             "last_reviewed": self.last_reviewed,
-            "review_history": [r.to_dict() for r in self.review_history],
+            "review_history": review_history,
         }
 
     @classmethod

src/openclaw_bridge.py

@@ -16,10 +16,33 @@ from pathlib import Path
 from datetime import datetime, timezone
 from typing import Optional, List, Dict, Any
 
+# Ensure project root is on sys.path for standalone usage
+project_root = str(Path(__file__).parent.parent)
+if project_root not in sys.path:
+    sys.path.insert(0, project_root)
+
+# Activate virtualenv if available (for chromadb etc.)
+venv_path = Path(__file__).parent.parent / ".venv"
+if venv_path.exists():
+    venv_site_packages = list((venv_path / "lib").glob("python3.*/site-packages"))
+    if venv_site_packages and str(venv_site_packages[0]) not in sys.path:
+        sys.path.insert(0, str(venv_site_packages[0]))
+
 # Second Brain Import
-from .store import EngramStore
-from .engram import Engram, Grounding
-from .retriever import Retriever
+from src.engram import Engram, Grounding
+from src.store import EngramStore
+
+# Retriever: optional (braucht chromadb)
+try:
+    from src.retriever import Retriever
+except ImportError:
+    Retriever = None
+
+# Chroma: optional (braucht chromadb)
+try:
+    from src.chroma_store import ChromaStore
+except Exception:
+    ChromaStore = None
 
 
 # --- Konfiguration ---
@@ -75,11 +98,6 @@ def heartbeat_check() -> Optional[str]:
     Rückgabe: Nachricht für den User, oder None wenn nichts zu tun.
     """
     store = get_brain()
-    ret = Retriever(store)
-
-    # A: Unbestätigte Engramme die seit längerem nicht geprüft wurden
-    # B: Hohe-Prioritäts-Themen (tags wie "wichtig", "dringend")
-    # C: Fehler-Engramme die repeating sind
 
     # Prüfe auf wichtige unbestätigte Engramme
     egs = store.get_all(limit=50)
@@ -89,8 +107,7 @@ def heartbeat_check() -> Optional[str]:
     ][:5]
 
     if unconfirmed:
-        ids = ", ".join([str(eg.id)[:8] for eg in unconfirmed])
-        contents = "\n".join([f"  - {eg.content[:80]}" for eg in unconfimed])
+        contents = "\n".join([f"  - {eg.content[:80]}" for eg in unconfirmed])
         return (
             f"🧠 Second Brain Heartbeat\n"
             f"Unbestätigte Engramme mit gutem Confidence-Score:\n{contents}\n"
@@ -195,8 +212,39 @@ def enrich_context(topic: str, limit: int = 3) -> str:
         # memory_context in das Prompt einbauen
     """
     store = get_brain()
-    ret = Retriever(store)
-    results = ret.retrieve(topic, limit=limit, min_confidence=0.3)
+
+    # Versuche Hybrid-Retrieval (FTS + optional Vector), fallback auf Textsuche
+    if Retriever:
+        chroma = None
+        if ChromaStore:
+            try:
+                chroma = ChromaStore(path=str(Path(__file__).parent.parent / "data" / "chroma"))
+            except Exception:
+                chroma = None
+        ret = Retriever(store, chroma=chroma)
+        try:
+            results = ret.hybrid_retrieve(topic, limit=limit * 3, min_confidence=0.3)
+        except Exception:
+            results = ret.retrieve(topic, limit=limit * 3, min_confidence=0.3)
+
+        # confirmed-first ranking
+        def _rank(r):
+            eg = r["engram"]
+            confirmed = 1 if getattr(eg.correctness, "confirmed", False) else 0
+            return (confirmed, float(r.get("score", 0.0)))
+
+        results.sort(key=_rank, reverse=True)
+
+        # If we have confirmed results, show only confirmed up to limit
+        confirmed_only = [r for r in results if r["engram"].correctness.confirmed]
+        if confirmed_only:
+            results = confirmed_only[:limit]
+        else:
+            results = results[:limit]
+    else:
+        results_raw = store.search_text(topic, limit=limit)
+        results = [{"engram": eg, "score": 0.5} for eg in results_raw]
+
     if not results:
         return ""
 

src/retriever.py

@@ -7,12 +7,10 @@ Phase 2: + Embedding + Fusion.
 from typing import List, Dict, Any, Optional
 from .engram import Engram
 from .store import EngramStore
-from .chroma_store import ChromaStore
-from .embedder import encode
 
 
 class Retriever:
-    def __init__(self, store: EngramStore, chroma: Optional[ChromaStore] = None):
+    def __init__(self, store: EngramStore, chroma: Optional[object] = None):
         self.store = store
         self.chroma = chroma
 
@@ -50,7 +48,6 @@ class Retriever:
         if not self.chroma:
             return []
         chroma_results = self.chroma.query(query, top_k=limit * 3)
-        eids = [r["id"] for r in chroma_results]
         results = []
         for r in chroma_results:
             eg = self.store.get(r["id"])

src/store.py

@@ -6,6 +6,7 @@ Keine externen Abhängigkeiten außer sqlite3 (stdlib).
 import json
 import sqlite3
 import os
+import re
 from pathlib import Path
 from typing import List, Optional, Dict, Any
 from uuid import UUID
@@ -127,6 +128,14 @@ class EngramStore:
         ).fetchall()
         return [self._row_to_engram(r) for r in rows]
 
+    def get_modified_since(self, iso_ts: str, limit: int = 5000) -> List[Engram]:
+        """Gibt Engramme zurück, deren `modified_at` nach `iso_ts` liegt."""
+        rows = self._conn.execute(
+            "SELECT * FROM engrams WHERE modified_at > ? ORDER BY modified_at ASC LIMIT ?",
+            (iso_ts, limit),
+        ).fetchall()
+        return [self._row_to_engram(r) for r in rows]
+
     def delete(self, engram_id: str) -> bool:
         """Löscht ein Engramm und alle Verknüpfungen."""
         rowid = self._conn.execute(
@@ -150,7 +159,12 @@ class EngramStore:
     def search_text(self, query: str, limit: int = 10) -> List[Engram]:
         """Full-Text-Suche über Engramm-Inhalt via SQLite FTS5 (OR-Verknüpfung)."""
         # FTS5-Syntax: Wörter mit OR verbinden für bessere Ergebnisse
-        words = [w.strip() for w in query.replace("'", "''").split() if w.strip()]
+        words = []
+        for word in query.split():
+            # Nur alphanumerische Zeichen als FTS5-Tokens akzeptieren
+            clean_word = re.sub(r'[^a-zA-Z0-9]+', '', word)
+            if clean_word:
+                words.append(clean_word)
         safe_query = " OR ".join(words) if len(words) > 1 else (words[0] if words else "*")
         sql = """
             SELECT e.* FROM engrams e
@@ -239,6 +253,13 @@ class EngramStore:
             "links": json.loads(row["links_json"]),
             "hierarchy": json.loads(row["hierarchy_json"]),
         }
+        # Keep Engram metadata timestamps aligned with DB columns so downstream
+        # consumers (e.g. vector indexing watermarks) can rely on them.
+        try:
+            d["metadata"]["created"] = row["created_at"]
+            d["metadata"]["modified"] = row["modified_at"]
+        except Exception:
+            pass
         emb = row["embedding_json"]
         if emb:
             d["embedding"] = json.loads(emb)

static/style.css

@@ -0,0 +1,401 @@
+/* ─── Reset & Base ────────────────────────────────────────────────────────── */
+* { margin: 0; padding: 0; box-sizing: border-box; }
+html { font-size: 14px; }
+body {
+    font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif;
+    background: #0f0f12;
+    color: #e8e8ee;
+    -webkit-font-smoothing: antialiased;
+    overscroll-behavior-y: contain;
+}
+
+.app {
+    max-width: 480px;
+    margin: 0 auto;
+    min-height: 100vh;
+    background: #141419;
+}
+
+/* ─── Stats Bar ───────────────────────────────────────────────────────────── */
+.stats-bar {
+    display: flex;
+    justify-content: space-around;
+    padding: 10px 8px;
+    background: linear-gradient(180deg, #1a1a22 0%, #131318 100%);
+    border-bottom: 1px solid #252530;
+    position: sticky;
+    top: 0;
+    z-index: 50;
+}
+
+.tabs-bar{
+    display:flex;
+    gap:8px;
+    padding:8px 12px 10px;
+    background:#141419;
+    border-bottom:1px solid #252530;
+    position: sticky;
+    top: 52px;
+    z-index: 45;
+}
+.tabs-bar .tab-btn{
+    flex:1;
+    background:#1e1e28;
+    border:1px solid #2a2a3a;
+    border-radius: 12px;
+    padding:10px 10px;
+    color:#cfd3ff;
+    font-weight:700;
+    font-size:0.82rem;
+}
+.tabs-bar .tab-btn.active{
+    border-color:#6c8af5;
+    box-shadow:0 0 0 1px rgba(108,138,245,0.22) inset;
+}
+.stat {
+    text-align: center;
+    min-width: 60px;
+}
+.stat-num {
+    display: block;
+    font-size: 1.3rem;
+    font-weight: 700;
+    color: #6c8af5;
+    line-height: 1.2;
+}
+.stat-label {
+    display: block;
+    font-size: 0.65rem;
+    color: #888899;
+    text-transform: uppercase;
+    letter-spacing: 0.5px;
+    margin-top: 2px;
+}
+
+/* ─── Search ──────────────────────────────────────────────────────────────── */
+.search-box {
+    display: flex;
+    gap: 8px;
+    padding: 10px 12px;
+    background: #141419;
+}
+
+/* tab buttons styled via .tabs-bar */
+
+/* ─── Panels (Graph/Status) ──────────────────────────────────────────────── */
+.panel {
+    margin: 8px 12px;
+    background: #1a1a24;
+    border: 1px solid #252533;
+    border-radius: 14px;
+    padding: 10px 12px;
+}
+.panel-title {
+    font-size: 0.8rem;
+    text-transform: uppercase;
+    letter-spacing: 0.5px;
+    color: #9aa3d9;
+    margin-bottom: 8px;
+}
+.kv-row {
+    display: flex;
+    gap: 10px;
+    padding: 6px 0;
+    border-bottom: 1px solid #20202a;
+}
+.kv-row:last-child { border-bottom: none; }
+.kv-key {
+    width: 110px;
+    color: #888899;
+    font-size: 0.78rem;
+}
+.kv-val {
+    flex: 1;
+    color: #e8e8ee;
+    font-size: 0.85rem;
+    word-break: break-word;
+}
+.pill {
+    display: inline-block;
+    margin: 2px 4px 2px 0;
+    padding: 2px 8px;
+    border-radius: 999px;
+    background: #2a2a3a;
+    color: #8a9aff;
+    font-size: 0.72rem;
+}
+.muted {
+    color: #888899;
+    font-size: 0.8rem;
+    margin-top: 6px;
+}
+.small { font-size: 0.75rem; }
+
+/* Graph canvas */
+#graphCanvas{
+    display:block;
+    margin: 8px auto 0;
+    background:#12121a;
+    border:1px solid #252533;
+    border-radius: 14px;
+}
+#searchInput {
+    flex: 1;
+    background: #1e1e28;
+    border: 1px solid #2a2a3a;
+    border-radius: 10px;
+    padding: 10px 14px;
+    color: #e8e8ee;
+    font-size: 0.95rem;
+    outline: none;
+}
+#searchInput:focus { border-color: #6c8af5; }
+#filterSelect {
+    background: #1e1e28;
+    border: 1px solid #2a2a3a;
+    border-radius: 10px;
+    padding: 10px;
+    color: #e8e8ee;
+    font-size: 0.85rem;
+    outline: none;
+}
+
+/* ─── New Engram ──────────────────────────────────────────────────────────── */
+.new-engram {
+    padding: 0 12px 8px;
+    display: flex;
+    flex-direction: column;
+    gap: 6px;
+}
+.new-engram textarea {
+    background: #1e1e28;
+    border: 1px solid #2a2a3a;
+    border-radius: 10px;
+    padding: 10px;
+    color: #e8e8ee;
+    font-size: 0.9rem;
+    resize: vertical;
+    min-height: 50px;
+}
+.new-engram input {
+    background: #1e1e28;
+    border: 1px solid #2a2a3a;
+    border-radius: 10px;
+    padding: 8px 10px;
+    color: #e8e8ee;
+    font-size: 0.85rem;
+}
+.new-engram button {
+    background: #3a7d3a;
+    border: none;
+    border-radius: 10px;
+    padding: 10px;
+    color: #fff;
+    font-weight: 600;
+    font-size: 0.95rem;
+}
+
+/* ─── Cards ───────────────────────────────────────────────────────────────── */
+.cards {
+    padding: 4px 12px;
+    display: flex;
+    flex-direction: column;
+    gap: 10px;
+}
+.card {
+    background: #1a1a24;
+    border: 1px solid #252533;
+    border-radius: 14px;
+    overflow: hidden;
+    transition: transform 0.15s ease, border-color 0.2s ease;
+    touch-action: manipulation;
+}
+.card:active { transform: scale(0.985); }
+.card.confirmed { border-left: 4px solid #3a7d3a; }
+.card.rejected { border-left: 4px solid #8a3a3a; }
+
+.card-header {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+    padding: 10px 12px 6px;
+    border-bottom: 1px solid #20202a;
+}
+.conf-badge {
+    font-size: 0.75rem;
+    font-weight: 700;
+    color: #fff;
+    padding: 2px 8px;
+    border-radius: 20px;
+    min-width: 36px;
+    text-align: center;
+}
+.tags {
+    flex: 1;
+    display: flex;
+    flex-wrap: wrap;
+    gap: 4px;
+}
+.tag {
+    background: #2a2a3a;
+    color: #8a9aff;
+    font-size: 0.68rem;
+    padding: 2px 8px;
+    border-radius: 12px;
+    text-transform: uppercase;
+    letter-spacing: 0.3px;
+}
+.date {
+    font-size: 0.65rem;
+    color: #666677;
+    white-space: nowrap;
+}
+
+.card-body {
+    padding: 10px 12px;
+    font-size: 0.9rem;
+    line-height: 1.45;
+    color: #ccccdd;
+    cursor: pointer;
+}
+
+.card-footer {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+    padding: 8px 12px 10px;
+    border-top: 1px solid #20202a;
+}
+.reason-input {
+    flex: 1;
+    background: #14141a;
+    border: 1px solid #2a2a3a;
+    border-radius: 8px;
+    padding: 6px 10px;
+    color: #b0b0c0;
+    font-size: 0.8rem;
+}
+.actions {
+    display: flex;
+    gap: 6px;
+}
+.actions button {
+    width: 34px;
+    height: 34px;
+    border-radius: 50%;
+    border: none;
+    font-size: 1rem;
+    cursor: pointer;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    transition: transform 0.1s;
+}
+.actions button:active { transform: scale(0.9); }
+.btn-ok { background: #2a5a2a; }
+.btn-no { background: #5a2a2a; }
+.btn-archive { background: #2a2a4a; }
+
+/* ─── Pagination ──────────────────────────────────────────────────────────── */
+.pagination {
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    gap: 16px;
+    padding: 14px;
+}
+.pagination button {
+    background: #252535;
+    border: none;
+    border-radius: 10px;
+    width: 40px;
+    height: 40px;
+    color: #e8e8ee;
+    font-size: 1.1rem;
+}
+.pagination button:disabled {
+    opacity: 0.3;
+}
+#pageNum {
+    font-weight: 700;
+    color: #6c8af5;
+}
+
+/* ─── Footer ──────────────────────────────────────────────────────────────── */
+.footer {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    padding: 10px 16px 20px;
+    color: #555566;
+    font-size: 0.75rem;
+}
+.refresh-btn {
+    background: #252535;
+    border: none;
+    border-radius: 50%;
+    width: 36px;
+    height: 36px;
+    color: #8888aa;
+    font-size: 1.2rem;
+}
+
+/* ─── Modal ───────────────────────────────────────────────────────────────── */
+.modal {
+    display: none;
+    position: fixed;
+    inset: 0;
+    background: rgba(0,0,0,0.85);
+    z-index: 100;
+    overflow-y: auto;
+    padding: 20px 16px;
+}
+.modal.open { display: block; }
+.modal-content {
+    background: #1a1a24;
+    border: 1px solid #333344;
+    border-radius: 16px;
+    padding: 20px 16px;
+    max-width: 480px;
+    margin: 0 auto;
+    position: relative;
+}
+.close-btn {
+    position: absolute;
+    top: 10px;
+    right: 14px;
+    background: none;
+    border: none;
+    color: #8888aa;
+    font-size: 1.5rem;
+    cursor: pointer;
+}
+.history {
+    list-style: none;
+    font-size: 0.8rem;
+    color: #9999aa;
+}
+.history li {
+    padding: 4px 0;
+    border-bottom: 1px solid #20202a;
+}
+.detail-content {
+    background: #14141a;
+    border-radius: 10px;
+    padding: 12px;
+    font-size: 0.88rem;
+    line-height: 1.5;
+    margin: 8px 0;
+    max-height: 40vh;
+    overflow-y: auto;
+}
+
+/* ─── Scrollbar ───────────────────────────────────────────────────────────── */
+::-webkit-scrollbar { width: 4px; }
+::-webkit-scrollbar-track { background: transparent; }
+::-webkit-scrollbar-thumb { background: #333344; border-radius: 4px; }
+
+/* ─── Touch fix ───────────────────────────────────────────────────────────── */
+@media (pointer: coarse) {
+    button, .card { -webkit-tap-highlight-color: transparent; }
+}

systemd/openclaw-memory-archive.service

@@ -0,0 +1,9 @@
+[Unit]
+Description=OpenClaw archive memory/*.md older than 7 days
+OnFailure=openclaw-secondbrain-notify@%n.service
+
+[Service]
+Type=oneshot
+WorkingDirectory=/root/.openclaw/workspace
+ExecStart=/bin/bash -lc 'flock -n /tmp/%n.lock /usr/bin/python3 /root/.openclaw/workspace/openclaw_cron_wrapper.py archive_memory_md'
+

systemd/openclaw-memory-archive.timer

@@ -0,0 +1,10 @@
+[Unit]
+Description=OpenClaw archive memory/*.md daily
+
+[Timer]
+OnCalendar=*-*-* 03:30:00
+Persistent=true
+
+[Install]
+WantedBy=timers.target
+

systemd/openclaw-secondbrain-backup.service

@@ -0,0 +1,8 @@
+[Unit]
+Description=OpenClaw Second-Brain backup_secondbrain
+OnFailure=openclaw-secondbrain-notify@%n.service
+
+[Service]
+Type=oneshot
+WorkingDirectory=/root/.openclaw/workspace
+ExecStart=/bin/bash -lc 'flock -n /tmp/%n.lock /usr/bin/python3 /root/.openclaw/workspace/openclaw_cron_wrapper.py backup_secondbrain'

systemd/openclaw-secondbrain-backup.timer

@@ -0,0 +1,10 @@
+[Unit]
+Description=OpenClaw Second-Brain backup_secondbrain (daily 02:00)
+
+[Timer]
+OnCalendar=*-*-* 02:00:00
+Persistent=true
+
+[Install]
+WantedBy=timers.target
+

systemd/openclaw-secondbrain-dashboard.service

@@ -0,0 +1,15 @@
+[Unit]
+Description=OpenClaw Second-Brain Dashboard (FastAPI)
+After=network.target
+
+[Service]
+Type=simple
+WorkingDirectory=/root/.openclaw/workspace/second-brain
+Environment=SECOND_BRAIN_WORKSPACE=/root/.openclaw/workspace/second-brain
+Environment=SECOND_BRAIN_PORT=8501
+ExecStart=/root/.openclaw/workspace/second-brain/.venv/bin/uvicorn fastapi_app:app --host 0.0.0.0 --port 8501
+Restart=always
+RestartSec=2
+
+[Install]
+WantedBy=multi-user.target

systemd/openclaw-secondbrain-export-obsidian.service

@@ -0,0 +1,8 @@
+[Unit]
+Description=OpenClaw Second-Brain export_obsidian
+OnFailure=openclaw-secondbrain-notify@%n.service
+
+[Service]
+Type=oneshot
+WorkingDirectory=/root/.openclaw/workspace
+ExecStart=/bin/bash -lc 'flock -n /tmp/%n.lock /usr/bin/python3 /root/.openclaw/workspace/openclaw_cron_wrapper.py export_obsidian'

systemd/openclaw-secondbrain-export-obsidian.timer

@@ -0,0 +1,10 @@
+[Unit]
+Description=OpenClaw Second-Brain export_obsidian (hourly)
+
+[Timer]
+OnCalendar=hourly
+Persistent=true
+
+[Install]
+WantedBy=timers.target
+

systemd/openclaw-secondbrain-heartbeat.service

@@ -0,0 +1,8 @@
+[Unit]
+Description=OpenClaw Second-Brain heartbeat_secondbrain
+OnFailure=openclaw-secondbrain-notify@%n.service
+
+[Service]
+Type=oneshot
+WorkingDirectory=/root/.openclaw/workspace
+ExecStart=/bin/bash -lc 'flock -n /tmp/%n.lock /usr/bin/python3 /root/.openclaw/workspace/openclaw_cron_wrapper.py heartbeat_secondbrain'

systemd/openclaw-secondbrain-heartbeat.timer

@@ -0,0 +1,11 @@
+[Unit]
+Description=OpenClaw Second-Brain heartbeat_secondbrain (every 6h)
+
+[Timer]
+OnCalendar=*-*-* 00,06,12,18:00:00
+RandomizedDelaySec=300
+Persistent=true
+
+[Install]
+WantedBy=timers.target
+

systemd/openclaw-secondbrain-index-vectors.service

@@ -0,0 +1,10 @@
+[Unit]
+Description=OpenClaw Second-Brain index_vectors
+OnFailure=openclaw-secondbrain-notify@%n.service
+
+[Service]
+Type=oneshot
+WorkingDirectory=/root/.openclaw/workspace
+Environment=HF_HOME=/root/.openclaw/workspace/second-brain/data/hf_cache
+Environment=SENTENCE_TRANSFORMERS_HOME=/root/.openclaw/workspace/second-brain/data/st_cache
+ExecStart=/bin/bash -lc 'flock -n /tmp/%n.lock /usr/bin/python3 /root/.openclaw/workspace/openclaw_cron_wrapper.py index_vectors'

systemd/openclaw-secondbrain-index-vectors.timer

@@ -0,0 +1,10 @@
+[Unit]
+Description=OpenClaw Second-Brain index_vectors (every 30 min)
+
+[Timer]
+OnCalendar=*:0/30
+Persistent=true
+
+[Install]
+WantedBy=timers.target
+

systemd/openclaw-secondbrain-ingest-memory.service

@@ -0,0 +1,8 @@
+[Unit]
+Description=OpenClaw Second-Brain ingest_memory
+OnFailure=openclaw-secondbrain-notify@%n.service
+
+[Service]
+Type=oneshot
+WorkingDirectory=/root/.openclaw/workspace
+ExecStart=/bin/bash -lc 'flock -n /tmp/%n.lock /usr/bin/python3 /root/.openclaw/workspace/openclaw_cron_wrapper.py ingest_memory'

systemd/openclaw-secondbrain-ingest-memory.timer

@@ -0,0 +1,9 @@
+[Unit]
+Description=OpenClaw Second-Brain ingest_memory (every 5 min)
+
+[Timer]
+OnCalendar=*:0/5
+Persistent=true
+
+[Install]
+WantedBy=timers.target

systemd/openclaw-secondbrain-ingest-obsidian.service

@@ -0,0 +1,8 @@
+[Unit]
+Description=OpenClaw Second-Brain ingest_obsidian
+OnFailure=openclaw-secondbrain-notify@%n.service
+
+[Service]
+Type=oneshot
+WorkingDirectory=/root/.openclaw/workspace
+ExecStart=/bin/bash -lc 'flock -n /tmp/%n.lock /usr/bin/python3 /root/.openclaw/workspace/openclaw_cron_wrapper.py ingest_obsidian'

systemd/openclaw-secondbrain-ingest-obsidian.timer

@@ -0,0 +1,10 @@
+[Unit]
+Description=OpenClaw Second-Brain ingest_obsidian (every 15 min)
+
+[Timer]
+OnCalendar=*:0/15
+Persistent=true
+
+[Install]
+WantedBy=timers.target
+

systemd/openclaw-secondbrain-ingest-transcript-to-db.service

@@ -0,0 +1,9 @@
+[Unit]
+Description=OpenClaw Second-Brain ingest transcript -> DB
+OnFailure=openclaw-secondbrain-notify@%n.service
+
+[Service]
+Type=oneshot
+WorkingDirectory=/root/.openclaw/workspace
+ExecStart=/bin/bash -lc 'flock -n /tmp/%n.lock /usr/bin/python3 /root/.openclaw/workspace/openclaw_cron_wrapper.py ingest_transcript_to_db'
+

systemd/openclaw-secondbrain-ingest-transcript-to-db.timer

@@ -0,0 +1,12 @@
+[Unit]
+Description=OpenClaw Second-Brain ingest transcript -> DB (every 5 min)
+
+[Timer]
+OnBootSec=90s
+OnUnitActiveSec=300s
+Unit=openclaw-secondbrain-ingest-transcript-to-db.service
+Persistent=true
+
+[Install]
+WantedBy=timers.target
+

systemd/openclaw-secondbrain-ingest-transcript-to-memory.service

@@ -0,0 +1,8 @@
+[Unit]
+Description=OpenClaw Second-Brain ingest transcript -> memory/*.md
+OnFailure=openclaw-secondbrain-notify@%n.service
+
+[Service]
+Type=oneshot
+WorkingDirectory=/root/.openclaw/workspace
+ExecStart=/bin/bash -lc 'flock -n /tmp/%n.lock /usr/bin/python3 /root/.openclaw/workspace/second-brain/cron_tasks/ingest_transcript_to_memory.py'

systemd/openclaw-secondbrain-ingest-transcript-to-memory.timer

@@ -0,0 +1,11 @@
+[Unit]
+Description=OpenClaw Second-Brain ingest transcript -> memory (every 1 min)
+
+[Timer]
+OnBootSec=30s
+OnUnitActiveSec=60s
+Unit=openclaw-secondbrain-ingest-transcript-to-memory.service
+
+[Install]
+WantedBy=timers.target
+

systemd/openclaw-secondbrain-notify@.service

@@ -0,0 +1,8 @@
+[Unit]
+Description=OpenClaw Second-Brain failure notify (%i)
+
+[Service]
+Type=oneshot
+WorkingDirectory=/root/.openclaw/workspace
+ExecStart=/bin/bash -lc '/root/.openclaw/workspace/notify-telegram.sh "❌ Second-Brain job failed: %i. Check: journalctl -u %i -n 50 --no-pager"'
+

systemd/openclaw-secondbrain-proactive-search.service

@@ -0,0 +1,10 @@
+[Unit]
+Description=OpenClaw Second-Brain proactive_search_wrapper
+Wants=network-online.target
+After=network-online.target
+OnFailure=openclaw-secondbrain-notify@%n.service
+
+[Service]
+Type=oneshot
+WorkingDirectory=/root/.openclaw/workspace
+ExecStart=/bin/bash -lc 'flock -n /tmp/%n.lock /usr/bin/python3 /root/.openclaw/workspace/openclaw_cron_wrapper.py proactive_search_wrapper'

systemd/openclaw-secondbrain-proactive-search.timer

@@ -0,0 +1,11 @@
+[Unit]
+Description=OpenClaw Second-Brain proactive_search_wrapper (every 4h)
+
+[Timer]
+OnCalendar=*-*-* 01,05,09,13,17,21:10:00
+RandomizedDelaySec=600
+Persistent=true
+
+[Install]
+WantedBy=timers.target
+

systemd/openclaw-secondbrain-review.service

@@ -0,0 +1,8 @@
+[Unit]
+Description=OpenClaw Second-Brain review_brain
+OnFailure=openclaw-secondbrain-notify@%n.service
+
+[Service]
+Type=oneshot
+WorkingDirectory=/root/.openclaw/workspace
+ExecStart=/bin/bash -lc 'flock -n /tmp/%n.lock /usr/bin/python3 /root/.openclaw/workspace/openclaw_cron_wrapper.py review_brain'

systemd/openclaw-secondbrain-review.timer

@@ -0,0 +1,9 @@
+[Unit]
+Description=OpenClaw Second-Brain review_brain (every 5 min)
+
+[Timer]
+OnCalendar=*:0/5
+Persistent=true
+
+[Install]
+WantedBy=timers.target

systemd/openclaw-secondbrain-task@.service

@@ -0,0 +1,13 @@
+[Unit]
+Description=OpenClaw Second-Brain task (%i)
+Wants=network-online.target
+After=network-online.target
+
+[Service]
+Type=oneshot
+WorkingDirectory=/root/.openclaw/workspace
+ExecStart=/usr/bin/python3 /root/.openclaw/workspace/openclaw_cron_wrapper.py %i
+Nice=10
+IOSchedulingClass=best-effort
+IOSchedulingPriority=6
+

systemd/openclaw-secondbrain-verify-pending.service

@@ -0,0 +1,9 @@
+[Unit]
+Description=OpenClaw Second-Brain verify_pending_external
+OnFailure=openclaw-secondbrain-notify@%n.service
+
+[Service]
+Type=oneshot
+WorkingDirectory=/root/.openclaw/workspace
+ExecStart=/bin/bash -lc 'flock -n /tmp/%n.lock /usr/bin/python3 /root/.openclaw/workspace/openclaw_cron_wrapper.py verify_pending_external'
+

systemd/openclaw-secondbrain-verify-pending.timer

@@ -0,0 +1,10 @@
+[Unit]
+Description=OpenClaw Second-Brain periodic verify_pending_external
+
+[Timer]
+OnBootSec=2min
+OnUnitActiveSec=5min
+Persistent=true
+
+[Install]
+WantedBy=timers.target

templates/dashboard.html

@@ -0,0 +1,488 @@
+<!DOCTYPE html>
+<html lang="de">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width; initial-scale=1.0; maximum-scale=1.0; user-scalable=no">
+    <title>🧠 Second Brain</title>
+    <link rel="stylesheet" href="/static/style.css">
+</head>
+<body>
+    <div class="app">
+        <!-- Stats Header -->
+        <header class="stats-bar" id="statsBar">
+            <div class="stat"><span class="stat-num" id="statTotal">-</span><span class="stat-label">Total</span></div>
+            <div class="stat"><span class="stat-num" id="statConfirmed">-</span><span class="stat-label">OK</span></div>
+            <div class="stat"><span class="stat-num" id="statPending">-</span><span class="stat-label">Pending</span></div>
+            <div class="stat"><span class="stat-num" id="statErrors">-</span><span class="stat-label">Err</span></div>
+        </header>
+
+        <div class="tabs-bar">
+            <button class="tab-btn active" id="tabCards" onclick="setView('cards')">Cards</button>
+            <button class="tab-btn" id="tabGraph" onclick="setView('graph')">Graph</button>
+            <button class="tab-btn" id="tabStatus" onclick="setView('status')">Status</button>
+        </div>
+
+        <!-- Search -->
+        <div class="search-box">
+            <input type="text" id="searchInput" placeholder="🔍 Suche..." />
+            <select id="filterSelect">
+                <option value="all">Alle</option>
+                <option value="pending">Pending</option>
+                <option value="confirmed">Confirmed</option>
+                <option value="errors">Errors</option>
+            </select>
+        </div>
+
+        <!-- New Engram -->
+        <div class="new-engram">
+            <textarea id="newContent" placeholder="Neues Engramm..."></textarea>
+            <input type="text" id="newTags" placeholder="Tags (comma sep)" />
+            <button onclick="createEngram()">➕ Speichern</button>
+        </div>
+
+        <!-- Cards -->
+        <div class="cards" id="cards"></div>
+
+        <!-- Graph -->
+        <div class="graph" id="graph" style="display:none;">
+            <canvas id="graphCanvas" width="440" height="520"></canvas>
+            <div class="muted small" id="graphHint">Lade Graph…</div>
+        </div>
+
+        <!-- Status -->
+        <div class="status" id="status" style="display:none;"></div>
+
+        <!-- Pagination -->
+        <div class="pagination" id="pagination">
+            <button id="btnPrev" onclick="prevPage()">◀</button>
+            <span id="pageNum">1</span>
+            <button id="btnNext" onclick="nextPage()">▶</button>
+        </div>
+
+        <div class="footer">
+            <span id="lastUpdate">--:--</span>
+            <button onclick="manualRefresh()" class="refresh-btn">↻</button>
+        </div>
+    </div>
+
+    <!-- Detail Modal -->
+    <div class="modal" id="detailModal">
+        <div class="modal-content">
+            <button class="close-btn" onclick="closeModal()">×</button>
+            <div id="modalBody"></div>
+        </div>
+    </div>
+
+<script>
+// ─── State ──────────────────────────────────────────────────────────────────
+let state = {
+    items: [],
+    offset: 0,
+    limit: 10,
+    filter: 'all',
+    search: '',
+    autoRefresh: true,
+    view: 'cards',
+    lastEvent: null,
+};
+
+// ─── Fetch ──────────────────────────────────────────────────────────────────
+async function api(path, opts = {}) {
+    const r = await fetch(path, opts);
+    if (!r.ok) throw new Error((await r.json()).error || r.statusText);
+    return r.json();
+}
+
+async function loadStats() {
+    const s = await api('/api/stats');
+    document.getElementById('statTotal').textContent = s.total;
+    document.getElementById('statConfirmed').textContent = s.confirmed;
+    document.getElementById('statPending').textContent = s.pending;
+    document.getElementById('statErrors').textContent = s.errors;
+}
+
+function updateStatsFromEvent(ev) {
+    if (!ev || !ev.stats) return;
+    const s = ev.stats;
+    document.getElementById('statTotal').textContent = s.total;
+    document.getElementById('statConfirmed').textContent = s.confirmed;
+    document.getElementById('statPending').textContent = s.pending;
+    document.getElementById('statErrors').textContent = s.errors;
+}
+
+function setView(view) {
+    state.view = view;
+    document.getElementById('tabCards').classList.toggle('active', view === 'cards');
+    document.getElementById('tabGraph').classList.toggle('active', view === 'graph');
+    document.getElementById('tabStatus').classList.toggle('active', view === 'status');
+
+    document.getElementById('cards').style.display = view === 'cards' ? '' : 'none';
+    document.getElementById('pagination').style.display = view === 'cards' ? '' : 'none';
+    document.getElementById('graph').style.display = view === 'graph' ? '' : 'none';
+    document.getElementById('status').style.display = view === 'status' ? '' : 'none';
+
+    if (view === 'graph') loadGraph();
+    if (view === 'status') loadStatus();
+}
+
+async function loadCards() {
+    let url = `/api/engrams?limit=${state.limit}&offset=${state.offset}`;
+    if (state.search) url += `&search=${encodeURIComponent(state.search)}`;
+    if (state.filter === 'confirmed') url += '&confirmed=1';
+    if (state.filter === 'pending') url += '&confirmed=0';
+    if (state.filter === 'errors') url += '&tag=error';
+
+    const data = await api(url);
+    state.items = data.items;
+    renderCards();
+    document.getElementById('pageNum').textContent = Math.floor(state.offset / state.limit) + 1;
+    document.getElementById('btnPrev').disabled = state.offset === 0;
+    document.getElementById('btnNext').disabled = data.items.length < state.limit;
+}
+
+async function loadStatus() {
+    const [cfg, db, jobs, ins, stor] = await Promise.all([
+        api('/api/config'),
+        api('/api/db_info'),
+        api('/api/jobs'),
+        api('/api/insights?limit=8'),
+        api('/api/storage_stats'),
+    ]);
+    const pend = await api('/api/pending?limit=20&offset=0');
+
+    const el = document.getElementById('status');
+    const jobsHtml = (jobs.items || []).map(j => `
+        <div class="kv-row">
+            <div class="kv-key">${j.unit}</div>
+            <div class="kv-val">${j.error ? ('ERR: ' + j.error) : (j.active + '/' + j.sub)}</div>
+        </div>
+    `).join('');
+
+    const topTags = (ins.top_tags || []).map(t => `<span class="pill">${t.key} (${t.count})</span>`).join(' ');
+    const topHosts = (ins.top_hosts || []).map(t => `<span class="pill">${t.key} (${t.count})</span>`).join(' ');
+    const bySource = Object.entries((stor.sql && stor.sql.by_source) ? stor.sql.by_source : {})
+        .slice(0, 8)
+        .map(([k,v]) => `<span class="pill">${k}: ${v}</span>`)
+        .join(' ');
+
+    const pendItems = (pend.items || []);
+    const pendHtml = pendItems.map(p => `
+        <div class="kv-row" onclick="showDetail('${p.id}')">
+            <div class="kv-key">${(p.source||'').slice(0,12)}</div>
+            <div class="kv-val">
+                <span class="pill">${p.id.substring(0,8)}</span>
+                ${escapeHtml((p.content||'').substring(0,120))}${(p.content||'').length>120?'…':''}
+                <div class="actions" style="margin-top:6px" onclick="event.stopPropagation()">
+                    <button class="btn-ok" onclick="confirm('${p.id}', event)">✅</button>
+                    <button class="btn-no" onclick="reject('${p.id}', event)">❌</button>
+                </div>
+            </div>
+        </div>
+    `).join('');
+
+    el.innerHTML = `
+        <div class="panel">
+            <div class="panel-title">Config</div>
+            <div class="kv-row"><div class="kv-key">workspace</div><div class="kv-val">${cfg.workspace}</div></div>
+            <div class="kv-row"><div class="kv-key">db</div><div class="kv-val">${db.db_path}</div></div>
+            <div class="kv-row"><div class="kv-key">db mtime</div><div class="kv-val">${new Date(db.mtime).toLocaleString()}</div></div>
+        </div>
+        <div class="panel">
+            <div class="panel-title">Storage</div>
+            <div class="kv-row"><div class="kv-key">SQL</div><div class="kv-val">${stor.sql.total_engrams} engrams (ok ${stor.sql.confirmed}, pending ${stor.sql.pending})</div></div>
+            <div class="kv-row"><div class="kv-key">Vector</div><div class="kv-val">chroma ${(stor.vector.chroma_size_bytes/1024/1024).toFixed(1)} MB, cache ${stor.vector.embedding_cache_files} files</div></div>
+            <div class="kv-row"><div class="kv-key">Obsidian</div><div class="kv-val">${stor.obsidian.configured ? 'configured' : 'not configured'}</div></div>
+            <div class="kv-row"><div class="kv-key">By source</div><div class="kv-val">${bySource || '-'}</div></div>
+        </div>
+        <div class="panel">
+            <div class="panel-title">Jobs</div>
+            ${jobsHtml || '<div class="muted">Keine Daten</div>'}
+        </div>
+        <div class="panel">
+            <div class="panel-title">Insights</div>
+            <div class="kv-row"><div class="kv-key">pending</div><div class="kv-val">${ins.pending}</div></div>
+            <div class="kv-row"><div class="kv-key">top tags</div><div class="kv-val">${topTags || '-'}</div></div>
+            <div class="kv-row"><div class="kv-key">top hosts</div><div class="kv-val">${topHosts || '-'}</div></div>
+        </div>
+        <div class="panel">
+            <div class="panel-title">Pending Queue (latest)</div>
+            ${pendHtml || '<div class="muted">Keine Pendings</div>'}
+        </div>
+    `;
+}
+
+async function loadGraph() {
+    const g = await api('/api/graph?limit_nodes=200');
+    renderGraph(g.nodes || [], g.edges || []);
+}
+
+function renderGraph(nodes, edges) {
+    const canvas = document.getElementById('graphCanvas');
+    const hint = document.getElementById('graphHint');
+    const ctx = canvas.getContext('2d');
+
+    // Fit canvas to container width (mobile)
+    const w = canvas.parentElement.clientWidth - 24;
+    canvas.width = Math.max(320, Math.min(520, w));
+    canvas.height = 520;
+
+    if (!nodes.length || !edges.length) {
+        hint.textContent = 'Graph: keine Kanten (noch keine Links/Tags/Hosts im Sample).';
+        ctx.clearRect(0,0,canvas.width,canvas.height);
+        return;
+    }
+
+    hint.textContent = `nodes=${nodes.length} edges=${edges.length}`;
+
+    const nodeById = new Map(nodes.map(n => [n.id, n]));
+    const sim = nodes.map(n => ({
+        id: n.id,
+        kind: n.kind,
+        label: n.label || n.id,
+        x: Math.random()*canvas.width,
+        y: Math.random()*canvas.height,
+        vx: 0, vy: 0,
+    }));
+    const simById = new Map(sim.map(n => [n.id, n]));
+
+    const links = edges
+        .map(e => ({a: simById.get(e.from), b: simById.get(e.to), kind: e.kind}))
+        .filter(l => l.a && l.b);
+
+    // Simple force layout (few iterations)
+    for (let iter=0; iter<180; iter++) {
+        // repulsion
+        for (let i=0; i<sim.length; i++) {
+            for (let j=i+1; j<sim.length; j++) {
+                const a = sim[i], b = sim[j];
+                const dx = a.x - b.x, dy = a.y - b.y;
+                const d2 = dx*dx + dy*dy + 0.01;
+                const f = 120 / d2;
+                a.vx += dx*f; a.vy += dy*f;
+                b.vx -= dx*f; b.vy -= dy*f;
+            }
+        }
+        // springs
+        for (const l of links) {
+            const a = l.a, b = l.b;
+            const dx = b.x - a.x, dy = b.y - a.y;
+            const dist = Math.sqrt(dx*dx + dy*dy) || 1;
+            const target = 60;
+            const k = 0.02;
+            const f = (dist - target) * k;
+            const fx = (dx/dist)*f, fy = (dy/dist)*f;
+            a.vx += fx; a.vy += fy;
+            b.vx -= fx; b.vy -= fy;
+        }
+        // integrate + bounds
+        for (const n of sim) {
+            n.vx *= 0.85; n.vy *= 0.85;
+            n.x += n.vx; n.y += n.vy;
+            n.x = Math.max(10, Math.min(canvas.width-10, n.x));
+            n.y = Math.max(10, Math.min(canvas.height-10, n.y));
+        }
+    }
+
+    ctx.clearRect(0,0,canvas.width,canvas.height);
+    // edges
+    ctx.globalAlpha = 0.5;
+    ctx.strokeStyle = '#3a3a55';
+    ctx.lineWidth = 1;
+    for (const l of links) {
+        ctx.beginPath();
+        ctx.moveTo(l.a.x, l.a.y);
+        ctx.lineTo(l.b.x, l.b.y);
+        ctx.stroke();
+    }
+    ctx.globalAlpha = 1.0;
+
+    // nodes
+    for (const n of sim) {
+        let r = 5;
+        let fill = '#6c8af5';
+        if (n.kind === 'tag') { fill = '#8a9aff'; r = 4; }
+        if (n.kind === 'host') { fill = '#f5b46c'; r = 4; }
+        if (n.kind === 'engram') { fill = '#6c8af5'; r = 5; }
+
+        ctx.beginPath();
+        ctx.fillStyle = fill;
+        ctx.arc(n.x, n.y, r, 0, Math.PI*2);
+        ctx.fill();
+    }
+}
+
+// Real-time updates via SSE
+function startEvents() {
+    try {
+        const es = new EventSource('/api/events');
+        es.onmessage = (msg) => {
+            try {
+                state.lastEvent = JSON.parse(msg.data);
+                updateStatsFromEvent(state.lastEvent);
+                if (state.view === 'status') {
+                    // refresh status panels without heavy re-render: just rerun loadStatus occasionally
+                    loadStatus();
+                }
+                if (state.view === 'graph') {
+                    // fetch graph less often (every ~15s)
+                    const t = Date.now();
+                    if (!state._lastGraphFetch || (t - state._lastGraphFetch) > 15000) {
+                        state._lastGraphFetch = t;
+                        loadGraph();
+                    }
+                }
+            } catch (e) {}
+        };
+        es.onerror = () => {
+            // keep UI usable even if SSE drops
+        };
+    } catch (e) {}
+}
+
+startEvents();
+
+function renderCards() {
+    const el = document.getElementById('cards');
+    el.innerHTML = state.items.map(item => `
+        <div class="card ${item.confirmed ? 'confirmed' : ''} ${item.rejections > 0 ? 'rejected' : ''}" data-id="${item.id}">
+            <div class="card-header">
+                <span class="conf-badge" style="background:hsl(${item.confidence*120},70%,40%)">${Math.round(item.confidence*100)}%</span>
+                <span class="tags">${item.tags.map(t => '<span class="tag">'+t+'</span>').join('')}</span>
+                <span class="date">${fmtDate(item.created)}</span>
+            </div>
+            <div class="card-body" onclick="showDetail('${item.id}')">
+                ${escapeHtml(item.content.substring(0, 200))}${item.content.length>200?'...':''}
+            </div>
+            <div class="card-footer">
+                <input type="text" class="reason-input" placeholder="Grund (optional)" id="reason-${item.id}"/>
+                <div class="actions">
+                    <button class="btn-ok" onclick="confirm('${item.id}', event)">✅</button>
+                    <button class="btn-no" onclick="reject('${item.id}', event)">❌</button>
+                    <button class="btn-archive" onclick="refresh('${item.id}', event)">🔄</button>
+                </div>
+            </div>
+        </div>
+    `).join('');
+}
+
+function fmtDate(iso) {
+    const d = new Date(iso);
+    return `${d.getDate().toString().padStart(2,'0')}.${(d.getMonth()+1).toString().padStart(2,'0')} ${d.getHours().toString().padStart(2,'0')}:${d.getMinutes().toString().padStart(2,'0')}`;
+}
+
+function escapeHtml(t) {
+    const d = document.createElement('div');
+    d.textContent = t;
+    return d.innerHTML;
+}
+
+// ─── Actions ────────────────────────────────────────────────────────────────
+async function confirm(id, ev) {
+    ev.stopPropagation();
+    const reason = document.getElementById('reason-'+id).value;
+    await api(`/api/engrams/${id}/confirm`, {
+        method: 'POST',
+        headers: {'Content-Type': 'application/x-www-form-urlencoded'},
+        body: new URLSearchParams({reason})
+    });
+    await loadCards(); await loadStats();
+}
+
+async function reject(id, ev) {
+    ev.stopPropagation();
+    const reason = document.getElementById('reason-'+id).value;
+    await api(`/api/engrams/${id}/reject`, {
+        method: 'POST',
+        headers: {'Content-Type': 'application/x-www-form-urlencoded'},
+        body: new URLSearchParams({reason})
+    });
+    await loadCards(); await loadStats();
+}
+
+async function refresh(id, ev) {
+    ev.stopPropagation();
+    await api(`/api/engrams/${id}/refresh`, {method: 'POST'});
+    await loadCards();
+}
+
+async function createEngram() {
+    const content = document.getElementById('newContent').value;
+    const tags = document.getElementById('newTags').value;
+    if (!content.trim()) return;
+    await api('/api/engrams', {
+        method: 'POST',
+        headers: {'Content-Type': 'application/x-www-form-urlencoded'},
+        body: new URLSearchParams({content, tags})
+    });
+    document.getElementById('newContent').value = '';
+    document.getElementById('newTags').value = '';
+    await loadCards(); await loadStats();
+}
+
+async function showDetail(id) {
+    const item = await api(`/api/engrams/${id}`);
+    const body = document.getElementById('modalBody');
+    body.innerHTML = `
+        <h3>Engramm ${item.id.substring(0,8)}</h3>
+        <p><b>Confidence:</b> ${Math.round(item.confidence*100)}%</p>
+        <p><b>Confirmed:</b> ${item.confirmed ? '✅' : '❌'}</p>
+        <p><b>Tags:</b> ${item.tags.map(t => '<span class="tag">'+t+'</span>').join(' ')}</p>
+        <p><b>Content:</b></p>
+        <div class="detail-content">${escapeHtml(item.content)}</div>
+        <p><b>History:</b></p>
+        <ul class="history">
+            ${(item.review_history || []).map(h => `<li>${fmtDate(h.at)} — ${h.action} (${h.note})</li>`).join('')}
+        </ul>
+        <p><b>Links:</b> ${item.links?.join(', ') || 'none'}</p>
+    `;
+    document.getElementById('detailModal').classList.add('open');
+}
+
+function closeModal() {
+    document.getElementById('detailModal').classList.remove('open');
+}
+
+// ─── Pagination ─────────────────────────────────────────────────────────────
+function nextPage() {
+    state.offset += state.limit;
+    loadCards();
+}
+
+function prevPage() {
+    state.offset = Math.max(0, state.offset - state.limit);
+    loadCards();
+}
+
+function manualRefresh() {
+    loadCards(); loadStats();
+}
+
+// ─── Search ─────────────────────────────────────────────────────────────────
+document.getElementById('searchInput').addEventListener('input', (e) => {
+    state.search = e.target.value;
+    state.offset = 0;
+    loadCards();
+});
+
+document.getElementById('filterSelect').addEventListener('change', (e) => {
+    state.filter = e.target.value;
+    state.offset = 0;
+    loadCards();
+});
+
+// ─── Auto Refresh ───────────────────────────────────────────────────────────
+setInterval(() => {
+    if (!state.autoRefresh) return;
+    loadStats();
+    loadCards();
+    const now = new Date();
+    document.getElementById('lastUpdate').textContent =
+        `${now.getHours().toString().padStart(2,'0')}:${now.getMinutes().toString().padStart(2,'0')}`;
+}, 5000);
+
+// ─── Init ───────────────────────────────────────────────────────────────────
+loadStats();
+loadCards();
+</script>
+</body>
+</html>

tests/test_core.py

@@ -4,16 +4,11 @@
 import sys
 import os
 import tempfile
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "src"))
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
 
-try:
-    from src.engram import Engram, Grounding, Correctness
-    from src.store import EngramStore
-    from src.retriever import Retriever
-except ImportError:
-    from engram import Engram, Grounding, Correctness
-    from store import EngramStore
-    from retriever import Retriever
+from src.engram import Engram, Grounding, Correctness
+from src.store import EngramStore
+from src.retriever import Retriever
 
 
 def test_engram_creation():