Initial commit: TrueRecall v2.2 with 30b curator and timer-based curation

debug_curator.py

@@ -0,0 +1,106 @@
+#!/usr/bin/env python3
+"""Debug curator with real data"""
+import json
+import requests
+import urllib.request
+
+QDRANT_URL = "http://10.0.0.40:6333"
+SOURCE_COLLECTION = "kimi_memories"
+
+# Get sample turns from real data
+filter_data = {
+    "must": [
+        {"key": "user_id", "match": {"value": "rob"}},
+        {"key": "date", "match": {"value": "2026-02-23"}}
+    ]
+}
+
+req = urllib.request.Request(
+    f"{QDRANT_URL}/collections/{SOURCE_COLLECTION}/points/scroll",
+    data=json.dumps({"limit": 5, "with_payload": True, "filter": filter_data}).encode(),
+    headers={"Content-Type": "application/json"},
+    method="POST"
+)
+
+with urllib.request.urlopen(req, timeout=30) as response:
+    result = json.loads(response.read().decode())
+    points = result.get("result", {}).get("points", [])
+    
+    turns = []
+    for point in points:
+        payload = point.get("payload", {})
+        user_msg = payload.get("user_message", "")
+        ai_msg = payload.get("ai_response", "")
+        
+        if user_msg or ai_msg:
+            turn = {
+                "turn": payload.get("turn_number", 0),
+                "user_id": payload.get("user_id", "rob"),
+                "user": user_msg[:300],  # Truncate
+                "ai": ai_msg[:300],      # Truncate
+                "conversation_id": payload.get("conversation_id", ""),
+                "timestamp": payload.get("created_at", ""),
+                "date": payload.get("date", "2026-02-23")
+            }
+            turns.append(turn)
+    
+    turns.sort(key=lambda x: (x.get("conversation_id", ""), x.get("turn", 0)))
+
+print(f"Got {len(turns)} turns")
+print("Sample:")
+for t in turns[:2]:
+    print(f"  User: {t['user'][:100]}...")
+    print(f"  AI: {t['ai'][:100]}...")
+
+# Now test with curator
+with open('/root/.openclaw/workspace/.projects/true-recall-v1/curator-prompt.md') as f:
+    prompt = f.read()
+
+conversation_json = json.dumps(turns[:5], indent=2)
+
+prompt_text = f"""## Input Conversation
+
+```json
+{conversation_json}
+```
+
+## Output
+"""
+
+response = requests.post(
+    'http://10.0.0.10:11434/api/generate',
+    json={
+        'model': 'qwen3:4b-instruct',
+        'system': prompt,
+        'prompt': prompt_text,
+        'stream': False,
+        'options': {'temperature': 0.1, 'num_predict': 3000}
+    },
+    timeout=120
+)
+
+result = response.json()
+output = result.get('response', '').strip()
+
+print("\n=== CURATOR OUTPUT ===")
+print(output[:3000])
+print("\n=== TRYING TO PARSE ===")
+
+# Try to parse
+try:
+    if '```json' in output:
+        parsed = output.split('```json')[1].split('```')[0].strip()
+        gems = json.loads(parsed)
+        print(f"Parsed {len(gems)} gems")
+    elif '```' in output:
+        parsed = output.split('```')[1].split('```')[0].strip()
+        gems = json.loads(parsed)
+        print(f"Parsed {len(gems)} gems")
+    else:
+        gems = json.loads(output)
+        print(f"Parsed {len(gems)} gems")
+except Exception as e:
+    print(f"Parse error: {e}")
+    print("Trying raw parse...")
+    gems = json.loads(output.strip())
+    print(f"Parsed {len(gems)} gems")