Full sync - all projects, memory, configs

extract_sessions.py

@@ -0,0 +1,96 @@
+#!/usr/bin/env python3
+"""
+Extract assistant turns from OpenClaw session files for auto-memory indexing.
+"""
+import sys
+import json
+import subprocess
+from collections import deque
+
+def extract_assistant_turns(session_file, max_turns=10):
+    """Extract the last N assistant turns with their preceding user messages."""
+    turns = []
+    user_msg = None
+    
+    try:
+        with open(session_file, 'r') as f:
+            for line in f:
+                try:
+                    entry = json.loads(line.strip())
+                    if entry.get('type') != 'message':
+                        continue
+                    
+                    message = entry.get('message', {})
+                    role = message.get('role')
+                    content = message.get('content', [])
+                    
+                    if role == 'user':
+                        # Extract text from user message
+                        text_content = []
+                        for item in content:
+                            if item.get('type') == 'text':
+                                text_content.append(item.get('text', ''))
+                        user_msg = ' '.join(text_content).strip()
+                    
+                    elif role == 'assistant' and user_msg:
+                        # Extract text from assistant message (skip thinking and tool calls)
+                        text_content = []
+                        for item in content:
+                            if item.get('type') == 'text':
+                                text_content.append(item.get('text', ''))
+                        assistant_text = ' '.join(text_content).strip()
+                        
+                        if assistant_text:  # Only store if there's actual text content
+                            turns.append({
+                                'user': user_msg,
+                                'assistant': assistant_text,
+                                'agent_id': 'case',
+                                'session': 'main'
+                            })
+                            # Keep only the last max_turns
+                            if len(turns) > max_turns:
+                                turns.pop(0)
+                
+                except json.JSONDecodeError:
+                    continue
+                    
+    except Exception as e:
+        print(f"Error reading session file: {e}", file=sys.stderr)
+        return []
+    
+    return turns
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: python3 extract_sessions.py <session_file>", file=sys.stderr)
+        return 1
+    
+    session_file = sys.argv[1]
+    turns = extract_assistant_turns(session_file)
+    
+    if not turns:
+        print("No assistant turns found", file=sys.stderr)
+        return 0
+    
+    # Pipe each turn to the auto-memory-hook.py script
+    hook_script = "/home/wdjones/.openclaw/workspace/tools/auto-memory-hook.py"
+    
+    for turn in turns:
+        try:
+            json_data = json.dumps(turn)
+            result = subprocess.run(
+                ["python3", hook_script], 
+                input=json_data, 
+                text=True, 
+                capture_output=True
+            )
+            if result.returncode != 0:
+                print(f"Error processing turn: {result.stderr}", file=sys.stderr)
+        except Exception as e:
+            print(f"Error running auto-memory-hook: {e}", file=sys.stderr)
+    
+    print(f"Processed {len(turns)} assistant turns")
+    return 0
+
+if __name__ == "__main__":
+    sys.exit(main())