87 lines
3.1 KiB
Python
87 lines
3.1 KiB
Python
#!/usr/bin/env python3
|
|
import json
|
|
import glob
|
|
import os
|
|
from collections import defaultdict
|
|
|
|
def extract_conversation_turns(session_file):
|
|
"""Extract user-assistant conversation pairs from a session file"""
|
|
turns = []
|
|
current_user_msg = None
|
|
|
|
try:
|
|
with open(session_file, 'r') as f:
|
|
for line in f:
|
|
if not line.strip():
|
|
continue
|
|
|
|
try:
|
|
data = json.loads(line)
|
|
except json.JSONDecodeError:
|
|
continue
|
|
|
|
if data.get('type') == 'message':
|
|
message = data.get('message', {})
|
|
role = message.get('role')
|
|
content = message.get('content', [])
|
|
|
|
if role == 'user':
|
|
# Extract text content from user message
|
|
text_content = []
|
|
for item in content:
|
|
if item.get('type') == 'text':
|
|
text_content.append(item.get('text', ''))
|
|
user_text = '\n'.join(text_content)
|
|
|
|
# Skip cron messages
|
|
if not user_text.startswith('[cron:'):
|
|
current_user_msg = user_text
|
|
|
|
elif role == 'assistant' and current_user_msg:
|
|
# Extract text content from assistant message
|
|
text_content = []
|
|
for item in content:
|
|
if item.get('type') == 'text':
|
|
text_content.append(item.get('text', ''))
|
|
assistant_text = '\n'.join(text_content)
|
|
|
|
if assistant_text.strip():
|
|
turns.append({
|
|
'user': current_user_msg,
|
|
'assistant': assistant_text,
|
|
'agent_id': 'case',
|
|
'session': 'main'
|
|
})
|
|
current_user_msg = None
|
|
|
|
except Exception as e:
|
|
print(f"Error processing {session_file}: {e}")
|
|
|
|
return turns
|
|
|
|
def main():
|
|
sessions_dir = '/home/wdjones/.openclaw/agents/main/sessions/'
|
|
session_files = glob.glob(os.path.join(sessions_dir, '*.jsonl'))
|
|
|
|
# Sort by modification time, newest first
|
|
session_files.sort(key=os.path.getmtime, reverse=True)
|
|
|
|
all_turns = []
|
|
|
|
# Process each session file until we get 10 turns
|
|
for session_file in session_files:
|
|
if len(all_turns) >= 10:
|
|
break
|
|
|
|
turns = extract_conversation_turns(session_file)
|
|
all_turns.extend(turns)
|
|
|
|
# Take the last 10 turns
|
|
recent_turns = all_turns[-10:] if len(all_turns) >= 10 else all_turns
|
|
|
|
# Output each turn as JSON for the auto-memory-hook.py
|
|
for turn in recent_turns:
|
|
print(json.dumps(turn))
|
|
|
|
if __name__ == '__main__':
|
|
main() |