@aiyiran/myclaw 1.1.135 → 1.1.136

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aiyiran/myclaw",
-  "version": "1.1.135",
+  "version": "1.1.136",
   "description": "",
   "main": "index.js",
   "bin": {

package/skills/chat-history-extractor/scripts/extract_chat.py

@@ -3,20 +3,25 @@
 Extract chat history from OpenClaw session URL(s) and generate JS data file(s).
 
 Usage:
-  # 单个会话
-  python3 extract_chat.py <session-url-or-key> [output-dir]
+  # 单个会话（输出到当前 workspace）
+  python3 extract_chat.py <session-url-or-key>
 
   # 多个会话（逗号分隔 / JSON 数组）
   python3 extract_chat.py "url1,url2,url3" [output-dir]
-  python3 extract_chat.py '["url1","url2","url3"]' [output-dir]
+  python3 extract_chat.py '[ "url1","url2","url3"]' [output-dir]
 
   # 扫描所有 agent 的所有会话，统计表格
-  python3 extract_chat.py --scan [output-dir]
+  python3 extract_chat.py --scan [--html]
 
-输出:
+输出（默认到当前 workspace /root/.openclaw/workspace-teacher）：
   - 每个会话生成独立的 <agentId>_<sessionName>_<date>_<time>.js
   - 生成 index.js，包含所有会话的元信息列表（含 work_url 字段）
   - 生成 chat_history.js（向后兼容，指向第一个会话）
+  - --html 时额外生成 summary.html（含可点击链接）
+
+Host 检测：
+  - 自动从 /root/.openclaw/myclaw/server/config.json 读取
+  - 可用 --host 覆盖
 
 work_url 字段:
   - 默认为空字符串
@@ -34,6 +39,31 @@ from datetime import datetime, timezone, timedelta
 tz_beijing = timezone(timedelta(hours=8))
 
 
+def detect_chat_host():
+    """Auto-detect chat host from config.json."""
+    config_path = '/root/.openclaw/myclaw/server/config.json'
+    try:
+        with open(config_path) as f:
+            cfg = json.load(f)
+        claw = cfg.get('claw', 'claw5')
+        return f"{claw}.kekouen.cn"
+    except Exception:
+        return 'claw5.kekouen.cn'
+
+
+def get_default_output_dir():
+    """Return the current workspace directory."""
+    # OPENCLAW_WORKSPACE is set to the workspace path
+    ws = os.environ.get('OPENCLAW_WORKSPACE', '')
+    if ws and os.path.isdir(ws):
+        return ws
+    # Fallback: derive from cwd (e.g. /root/.openclaw/workspace-teacher)
+    cwd = os.getcwd()
+    if '/workspace-' in cwd:
+        return cwd
+    return cwd
+
+
 def parse_time(ts_str):
     try:
         ts_str = ts_str.replace('Z', '')
@@ -202,10 +232,12 @@ const chatData = {json.dumps(output_data, ensure_ascii=False, indent=2)};
     return len(conversations), session_name
 
 
-def session_key_to_url(session_key):
-    """Build the claw6 chat URL from a session key."""
+def session_key_to_url(session_key, host=None):
+    """Build the chat URL from a session key. Host auto-detected from config.json."""
+    if host is None:
+        host = detect_chat_host()
     encoded = quote(session_key, safe='')
-    return f"https://claw6.kekouen.cn/chat?session={encoded}"
+    return f"https://{host}/chat?session={encoded}&token=aiyiran"
 
 
 def scan_all_agents():
@@ -238,21 +270,141 @@ def scan_all_agents():
     return results
 
 
-def print_summary_table(entries):
+def print_summary_table(entries, host=None):
+    if host is None:
+        host = detect_chat_host()
     """
     Print the summary table.
     entries: list of dicts with keys: index, session_name, agent_id, total_pairs, work_url, session_key, first_time, last_time
     """
-    print(f"\n{'#':>3}  {'workspace':<16} {'会话名':<28} {'对话数':>6}  {'起始时间':<20}  {'最后更新':<20}  {'作品链接':<12}  {'聊天记录URL'}")
-    print(f"{'-'*3}  {'-'*16} {'-'*28} {'-'*6}  {'-'*20}  {'-'*20}  {'-'*12}  {'-'*50}")
+    print(f"\n{'#':>3}  {'workspace':<16} {'会话名':<28} {'对话数':>6}  {'起始时间':<20}  {'最后更新':<20}  {'作品链接':<14}  {'对话链接'}")
+    print(f"{'-'*3}  {'-'*16} {'-'*28} {'-'*6}  {'-'*20}  {'-'*20}  {'-'*14}  {'-'*50}")
     for e in entries:
         work = e.get('work_url') or '（待填）'
-        url = session_key_to_url(e['session_key'])
+        url = session_key_to_url(e['session_key'], host)
         name = (e['session_name'] or '')[:26]
         agent = (e.get('agent_id') or '')[:16]
         first_t = (e.get('first_time') or '')[:19]
         last_t = (e.get('last_time') or '')[:19]
-        print(f"{e['index']:>3}  {agent:<16} {name:<28} {e['total_pairs']:>6}  {first_t:<20}  {last_t:<20}  {work:<12}  {url}")
+        print(f"{e['index']:>3}  {agent:<16} {name:<28} {e['total_pairs']:>6}  {first_t:<20}  {last_t:<20}  {work:<14}  {url}")
+
+
+def generate_html_table(entries, host, output_path):
+    """Generate an HTML file with a clickable table of all sessions."""
+    total_pairs = sum(e['total_pairs'] for e in entries)
+    rows_html = []
+    for e in entries:
+        work_url = e.get('work_url', '')
+        if work_url:
+            work_cell = f'<a href="{work_url}" target="_blank" class="link">🔗 查看作品</a>'
+        else:
+            work_cell = '<span class="pending">（待填）</span>'
+
+        chat_url = session_key_to_url(e['session_key'], host)
+        name = e.get('session_name', '') or ''
+        agent = e.get('agent_id', '') or ''
+        chat_cell = f'<a href="{chat_url}" target="_blank" class="link">💬 打开对话</a>'
+
+        rows_html.append(f"""
+        <tr>
+          <td class="num">{e['index']}</td>
+          <td>{agent}</td>
+          <td>{name}</td>
+          <td class="num">{e['total_pairs']}</td>
+          <td>{e.get('first_time', '')}</td>
+          <td>{e.get('last_time', '')}</td>
+          <td>{work_cell}</td>
+          <td>{chat_cell}</td>
+        </tr>""")
+
+    rows = '\n'.join(rows_html)
+    html = f'''<!DOCTYPE html>
+<html lang="zh-CN">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>作品扫描 - {len(entries)} sessions</title>
+  <style>
+    * {{ box-sizing: border-box; }}
+    body {{
+      font-family: -apple-system, BlinkMacSystemFont, "PingFang SC", "Microsoft YaHei", sans-serif;
+      background: linear-gradient(135deg, #f5f7fa 0%, #e9ecf3 100%);
+      margin: 0; padding: 24px; min-height: 100vh; color: #2d3748;
+    }}
+    .container {{ max-width: 1200px; margin: 0 auto; }}
+    .header {{
+      background: linear-gradient(135deg, #667eea, #764ba2);
+      color: white; padding: 30px; border-radius: 16px; margin-bottom: 24px;
+      box-shadow: 0 10px 30px rgba(102,126,234,0.3);
+    }}
+    .header h1 {{ margin: 0 0 8px 0; font-size: 1.8em; }}
+    .header p {{ margin: 0; opacity: 0.9; }}
+    .summary-bar {{
+      display: flex; gap: 16px; margin-top: 16px; flex-wrap: wrap;
+    }}
+    .summary-bar .stat {{
+      background: rgba(255,255,255,0.2); padding: 8px 16px; border-radius: 8px;
+      backdrop-filter: blur(10px);
+    }}
+    .stat strong {{ font-size: 1.3em; margin-right: 6px; }}
+    table {{
+      width: 100%; background: white; border-radius: 12px; overflow: hidden;
+      border-collapse: collapse; box-shadow: 0 4px 20px rgba(0,0,0,0.08);
+    }}
+    th {{
+      background: #f7fafc; padding: 14px 12px; text-align: left;
+      font-weight: 600; color: #4a5568; border-bottom: 2px solid #e2e8f0;
+      font-size: 0.9em;
+    }}
+    td {{ padding: 12px; border-bottom: 1px solid #edf2f7; font-size: 0.92em; }}
+    tr:hover td {{ background: #f7fafc; }}
+    .num {{ text-align: right; font-variant-numeric: tabular-nums; }}
+    .link {{
+      color: #667eea; text-decoration: none; font-weight: 500;
+      padding: 4px 10px; border-radius: 6px; background: #edf2f7;
+      transition: all 0.2s; display: inline-block;
+    }}
+    .link:hover {{ background: #667eea; color: white; transform: translateY(-1px); }}
+    .pending {{ color: #a0aec0; font-style: italic; }}
+    .footer {{
+      text-align: center; margin-top: 24px; color: #718096; font-size: 0.85em;
+    }}
+  </style>
+</head>
+<body>
+  <div class="container">
+    <div class="header">
+      <h1>📋 作品扫描</h1>
+      <p>Generated by chat-history-extractor</p>
+      <div class="summary-bar">
+        <div class="stat"><strong>{len(entries)}</strong> sessions</div>
+        <div class="stat"><strong>{total_pairs}</strong> conversation pairs</div>
+        <div class="stat"><strong>host:</strong> {host}</div>
+      </div>
+    </div>
+    <table>
+      <thead>
+        <tr>
+          <th class="num">#</th>
+          <th>workspace</th>
+          <th>会话名</th>
+          <th class="num">对话数</th>
+          <th>起始时间</th>
+          <th>最后更新</th>
+          <th>作品链接</th>
+          <th>对话链接</th>
+        </tr>
+      </thead>
+      <tbody>{rows}
+      </tbody>
+    </table>
+    <p class="footer">提示：点击「作品链接」和「对话链接」在新页面打开。后续可在 JS 文件中编辑 work_url 字段补上作品链接。</p>
+  </div>
+</body>
+</html>
+'''
+    with open(output_path, 'w', encoding='utf-8') as f:
+        f.write(html)
 
 
 def process_one(url_or_key, output_dir, index):
@@ -316,8 +468,10 @@ const chatIndex = {json.dumps(sessions, ensure_ascii=False, indent=2)};
     print(f"\nIndex: {index_path} ({len(sessions)} sessions)")
 
 
-def run_scan(output_dir=None):
-    """Scan all agents, count conversations, show table. Optionally generate JS files."""
+def run_scan(output_dir=None, host=None, html_output=False):
+    if host is None:
+        host = detect_chat_host()
+    """Scan all agents, count conversations, show table. Optionally generate JS files + HTML."""
     all_sessions = scan_all_agents()
     print(f"Found {len(all_sessions)} session(s) across all agents.\n")
 
@@ -340,7 +494,13 @@ def run_scan(output_dir=None):
         except Exception as e:
             print(f"  [SKIP] {session_key}: {e}")
 
-    print_summary_table(entries)
+    # Sort by first_time descending (newest first)
+    entries.sort(key=lambda e: (e.get('first_time') or '') or '', reverse=True)
+    # Re-assign index after sorting
+    for i, e in enumerate(entries, 1):
+        e['index'] = i
+
+    print_summary_table(entries, host)
 
     # Generate JS files if output_dir specified
     if output_dir:
@@ -363,32 +523,71 @@ def run_scan(output_dir=None):
             import shutil
             shutil.copy2(first_js, compat_js)
 
+    # Generate HTML table with clickable links
+    if html_output:
+        target_dir = output_dir if output_dir else os.getcwd()
+        os.makedirs(target_dir, exist_ok=True)
+        now_str = datetime.now().strftime('%Y%m%d_%H%M%S')
+        html_filename = f"作品扫描_{now_str}.html"
+        html_path = os.path.join(target_dir, html_filename)
+        generate_html_table(entries, host, html_path)
+        print(f"HTML: {html_path}")
+
     total_pairs = sum(e['total_pairs'] for e in entries)
     print(f"\n合计：{len(entries)} 个会话，{total_pairs} 对对话。")
     return entries
 
 
 def main():
-    if len(sys.argv) < 2:
+    # Parse flags: --host HOST, --html, --scan
+    # Position: positional args (no --) come first, flags can be interleaved
+    args = sys.argv[1:]
+
+    host = detect_chat_host()
+    html_output = False
+    scan_mode = False
+    positional = []
+
+    i = 0
+    while i < len(args):
+        a = args[i]
+        if a == '--host' and i + 1 < len(args):
+            host = args[i + 1]
+            i += 2
+        elif a == '--html':
+            html_output = True
+            i += 1
+        elif a == '--scan':
+            scan_mode = True
+            i += 1
+        else:
+            positional.append(a)
+            i += 1
+
+    if not positional and not scan_mode:
         print("Usage:")
-        print("  python3 extract_chat.py <url-or-key> [output-dir]")
-        print("  python3 extract_chat.py 'url1,url2,url3' [output-dir]")
-        print('  python3 extract_chat.py \'["url1","url2"]\' [output-dir]')
-        print("  python3 extract_chat.py --scan [output-dir]")
+        print("  python3 extract_chat.py <url-or-key> [output-dir] [--host HOST] [--html]")
+        print("  python3 extract_chat.py 'url1,url2,url3' [output-dir] [--host HOST] [--html]")
+        print('  python3 extract_chat.py \'["url1","url2"]\' [output-dir] [--host HOST] [--html]')
+        print("  python3 extract_chat.py --scan [output-dir] [--host HOST] [--html]")
+        print("Flags:")
+        print("  --host HOST     Override chat host (default: auto-detect from config.json)")
+        print("  --html          Also generate summary.html with clickable links")
+        print("  --scan          Scan all agents")
         sys.exit(1)
 
-    arg1 = sys.argv[1]
-
     # --scan mode
-    if arg1 == '--scan':
-        output_dir = sys.argv[2] if len(sys.argv) > 2 else None
-        run_scan(output_dir)
+    if scan_mode:
+        output_dir = positional[0] if positional else get_default_output_dir()
+        run_scan(output_dir, host=host, html_output=html_output)
         return
 
     # Normal mode
-    output_dir = sys.argv[2] if len(sys.argv) > 2 else os.getcwd()
+    arg1 = positional[0]
+    output_dir = positional[1] if len(positional) > 1 else get_default_output_dir()
     items = parse_input(arg1)
     print(f"Input: {len(items)} session(s)")
+    print(f"Host: {detect_chat_host()}")
 
     os.makedirs(output_dir, exist_ok=True)
 
@@ -413,7 +612,14 @@ def main():
         print(f"Compat: chat_history.js -> {results[0]['js_file']}")
 
     # Summary table
-    print_summary_table(results)
+    print_summary_table(results, host)
+
+    # HTML output
+    if html_output:
+        html_path = os.path.join(output_dir, 'summary.html')
+        generate_html_table(results, host, html_path)
+        print(f"HTML: {html_path}")
+
     total_pairs = sum(r['total_pairs'] for r in results)
     print(f"\n合计：{len(results)} 个会话，{total_pairs} 对对话。")