修改版本

tools/sync.py

@@ -4,7 +4,7 @@ Wiki ↔ Raw 三向同步工具
 
 功能：
   - 检测 raw/ 下文件变化（新增/修改/删除）
-  - 自动调用 ingest.py 进行同步
+  - 调用 Claude Code agent 进行同步（不使用 litellm）
   - 维护 manifest.json 状态映射
   - 检测 orphan entity/concept（仅报告，不删除）
 
@@ -12,7 +12,6 @@ Wiki ↔ Raw 三向同步工具
     python tools/sync.py --check        预览变化（不执行）
     python tools/sync.py --sync         执行同步
     python tools/sync.py --rebuild      从 manifest 重建 wiki/index（兜底）
-    python tools/sync.py --bootstrap    从现有 wiki sources 反向生成 manifest（首次用，跳过已 ingest 的文件）
 
 manifest.json 格式：
 {
@@ -39,9 +38,10 @@ from pathlib import Path
 from datetime import datetime, timezone
 
 
-REPO_ROOT = Path(__file__).parent.parent
+REPO_ROOT = Path(__file__).parent.parent.resolve()
 WIKI_DIR = REPO_ROOT / "wiki"
-MANIFEST_FILE = WIKI_DIR / "manifest.json"
+# manifest.json 放在 tools/ 而非 wiki/，避免 symlink 路径问题
+MANIFEST_FILE = Path(__file__).parent / "manifest.json"
 SCHEMA_FILE = REPO_ROOT / "CLAUDE.md"
 
 
@@ -127,26 +127,71 @@ def build_slug_from_path(rel_path: str) -> str:
     return name or "untitled"
 
 
-def call_ingest(source_path: str, slug: str = None) -> dict:
-    """调用 ingest.py，返回结果"""
-    cmd = [sys.executable, str(REPO_ROOT / "tools" / "ingest.py"), source_path]
-    try:
-        result = subprocess.run(
-            cmd,
-            capture_output=True,
-            text=True,
-            timeout=300,
-            cwd=str(REPO_ROOT),
-        )
-        return {
-            "success": result.returncode == 0,
-            "stdout": result.stdout,
-            "stderr": result.stderr,
-        }
-    except subprocess.TimeoutExpired:
-        return {"success": False, "stdout": "", "stderr": "Timeout (>5min)"}
-    except Exception as e:
-        return {"success": False, "stdout": "", "stderr": str(e)}
+def call_ingest(abs_path: str, slug: str, json_mode: bool = False) -> dict:
+    """调用 Claude Code agent 执行 /wiki-ingest，返回结果
+    
+    使用 TMUX 交互模式调用 Claude Code Agent
+    返回 special status 让 Hermes 可以手动处理 TMUX 会话
+    """
+    return {
+        "status": "needs_manual_tmux",
+        "abs_path": abs_path,
+        "slug": slug,
+        "message": "需要通过 TMUX 手动执行 /wiki-ingest，请使用 llm-wiki-sync 技能流程",
+    }
+
+
+def start_tmux_session() -> bool:
+    """启动 TMUX session 用于 wiki ingest"""
+    TMUX_SESSION = "wiki-ingest"
+    
+    # 检查 TMUX session 是否存在
+    check = subprocess.run(
+        ["tmux", "has-session", "-t", TMUX_SESSION],
+        capture_output=True,
+    )
+    
+    if check.returncode == 0:
+        print(f"  TMUX session '{TMUX_SESSION}' already exists")
+        return True
+    
+    # 创建新 session
+    subprocess.run(
+        ["tmux", "new-session", "-d", "-s", TMUX_SESSION, 
+         f"cd {REPO_ROOT} && claude --permission-mode bypassPermissions"],
+        check=True,
+    )
+    print(f"  Created TMUX session '{TMUX_SESSION}'")
+    return True
+
+
+def send_to_tmux(command: str) -> bool:
+    """发送命令到 TMUX session"""
+    TMUX_SESSION = "wiki-ingest"
+    subprocess.run(
+        ["tmux", "send-keys", "-t", TMUX_SESSION, f"{command}\n"],
+        check=True,
+    )
+    return True
+
+
+def wait_for_completion(seconds: int = 120) -> bool:
+    """等待 Claude Code 完成处理"""
+    import time
+    print(f"  Waiting {seconds}s for Claude Code to complete...")
+    time.sleep(seconds)
+    return True
+
+
+def cleanup_tmux() -> bool:
+    """清理 TMUX session"""
+    TMUX_SESSION = "wiki-ingest"
+    subprocess.run(
+        ["tmux", "kill-session", "-t", TMUX_SESSION],
+        capture_output=True,
+    )
+    print(f"  Killed TMUX session '{TMUX_SESSION}'")
+    return True
 
 
 def find_orphan_entity_concept(manifest: dict) -> tuple[list, list]:
@@ -225,13 +270,12 @@ def check_changes(manifest: dict, raw_files: dict) -> dict:
     return changes
 
 
-def run_sync(dry_run: bool = False, verbose: bool = False):
-    print(f"\n{bold('=== Wiki Sync')}\n")
-    print(f"  Date:    {datetime.now().strftime('%Y-%m-%d %H:%M')}")
-    print(f"  Raw:     {REPO_ROOT / 'raw'}")
-    print(f"  Wiki:    {WIKI_DIR}")
+def run_sync(dry_run: bool = False, verbose: bool = False, json_mode: bool = False):
+    print(f"\n{bold('=== Wiki Sync')}\n", end="")
+    print(f"  Date:    {datetime.now().strftime('%Y-%m-%d %H:%M')}\n")
+    print(f"  Raw:     {REPO_ROOT / 'raw'}\n")
+    print(f"  Wiki:    {WIKI_DIR}\n")
     print(f"  Mode:    {'DRY-RUN (preview only)' if dry_run else 'LIVE SYNC'}")
-    print()
 
     # Step 1: load manifest
     manifest = load_manifest()
@@ -250,190 +294,150 @@ def run_sync(dry_run: bool = False, verbose: bool = False):
         return
 
     # ─── Report ───
-    print(f"\n{bold('--- Changes ---')}")
-    print(f"  {green('+')} New:     {len(changes['new'])}")
-    print(f"  {yellow('~')} Updated: {len(changes['updated'])}")
-    print(f"  {red('-')} Deleted: {len(changes['deleted'])}")
+    if not json_mode:
+        print(f"\n{bold('--- Changes ---')}")
+        print(f"  {green('+')} New:     {len(changes['new'])}")
+        print(f"  {yellow('~')} Updated: {len(changes['updated'])}")
+        print(f"  {red('-')} Deleted: {len(changes['deleted'])}")
 
     if verbose or not dry_run:
         if changes["new"]:
-            print(f"\n  {bold('New Files:')}")
+            if not json_mode:
+                print(f"\n  {bold('New Files:')}")
             for f in changes["new"]:
-                log(f"{green('[+')} {f['rel_path']}", "normal")
+                if json_mode:
+                    print(json.dumps({
+                        "event": "new_detected",
+                        "rel_path": f["rel_path"],
+                        "slug": build_slug_from_path(f["rel_path"]),
+                    }))
+                else:
+                    log(f"{green('[+')} {f['rel_path']}", "normal")
 
         if changes["updated"]:
-            print(f"\n  {bold('Updated Files:')}")
+            if not json_mode:
+                print(f"\n  {bold('Updated Files:')}")
             for f in changes["updated"]:
-                log(f"{yellow('[~]')} {f['rel_path']} (hash changed)", "normal")
+                if json_mode:
+                    print(json.dumps({
+                        "event": "updated_detected",
+                        "rel_path": f["rel_path"],
+                        "slug": manifest["files"].get(f["rel_path"], {}).get("slug") or build_slug_from_path(f["rel_path"]),
+                    }))
+                else:
+                    log(f"{yellow('[~]')} {f['rel_path']} (hash changed)", "normal")
 
         if changes["deleted"]:
-            print(f"\n  {bold('Deleted Files:')}")
+            if not json_mode:
+                print(f"\n  {bold('Deleted Files:')}")
             for f in changes["deleted"]:
-                log(f"{red('[-]')} {f['rel_path']}", "normal")
+                if json_mode:
+                    print(json.dumps({
+                        "event": "deleted_detected",
+                        "rel_path": f["rel_path"],
+                    }))
+                else:
+                    log(f"{red('[-]')} {f['rel_path']}", "normal")
 
     if dry_run:
         log("\nDry-run complete. Run with --sync to apply.", "warn")
         return
 
     # ─── Apply Sync ───
-    print(f"\n{bold('--- Applying Sync ---')}")
+    # 注意：call_ingest 现在返回 needs_manual_tmux，提示 Hermes 通过 TMUX 手动执行
+    # 这里只做 manifest 记录，不实际调用 Claude Code
+    if not json_mode:
+        print(f"\n{bold('--- Applying Sync ---')}")
+        print("  Note: Ingest execution requires manual TMUX workflow")
+        print("  Use llm-wiki-sync skill for actual ingestion")
+        print()
 
     updated_manifest = manifest.copy()
     updated_manifest["files"] = manifest.get("files", {}).copy()
 
-    # ① 新增 → ingest
+    # 标记新增和更新的文件为待处理（由 Hermes 手动执行）
+    pending_files = []
+    
+    # ① 新增 → 标记待处理
     for f in changes["new"]:
         rel_path = f["rel_path"]
         abs_path = f["abs_path"]
         slug = build_slug_from_path(rel_path)
-        print(f"\n  {green('[+]')} New: {rel_path}")
-        print(f"      slug: {slug}")
-
-        result = call_ingest(abs_path, slug)
-        if result["success"]:
-            log(f"Ingested: {slug}.md", "success")
-            updated_manifest["files"][rel_path] = {
-                "hash": f["hash"],
-                "modified": f["modified"],
-                "slug": slug,
-                "source_path": f"wiki/sources/{slug}.md",
-                "ingested": True,
-                "ingested_at": iso_now(),
-            }
-        else:
-            log(f"Failed: {result['stderr'][:200]}", "error")
-            # 仍然记录（避免重复 ingest）
-            updated_manifest["files"][rel_path] = {
-                "hash": f["hash"],
-                "modified": f["modified"],
-                "slug": slug,
-                "source_path": f"wiki/sources/{slug}.md",
-                "ingested": False,
-                "ingested_at": None,
-                "error": result["stderr"][:500],
-            }
-
-    # ② 修改 → re-ingest
+        
+        if json_mode:
+            print(json.dumps({"event": "pending", "rel_path": rel_path, "slug": slug, "action": "new"}))
+        
+        pending_files.append({"rel_path": rel_path, "abs_path": abs_path, "slug": slug, "action": "new"})
+        
+        # 先不更新 manifest，等实际执行完成后再更新
+        # updated_manifest["files"][rel_path] = {...}
+    
+    # ② 修改 → 标记待处理
     for f in changes["updated"]:
         rel_path = f["rel_path"]
         abs_path = f["abs_path"]
         old_slug = manifest["files"].get(rel_path, {}).get("slug") or build_slug_from_path(rel_path)
-        print(f"\n  {yellow('[~]')} Updated: {rel_path}")
+        
+        if json_mode:
+            print(json.dumps({"event": "pending", "rel_path": rel_path, "slug": old_slug, "action": "updated"}))
+        
+        pending_files.append({"rel_path": rel_path, "abs_path": abs_path, "slug": old_slug, "action": "updated"})
 
-        result = call_ingest(abs_path, old_slug)
-        if result["success"]:
-            log(f"Re-ingested: {old_slug}.md", "success")
-            updated_manifest["files"][rel_path] = {
-                **updated_manifest["files"].get(rel_path, {}),
-                "hash": f["hash"],
-                "modified": f["modified"],
-                "slug": old_slug,
-                "source_path": f"wiki/sources/{old_slug}.md",
-                "ingested": True,
-                "ingested_at": iso_now(),
-            }
-        else:
-            log(f"Failed: {result['stderr'][:200]}", "error")
-
-    # ③ 删除 → 保留 wiki 内容，仅从 manifest 移除（按用户要求保留 orphan）
+    # ③ 删除 → 保留 wiki 内容，仅从 manifest 移除
+    deleted_files = []
     for f in changes["deleted"]:
         rel_path = f["rel_path"]
         source_path = f.get("source_path")
-        print(f"\n  {red('[-]')} Deleted: {rel_path}")
+        log(f"Deleted: {rel_path}", "warn")
         if source_path:
             sp = WIKI_DIR / source_path
             log(f"      Wiki source kept: {sp}", "warn")
-        # 从 manifest 移除（不删除 wiki 文件）
         if rel_path in updated_manifest["files"]:
             del updated_manifest["files"][rel_path]
+        deleted_files.append(rel_path)
 
-    # Step 4: Save manifest
+    # Step 4: Save manifest（不保存 pending files，等待实际执行后更新）
+    # 注意：不再在 --sync 时自动更新 manifest，而是由 Hermes 手动更新
+    # 这样可以追踪哪些文件需要处理
+    # 只保存已删除的文件变更
     save_manifest(updated_manifest)
     log(f"\nmanifest.json updated ({len(updated_manifest['files'])} entries)", "success")
 
+    # 输出 pending files 列表，供 Hermes 手动执行
+    if json_mode:
+        print(json.dumps({
+            "event": "sync_complete",
+            "summary": {
+                "pending": len(pending_files),
+                "deleted": len(deleted_files),
+                "manifest_entries": len(updated_manifest["files"]),
+            },
+            "pending_files": pending_files,
+            "deleted_files": deleted_files,
+        }))
+
     # Step 5: Orphan detection
     orphan_entities, orphan_concepts = find_orphan_entity_concept(updated_manifest)
-    if orphan_entities or orphan_concepts:
-        print(f"\n{bold('--- Orphan Report (kept as requested) ---')}")
-        if orphan_entities:
-            print(f"  {bold('Orphan Entities')} ({len(orphan_entities)}):")
-            for e in sorted(orphan_entities):
-                print(f"    {dim('?')} {e}")
-        if orphan_concepts:
-            print(f"  {bold('Orphan Concepts')} ({len(orphan_concepts)}):")
-            for c in sorted(orphan_concepts):
-                print(f"    {dim('?')} {c}")
-        log("\nOrphan pages are kept (not deleted per user request).", "info")
-    else:
-        log("No orphan entity/concept detected.", "success")
+    if not json_mode:
+        if orphan_entities or orphan_concepts:
+            print(f"\n{bold('--- Orphan Report (kept as requested) ---')}")
+            if orphan_entities:
+                print(f"  {bold('Orphan Entities')} ({len(orphan_entities)}):")
+                for e in sorted(orphan_entities):
+                    print(f"    {dim('?')} {e}")
+            if orphan_concepts:
+                print(f"  {bold('Orphan Concepts')} ({len(orphan_concepts)}):")
+                for c in sorted(orphan_concepts):
+                    print(f"    {dim('?')} {c}")
+            log("\nOrphan pages are kept (not deleted per user request).", "info")
+        else:
+            log("No orphan entity/concept detected.", "success")
 
+    # Step 6: JSON summary（已在上面输出 pending_files）
+    # 旧的 summary 输出已删除，因为不再自动执行 ingest
     print(f"\n{bold('Done.')}")
-
-
-def run_bootstrap():
-    """从现有 wiki sources 反向生成 manifest，跳过已 ingest 的文件"""
-    import re
-
-    print(f"\n{bold('=== Wiki Bootstrap')}\n")
-    print(f"  Scanning existing wiki sources to build manifest ...\n")
-
-    sources_dir = WIKI_DIR / "sources"
-    if not sources_dir.exists():
-        print(f"  {red('✗')} No wiki/sources/ directory found. Nothing to bootstrap.")
-        return
-
-    wikilink_pattern = re.compile(r"\[\[?raw/([^\]\s]+\.md)\]?]?", re.IGNORECASE)
-
-    manifest = {"version": 1, "updated_at": iso_now(), "files": {}}
-    raw_dir = (REPO_ROOT / "raw").resolve()  # 解析 symlink 到真实路径
-    repo_raw_prefix = str(REPO_ROOT / "raw")  # 用于 strip 前缀得到相对路径
-    bootstrapped = 0
-    skipped_not_found = 0
-    skipped_no_source_field = 0
-
-    for src in sources_dir.glob("*.md"):
-        content = src.read_text(encoding="utf-8")
-
-        # 尝试从 ## Source File 字段提取原始路径
-        match = wikilink_pattern.search(content)
-        if not match:
-            skipped_no_source_field += 1
-            continue
-
-        # raw_rel 格式如 "Agent/usecases/xxx.md"（不含 raw/ 前缀）
-        raw_rel = match.group(1).lstrip("/")
-        # 用 resolved 后的 raw_dir 拼接（follow symlink）
-        raw_path = raw_dir / raw_rel
-
-        if not raw_path.exists():
-            # 文件已删除，保留 source page 但不加入 manifest
-            skipped_not_found += 1
-            continue
-
-        stat = raw_path.stat()
-        file_hash = sha256_file(raw_path)
-        slug = src.stem
-
-        # manifest key 用 "raw/Agent/xxx.md" 格式（REPO_ROOT 相对路径）
-        manifest_key = f"raw/{raw_rel}"
-        manifest["files"][manifest_key] = {
-            "hash": file_hash,
-            "modified": datetime.fromtimestamp(stat.st_mtime, tz=timezone.utc).isoformat(),
-            "slug": slug,
-            "source_path": f"wiki/sources/{slug}.md",
-            "ingested": True,
-            "ingested_at": datetime.fromtimestamp(stat.st_mtime, tz=timezone.utc).isoformat(),
-        }
-        bootstrapped += 1
-
-    save_manifest(manifest)
-
-    print(f"  {bold('Result:')}")
-    print(f"    {green('✓')} Manifest entries created: {bootstrapped}")
-    print(f"    {yellow('~')} Skipped (source file deleted): {skipped_not_found}")
-    print(f"    {dim('-')} Skipped (no source_file field): {skipped_no_source_field}")
-    print(f"\n  {green('✓')} manifest.json created at: {MANIFEST_FILE}")
-    print(f"\n  Run now: {bold('python tools/sync.py --check')}  to preview new/updated files.\n")
+    print(f"\n  Pending files for manual TMUX ingestion: {len(pending_files)}")
+    print("  Use llm-wiki-sync skill to process these files.")
 
 
 def run_check():
@@ -537,26 +541,56 @@ if __name__ == "__main__":
         help="从 manifest 重建 wiki/index.md（兜底方案）",
     )
     parser.add_argument(
-        "--bootstrap",
+        "--reset-failed",
         action="store_true",
-        help="从现有 wiki sources 反向生成 manifest（首次使用，跳过已 ingest 的文件）",
+        help="重置所有 failed 的 ingest 状态（让它们重新待处理）",
+    )
+    parser.add_argument(
+        "--pending",
+        action="store_true",
+        help="列出所有待摄取的 pending 文件",
     )
     parser.add_argument(
         "--verbose", "-v",
         action="store_true",
         help="详细输出",
     )
+    parser.add_argument(
+        "--json",
+        action="store_true",
+        help="JSON 行输出模式（供调用方解析）",
+    )
 
     args = parser.parse_args()
 
-    if args.bootstrap:
-        run_bootstrap()
-    elif args.rebuild:
+    if args.rebuild:
         run_rebuild()
+    elif args.pending:
+        # 列出待摄取的文件
+        manifest = load_manifest()
+        pending = [k for k, v in manifest["files"].items() if not v.get("ingested")]
+        print(f"=== Pending Ingest Files ({len(pending)}) ===\n")
+        for i, path in enumerate(pending, 1):
+            print(f"{i:3}. {path}")
+    elif args.reset_failed:
+        # 重置失败的 ingest 状态
+        manifest = load_manifest()
+        reset_count = 0
+        for k, v in manifest["files"].items():
+            if v.get("error"):
+                v["ingested"] = False
+                v.pop("error", None)
+                v.pop("ingested_at", None)
+                reset_count += 1
+        if reset_count > 0:
+            save_manifest(manifest)
+            print(f"Reset {reset_count} failed entries to pending.")
+        else:
+            print("No failed entries found.")
     elif args.check:
         run_check()
     elif args.sync:
-        run_sync(dry_run=False, verbose=args.verbose)
+        run_sync(dry_run=False, verbose=args.verbose, json_mode=args.json)
     else:
         parser.print_help()
         print("\n示例:")
@@ -564,4 +598,3 @@ if __name__ == "__main__":
         print("  python tools/sync.py --sync        # 执行同步")
         print("  python tools/sync.py --sync -v     # 详细模式")
         print("  python tools/sync.py --rebuild     # 重建 index")
-        print("  python tools/sync.py --bootstrap   # 首次：从 wiki sources 生成 manifest")