vault backup: 2026-02-26 21:10:47

.scripts/memory/index_common.py

@@ -1,8 +1,8 @@
 #!/usr/bin/env python3
 
-import fcntl
 import hashlib
 import os
+import sys
 import time
 from contextlib import contextmanager
 from pathlib import Path
@@ -62,29 +62,33 @@ def _sample_head_mid_tail(content: bytes, span: int = 1200) -> str:
     return sampled.decode('utf-8', errors='ignore').lower()
 
 
-def is_excluded(file_path: Path) -> bool:
+def is_excluded(file_path: Path) -> str | None:
+    """返回排除原因字符串，未排除则返回 None。"""
     rel = safe_rel(file_path)
     if rel is None:
-        return True
+        return 'path:unresolvable'
 
     parts = set(Path(rel).parts)
-    if parts.intersection(EXCLUDE_DIR_NAMES):
-        return True
-    if parts.intersection(EXCLUDE_PATH_PARTS):
-        return True
-    if any(kw in file_path.name.lower() for kw in EXCLUDE_FILENAME_KEYWORDS):
-        return True
+    for name in parts.intersection(EXCLUDE_DIR_NAMES):
+        return f'dir:{name}'
+    for name in parts.intersection(EXCLUDE_PATH_PARTS):
+        return f'path:{name}'
+    for kw in EXCLUDE_FILENAME_KEYWORDS:
+        if kw in file_path.name.lower():
+            return f'filename:{kw}'
 
     try:
         snippet = _sample_head_mid_tail(file_path.read_bytes())
-        if any(marker in snippet for marker in SENSITIVE_LITERAL_MARKERS):
-            return True
-        if any(pattern.search(snippet) for pattern in SENSITIVE_REGEX_PATTERNS):
-            return True
+        for marker in SENSITIVE_LITERAL_MARKERS:
+            if marker in snippet:
+                return f'content:literal:{marker[:20]}'
+        for pattern in SENSITIVE_REGEX_PATTERNS:
+            if pattern.search(snippet):
+                return f'content:regex:{pattern.pattern[:30]}'
     except Exception:
-        return True
+        return 'content:read_error'
 
-    return False
+    return None
 
 
 @contextmanager
@@ -92,11 +96,20 @@ def index_lock():
     lock_file = Path(os.getenv('INDEX_LOCK_FILE', str(VAULT_ROOT / '.memory-index.lock')))
     lock_file.parent.mkdir(parents=True, exist_ok=True)
     with open(lock_file, 'w', encoding='utf-8') as fh:
-        fcntl.flock(fh, fcntl.LOCK_EX)
-        try:
-            yield
-        finally:
-            fcntl.flock(fh, fcntl.LOCK_UN)
+        if sys.platform == 'win32':
+            import msvcrt
+            msvcrt.locking(fh.fileno(), msvcrt.LK_LOCK, 1)
+            try:
+                yield
+            finally:
+                msvcrt.locking(fh.fileno(), msvcrt.LK_UNLCK, 1)
+        else:
+            import fcntl as _fcntl
+            _fcntl.flock(fh, _fcntl.LOCK_EX)
+            try:
+                yield
+            finally:
+                _fcntl.flock(fh, _fcntl.LOCK_UN)
 
 
 def embed_text(text: str) -> list[float]:
@@ -118,7 +131,7 @@ def embed_text(text: str) -> list[float]:
     if title:
         headers['X-OpenRouter-Title'] = title
 
-    payload = {'model': model, 'input': text}
+    payload = {'model': model, 'input': text, 'encoding_format': 'float'}
     last_error: Exception | None = None
 
     for attempt in range(1, 4):