更新 update_agent.py

tools/update_agent.py

@@ -88,9 +88,79 @@ def _git_rev_parse(ref: str, *, cwd: Path) -> str:
     return out
 
 
-def _git_is_dirty(*, cwd: Path) -> bool:
+def _git_has_tracked_changes(*, cwd: Path) -> bool:
-    out = subprocess.check_output(["git", "status", "--porcelain"], cwd=str(cwd), text=True)
+    """是否存在 tracked 的未提交修改（含暂存区）。"""
-    return bool(out.strip())
+    for cmd in (["git", "diff", "--quiet"], ["git", "diff", "--cached", "--quiet"]):
+        proc = subprocess.run(cmd, cwd=str(cwd))
+        if proc.returncode == 1:
+            return True
+        if proc.returncode != 0:
+            raise RuntimeError(f"{' '.join(cmd)} failed with code {proc.returncode}")
+    return False
+
+
+def _normalize_prefixes(prefixes: Tuple[str, ...]) -> Tuple[str, ...]:
+    normalized = []
+    for p in prefixes:
+        text = str(p or "").strip()
+        if not text:
+            continue
+        if not text.endswith("/"):
+            text += "/"
+        normalized.append(text)
+    return tuple(normalized)
+
+
+def _git_has_untracked_changes(*, cwd: Path, ignore_prefixes: Tuple[str, ...]) -> Tuple[bool, int, list[str]]:
+    """检查 untracked 文件（尊重 .gitignore），并忽略指定前缀目录。"""
+    ignore_prefixes = _normalize_prefixes(ignore_prefixes)
+    out = subprocess.check_output(["git", "ls-files", "--others", "--exclude-standard"], cwd=str(cwd), text=True)
+    paths = [line.strip() for line in out.splitlines() if line.strip()]
+
+    filtered = []
+    for p in paths:
+        if ignore_prefixes and any(p.startswith(prefix) for prefix in ignore_prefixes):
+            continue
+        filtered.append(p)
+
+    samples = filtered[:20]
+    return (len(filtered) > 0), len(filtered), samples
+
+
+def _git_is_dirty(*, cwd: Path, ignore_untracked_prefixes: Tuple[str, ...] = ("data/",)) -> dict:
+    """
+    判断工作区是否“脏”：
+    - tracked 变更（含暂存区）一律算脏
+    - untracked 文件默认忽略 data/（运行时数据目录，避免后台长期提示）
+    """
+    tracked_dirty = False
+    untracked_dirty = False
+    untracked_count = 0
+    untracked_samples: list[str] = []
+    try:
+        tracked_dirty = _git_has_tracked_changes(cwd=cwd)
+    except Exception:
+        # 若 diff 检测异常，回退到保守策略：认为脏
+        tracked_dirty = True
+
+    try:
+        untracked_dirty, untracked_count, untracked_samples = _git_has_untracked_changes(
+            cwd=cwd, ignore_prefixes=ignore_untracked_prefixes
+        )
+    except Exception:
+        # 若 untracked 检测异常，回退到不影响更新：不计入 dirty
+        untracked_dirty = False
+        untracked_count = 0
+        untracked_samples = []
+
+    return {
+        "dirty": bool(tracked_dirty or untracked_dirty),
+        "dirty_tracked": bool(tracked_dirty),
+        "dirty_untracked": bool(untracked_dirty),
+        "dirty_ignore_untracked_prefixes": list(_normalize_prefixes(ignore_untracked_prefixes)),
+        "untracked_count": int(untracked_count),
+        "untracked_samples": list(untracked_samples),
+    }
 
 
 def _compose_cmd() -> list[str]:
@@ -151,7 +221,7 @@ def check_updates(*, paths: Paths, branch: str, log_fp=None) -> dict:
     err = ""
     local = ""
     remote = ""
-    dirty = False
+    dirty_info: dict = {}
     try:
         if log_fp:
             _run(["git", "fetch", "origin", branch], cwd=paths.repo_dir, log_fp=log_fp, env=env)
@@ -159,7 +229,7 @@ def check_updates(*, paths: Paths, branch: str, log_fp=None) -> dict:
             subprocess.run(["git", "fetch", "origin", branch], cwd=str(paths.repo_dir), env={**os.environ, **env}, check=True)
         local = _git_rev_parse("HEAD", cwd=paths.repo_dir)
         remote = _git_rev_parse(f"origin/{branch}", cwd=paths.repo_dir)
-        dirty = _git_is_dirty(cwd=paths.repo_dir)
+        dirty_info = _git_is_dirty(cwd=paths.repo_dir, ignore_untracked_prefixes=("data/",))
     except Exception as e:
         err = f"{type(e).__name__}: {e}"
 
@@ -170,7 +240,7 @@ def check_updates(*, paths: Paths, branch: str, log_fp=None) -> dict:
         "local_commit": local,
         "remote_commit": remote,
         "update_available": update_available,
-        "dirty": dirty,
+        **(dirty_info or {"dirty": False}),
         "error": err,
     }