tools/file: tree skip_dirs noise defaults and path_denylist walk

Default noise basenames (node_modules, __pycache__, …); skip_dirs=[] disables;
apply_path_denylist hides denied children mid-tree.

src/plyngent/tools/file/tree.py

@@ -4,9 +4,10 @@ from dataclasses import dataclass
 from typing import TYPE_CHECKING
 
 from plyngent.agent import tool
-from plyngent.tools.workspace import WorkspaceError, resolve_path
+from plyngent.tools.workspace import WorkspaceError, get_path_denylist, resolve_path
 
 if TYPE_CHECKING:
+    from collections.abc import Sequence
     from pathlib import Path
 
 DEFAULT_MAX_DEPTH = 4
@@ -26,21 +27,58 @@ VCS_DIR_NAMES: frozenset[str] = frozenset(
     }
 )
 
+# Extra noise dirs skipped by default (in addition to VCS / optional hidden).
+# Pass skip_dirs=[] to disable this list (VCS still always skipped).
+DEFAULT_NOISE_DIR_NAMES: frozenset[str] = frozenset(
+    {
+        "node_modules",
+        "__pycache__",
+        ".venv",
+        "venv",
+        "dist",
+        "build",
+        "target",
+        ".tox",
+        ".mypy_cache",
+        ".ruff_cache",
+        ".pytest_cache",
+        "coverage",
+        ".next",
+        ".nuxt",
+        ".turbo",
+        ".cache",
+        "eggs",
+        ".eggs",
+        "htmlcov",
+    }
+)
+
 
 @dataclass(frozen=True, slots=True)
 class _TreeLimits:
     max_depth: int
     max_entries: int
     skip_hidden_dirs: bool
+    skip_basenames: frozenset[str]
+    apply_path_denylist: bool
 
 
-def _skip_directory(name: str, *, skip_hidden_dirs: bool) -> bool:
-    if name in VCS_DIR_NAMES:
+def _skip_directory(name: str, *, limits: _TreeLimits) -> bool:
+    if name in VCS_DIR_NAMES or name in limits.skip_basenames:
         return True
-    return bool(skip_hidden_dirs and name.startswith("."))
+    return bool(limits.skip_hidden_dirs and name.startswith("."))
 
 
-def _list_children(directory: Path, *, skip_hidden_dirs: bool) -> list[Path] | str:
+def _path_denied(path: Path) -> bool:
+    """True when resolved path matches a path_denylist substring."""
+    denylist = get_path_denylist()
+    if not denylist:
+        return False
+    resolved_str = str(path).replace("\\", "/")
+    return any(pattern and pattern.replace("\\", "/") in resolved_str for pattern in denylist)
+
+
+def _list_children(directory: Path, *, limits: _TreeLimits) -> list[Path] | str:
     try:
         children = list(directory.iterdir())
     except OSError as exc:
@@ -51,7 +89,9 @@ def _list_children(directory: Path, *, skip_hidden_dirs: bool) -> list[Path] | s
             is_dir = child.is_dir()
         except OSError:
             continue
-        if is_dir and _skip_directory(child.name, skip_hidden_dirs=skip_hidden_dirs):
+        if is_dir and _skip_directory(child.name, limits=limits):
+            continue
+        if limits.apply_path_denylist and _path_denied(child):
             continue
         visible.append(child)
     # Directories first, then files; alphabetical within each group.
@@ -70,7 +110,7 @@ def _render_tree(
     if depth >= limits.max_depth:
         return
 
-    children = _list_children(directory, skip_hidden_dirs=limits.skip_hidden_dirs)
+    children = _list_children(directory, limits=limits)
     if isinstance(children, str):
         lines.append(f"{prefix}{children}")
         return
@@ -104,6 +144,13 @@ def _render_tree(
         lines.append(f"{prefix}└── … ({more} more entries not shown)")
 
 
+def _resolve_skip_basenames(skip_dirs: Sequence[str] | None) -> frozenset[str]:
+    """None → default noise set; explicit list (including empty) replaces defaults."""
+    if skip_dirs is None:
+        return DEFAULT_NOISE_DIR_NAMES
+    return frozenset(name for name in skip_dirs if name)
+
+
 @tool
 def tree(
     path: str = ".",
@@ -111,13 +158,22 @@ def tree(
     max_depth: int = DEFAULT_MAX_DEPTH,
     max_entries: int = DEFAULT_MAX_ENTRIES,
     skip_hidden_dirs: bool = True,
+    skip_dirs: list[str] | None = None,
+    apply_path_denylist: bool = True,
 ) -> str:
     """Show a directory tree under the workspace.
 
     Always skips VCS metadata directories (``.git``, ``.hg``, ``.svn``, …).
+    By default also skips common noise dirs (``node_modules``, ``__pycache__``,
+    ``.venv``, ``dist``, …). Pass ``skip_dirs=[]`` to disable the noise list
+    (VCS still skipped). Pass an explicit list to replace the default noise set.
+
     By default skips other dot-directories (not hidden files). Use
     ``skip_hidden_dirs=false`` to include them.
 
+    ``apply_path_denylist`` (default true) hides entries whose full path matches
+    the agent ``path_denylist`` policy.
+
     ``max_depth`` limits how deep directories are expanded (1 = origin + children).
     ``max_entries`` caps how many entries are listed per directory.
     """
@@ -135,15 +191,18 @@ def tree(
 
     root_label = path.rstrip("/\\") or "."
     lines = [f"{root_label}/"]
+    limits = _TreeLimits(
+        max_depth=max_depth,
+        max_entries=max_entries,
+        skip_hidden_dirs=skip_hidden_dirs,
+        skip_basenames=_resolve_skip_basenames(skip_dirs),
+        apply_path_denylist=apply_path_denylist,
+    )
     _render_tree(
         origin,
         prefix="",
         depth=0,
-        limits=_TreeLimits(
-            max_depth=max_depth,
-            max_entries=max_entries,
-            skip_hidden_dirs=skip_hidden_dirs,
-        ),
+        limits=limits,
         lines=lines,
     )
     return "\n".join(lines)

tests/test_tools/test_tree.py

@@ -83,3 +83,58 @@ def test_tree_invalid_limits(workspace: object) -> None:
     del workspace
     assert "max_depth" in call_sync(tree, ".", max_depth=0)
     assert "max_entries" in call_sync(tree, ".", max_entries=0)
+
+
+def test_tree_default_noise_dirs(workspace: object) -> None:
+    assert isinstance(workspace, Path)
+    (workspace / "src").mkdir()
+    _ = (workspace / "src" / "app.py").write_text("x", encoding="utf-8")
+    (workspace / "node_modules").mkdir()
+    _ = (workspace / "node_modules" / "pkg.js").write_text("x", encoding="utf-8")
+    (workspace / "__pycache__").mkdir()
+    _ = (workspace / "__pycache__" / "x.pyc").write_text("x", encoding="utf-8")
+    out = call_sync(tree, ".")
+    assert "src/" in out
+    assert "app.py" in out
+    assert "node_modules" not in out
+    assert "__pycache__" not in out
+
+
+def test_tree_skip_dirs_empty_shows_noise(workspace: object) -> None:
+    assert isinstance(workspace, Path)
+    (workspace / "node_modules").mkdir()
+    _ = (workspace / "node_modules" / "pkg.js").write_text("x", encoding="utf-8")
+    out = call_sync(tree, ".", skip_dirs=[])
+    assert "node_modules/" in out
+    assert "pkg.js" in out
+
+
+def test_tree_skip_dirs_custom(workspace: object) -> None:
+    assert isinstance(workspace, Path)
+    (workspace / "keep_me").mkdir()
+    _ = (workspace / "keep_me" / "a.txt").write_text("x", encoding="utf-8")
+    (workspace / "drop_me").mkdir()
+    _ = (workspace / "drop_me" / "b.txt").write_text("x", encoding="utf-8")
+    # Custom list replaces default noise set (node_modules not in list → would show if present).
+    out = call_sync(tree, ".", skip_dirs=["drop_me"])
+    assert "keep_me/" in out
+    assert "drop_me" not in out
+
+
+def test_tree_path_denylist_walk(workspace: object) -> None:
+    from plyngent.tools.workspace import set_path_denylist
+
+    assert isinstance(workspace, Path)
+    (workspace / "ok").mkdir()
+    _ = (workspace / "ok" / "a.txt").write_text("x", encoding="utf-8")
+    (workspace / "secrets").mkdir()
+    _ = (workspace / "secrets" / "key.txt").write_text("x", encoding="utf-8")
+    set_path_denylist(["/secrets"])
+    try:
+        out = call_sync(tree, ".")
+        assert "ok/" in out
+        assert "secrets" not in out
+        out2 = call_sync(tree, ".", apply_path_denylist=False, skip_dirs=[])
+        assert "secrets/" in out2
+    finally:
+        set_path_denylist(None)