fix(runtime): stage symlink-safe copies for LocalDir uploads (#766)

The sandbox SDK's LocalDir walker rejects any symlink outright
(LocalDirReadError, reason=symlink_not_supported), so uploading a cloned
repository that commits symlinks (common in JS/TS monorepos) aborts before
the agent starts. Stage such trees into a temp copy first: in-tree links
are dereferenced; out-of-tree, dangling, and cyclic links are dropped and
never followed, preserving the walker's path-escape safety. Symlink-free
trees are uploaded as-is.

tests/test_local_dir_staging.py

@@ -0,0 +1,108 @@
+"""Tests for symlink-safe LocalDir staging."""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+from strix.runtime.local_dir_staging import stage_symlink_safe_dir, tree_has_symlink
+
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+
+def _make_repo(tmp_path: Path) -> Path:
+    repo = tmp_path / "repo"
+    (repo / "pkg").mkdir(parents=True)
+    (repo / "pkg" / "mod.py").write_text("x = 1\n")
+    (repo / "README.md").write_text("readme\n")
+    return repo
+
+
+def test_tree_without_symlinks_used_as_is(tmp_path: Path) -> None:
+    repo = _make_repo(tmp_path)
+
+    upload_path, staged = stage_symlink_safe_dir(repo)
+
+    assert staged is None
+    assert upload_path == repo.resolve()
+    assert not tree_has_symlink(repo)
+
+
+def test_in_tree_file_symlink_is_dereferenced(tmp_path: Path) -> None:
+    repo = _make_repo(tmp_path)
+    (repo / "link.py").symlink_to(repo / "pkg" / "mod.py")
+
+    upload_path, staged = stage_symlink_safe_dir(repo)
+
+    assert staged is not None
+    assert upload_path == staged
+    assert not (staged / "link.py").is_symlink()
+    assert (staged / "link.py").read_text() == "x = 1\n"
+    assert (staged / "pkg" / "mod.py").read_text() == "x = 1\n"
+    assert not tree_has_symlink(staged)
+
+
+def test_in_tree_relative_dir_symlink_is_dereferenced(tmp_path: Path) -> None:
+    repo = _make_repo(tmp_path)
+    (repo / "pkg_alias").symlink_to("pkg")
+
+    _upload, staged = stage_symlink_safe_dir(repo)
+
+    assert staged is not None
+    assert (staged / "pkg_alias" / "mod.py").read_text() == "x = 1\n"
+    assert not tree_has_symlink(staged)
+
+
+def test_out_of_tree_symlink_is_dropped(tmp_path: Path) -> None:
+    repo = _make_repo(tmp_path)
+    outside = tmp_path / "outside.txt"
+    outside.write_text("secret\n")
+    (repo / "escape.txt").symlink_to(outside)
+    (repo / "abs_escape").symlink_to("/etc")
+
+    _upload, staged = stage_symlink_safe_dir(repo)
+
+    assert staged is not None
+    assert not (staged / "escape.txt").exists()
+    assert not (staged / "abs_escape").exists()
+    assert (staged / "README.md").exists()
+
+
+def test_dangling_symlink_is_dropped(tmp_path: Path) -> None:
+    repo = _make_repo(tmp_path)
+    (repo / "dangling").symlink_to(repo / "does-not-exist")
+
+    _upload, staged = stage_symlink_safe_dir(repo)
+
+    assert staged is not None
+    assert not (staged / "dangling").exists()
+    assert not (staged / "dangling").is_symlink()
+
+
+def test_cyclic_symlink_terminates(tmp_path: Path) -> None:
+    repo = _make_repo(tmp_path)
+    (repo / "self").symlink_to(repo)
+    (repo / "pkg" / "up").symlink_to("..")
+
+    _upload, staged = stage_symlink_safe_dir(repo)
+
+    assert staged is not None
+    assert (staged / "README.md").exists()
+    assert not tree_has_symlink(staged)
+
+
+def test_nested_symlinks_inside_linked_dir(tmp_path: Path) -> None:
+    repo = _make_repo(tmp_path)
+    shared = repo / "shared"
+    shared.mkdir()
+    (shared / "conf.json").write_text("{}\n")
+    (shared / "escape").symlink_to("/etc/passwd")
+    (repo / "pkg" / "shared_link").symlink_to(shared)
+
+    _upload, staged = stage_symlink_safe_dir(repo)
+
+    assert staged is not None
+    assert (staged / "pkg" / "shared_link" / "conf.json").read_text() == "{}\n"
+    assert not (staged / "pkg" / "shared_link" / "escape").exists()
+    assert not (staged / "shared" / "escape").exists()

tests/test_session_entries.py

@@ -18,15 +18,18 @@ def _source(subdir: str, path: str, *, mount: bool = False) -> dict[str, Any]:
 
 
 def test_copied_source_becomes_localdir_entry(tmp_path: Path) -> None:
-    entries, bind_mounts = build_session_entries([_source("repo", str(tmp_path))])
+    entries, bind_mounts, staged_dirs = build_session_entries([_source("repo", str(tmp_path))])
 
     assert bind_mounts == []
+    assert staged_dirs == []
     assert isinstance(entries["repo"], LocalDir)
     assert entries["repo"].src == tmp_path.resolve()
 
 
 def test_mounted_source_becomes_bind_mount(tmp_path: Path) -> None:
-    entries, bind_mounts = build_session_entries([_source("repo", str(tmp_path), mount=True)])
+    entries, bind_mounts, _staged = build_session_entries(
+        [_source("repo", str(tmp_path), mount=True)]
+    )
 
     assert entries == {}
     assert bind_mounts == [
@@ -44,7 +47,7 @@ def test_mixed_sources_split_correctly(tmp_path: Path) -> None:
     copied.mkdir()
     mounted.mkdir()
 
-    entries, bind_mounts = build_session_entries(
+    entries, bind_mounts, _staged = build_session_entries(
         [
             _source("copied", str(copied)),
             _source("mounted", str(mounted), mount=True),
@@ -57,7 +60,7 @@ def test_mixed_sources_split_correctly(tmp_path: Path) -> None:
 
 
 def test_incomplete_sources_are_skipped() -> None:
-    entries, bind_mounts = build_session_entries(
+    entries, bind_mounts, staged_dirs = build_session_entries(
         [
             {"source_path": "", "workspace_subdir": "x"},
             {"source_path": "/p", "workspace_subdir": ""},
@@ -65,3 +68,20 @@ def test_incomplete_sources_are_skipped() -> None:
     )
     assert entries == {}
     assert bind_mounts == []
+    assert staged_dirs == []
+
+
+def test_symlink_tree_is_staged(tmp_path: Path) -> None:
+    repo = tmp_path / "repo"
+    repo.mkdir()
+    (repo / "real.txt").write_text("content")
+    (repo / "link.txt").symlink_to(repo / "real.txt")
+
+    entries, _mounts, staged_dirs = build_session_entries([_source("repo", str(repo))])
+
+    assert len(staged_dirs) == 1
+    entry = entries["repo"]
+    assert isinstance(entry, LocalDir)
+    assert entry.src == staged_dirs[0]
+    assert not (staged_dirs[0] / "link.txt").is_symlink()
+    assert (staged_dirs[0] / "link.txt").read_text() == "content"