Fix container sync races that leaked orphan blobs; add a system-prune CLI command

sync_workspace (user-triggered) and the reconciler's sync_bidirectional_sync could run concurrently for the same project, and store_upload's read-then- write on a changed path meant two racing imports each wrote their own blob while only one ever got referenced - the loser leaked forever. Combined with no build-artifact exclusion, an actively-compiling workspace hit this constantly and leaked 5.9M orphan blobs (~96GB) in production before it was caught. Closes it at the root: api._sync_dir_bidirectional_locked serializes both call sites per-project (non-blocking - a project already mid-sync is simply skipped until the next tick), and IMPORT_SKIP_NAMES/IMPORT_SKIP_EXTENSIONS keep build output (build/, dist/, *.o, *.pyc, ...) out of the walk entirely. Recovering what already leaked is a separate concern: a new CLI subcommand (plus matching make targets) sweeps soft-deleted attachment/project-file blobs and any blob with zero DB reference at all, plus orphaned container workspace directories. run_maintenance_cleanup.sh wraps the existing prune/clear commands for routine disk upkeep. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01BWJy6PrMMt5hwWxQwia2rd
2026-09-08 03:43:49 +02:00
parent 85bd8fad47
commit 7880bf4b31
19 changed files with 1068 additions and 19 deletions
@@ -570,6 +570,85 @@ def test_bidirectional_sync_manifest_is_pruned_after_both_sides_agree(env, tmp_p
    assert remaining == []


+def test_bidirectional_sync_skips_build_artifact_directories(env, tmp_path):
+    workspace = tmp_path / "sync-build-ws"
+    workspace.mkdir()
+    pid = env["project"]["uid"]
+    user = env["user"]
+    (workspace / "build").mkdir()
+    (workspace / "build" / "output.bin").write_text("junk")
+    (workspace / "dist").mkdir()
+    (workspace / "dist" / "bundle.js").write_text("junk")
+    (workspace / "real.txt").write_text("keep me\n")
+
+    counts = project_files.sync_dir_bidirectional(pid, str(workspace), user)
+
+    assert counts["imported"] == 1
+    assert project_files.get_node(pid, "real.txt") is not None
+    assert project_files.get_node(pid, "build/output.bin") is None
+    assert project_files.get_node(pid, "dist/bundle.js") is None
+
+
+def test_bidirectional_sync_skips_compiled_artifact_extensions(env, tmp_path):
+    workspace = tmp_path / "sync-ext-ws"
+    workspace.mkdir()
+    pid = env["project"]["uid"]
+    user = env["user"]
+    (workspace / "main.o").write_bytes(b"junk")
+    (workspace / "helper.pyc").write_bytes(b"junk")
+    (workspace / "main.c").write_text("int main() { return 0; }\n")
+
+    counts = project_files.sync_dir_bidirectional(pid, str(workspace), user)
+
+    assert counts["imported"] == 1
+    assert project_files.get_node(pid, "main.c") is not None
+    assert project_files.get_node(pid, "main.o") is None
+    assert project_files.get_node(pid, "helper.pyc") is None
+
+
+def test_sync_dir_bidirectional_locked_skips_concurrent_run_for_same_project(
+    env, tmp_path
+):
+    workspace = tmp_path / "sync-lock-ws"
+    workspace.mkdir()
+    pid = env["project"]["uid"]
+    user = env["user"]
+
+    lock = api._sync_lock_for(pid)
+    lock.acquire()
+    try:
+        counts = api._sync_dir_bidirectional_locked(pid, str(workspace), user)
+    finally:
+        lock.release()
+
+    assert counts == {
+        "exported": 0,
+        "imported": 0,
+        "deleted_in_project": 0,
+        "deleted_in_workspace": 0,
+    }
+    assert project_files.get_node(pid, "real.txt") is None
+
+
+def test_sync_dir_bidirectional_locked_runs_when_lock_is_free(env, tmp_path):
+    workspace = tmp_path / "sync-lock-free-ws"
+    workspace.mkdir()
+    pid = env["project"]["uid"]
+    user = env["user"]
+    (workspace / "real.txt").write_text("keep me\n")
+
+    counts = api._sync_dir_bidirectional_locked(pid, str(workspace), user)
+
+    assert counts["imported"] == 1
+    assert project_files.get_node(pid, "real.txt") is not None
+
+
+def test_sync_dir_bidirectional_locked_is_per_project(env, tmp_path):
+    other_pid = "sync-lock-other-project"
+    lock = api._sync_lock_for(other_pid)
+    assert lock is not api._sync_lock_for(env["project"]["uid"])
+
+

 def _proxy_scope(kind: str, headers: dict, scheme: str, query: str = "") -> dict:
    return {
@@ -0,0 +1,76 @@
+# retoor <retoor@molodetz.nl>
+
+import pytest
+
+from devplacepy.database import get_table, init_db
+from devplacepy.services.containers import store
+from devplacepy.utils import generate_uid
+
+
+@pytest.fixture(autouse=True)
+def _init_db_containers_store():
+    init_db()
+    yield
+
+
+def _make_instance(project_uid, deleted_at=None):
+    uid = generate_uid()
+    get_table("instances").insert(
+        {
+            "uid": uid,
+            "project_uid": project_uid,
+            "deleted_at": deleted_at,
+            "deleted_by": None,
+            "name": f"inst-{uid[:8]}",
+            "status": "running",
+            "desired_state": "running",
+        }
+    )
+    return uid
+
+
+def test_gc_workspaces_removes_directories_with_no_live_instance(
+    local_db, tmp_path, monkeypatch
+):
+    monkeypatch.setattr("devplacepy.config.CONTAINER_WORKSPACES_DIR", tmp_path)
+    active_project = "gcws-active-project"
+    orphan_project = "gcws-orphan-project"
+    (tmp_path / active_project).mkdir()
+    (tmp_path / orphan_project).mkdir()
+    _make_instance(active_project)
+
+    removed = store.gc_workspaces()
+
+    assert removed == 1
+    assert (tmp_path / active_project).exists()
+    assert not (tmp_path / orphan_project).exists()
+
+
+def test_gc_workspaces_ignores_soft_deleted_instances(local_db, tmp_path, monkeypatch):
+    monkeypatch.setattr("devplacepy.config.CONTAINER_WORKSPACES_DIR", tmp_path)
+    project = "gcws-soft-deleted-project"
+    (tmp_path / project).mkdir()
+    _make_instance(project, deleted_at="2020-01-01T00:00:00+00:00")
+
+    removed = store.gc_workspaces()
+
+    assert removed == 1
+    assert not (tmp_path / project).exists()
+
+
+def test_gc_workspaces_dry_run_changes_nothing(local_db, tmp_path, monkeypatch):
+    monkeypatch.setattr("devplacepy.config.CONTAINER_WORKSPACES_DIR", tmp_path)
+    orphan_project = "gcws-dry-run-project"
+    (tmp_path / orphan_project).mkdir()
+
+    removed = store.gc_workspaces(dry_run=True)
+
+    assert removed == 1
+    assert (tmp_path / orphan_project).exists()
+
+
+def test_gc_workspaces_missing_base_dir_is_a_noop(local_db, tmp_path, monkeypatch):
+    monkeypatch.setattr(
+        "devplacepy.config.CONTAINER_WORKSPACES_DIR", tmp_path / "does-not-exist"
+    )
+    assert store.gc_workspaces() == 0