Fix bug in dataset root resolution

src/lerobot_robot_ufactory/robots/uf_robot/uf_robot.py

@@ -449,9 +449,9 @@ class UFRobot(Robot, Thread):
         warn_code = getattr(arm, "warn_code", "unknown")
         return f"mode={mode}, state={state}, error_code={error_code}, warn_code={warn_code}"
 
-    def _check_motion_code(self, command: str, code: int) -> None:
-        """Fail loudly when the SDK rejects a joint command."""
-        if code != 0:
+    def _check_motion_code(self, command: str, code: int | None) -> None:
+        """Fail loudly when the SDK explicitly rejects a motion command."""
+        if code is not None and code != 0:
             raise RuntimeError(f"{command} failed, code={code}, {self._motion_status()}")
 
     def send_action(self, action: dict) -> np.ndarray:

src/lerobot_robot_ufactory/scripts/uf_lerobot_record.py

@@ -510,26 +510,40 @@ def _ask_choice(prompt: str, options: dict[str, str]) -> str:
         print(f"Invalid choice, please enter {keys}.")
 
 
+def _missing_dataset_files(root: Path) -> list[str]:
+    """Return the local files required before a dataset can be resumed."""
+    missing = []
+    for relative_path in ("meta/info.json", "meta/tasks.parquet"):
+        if not (root / relative_path).is_file():
+            missing.append(relative_path)
+    if not any((root / "meta" / "episodes").glob("*/*.parquet")):
+        missing.append("meta/episodes/*/*.parquet")
+    if not any((root / "data").glob("*/*.parquet")):
+        missing.append("data/*/*.parquet")
+    return missing
+
+
 def _prepare_dataset_root(cfg: UFRecordConfig) -> None:
-    """Create the dataset root and ask how to handle an existing dataset."""
+    """Prepare an existing dataset root without pre-creating a new one."""
     root = Path(cfg.dataset.root)
     existed = root.exists()
 
-    # Create the dataset root (and any parent directories) first.
-    root.mkdir(parents=True, exist_ok=True)
-
-    if not existed or cfg.resume:
+    if not existed:
+        if cfg.resume:
+            raise RuntimeError(f"Cannot resume because the dataset directory does not exist: {root}")
         return
 
-    if not (root / "meta" / "info.json").is_file():
-        # The directory exists but is not a valid LeRobot dataset.
-        if not sys.stdin.isatty():
-            raise RuntimeError(
-                f"Dataset directory exists but is not a valid LeRobot dataset: {root}\n"
-                "Choose a new dataset.root, or remove this empty/incomplete directory before recording."
+    missing = _missing_dataset_files(root)
+    if missing:
+        missing_text = ", ".join(missing)
+        message = (
+            f"Dataset directory is incomplete and cannot be resumed: {root}\n"
+            f"Missing: {missing_text}"
         )
+        if cfg.resume or not sys.stdin.isatty():
+            raise RuntimeError(message)
         choice = _ask_choice(
-            f"Directory exists but is not a valid LeRobot dataset: {root}",
+            message,
             options={
                 "o": "Overwrite: remove this directory and record a new dataset",
                 "c": "Cancel",
@@ -541,6 +555,9 @@ def _prepare_dataset_root(cfg: UFRecordConfig) -> None:
             raise SystemExit("Recording cancelled.")
         return
 
+    if cfg.resume:
+        return
+
     # A valid LeRobot dataset already exists.
     if not sys.stdin.isatty():
         # Non-interactive run: keep the previous auto-resume behaviour.

start_manual_record.sh

@@ -2,49 +2,7 @@
 
 set -euo pipefail
 
-repo_root="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
-cd "$repo_root"
-
-config_path="config/manual_mode/xarm7_manual_record_config.yaml"
-dataset_root="$(
-  sed -n '/^dataset:/,/^[^[:space:]]/s/^[[:space:]]*root:[[:space:]]*//p' "$config_path" \
-    | head -n 1 \
-    | tr -d "\"'"
-)"
-
-if [[ -z "$dataset_root" ]]; then
-  printf 'Could not read dataset.root from %s\n' "$config_path" >&2
-  exit 1
-fi
-
-if [[ "$dataset_root" != /* ]]; then
-  dataset_root="$repo_root/$dataset_root"
-fi
-
-record_args=("$@")
-resume_requested=false
-for arg in "${record_args[@]}"; do
-  if [[ "$arg" == "-r" ]]; then
-    resume_requested=true
-    break
-  fi
-done
-
-if [[ -e "$dataset_root" ]]; then
-  if [[ ! -f "$dataset_root/meta/info.json" ]]; then
-    printf 'Dataset directory exists but is not a valid LeRobot dataset: %s\n' "$dataset_root" >&2
-    printf 'Choose a new dataset.root, or remove this empty/incomplete directory before recording.\n' >&2
-    exit 1
-  fi
-
-  if [[ "$resume_requested" == false ]]; then
-    record_args=("-r" "${record_args[@]}")
-  fi
-elif [[ "$resume_requested" == true ]]; then
-  printf 'Cannot resume because the dataset directory does not exist: %s\n' "$dataset_root" >&2
-  exit 1
-fi
 
 exec uv run uf-lerobot-record \
-  --config_path "$config_path" \
-  "${record_args[@]}"
+  --config_path config/manual_mode/xarm7_manual_record_config.yaml \
+  "$@"

tests/test_manual_mode.py

@@ -315,6 +315,27 @@ def test_prepare_dataset_root_rejects_incomplete_resume(tmp_path):
         _prepare_dataset_root(cfg)
 
 
+def test_prepare_dataset_root_rejects_resume_when_root_is_missing(tmp_path):
+    cfg = SimpleNamespace(dataset=SimpleNamespace(root=tmp_path / "missing"), resume=True)
+
+    with pytest.raises(RuntimeError, match="does not exist"):
+        _prepare_dataset_root(cfg)
+
+
+def test_prepare_dataset_root_resumes_complete_dataset_without_prompt(tmp_path, monkeypatch):
+    root = tmp_path / "dataset"
+    (root / "meta" / "episodes" / "chunk-000").mkdir(parents=True)
+    (root / "data" / "chunk-000").mkdir(parents=True)
+    (root / "meta" / "info.json").write_text("{}")
+    (root / "meta" / "tasks.parquet").write_bytes(b"tasks")
+    (root / "meta" / "episodes" / "chunk-000" / "file-000.parquet").write_bytes(b"episodes")
+    (root / "data" / "chunk-000" / "file-000.parquet").write_bytes(b"data")
+    cfg = SimpleNamespace(dataset=SimpleNamespace(root=root), resume=True)
+    monkeypatch.setattr(record_module.sys.stdin, "isatty", lambda: True)
+
+    _prepare_dataset_root(cfg)
+
+
 def test_manual_record_loop_writes_actual_state_as_action(tmp_path):
     class FakeRobot:
         name = "fake_manual_robot"