fix: pre-commit auto-fix (prettier markdown table formatting)

The DAgger phase transitions run blocking smooth handovers: on pause the
leader is driven to the follower (~2 s), and on correction start the
follower is slid to the teleop pose (~1 s), both inside the record loop.

For clutch-style teleoperators (e.g. VR controllers) that re-reference
their command frame at the current robot pose on engage, the handover is
already continuous — the interpolation only delays the start of the
correction and eats its first frames.

Add --strategy.smooth_handover (default true, existing behavior
unchanged) to let such setups skip it, mirroring the episodic strategy's
smooth_leader_to_follower_handover flag.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

docs/source/inference.mdx

@@ -149,13 +149,14 @@ lerobot-rollout \
 
 Foot pedal input is also supported via `--strategy.input_device=pedal`. Configure pedal codes with `--strategy.pedal.*` flags.
 
-| Flag                                 | Description                                             |
-| ------------------------------------ | ------------------------------------------------------- |
-| `--strategy.num_episodes`            | Number of correction episodes to record (default: 10)   |
-| `--strategy.record_autonomous`       | Record autonomous frames too (default: false)           |
-| `--strategy.upload_every_n_episodes` | Push to Hub every N episodes (default: 5)               |
-| `--strategy.input_device`            | Input device: `keyboard` or `pedal` (default: keyboard) |
-| `--teleop.type`                      | **Required.** Teleoperator type                         |
+| Flag                                 | Description                                                                                                                                                    |
+| ------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `--strategy.num_episodes`            | Number of correction episodes to record (default: 10)                                                                                                          |
+| `--strategy.record_autonomous`       | Record autonomous frames too (default: false)                                                                                                                  |
+| `--strategy.upload_every_n_episodes` | Push to Hub every N episodes (default: 5)                                                                                                                      |
+| `--strategy.input_device`            | Input device: `keyboard` or `pedal` (default: keyboard)                                                                                                        |
+| `--strategy.smooth_handover`         | Smoothly hand control over at pause / correction start (default: true). Disable for clutch-style teleops that re-reference at the current robot pose on engage |
+| `--teleop.type`                      | **Required.** Teleoperator type                                                                                                                                |
 
 ### Episodic (`--strategy.type=episodic`)
 

docs/source/using_dataset_tools.mdx

@@ -252,6 +252,10 @@ lerobot-dataset-viz \
     --episode-index 0
 ```
 
+For a private or gated dataset, authenticate first with `hf auth login`, or set the
+`HF_TOKEN` environment variable. The Hub client then discovers the credential
+automatically; no token argument is needed.
+
 **From a local folder:**
 Add the `--root` option and set `--mode local`. For example, to search in `./my_local_data_dir/lerobot/pusht`:
 

src/lerobot/cameras/reachy2_camera/reachy2_camera.py

@@ -173,7 +173,8 @@ class Reachy2Camera(Camera):
             raise ValueError(
                 f"Invalid color mode '{self.color_mode}'. Expected {ColorMode.RGB} or {ColorMode.BGR}."
             )
-        if self.color_mode == ColorMode.RGB:
+        is_depth_frame = self.config.name == "depth" and self.config.image_type == "depth"
+        if not is_depth_frame and self.color_mode == ColorMode.RGB:
             frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
 
         self.latest_frame = frame

src/lerobot/cameras/realsense/camera_realsense.py

@@ -453,7 +453,7 @@ class RealSenseCamera(Camera):
             )
 
         processed_image = image
-        if self.color_mode == ColorMode.BGR:
+        if not depth_frame and self.color_mode == ColorMode.BGR:
             processed_image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
 
         if self.rotation in [cv2.ROTATE_90_CLOCKWISE, cv2.ROTATE_90_COUNTERCLOCKWISE, cv2.ROTATE_180]:

src/lerobot/datasets/dataset_metadata.py

@@ -73,6 +73,8 @@ class LeRobotDatasetMetadata:
         revision: str | None = None,
         force_cache_sync: bool = False,
         metadata_buffer_size: int = 10,
+        *,
+        token: str | bool | None = None,
     ):
         """Load or download metadata for an existing LeRobot dataset.
 
@@ -94,6 +96,10 @@ class LeRobotDatasetMetadata:
                 even when local files exist.
             metadata_buffer_size: Number of episode metadata records to buffer
                 in memory before flushing to parquet.
+            token: Authentication token used for Hub requests. Pass a string
+                token, ``True`` to require the locally stored token, ``False``
+                to disable authentication, or ``None`` to use the Hugging Face
+                Hub default.
         """
         self.repo_id = repo_id
         self.revision = revision if revision else CODEBASE_VERSION
@@ -113,9 +119,12 @@ class LeRobotDatasetMetadata:
             self._load_metadata()
         except (FileNotFoundError, NotADirectoryError):
             if is_valid_version(self.revision):
-                self.revision = get_safe_version(self.repo_id, self.revision)
+                if token is None:
+                    self.revision = get_safe_version(self.repo_id, self.revision)
+                else:
+                    self.revision = get_safe_version(self.repo_id, self.revision, token=token)
 
-            self._pull_from_repo(allow_patterns="meta/")
+            self._pull_from_repo(allow_patterns="meta/", token=token)
             self._load_metadata()
 
     def _flush_metadata_buffer(self) -> None:
@@ -220,7 +229,10 @@ class LeRobotDatasetMetadata:
         self,
         allow_patterns: list[str] | str | None = None,
         ignore_patterns: list[str] | str | None = None,
+        *,
+        token: str | bool | None = None,
     ) -> None:
+        token_kwargs = {} if token is None else {"token": token}
         if self._requested_root is None:
             self.root = Path(
                 snapshot_download(
@@ -230,6 +242,7 @@ class LeRobotDatasetMetadata:
                     cache_dir=HF_LEROBOT_HUB_CACHE,
                     allow_patterns=allow_patterns,
                     ignore_patterns=ignore_patterns,
+                    **token_kwargs,
                 )
             )
             return
@@ -242,6 +255,7 @@ class LeRobotDatasetMetadata:
             local_dir=self._requested_root,
             allow_patterns=allow_patterns,
             ignore_patterns=ignore_patterns,
+            **token_kwargs,
         )
         self.root = self._requested_root
 

src/lerobot/datasets/lerobot_dataset.py

@@ -65,6 +65,8 @@ class LeRobotDataset(torch.utils.data.Dataset):
         encoder_threads: int | None = None,
         streaming_encoding: bool = False,
         encoder_queue_maxsize: int = 30,
+        *,
+        token: str | bool | None = None,
     ):
         """
         2 modes are available for instantiating this class, depending on 2 different use cases:
@@ -197,6 +199,11 @@ class LeRobotDataset(torch.utils.data.Dataset):
                 instead of writing PNG images first. This makes save_episode() near-instant. Defaults to False.
             encoder_queue_maxsize (int, optional): Maximum number of frames to buffer per camera when using
                 streaming encoding. Defaults to 30 (~1s at 30fps).
+            token: Authentication token used while downloading this dataset
+                from the Hub. Pass a string token, ``True`` to require the
+                locally stored token, ``False`` to disable authentication, or
+                ``None`` to use the Hugging Face Hub default. The token is not
+                retained on the dataset instance after initialization.
 
         Note:
             Write-mode parameters (``streaming_encoding``, ``batch_encoding_size``) passed to
@@ -220,7 +227,11 @@ class LeRobotDataset(torch.utils.data.Dataset):
 
         # Load metadata (sets self.root once from the resolved metadata root)
         self.meta = LeRobotDatasetMetadata(
-            self.repo_id, self._requested_root, self.revision, force_cache_sync=force_cache_sync
+            self.repo_id,
+            self._requested_root,
+            self.revision,
+            force_cache_sync=force_cache_sync,
+            token=token,
         )
         self.root = self.meta.root
         self.revision = self.meta.revision
@@ -260,8 +271,11 @@ class LeRobotDataset(torch.utils.data.Dataset):
         # Load actual data
         if force_cache_sync or not self.reader.try_load():
             if is_valid_version(self.revision):
-                self.revision = get_safe_version(self.repo_id, self.revision)
-            self._download(download_videos)
+                if token is None:
+                    self.revision = get_safe_version(self.repo_id, self.revision)
+                else:
+                    self.revision = get_safe_version(self.repo_id, self.revision, token=token)
+            self._download(download_videos, token=token)
             self.reader.load_and_activate()
 
         # Detect write-mode params for backward compatibility
@@ -626,10 +640,11 @@ class LeRobotDataset(torch.utils.data.Dataset):
                 hub_api.delete_tag(self.repo_id, tag=CODEBASE_VERSION, repo_type="dataset")
             hub_api.create_tag(self.repo_id, tag=CODEBASE_VERSION, revision=branch, repo_type="dataset")
 
-    def _download(self, download_videos: bool = True) -> None:
+    def _download(self, download_videos: bool = True, *, token: str | bool | None = None) -> None:
         """Downloads the dataset from the given 'repo_id' at the provided version."""
         ignore_patterns = None if download_videos else "videos/"
         files = None
+        token_kwargs = {} if token is None else {"token": token}
         if self.episodes is not None:
             # Reader is guaranteed to exist here (created in __init__ before _download)
             files = self.reader.get_episodes_file_paths()
@@ -643,6 +658,7 @@ class LeRobotDataset(torch.utils.data.Dataset):
                     cache_dir=HF_LEROBOT_HUB_CACHE,
                     allow_patterns=files,
                     ignore_patterns=ignore_patterns,
+                    **token_kwargs,
                 )
             )
         else:
@@ -654,6 +670,7 @@ class LeRobotDataset(torch.utils.data.Dataset):
                 local_dir=self._requested_root,
                 allow_patterns=files,
                 ignore_patterns=ignore_patterns,
+                **token_kwargs,
             )
             self.meta.root = self._requested_root
 
@@ -793,6 +810,8 @@ class LeRobotDataset(torch.utils.data.Dataset):
         image_writer_threads: int = 0,
         streaming_encoding: bool = False,
         encoder_queue_maxsize: int = 30,
+        *,
+        token: str | bool | None = None,
     ) -> "LeRobotDataset":
         """Resume recording on an existing dataset.
 
@@ -826,6 +845,8 @@ class LeRobotDataset(torch.utils.data.Dataset):
             streaming_encoding: If ``True``, encode video in real-time during
                 capture.
             encoder_queue_maxsize: Max buffered frames per camera for streaming.
+            token: Authentication token used if metadata must be downloaded
+                from the Hub. The token is not retained on the dataset instance.
 
         Returns:
             A :class:`LeRobotDataset` in write mode, ready to append episodes.
@@ -854,7 +875,11 @@ class LeRobotDataset(torch.utils.data.Dataset):
 
         # Load metadata (revision-safe when root is not provided)
         obj.meta = LeRobotDatasetMetadata(
-            obj.repo_id, obj._requested_root, obj.revision, force_cache_sync=force_cache_sync
+            obj.repo_id,
+            obj._requested_root,
+            obj.revision,
+            force_cache_sync=force_cache_sync,
+            token=token,
         )
 
         obj._encoder_threads = encoder_threads

src/lerobot/datasets/multi_dataset.py

@@ -48,6 +48,8 @@ class MultiLeRobotDataset(torch.utils.data.Dataset):
         tolerances_s: dict | None = None,
         download_videos: bool = True,
         video_backend: str | None = None,
+        *,
+        token: str | bool | None = None,
     ):
         super().__init__()
         self.repo_ids = repo_ids
@@ -65,6 +67,7 @@ class MultiLeRobotDataset(torch.utils.data.Dataset):
                 tolerance_s=self.tolerances_s[repo_id],
                 download_videos=download_videos,
                 video_backend=video_backend,
+                token=token,
             )
             for repo_id in repo_ids
         ]

src/lerobot/datasets/streaming_dataset.py

@@ -256,6 +256,8 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
         shuffle: bool = True,
         return_uint8: bool = False,
         depth_output_unit: str = DEFAULT_DEPTH_UNIT,
+        *,
+        token: str | bool | None = None,
     ):
         """Initialize a StreamingLeRobotDataset.
 
@@ -278,6 +280,11 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
             shuffle (bool, optional): Whether to shuffle the dataset across exhaustions. Defaults to True.
             depth_output_unit (str, optional): Physical unit depth maps are dequantized to ("m" or "mm").
                 Defaults to "mm".
+            token: Authentication token used while streaming this dataset from
+                the Hub. Pass a string token, ``True`` to require the locally
+                stored token, ``False`` to disable authentication, or ``None``
+                to use the Hugging Face Hub default. The token is not retained
+                on the dataset instance after initialization.
         """
         super().__init__()
         self.repo_id = repo_id
@@ -306,7 +313,11 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
 
         # Load metadata
         self.meta = LeRobotDatasetMetadata(
-            self.repo_id, self._requested_root, self.revision, force_cache_sync=force_cache_sync
+            self.repo_id,
+            self._requested_root,
+            self.revision,
+            force_cache_sync=force_cache_sync,
+            token=token,
         )
         self.root = self.meta.root
         self.revision = self.meta.revision
@@ -334,12 +345,14 @@ class StreamingLeRobotDataset(torch.utils.data.IterableDataset):
             self.delta_timestamps = delta_timestamps
             self.delta_indices = get_delta_indices(self.delta_timestamps, self.fps)
 
+        token_kwargs = {} if token is None or self.streaming_from_local else {"token": token}
         self.hf_dataset: datasets.IterableDataset = load_dataset(
             self.repo_id if not self.streaming_from_local else str(self.root),
             split="train",
             streaming=self.streaming,
             data_files="data/*/*.parquet",
             revision=self.revision,
+            **token_kwargs,
         )
 
         self.num_shards = min(self.hf_dataset.num_shards, max_num_shards)

src/lerobot/datasets/utils.py

@@ -325,16 +325,19 @@ def check_version_compatibility(
         logging.warning(FUTURE_MESSAGE.format(repo_id=repo_id, version=v_check))
 
 
-def get_repo_versions(repo_id: str) -> list[packaging.version.Version]:
+def get_repo_versions(repo_id: str, *, token: str | bool | None = None) -> list[packaging.version.Version]:
     """Return available valid versions (branches and tags) on a given Hub repo.
 
     Args:
         repo_id (str): The repository ID on the Hugging Face Hub.
+        token: Authentication token used for Hub requests. Pass a string token,
+            ``True`` to require the locally stored token, ``False`` to disable
+            authentication, or ``None`` to use the Hugging Face Hub default.
 
     Returns:
         list[packaging.version.Version]: A list of valid versions found.
     """
-    api = HfApi()
+    api = HfApi() if token is None else HfApi(token=token)
     repo_refs = api.list_repo_refs(repo_id, repo_type="dataset")
     repo_refs = [b.name for b in repo_refs.branches + repo_refs.tags]
     repo_versions = []
@@ -345,7 +348,12 @@ def get_repo_versions(repo_id: str) -> list[packaging.version.Version]:
     return repo_versions
 
 
-def get_safe_version(repo_id: str, version: str | packaging.version.Version) -> str:
+def get_safe_version(
+    repo_id: str,
+    version: str | packaging.version.Version,
+    *,
+    token: str | bool | None = None,
+) -> str:
     """Return the specified version if available on repo, or the latest compatible one.
 
     If the exact version is not found, it looks for the latest version with the
@@ -354,6 +362,7 @@ def get_safe_version(repo_id: str, version: str | packaging.version.Version) ->
     Args:
         repo_id (str): The repository ID on the Hugging Face Hub.
         version (str | packaging.version.Version): The target version.
+        token: Authentication token forwarded to the Hub version lookup.
 
     Returns:
         str: The safe version string (e.g., "v1.2.3") to use as a revision.
@@ -366,7 +375,7 @@ def get_safe_version(repo_id: str, version: str | packaging.version.Version) ->
     target_version = (
         packaging.version.parse(version) if not isinstance(version, packaging.version.Version) else version
     )
-    hub_versions = get_repo_versions(repo_id)
+    hub_versions = get_repo_versions(repo_id) if token is None else get_repo_versions(repo_id, token=token)
 
     if not hub_versions:
         raise RevisionNotFoundError(

src/lerobot/rollout/configs.py

@@ -180,6 +180,14 @@ class DAggerStrategyConfig(RolloutStrategyConfig):
     # Target video file size in MB for episode rotation (record_autonomous
     # mode only).  Defaults to DEFAULT_VIDEO_FILE_SIZE_IN_MB when None.
     target_video_file_size_mb: int | None = None
+    # Whether to turn on or off the smooth handover behavior at phase transitions:
+    # the leader is driven to the follower position on pause (teleops with
+    # `send_feedback` capability), and the follower is slid to the teleop pose when
+    # a correction starts (non-actuated teleops). Disable for clutch-style
+    # teleoperators (e.g. VR controllers) that re-reference at the current robot
+    # pose on engage: the handover is already continuous there, and the blocking
+    # interpolation only delays the start of the correction.
+    smooth_handover: bool = True
     input_device: str = "keyboard"
     keyboard: DAggerKeyboardConfig = field(default_factory=DAggerKeyboardConfig)
     pedal: DAggerPedalConfig = field(default_factory=DAggerPedalConfig)

src/lerobot/rollout/strategies/dagger.py

@@ -623,8 +623,8 @@ class DAggerStrategy(RolloutStrategy):
     # State-machine transition side-effects
     # ------------------------------------------------------------------
 
-    @staticmethod
     def _apply_transition(
+        self,
         old_phase: DAggerPhase,
         new_phase: DAggerPhase,
         engine,
@@ -634,6 +634,10 @@ class DAggerStrategy(RolloutStrategy):
     ) -> None:
         """Execute side-effects for a validated phase transition, including smooth handovers.
 
+        The smooth handovers below can be disabled with
+        ``--strategy.smooth_handover=false`` (useful for clutch-style teleops
+        that re-reference at the current robot pose on engage).
+
         AUTONOMOUS -> PAUSED (actuated teleop):
             Pause the engine, then drive the leader arm to the follower's last
             commanded position so the operator takes over without a jerk.
@@ -657,7 +661,7 @@ class DAggerStrategy(RolloutStrategy):
             logger.info("Pausing engine - robot holds position")
             engine.pause()
 
-            if teleop_supports_feedback(teleop) and prev_action is not None:
+            if self.config.smooth_handover and teleop_supports_feedback(teleop) and prev_action is not None:
                 # TODO(Maxime): prev_action is in robot action key space (output of robot_action_processor).
                 # send_feedback expects teleop feedback key space. For homogeneous setups (e.g. SO-101
                 # leader + SO-101 follower) the keys are identical so this works. If the processor pipeline
@@ -668,7 +672,11 @@ class DAggerStrategy(RolloutStrategy):
 
         elif old_phase == DAggerPhase.PAUSED and new_phase == DAggerPhase.CORRECTING:
             logger.info("Entering correction mode - human teleop control")
-            if not teleop_supports_feedback(teleop) and prev_action is not None:
+            if (
+                self.config.smooth_handover
+                and not teleop_supports_feedback(teleop)
+                and prev_action is not None
+            ):
                 logger.info("Smooth handover: sliding follower to teleop position")
                 obs = robot.get_observation()
                 teleop_action = teleop.get_action()

tests/cameras/test_opencv.py

@@ -26,7 +26,7 @@ import cv2
 import numpy as np
 import pytest
 
-from lerobot.cameras.configs import Cv2Rotation
+from lerobot.cameras.configs import ColorMode, Cv2Rotation
 from lerobot.cameras.opencv import OpenCVCamera, OpenCVCameraConfig
 from lerobot.utils.errors import DeviceAlreadyConnectedError, DeviceNotConnectedError
 
@@ -132,6 +132,28 @@ def test_read(index_or_path):
         assert isinstance(img, np.ndarray)
 
 
+@pytest.mark.parametrize("index_or_path", TEST_IMAGE_PATHS, ids=TEST_IMAGE_SIZES)
+def test_color_mode_conversion(index_or_path):
+    """RGB and BGR reads of the same frame must differ only by a channel-axis reversal."""
+    rgb_config = OpenCVCameraConfig(index_or_path=index_or_path, color_mode=ColorMode.RGB, warmup_s=0)
+    bgr_config = OpenCVCameraConfig(index_or_path=index_or_path, color_mode=ColorMode.BGR, warmup_s=0)
+    with OpenCVCamera(rgb_config) as rgb_cam:
+        rgb = rgb_cam.read()
+    with OpenCVCamera(bgr_config) as bgr_cam:
+        bgr = bgr_cam.read()
+
+    assert rgb.shape == bgr.shape
+    np.testing.assert_array_equal(rgb, bgr[..., ::-1])
+
+
+def test_postprocess_invalid_color_mode():
+    config = OpenCVCameraConfig(index_or_path=DEFAULT_PNG_FILE_PATH)
+    camera = OpenCVCamera(config)
+    camera.color_mode = "invalid"
+    with pytest.raises(ValueError):
+        camera._postprocess_image(np.zeros((120, 160, 3), dtype=np.uint8))
+
+
 def test_read_before_connect():
     config = OpenCVCameraConfig(index_or_path=DEFAULT_PNG_FILE_PATH)
 

tests/cameras/test_reachy2_camera.py

@@ -22,6 +22,7 @@ import pytest
 
 pytest.importorskip("reachy2_sdk")
 
+from lerobot.cameras.configs import ColorMode
 from lerobot.cameras.reachy2_camera import Reachy2Camera, Reachy2CameraConfig
 from lerobot.utils.errors import DeviceNotConnectedError
 
@@ -33,28 +34,19 @@ PARAMS = [
 ]
 
 
-def _make_cam_manager_mock():
+def _make_cam_manager_mock(color_frame, depth_frame=None):
     c = MagicMock(name="CameraManagerMock")
 
     teleop = MagicMock(name="TeleopCam")
     teleop.width = 640
     teleop.height = 480
-    teleop.get_frame = MagicMock(
-        side_effect=lambda *_, **__: (
-            np.zeros((480, 640, 3), dtype=np.uint8),
-            time.time(),
-        )
-    )
+    teleop.get_frame = MagicMock(side_effect=lambda *_, **__: (color_frame, time.time()))
 
     depth = MagicMock(name="DepthCam")
     depth.width = 640
     depth.height = 480
-    depth.get_frame = MagicMock(
-        side_effect=lambda *_, **__: (
-            np.zeros((480, 640, 3), dtype=np.uint8),
-            time.time(),
-        )
-    )
+    depth.get_frame = MagicMock(side_effect=lambda *_, **__: (color_frame, time.time()))
+    depth.get_depth_frame = MagicMock(side_effect=lambda *_, **__: (depth_frame, time.time()))
 
     c.is_connected.return_value = True
     c.teleop = teleop
@@ -84,12 +76,14 @@ def _make_cam_manager_mock():
     # ids=["teleop-left", "teleop-right", "torso-rgb", "torso-depth"],
     ids=["teleop-left", "teleop-right", "torso-rgb"],
 )
-def camera(request):
+def camera(request, img_array_factory):
     name, image_type = request.param
+    color_frame = img_array_factory(height=480, width=640)
+    depth_frame = img_array_factory(height=480, width=640, channels=1, dtype=np.uint16)[..., 0]
     with (
         patch(
             "lerobot.cameras.reachy2_camera.reachy2_camera.CameraManager",
-            side_effect=lambda *a, **k: _make_cam_manager_mock(),
+            side_effect=lambda *a, **k: _make_cam_manager_mock(color_frame, depth_frame),
         ),
     ):
         config = Reachy2CameraConfig(name=name, image_type=image_type)
@@ -188,6 +182,41 @@ def test_read_latest_too_old(camera):
         _ = camera.read_latest(max_age_ms=0)  # immediately too old
 
 
+def test_color_mode_conversion(img_array_factory):
+    """teleop frames are native BGR: RGB reverses the channel axis, BGR is passed through."""
+    frame = img_array_factory(height=8, width=8)
+
+    outputs = {}
+    for color_mode in (ColorMode.RGB, ColorMode.BGR):
+        with patch(
+            "lerobot.cameras.reachy2_camera.reachy2_camera.CameraManager",
+            side_effect=lambda *a, **k: _make_cam_manager_mock(frame),
+        ):
+            cam = Reachy2Camera(Reachy2CameraConfig(name="teleop", image_type="left", color_mode=color_mode))
+            cam.connect()
+            outputs[color_mode] = cam.read()
+            cam.disconnect()
+
+    np.testing.assert_array_equal(outputs[ColorMode.BGR], frame)
+    np.testing.assert_array_equal(outputs[ColorMode.RGB], frame[..., ::-1])
+
+
+def test_depth_frame_not_color_converted(img_array_factory):
+    """A depth/depth frame must be returned as-is, without BGR<->RGB conversion."""
+    color_frame = img_array_factory(height=8, width=8)
+    depth = img_array_factory(height=8, width=8, channels=1, dtype=np.uint16)[..., 0]
+    with patch(
+        "lerobot.cameras.reachy2_camera.reachy2_camera.CameraManager",
+        side_effect=lambda *a, **k: _make_cam_manager_mock(color_frame, depth_frame=depth),
+    ):
+        cam = Reachy2Camera(Reachy2CameraConfig(name="depth", image_type="depth"))
+        cam.connect()
+        out = cam.read()
+        cam.disconnect()
+
+    np.testing.assert_array_equal(out, depth)
+
+
 def test_wrong_camera_name():
     with pytest.raises(ValueError):
         _ = Reachy2CameraConfig(name="wrong-name", image_type="left")

tests/cameras/test_realsense.py

@@ -25,7 +25,7 @@ from unittest.mock import patch
 import numpy as np
 import pytest
 
-from lerobot.cameras.configs import Cv2Rotation
+from lerobot.cameras.configs import ColorMode, Cv2Rotation
 from lerobot.utils.errors import DeviceAlreadyConnectedError, DeviceNotConnectedError
 
 pytest.importorskip("pyrealsense2")
@@ -109,6 +109,32 @@ def test_read_depth():
     assert isinstance(img, np.ndarray)
 
 
+# These exercise _postprocess_image directly rather than read(): the bag playback returns
+# non-deterministic frames we can't compare against, and the depth read() path is skipped
+# (see test_read_depth) with the current pyrealsense2 version.
+def test_color_mode_conversion(img_array_factory):
+    """RGB (native for RealSense) is passed through; BGR reverses the channel axis."""
+    color = img_array_factory(height=3, width=4)
+
+    outputs = {}
+    for color_mode in (ColorMode.RGB, ColorMode.BGR):
+        camera = RealSenseCamera(RealSenseCameraConfig(serial_number_or_name="042", color_mode=color_mode))
+        camera.capture_height, camera.capture_width = color.shape[:2]
+        outputs[color_mode] = camera._postprocess_image(color)
+
+    np.testing.assert_array_equal(outputs[ColorMode.RGB], color)
+    np.testing.assert_array_equal(outputs[ColorMode.BGR], color[..., ::-1])
+
+
+def test_depth_frame_not_color_converted(img_array_factory):
+    """Depth frames must bypass color conversion, even when a BGR color_mode is set."""
+    camera = RealSenseCamera(RealSenseCameraConfig(serial_number_or_name="042", color_mode=ColorMode.BGR))
+    depth = img_array_factory(height=3, width=4, channels=1, dtype=np.uint16)[..., 0]
+    camera.capture_height, camera.capture_width = depth.shape
+
+    np.testing.assert_array_equal(camera._postprocess_image(depth, depth_frame=True), depth)
+
+
 def test_read_before_connect():
     config = RealSenseCameraConfig(serial_number_or_name="042")
     camera = RealSenseCamera(config)

tests/datasets/test_dataset_utils.py

@@ -14,16 +14,21 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+from types import SimpleNamespace
+from unittest.mock import Mock
+
 import pytest
 import torch
+from packaging.version import Version
 
 pytest.importorskip("datasets", reason="datasets is required (install lerobot[dataset])")
 
 from datasets import Dataset  # noqa: E402
 from huggingface_hub import DatasetCard
 
+import lerobot.datasets.utils as dataset_utils
 from lerobot.datasets.io_utils import hf_transform_to_torch
-from lerobot.datasets.utils import create_lerobot_dataset_card
+from lerobot.datasets.utils import create_lerobot_dataset_card, get_repo_versions, get_safe_version
 from lerobot.utils.constants import ACTION, OBS_IMAGES
 from lerobot.utils.feature_utils import combine_feature_dicts
 
@@ -57,6 +62,30 @@ def test_default_parameters():
     ]
 
 
+@pytest.mark.parametrize("token", ["hf_test_token", True, False])
+def test_get_repo_versions_forwards_token(monkeypatch, token):
+    api = Mock()
+    api.list_repo_refs.return_value = SimpleNamespace(
+        branches=[SimpleNamespace(name="v3.0")],
+        tags=[],
+    )
+    hf_api = Mock(return_value=api)
+    monkeypatch.setattr(dataset_utils, "HfApi", hf_api)
+
+    assert get_repo_versions("private/repo", token=token) == [Version("3.0")]
+    hf_api.assert_called_once_with(token=token)
+    api.list_repo_refs.assert_called_once_with("private/repo", repo_type="dataset")
+
+
+@pytest.mark.parametrize("token", ["hf_test_token", True, False])
+def test_get_safe_version_forwards_token(monkeypatch, token):
+    get_versions = Mock(return_value=[Version("3.0")])
+    monkeypatch.setattr(dataset_utils, "get_repo_versions", get_versions)
+
+    assert get_safe_version("private/repo", "v3.0", token=token) == "v3.0"
+    get_versions.assert_called_once_with("private/repo", token=token)
+
+
 def test_with_tags():
     tags = ["tag1", "tag2"]
     card = create_lerobot_dataset_card(tags=tags)

tests/datasets/test_lerobot_dataset.py

@@ -20,6 +20,7 @@ property delegation, and the full create-record-finalize-read lifecycle.
 """
 
 from pathlib import Path
+from types import SimpleNamespace
 from unittest.mock import Mock
 
 import pytest
@@ -191,6 +192,48 @@ def test_metadata_without_root_uses_hub_cache_snapshot_download(
     }
 
 
+@pytest.mark.parametrize("token", ["hf_test_token", True, False])
+def test_metadata_download_forwards_token(tmp_path, monkeypatch, token):
+    snapshot_root = tmp_path / "snapshot"
+    snapshot_download = Mock(return_value=str(snapshot_root))
+    get_safe_version = Mock(return_value="v3.0")
+    load_metadata = Mock(side_effect=[FileNotFoundError, None])
+    monkeypatch.setattr(dataset_metadata_module, "snapshot_download", snapshot_download)
+    monkeypatch.setattr(dataset_metadata_module, "get_safe_version", get_safe_version)
+    monkeypatch.setattr(LeRobotDatasetMetadata, "_load_metadata", load_metadata)
+
+    meta = LeRobotDatasetMetadata(
+        repo_id=DUMMY_REPO_ID,
+        revision="v3.0",
+        token=token,
+    )
+
+    assert meta.root == snapshot_root
+    assert not hasattr(meta, "_token")
+    get_safe_version.assert_called_once_with(DUMMY_REPO_ID, "v3.0", token=token)
+    assert snapshot_download.call_args.kwargs["token"] is token
+
+
+@pytest.mark.parametrize("token", ["hf_test_token", True, False])
+def test_data_download_forwards_token(tmp_path, monkeypatch, token):
+    snapshot_root = tmp_path / "snapshot"
+    snapshot_download = Mock(return_value=str(snapshot_root))
+    monkeypatch.setattr(lerobot_dataset_module, "snapshot_download", snapshot_download)
+
+    dataset = LeRobotDataset.__new__(LeRobotDataset)
+    dataset.repo_id = DUMMY_REPO_ID
+    dataset.revision = "main"
+    dataset.episodes = None
+    dataset._requested_root = None
+    dataset.meta = SimpleNamespace(root=None)
+    dataset.reader = SimpleNamespace(root=None)
+
+    dataset._download(token=token)
+
+    assert dataset.root == snapshot_root
+    assert snapshot_download.call_args.kwargs["token"] is token
+
+
 def test_without_root_reads_different_revisions_from_distinct_snapshot_roots(
     tmp_path,
     info_factory,

tests/datasets/test_streaming.py

@@ -13,12 +13,16 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+from types import SimpleNamespace
+from unittest.mock import Mock
+
 import numpy as np
 import pytest
 import torch
 
 pytest.importorskip("datasets", reason="datasets is required (install lerobot[dataset])")
 
+import lerobot.datasets.streaming_dataset as streaming_dataset_module
 from lerobot.datasets.streaming_dataset import StreamingLeRobotDataset
 from lerobot.datasets.utils import safe_shard
 from lerobot.utils.constants import ACTION
@@ -71,6 +75,40 @@ def get_frames_expected_order(streaming_ds: StreamingLeRobotDataset) -> list[int
     return expected_indices
 
 
+@pytest.mark.parametrize("token", ["hf_test_token", True, False])
+@pytest.mark.parametrize("from_local", [False, True])
+def test_streaming_dataset_forwards_hub_token_only_for_remote_data(tmp_path, monkeypatch, token, from_local):
+    requested_root = tmp_path / "local" if from_local else None
+    metadata = SimpleNamespace(
+        root=requested_root or tmp_path / "snapshot",
+        revision=streaming_dataset_module.CODEBASE_VERSION,
+        _version=streaming_dataset_module.CODEBASE_VERSION,
+        features={},
+        depth_keys=[],
+        image_keys=[],
+        rescale_depth_stats=Mock(),
+    )
+    metadata_cls = Mock(return_value=metadata)
+    load_dataset = Mock(return_value=SimpleNamespace(num_shards=1))
+    monkeypatch.setattr(streaming_dataset_module, "LeRobotDatasetMetadata", metadata_cls)
+    monkeypatch.setattr(streaming_dataset_module, "load_dataset", load_dataset)
+
+    dataset = StreamingLeRobotDataset(DUMMY_REPO_ID, root=requested_root, token=token)
+
+    metadata_cls.assert_called_once_with(
+        DUMMY_REPO_ID,
+        requested_root,
+        streaming_dataset_module.CODEBASE_VERSION,
+        force_cache_sync=False,
+        token=token,
+    )
+    if from_local:
+        assert "token" not in load_dataset.call_args.kwargs
+    else:
+        assert load_dataset.call_args.kwargs["token"] is token
+    assert not hasattr(dataset, "_token")
+
+
 def test_single_frame_consistency(tmp_path, lerobot_dataset_factory):
     """Test if are correctly accessed"""
     ds_num_frames = 400