chore(ci): make quality checks pass across repo

- fix ruff violations in dataset, recording, and value modules

- fix typos findings and markdown/workflow lint issues

- update pages workflow checkout to disable credential persistence

- apply pre-commit auto-formatting and EOF normalization

- include requested repo housekeeping updates (.gitignore and README)
这个提交包含在:
Elvin
2026-03-04 11:02:06 +08:00
父节点 8b6a85cf0f
当前提交 c96c678772
共有 26 个文件被更改,包括 143 次插入 和 115 次删除

查看文件

@ -836,7 +836,11 @@ def _copy_and_reindex_episodes_metadata(
for key in schema.names:
if key in {"episode_index", "tasks", "length"}:
continue
if key.startswith("stats/") or key.startswith("__index_level_") or key.startswith("meta/episodes/"):
if (
key.startswith("stats/")
or key.startswith("__index_level_")
or key.startswith("meta/episodes/")
):
continue
if key not in seen_preserved_keys:
seen_preserved_keys.add(key)

查看文件

@ -729,15 +729,14 @@ class LeRobotDataset(torch.utils.data.Dataset):
# Check if cached dataset contains all requested episodes
if not self._check_cached_episodes_sufficient():
raise FileNotFoundError("Cached dataset doesn't contain all requested episodes")
except (AssertionError, FileNotFoundError, NotADirectoryError):
except (AssertionError, FileNotFoundError, NotADirectoryError) as err:
if is_valid_version(self.revision):
self.revision = get_safe_version(self.repo_id, self.revision)
self.download(download_videos)
self.hf_dataset = self.load_hf_dataset()
if not self._check_cached_episodes_sufficient():
missing_videos_hint = (
" Missing video files are required by this dataset. "
"Retry with `download_videos=True`."
" Missing video files are required by this dataset. Retry with `download_videos=True`."
if len(self.meta.video_keys) > 0 and not download_videos
else ""
)
@ -745,7 +744,7 @@ class LeRobotDataset(torch.utils.data.Dataset):
"Cached dataset is incomplete after download. "
"Some requested episodes or files are missing."
f"{missing_videos_hint}"
)
) from err
# Create mapping from absolute indices to relative indices when only a subset of the episodes are loaded
# Build a mapping: absolute_index -> relative_index_in_filtered_dataset