From 867b58cfb2abaa31c8248cf7a8ee74011c264533 Mon Sep 17 00:00:00 2001
From: Nikodem Bartnik <39432165+NikodemBartnik@users.noreply.github.com>
Date: Wed, 15 Jul 2026 16:32:02 +0200
Subject: [PATCH] generate new readme (#4029)

Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com>
---
 src/lerobot/scripts/lerobot_annotate.py | 30 ++++++++++++-------------
 tests/scripts/test_lerobot_annotate.py  | 16 ++++++++++++-
 2 files changed, 29 insertions(+), 17 deletions(-)

diff --git a/src/lerobot/scripts/lerobot_annotate.py b/src/lerobot/scripts/lerobot_annotate.py
index e95036a6b..579175052 100644
--- a/src/lerobot/scripts/lerobot_annotate.py
+++ b/src/lerobot/scripts/lerobot_annotate.py
@@ -127,6 +127,9 @@ def _push_to_hub(root: Path, cfg: AnnotationPipelineConfig) -> None:
     """
     from huggingface_hub import HfApi  # noqa: PLC0415
 
+    from lerobot.datasets.io_utils import load_info  # noqa: PLC0415
+    from lerobot.datasets.utils import create_lerobot_dataset_card  # noqa: PLC0415
+
     repo_id = cfg.new_repo_id or cfg.repo_id
     commit_message = cfg.push_commit_message or "Add steerable annotations (lerobot-annotate)"
     api = HfApi()
@@ -143,10 +146,17 @@ def _push_to_hub(root: Path, cfg: AnnotationPipelineConfig) -> None:
         repo_id=repo_id,
         repo_type="dataset",
         commit_message=commit_message,
-        ignore_patterns=[".annotate_staging/**", "**/.DS_Store"],
+        # README.md is excluded because when pushing to ``new_repo_id`` the
+        # source card's links (e.g. the visualize badge) would keep pointing
+        # at the source dataset; a fresh card is generated below instead.
+        ignore_patterns=[".annotate_staging/**", "**/.DS_Store", "README.md"],
     )
     print(f"[lerobot-annotate] uploaded to https://huggingface.co/datasets/{repo_id}", flush=True)
 
+    dataset_info = load_info(root)
+    card = create_lerobot_dataset_card(dataset_info=dataset_info, license="apache-2.0", repo_id=repo_id)
+    card.push_to_hub(repo_id=repo_id, repo_type="dataset")
+
     # Tag the upload with the codebase version. ``LeRobotDatasetMetadata``
     # resolves the dataset revision via ``get_safe_version`` which scans
     # for tags like ``v3.0``; without a tag it raises
@@ -155,21 +165,9 @@ def _push_to_hub(root: Path, cfg: AnnotationPipelineConfig) -> None:
     # actually wrote (no accidental drift if the codebase floor moves).
     from lerobot.datasets.dataset_metadata import CODEBASE_VERSION  # noqa: PLC0415
 
-    info_path = root / "meta" / "info.json"
-    version_tag = CODEBASE_VERSION
-    if info_path.exists():
-        try:
-            from lerobot.utils.io_utils import load_json  # noqa: PLC0415
-
-            info = load_json(info_path)
-            ds_version = info.get("codebase_version")
-            if isinstance(ds_version, str) and ds_version.startswith("v"):
-                version_tag = ds_version
-        except Exception as exc:  # noqa: BLE001
-            print(
-                f"[lerobot-annotate] could not read codebase_version from info.json ({exc}); falling back to {version_tag}",
-                flush=True,
-            )
+    version_tag = (
+        dataset_info.codebase_version if dataset_info.codebase_version.startswith("v") else CODEBASE_VERSION
+    )
     revision = getattr(commit_info, "oid", None)
     tag_kwargs = {
         "repo_id": repo_id,
diff --git a/tests/scripts/test_lerobot_annotate.py b/tests/scripts/test_lerobot_annotate.py
index 6405bdc52..03f1ee104 100644
--- a/tests/scripts/test_lerobot_annotate.py
+++ b/tests/scripts/test_lerobot_annotate.py
@@ -30,7 +30,9 @@ def test_push_to_hub_tags_uploaded_dataset_revision(tmp_path, monkeypatch):
 
     root = tmp_path / "dataset"
     (root / "meta").mkdir(parents=True)
-    (root / "meta" / "info.json").write_text(json.dumps({"codebase_version": "v3.0"}))
+    (root / "meta" / "info.json").write_text(
+        json.dumps({"codebase_version": "v3.0", "fps": 30, "features": {}})
+    )
 
     calls = {}
 
@@ -55,6 +57,11 @@ def test_push_to_hub_tags_uploaded_dataset_revision(tmp_path, monkeypatch):
 
     monkeypatch.setattr("huggingface_hub.HfApi", FakeHfApi)
 
+    def fake_card_push(self, **kwargs):
+        calls["card_push"] = {"content": str(self), **kwargs}
+
+    monkeypatch.setattr("huggingface_hub.DatasetCard.push_to_hub", fake_card_push)
+
     cfg = SimpleNamespace(
         repo_id="source/dataset",
         new_repo_id="annotated/dataset",
@@ -71,6 +78,13 @@ def test_push_to_hub_tags_uploaded_dataset_revision(tmp_path, monkeypatch):
         "exist_ok": True,
     }
     assert calls["upload_folder"]["repo_id"] == "annotated/dataset"
+    # The source README must not be copied over: its links (e.g. the
+    # visualize badge) point at the source dataset. A card regenerated for
+    # the target repo is pushed instead.
+    assert "README.md" in calls["upload_folder"]["ignore_patterns"]
+    assert calls["card_push"]["repo_id"] == "annotated/dataset"
+    assert "visualize_dataset?path=annotated/dataset" in calls["card_push"]["content"]
+    assert "source/dataset" not in calls["card_push"]["content"]
     # A stale tag (e.g. from a previous annotation run) is deleted first so
     # the new tag always points at the upload we just made.
     assert calls["delete_tag"] == {