Merge branch 'main' into feat/smolvla-on-steerable

tests/annotations/test_modules.py

@@ -85,7 +85,7 @@ def _spy_responder(captured: list[list[dict[str, Any]]], reply: Any):
 def test_module1_plan_memory_subtask_smoke(fixture_dataset_root: Path, tmp_path: Path) -> None:
     vlm = make_canned_responder(
         {
-            "atomic subtasks": {
+            "COMPLETED manipulation events": {
                 "subtasks": [
                     {"text": "grasp the handle of the sponge", "start": 0.0, "end": 0.4},
                     {"text": "wipe the counter from left to right", "start": 0.4, "end": 0.8},
@@ -126,7 +126,7 @@ def test_module1_emit_memory_false_skips_memory_keeps_subtasks_and_plan(
     leaving subtask + plan generation intact — symmetric to ``emit_plan``."""
     vlm = make_canned_responder(
         {
-            "atomic subtasks": {
+            "COMPLETED manipulation events": {
                 "subtasks": [
                     {"text": "grasp the handle of the sponge", "start": 0.0, "end": 0.4},
                     {"text": "wipe the counter from left to right", "start": 0.4, "end": 0.8},
@@ -318,7 +318,7 @@ def test_module1_attaches_contact_sheets_to_subtask_prompt(
                     return block.get("text", "")
         return ""
 
-    subtask_calls = [m for m in captured if "atomic subtasks" in _prompt_text(m)]
+    subtask_calls = [m for m in captured if "COMPLETED manipulation events" in _prompt_text(m)]
     assert len(subtask_calls) == 1, "expected exactly one subtask-prompt VLM call"
     content = subtask_calls[0][0]["content"]
     video_blocks = [b for b in content if isinstance(b, dict) and b.get("type") == "video"]

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"] == {