Files
lerobot-clone/tests/processor/test_render_messages_processor.py

61 lines
2.1 KiB
Python
Raw Normal View History

2026-04-27 10:56:32 +02:00
#!/usr/bin/env python
import pytest
2026-04-27 10:56:32 +02:00
pytest.importorskip("datasets", reason="datasets is required (install lerobot[dataset])")
import torch # noqa: E402
from lerobot.configs.recipe import MessageTurn, TrainingRecipe # noqa: E402
from lerobot.processor.converters import create_transition # noqa: E402
from lerobot.processor.render_messages_processor import RenderMessagesStep # noqa: E402
from lerobot.types import TransitionKey # noqa: E402
2026-04-27 10:56:32 +02:00
def test_render_messages_step_noops_without_language_columns():
recipe = TrainingRecipe(
messages=[
MessageTurn(role="user", content="${task}", stream="high_level"),
MessageTurn(role="assistant", content="${subtask}", stream="low_level", target=True),
]
)
transition = create_transition(complementary_data={"task": "do it"})
assert RenderMessagesStep(recipe)(transition) == transition
def test_render_messages_step_renders_and_drops_raw_language():
recipe = TrainingRecipe(
messages=[
MessageTurn(role="user", content="${task}", stream="high_level"),
MessageTurn(role="assistant", content="${subtask}", stream="low_level", target=True),
]
)
transition = create_transition(
complementary_data={
"task": "do it",
"timestamp": torch.tensor(0.0),
"index": torch.tensor(7),
"language_persistent": [
{
"role": "assistant",
"content": "reach carefully",
"style": "subtask",
"timestamp": 0.0,
feat(language): per-camera tagging on view-dependent styles Adds a nullable `camera` field to the language row struct (both persistent and event variants) so view-dependent styles like `vqa` can carry which `observation.images.*` view they were grounded against. Without this, multi-camera datasets ended up with multiple `(vqa, role)` rows at the same timestamp that the resolver could not disambiguate. - `language.py`: add `camera` to PERSISTENT_ROW_FIELDS / EVENT_ROW_FIELDS, to both Arrow struct types and the HF datasets feature mappings; introduce VIEW_DEPENDENT_STYLES = {vqa, motion, trace} plus `is_view_dependent_style` and `validate_camera_field` helpers (camera required iff style is view-dependent). - `language_render.py`: thread an optional `camera=` kwarg through every resolver (`active_at`, `emitted_at`, `nth_prev`, `nth_next`) and through `_matching_rows` / `_select_*`, so recipes can disambiguate per-camera VQA with `emitted_at(t, style=vqa, role=assistant, camera=...)`. Without a `camera` filter, multi-row matches keep raising the existing ambiguity error — which is the desired behaviour on multi-camera data. - `recipes/pi05_hirobot.yaml`: replace the single `ask_vqa` branch with `ask_vqa_top` and `ask_vqa_wrist` per-camera sub-recipes (each carrying the matching image block), keeping the original 0.20 budget and documenting the customization point for datasets with different cameras. - Tests: schema test asserts the new field order; new tests cover `is_view_dependent_style`, `validate_camera_field` (both required and forbidden directions), per-camera `emitted_at` filtering, and the ambiguity error when two cameras emit `(vqa, assistant)` at the same timestamp without a `camera=` filter. RenderMessagesStep + dataset passthrough fixtures updated to include the new field. - `docs/source/language_and_recipes.mdx`: document the `camera` field, the per-camera resolver pattern, and the canonical recipe convention. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-30 10:48:17 +02:00
"camera": None,
2026-04-27 10:56:32 +02:00
"tool_calls": None,
}
],
"language_events": [],
}
)
out = RenderMessagesStep(recipe)(transition)
data = out[TransitionKey.COMPLEMENTARY_DATA]
assert "language_persistent" not in data
assert "language_events" not in data
assert data["messages"][-1]["content"] == "reach carefully"
assert data["message_streams"] == ["high_level", "low_level"]
assert data["target_message_indices"] == [1]