review: emitted_at uses 0.1s tolerance; MessageTurn requires stream at construction

* **Float tolerance in `emitted_at` for persistent styles.** The
  ``_timestamp(row) == t`` exact-equality check silently missed any
  caller that derived ``t`` arithmetically (e.g. ``frame_idx / fps``)
  even though the parquet timestamp would only differ by ULPs. Added
  ``EMITTED_AT_TOLERANCE_S = 0.1`` and check ``abs(...) <= tolerance``
  instead, with a docstring explaining why exact equality wasn't
  enough and why 0.1 s is safe at typical 30–100 Hz control rates.
  Test asserts the new behavior at half-window (matches) and
  double-window (no match) using the constant so it stays in sync.

* **`MessageTurn.stream` is required at construction.** It was typed
  ``MessageStream | None = None`` so YAML could omit ``stream:`` and
  pass the dataclass invariant — but ``_validate_rendered`` rejected
  ``None`` streams later, surfacing the error at the first sample
  instead of at recipe load. Now ``__post_init__`` raises
  ``ValueError`` if ``stream`` is ``None``, with the list of valid
  streams in the message. The redundant late-stage check in
  ``_validate_rendered`` is replaced with a one-line comment that
  cites the upstream invariant. Test pins the new construction-time
  rejection.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Pepijn
2026-05-06 19:55:08 +02:00
parent beb22afd81
commit e7e5fca5de
4 changed files with 59 additions and 10 deletions
+11
View File
@@ -29,6 +29,17 @@ def test_message_recipe_validates_unknown_binding():
)
def test_message_turn_requires_a_stream():
"""Every turn must declare a stream — None is rejected at construction.
Previously this only failed at render time (``_validate_rendered``);
catching it here means a malformed recipe YAML errors at load instead
of at the first training sample.
"""
with pytest.raises(ValueError, match="missing a stream"):
MessageTurn(role="user", content="${task}")
def test_message_recipe_requires_at_least_one_target():
with pytest.raises(ValueError, match="target"):
TrainingRecipe(
+16
View File
@@ -6,6 +6,7 @@ pytest.importorskip("datasets", reason="datasets is required (install lerobot[da
from lerobot.configs.recipe import MessageTurn, TrainingRecipe # noqa: E402
from lerobot.datasets.language_render import ( # noqa: E402
EMITTED_AT_TOLERANCE_S,
active_at,
emitted_at,
nth_next,
@@ -342,6 +343,21 @@ def test_resolve_task_explicit_override_beats_rephrasings():
assert rendered["messages"][0]["content"] == "explicit override wins"
def test_emitted_at_persistent_tolerates_small_timestamp_drift():
"""Persistent ``emitted_at`` should match within EMITTED_AT_TOLERANCE_S
so callers that derive ``t`` arithmetically (``frame_idx / fps``) still
line up with the parquet-stored timestamp.
"""
rows = [persistent_row("assistant", "memo", "memory", 1.0)]
# Half a tolerance window — bit-different float, comfortably inside
inside = emitted_at(1.0 + EMITTED_AT_TOLERANCE_S / 2, persistent=rows, events=[], style="memory")
assert inside is not None and inside["content"] == "memo"
# Just past the window — no match
outside = emitted_at(1.0 + EMITTED_AT_TOLERANCE_S * 2, persistent=rows, events=[], style="memory")
assert outside is None
def test_render_sample_rejects_non_dict_language_rows():
"""``_normalize_rows`` must surface malformed inputs as TypeError.