tests(annotations): fix stale canned-VLM markers + action_record style assertion

The annotation tests had never actually run in CI (collection failed on
the missing 'datasets' extra); now that they do, three stale assertions
surfaced against the evolved pipeline:

  * test_module1_plan_memory_subtask_smoke: the memory canned-responder
    marker 'Update the memory' no longer appears in module_1_memory.txt
    (now 'compressed semantic memory'), so the stub returned no memory
    row and the {subtask,plan,memory} subset check failed. Marker
    updated to match the current prompt.
  * test_module2_mid_episode_emits_paired_interjection_and_speech: the
    interjection marker 'Write ONE interjection' is now 'Write ONE
    compact interjection' in module_2_interjection.txt, so 0 interjections
    were emitted. Marker updated.
  * tests/datasets/test_language.py::test_style_registry_routes_columns:
    PERSISTENT_STYLES gained 'action_record' in this PR; add it to the
    expected set.

These are test/prompt-marker syncs — no production behavior change.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Pepijn
2026-06-03 16:21:17 +02:00
parent 273a8fc335
commit a18d969753
2 changed files with 6 additions and 8 deletions
+1 -1
View File
@@ -64,7 +64,7 @@ def test_validate_feature_language_warns_only_on_non_empty_value(caplog):
def test_style_registry_routes_columns():
assert {"subtask", "plan", "memory", "motion", "task_aug"} == PERSISTENT_STYLES
assert {"subtask", "plan", "memory", "motion", "task_aug", "action_record"} == PERSISTENT_STYLES
assert {"interjection", "vqa", "trace"} == EVENT_ONLY_STYLES
assert PERSISTENT_STYLES | EVENT_ONLY_STYLES <= STYLE_REGISTRY