Align pi0.7 minimal structure with paper

tests/test_tokenizer.py

@@ -9,7 +9,6 @@ def metadata() -> EpisodeMetadata:
         quality=5,
         mistake=False,
         control_mode="ee",
-        source_type="autonomous_rollout",
     )
 
 
@@ -21,10 +20,18 @@ def test_prompt_contains_rich_metadata_and_control_tokens() -> None:
     assert tokenizer.SPEED_MARKER in prompt
     assert tokenizer.QUALITY_MARKER in prompt
     assert tokenizer.MISTAKE_MARKER in prompt
-    assert tokenizer.SOURCE_MARKER in prompt
     assert tokenizer.CONTROL_MARKER in prompt
     assert tokenizer.CONTROL_EE in prompt
-    assert len(metadata_indices) == 8
+    assert len(metadata_indices) == 6
+
+
+def test_high_level_prompt_contains_past_subtasks_and_next_query() -> None:
+    tokenizer = MiniTokenizer()
+    prompt = tokenizer.encode_high_level_prompt(
+        "drive", ("keep_lane", "slow_down"), metadata()
+    )
+    assert prompt[-1] == tokenizer.NEXT_SUBTASK_MARKER
+    assert torch.count_nonzero(prompt == tokenizer.SUBTASK_MARKER) == 2
 
 
 def test_metadata_cfg_pair_drops_metadata_but_retains_control_mode() -> None:
@@ -62,4 +69,3 @@ def test_fast_lite_dct_round_trip_has_bounded_error() -> None:
     torch.testing.assert_close(exact, actions, atol=1e-5, rtol=1e-5)
     decoded = tokenizer.decode_actions(tokenizer.encode_actions(actions))
     assert torch.sqrt(torch.mean((decoded - actions) ** 2)) < 0.3
-