mirror of
https://github.com/huggingface/lerobot.git
synced 2026-07-23 09:46:00 +00:00
Pepijn
4fa9578e3d
Cleanup pass over the language-support PR to cut LOC and scope creep. Removals: - SayTool + tools/ package (registry, Tool protocol, [tools] extra) and the runtime's tool-dispatch path. Kept <say> training supervision and inference stripping so speech-annotated datasets still train. - WeightedEpisodeAwareSampler + VQA oversampling wiring (_build_vqa_oversample_weights, vqa_target_fraction) — training uses plain EpisodeAwareSampler again. - Debug env-gates PI052_DEBUG_TENSORS, PI052_SUBTASK_USE_TASK, EVAL_TASK_OVERRIDE. - Dead code: broken _tp._DUMP_BUDGET block, unused imports (copy/Tensor, RevisionNotFoundError, LeRobotDataset, os), messages_for_vqa, steps.py shim (modeling imports pi052_adapter directly), duplicated _emit, builtins.type[T]. Moves: - Policy-agnostic runtime -> src/lerobot/runtime/ (LanguageConditionedRuntime + adapter Protocol + state); pi052 keeps only its adapter + CLI. Tests -> tests/runtime/. Other: - Compacted verbose AI-authored comments/docstrings across pi052 (kept the hard-won DDP / barrier-timeout / reduce-max / VQA-routing notes). - Relocated LM-head prediction debug helper to pi052/debug_utils.py. - Fixed test_render_messages: assert task-fallback render (current behavior) instead of the stale no-op expectation. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
52 lines
2.1 KiB
Python
52 lines
2.1 KiB
Python
from types import SimpleNamespace
|
|
|
|
from lerobot.policies.pi052.inference.pi052_adapter import PI052PolicyAdapter, split_plan_and_say
|
|
from lerobot.runtime import RuntimeState
|
|
|
|
|
|
def test_pi052_adapter_builds_recipe_prompts_from_runtime_state():
|
|
adapter = PI052PolicyAdapter(policy=object())
|
|
state = RuntimeState(
|
|
task="clean the kitchen",
|
|
language_context={"memory": "cup moved", "plan": "pick then place"},
|
|
extra={"prior_subtask": "pick the cup"},
|
|
)
|
|
|
|
assert adapter.messages_for("subtask", state) == [{"role": "user", "content": "clean the kitchen"}]
|
|
assert adapter.messages_for("memory", state) == [
|
|
{"role": "user", "content": "clean the kitchen"},
|
|
{"role": "assistant", "content": "Previous memory: cup moved"},
|
|
{"role": "user", "content": "Completed subtask: pick the cup"},
|
|
]
|
|
assert adapter.messages_for("interjection", state, user_text="wait") == [
|
|
{"role": "user", "content": "clean the kitchen"},
|
|
{"role": "assistant", "content": "Previous plan:\npick then place"},
|
|
{"role": "user", "content": "wait"},
|
|
]
|
|
assert adapter.messages_for("vqa", state, user_text="where is the cup?") == [
|
|
{"role": "user", "content": "where is the cup?"}
|
|
]
|
|
|
|
|
|
def test_pi052_adapter_strips_say_markers_from_plan_text():
|
|
adapter = PI052PolicyAdapter(policy=object())
|
|
text = "Move to the sink. <say>heading to the sink</say>"
|
|
|
|
assert split_plan_and_say(text) == ("Move to the sink.", "heading to the sink")
|
|
assert adapter.plan_from_text(text) == "Move to the sink."
|
|
|
|
|
|
def test_pi052_runtime_cli_smoke_does_not_load_model(monkeypatch):
|
|
from lerobot.policies.pi052.inference import runtime_cli
|
|
|
|
fake_policy = SimpleNamespace(config=SimpleNamespace(device="cpu"))
|
|
|
|
monkeypatch.setattr(
|
|
runtime_cli,
|
|
"_load_policy_and_preprocessor",
|
|
lambda policy_path, dataset_repo_id: (fake_policy, None, None, None),
|
|
)
|
|
monkeypatch.setattr(runtime_cli, "_run_repl", lambda runtime, initial_task, max_ticks: 0)
|
|
|
|
assert runtime_cli.main(["--policy.path=fake", "--no_robot", "--task=clean", "--max_ticks=0"]) == 0
|