mirror of
https://github.com/huggingface/lerobot.git
synced 2026-07-06 09:37:06 +00:00
Pepijn
edc3a5eb4f
Make the policy adapter architecturally clean and set up a single general entry point for any language-conditioned policy. Adapter architecture (Template Method): - New lerobot/runtime/adapter.py: BaseLanguageAdapter owns the generic control loop (throttle → generate → gibberish/empty reject → subtask→memory cascade → diagnostics) and plan_from_text/handle_interjection. A policy supplies only select_action + generate_text + build_messages. The subtask→memory cascade is an overridable hook (_regenerate_context). - GenerationConfig (typed, constructor-time) replaces config smuggled through RuntimeState.extra (temperature/top_p/min_new_tokens/chunks_per_regen). - LanguageDiagnostics (typed, keyed by kind) replaces ~8 loose state.extra counter keys; the panel reads it via the adapter. - looks_like_gibberish + split_plan_and_say move to runtime (generic). Contract: - LanguageConditionedPolicyAdapter protocol now states the true contract (select_action, update_language_state, handle_interjection); the runtime drops both getattr fallbacks. - PI052PolicyAdapter shrinks to just its primitives (132 → ~half). General entry point: - lerobot/runtime/registry.py maps policy type → adapter (lazy import). - run() resolves the adapter from the registry by policy type and defaults the panel label to it, so one CLI serves every policy. - Rename lerobot-pi052-runtime → lerobot-language-runtime (general script); a new policy just registers its adapter, no new script. Tests: new tests/runtime/test_adapter.py covers throttle/reject/cascade/ interjection; adapter + runtime + CLI-smoke tests updated for the new shape. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
68 lines
2.1 KiB
Python
68 lines
2.1 KiB
Python
from lerobot.runtime import (
|
|
LanguageConditionedRuntime,
|
|
RuntimeState,
|
|
)
|
|
|
|
|
|
class FakeAdapter:
|
|
def __init__(self):
|
|
self.updated = False
|
|
self.interjections = []
|
|
|
|
def select_action(self, observation, state):
|
|
assert observation == {"observation.state": 1}
|
|
assert state.task == "clean"
|
|
return ["a0", "a1"]
|
|
|
|
def update_language_state(self, observation, state):
|
|
self.updated = True
|
|
state.set_context("subtask", "pick cup", label="subtask")
|
|
|
|
def handle_interjection(self, user_text, observation, state):
|
|
self.interjections.append(user_text)
|
|
state.set_context("plan", "new plan", label="plan")
|
|
|
|
|
|
def test_runtime_tick_updates_language_enqueues_and_dispatches_action():
|
|
adapter = FakeAdapter()
|
|
executed = []
|
|
runtime = LanguageConditionedRuntime(
|
|
policy_adapter=adapter,
|
|
observation_provider=lambda: {"observation.state": 1},
|
|
action_executor=executed.append,
|
|
)
|
|
runtime.set_task("clean")
|
|
|
|
logs = runtime.step_once()
|
|
|
|
assert adapter.updated
|
|
assert runtime.state.language_context["subtask"] == "pick cup"
|
|
assert executed == ["a0"]
|
|
assert list(runtime.state.action_queue) == ["a1"]
|
|
assert " subtask: pick cup" in logs
|
|
|
|
|
|
def test_runtime_handles_user_interjection():
|
|
adapter = FakeAdapter()
|
|
runtime = LanguageConditionedRuntime(
|
|
policy_adapter=adapter,
|
|
observation_provider=lambda: {"observation.state": 1},
|
|
)
|
|
runtime.set_task("clean")
|
|
runtime.state.extra["recent_interjection"] = "please say ok"
|
|
runtime.state.emit("user_interjection")
|
|
|
|
runtime.step_once()
|
|
|
|
assert "please say ok" in adapter.interjections
|
|
assert runtime.state.language_context["plan"] == "new plan"
|
|
|
|
|
|
def test_runtime_state_aliases_legacy_keys_to_language_context():
|
|
state = RuntimeState()
|
|
state["current_subtask"] = "open drawer"
|
|
state["current_memory"] = "drawer open"
|
|
|
|
assert state.get("current_subtask") == "open drawer"
|
|
assert state.language_context == {"subtask": "open drawer", "memory": "drawer open"}
|