feat(smolvla2): inference runtime — select_message + multi-rate REPL

Closes the loop on PR 3: SmolVLA2 can now be queried interactively at
inference, dispatching the same five sub-recipe shapes it was trained
on (action chunks, subtask gen, memory updates, plan/speech on
interjection, VQA on questions).

Modeling fixes + additions
--------------------------

- ``_compute_text_loss``: standard next-token CE shift was missing
  (logits at position t were CE'd against the label at t — identity-
  mapped, learning nothing). Adds ``logits[:, :-1]`` /
  ``labels[:, 1:]`` shift to match HuggingFace ``LlamaForCausalLM``.

- New ``select_message`` on ``SmolVLA2Policy``: AR text generation
  with KV caching, mirroring SmolVLA's ``select_action`` pattern.
  Single prefix forward fills the cache, then per-token forwards
  reuse it. Greedy + top-p nucleus sampling. Returns the decoded
  string with the prompt stripped.

Runtime package — ``src/lerobot/policies/smolvla2/inference/``
-------------------------------------------------------------

- ``triggers.py`` — ``Trigger`` Protocol + ``HzTrigger`` /
  ``EventTrigger`` + ``TickClock``. The whole runtime ticks at
  ``max_rate_hz=50`` and each step gates itself off its own
  cadence.

- ``runtime_state.py`` — runtime state dict factory plus tiny
  helpers (``take_event``, ``set_if_changed``, ``push_log``).
  Stable keys are documented at the top of the module.

- ``steps.py`` — :class:`InferenceStep` base + concrete steps:
  ``LowLevelForward`` / ``DispatchAction`` (action path),
  ``HighLevelSubtaskFwd`` / ``MemoryUpdateFwd`` /
  ``UserInterjectionFwd`` / ``AskVQAFwd`` (text paths),
  ``DispatchToolCalls`` (tool registry → ``Tool.call``). Each
  text step builds a chat-template prompt from current
  ``RuntimeState`` (task / plan / memory / subtask) matching
  what ``smolvla2_hirobot.yaml`` renders during training.
  Includes a tiny ``<say>...</say>`` parser for the
  ``user_interjection_response`` branch's combined plan + speech
  output.

- ``runtime.py`` — :class:`SmolVLA2Runtime` composes the pipeline,
  drives ticks via ``TickClock``, polls a user-supplied
  ``event_collector`` per tick, and prints state-change log lines.

- ``repl.py`` — :class:`StdinReader` non-blocking line reader
  with simple intent classification: ``stop`` / ``quit`` /
  ``exit`` → terminate; ``?`` suffix → ``user_vqa_query`` event;
  first line → set task; other lines → ``user_interjection``.

CLI
---

- ``src/lerobot/scripts/lerobot_smolvla2_runtime.py``: console
  script ``lerobot-smolvla2-runtime`` that loads a checkpoint,
  optionally instantiates ``SayTool`` (pocket-tts), wires up
  ``SmolVLA2Runtime`` + ``StdinReader``, and runs.

  Real-robot wiring (observation_provider / robot_executor) is
  intentionally left as a follow-up — v1 is dry-run / language-
  only so the REPL works without robot hardware.

  Registered in ``pyproject.toml`` ``[project.scripts]``.

Known follow-ups
----------------

- Real-robot integration: today ``LowLevelForward`` only fires when
  an observation_provider is wired. The CLI prints a warning if
  ``--no_robot`` is omitted.
- ``select_message`` runs an extra prefix forward; could share with
  the action path's prefix when both are needed in the same tick.
- Tests: no end-to-end runtime test yet (would need a tiny SmolVLM
  fixture). The components compile and the public surface is
  exercised by the CLI's argument-parsing path.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

pyproject.toml

@@ -307,6 +307,7 @@ lerobot-imgtransform-viz="lerobot.scripts.lerobot_imgtransform_viz:main"
 lerobot-edit-dataset="lerobot.scripts.lerobot_edit_dataset:main"
 lerobot-setup-can="lerobot.scripts.lerobot_setup_can:main"
 lerobot-annotate="lerobot.scripts.lerobot_annotate:main"
+lerobot-smolvla2-runtime="lerobot.scripts.lerobot_smolvla2_runtime:main"
 
 # ---------------- Tool Configurations ----------------
 [tool.setuptools.package-data]