feat(annotate): attach camera keyframes to module prompts; default to Qwen3.6-27B-FP8

Closes the visual-grounding gap flagged after the initial PR review:
modules now decode actual camera frames at the relevant timestamps and
attach them as `{"type":"image", "image":<PIL>}` content blocks to the
VLM prompts.

- New `frames.py`:
  - `FrameProvider` Protocol; `VideoFrameProvider` decodes from the
    dataset's first `observation.images.*` stream via
    `LeRobotDatasetMetadata.get_video_file_path` and
    `decode_video_frames`, with the same `from_timestamp` shift the main
    dataset uses.
  - Per-process LRU cache so co-timestamped Module 1 plan-update + Module
    2 calls share decode work.
  - `make_frame_provider` falls back to a null provider when the dataset
    has no video tracks → text-only prompts (graceful absence).
- Modules 1/2/3 take an optional `frame_provider` (default null) and
  prepend image blocks before the text block.
  - Module 1 attaches `keyframes_per_episode` keyframes to the subtask
    decomposition prompt.
  - Module 2 attaches the frame at the interjection timestamp.
  - Module 3 attaches the exact emission frame to each VQA pair.
- VlmConfig: backend now defaults to `vllm`; default model is
  `Qwen/Qwen3.6-27B-FP8`. New knobs: `--vlm.tensor_parallel_size`,
  `--vlm.camera_key` (override the keyframe stream).
- `_make_vllm_client` honours `tensor_parallel_size` so 27B-FP8 sharded
  on 2× GPUs works out of the box.
- `test_module3_attaches_frame_image_block_to_prompt` asserts modules
  emit one image block per VQA prompt at the exact emission timestamp.
- Docs: example switched to `imstevenpmwork/super_poulain_draft` +
  Qwen3.6-27B-FP8 + tensor_parallel_size=2; documents the keyframe
  attachment behaviour and the no-video fallback.

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

src/lerobot/annotations/steerable_pipeline/modules/general_vqa.py

@@ -30,10 +30,11 @@ from __future__ import annotations
 import json
 import random
 from collections.abc import Sequence
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from typing import Any
 
 from ..config import Module3Config
+from ..frames import FrameProvider, null_provider, to_image_blocks
 from ..prompts import load as load_prompt
 from ..reader import EpisodeRecord
 from ..staging import EpisodeStaging
@@ -83,6 +84,7 @@ class GeneralVqaModule:
     vlm: VlmClient
     config: Module3Config
     seed: int = 1729
+    frame_provider: FrameProvider = field(default_factory=null_provider)
 
     @property
     def enabled(self) -> bool:
@@ -100,7 +102,7 @@ class GeneralVqaModule:
         for idx in anchor_idx:
             ts = float(record.frame_timestamps[idx])
             qtype = rng.choice(self.config.question_types)
-            qa = self._generate_one(record, qtype)
+            qa = self._generate_one(record, qtype, ts)
             if qa is None:
                 continue
             question, answer = qa
@@ -124,12 +126,16 @@ class GeneralVqaModule:
             )
         staging.write("module_3", rows)
 
-    def _generate_one(self, record: EpisodeRecord, question_type: str) -> tuple[str, dict[str, Any]] | None:
+    def _generate_one(
+        self, record: EpisodeRecord, question_type: str, frame_timestamp: float
+    ) -> tuple[str, dict[str, Any]] | None:
         prompt = load_prompt("module_3_vqa").format(
             episode_task=record.episode_task,
             question_type=question_type,
         )
-        messages = [{"role": "user", "content": [{"type": "text", "text": prompt}]}]
+        images = self.frame_provider.frames_at(record, [frame_timestamp])
+        content = [*to_image_blocks(images), {"type": "text", "text": prompt}]
+        messages = [{"role": "user", "content": content}]
         result = self.vlm.generate_json([messages])[0]
         if not isinstance(result, dict):
             return None