fix(rollout): propagating VideoEncoderConfig to the latest recording modes

src/lerobot/configs/dataset.py

@@ -14,10 +14,12 @@
 
 """Shared dataset recording configuration used by both ``lerobot-record`` and ``lerobot-rollout``."""
 
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from datetime import datetime
 from pathlib import Path
 
+from lerobot.datasets.video_utils import VideoEncoderConfig, camera_encoder_defaults
+
 
 @dataclass
 class DatasetRecordConfig:
@@ -55,10 +57,9 @@ class DatasetRecordConfig:
     # Number of episodes to record before batch encoding videos
     # Set to 1 for immediate encoding (default behavior), or higher for batched encoding
     video_encoding_batch_size: int = 1
-    # Video codec for encoding videos. Options: 'h264', 'hevc', 'libsvtav1', 'auto',
-    # or hardware-specific: 'h264_videotoolbox', 'h264_nvenc', 'h264_vaapi', 'h264_qsv'.
-    # Use 'auto' to auto-detect the best available hardware encoder.
-    vcodec: str = "libsvtav1"
+    # Video encoder settings for camera MP4s (codec, quality, GOP, etc.). Tuned via CLI nested keys,
+    # e.g. ``--dataset.camera_encoder_config.vcodec=h264`` (see ``VideoEncoderConfig``).
+    camera_encoder_config: VideoEncoderConfig = field(default_factory=camera_encoder_defaults)
     # Enable streaming video encoding: encode frames in real-time during capture instead
     # of writing PNG images first. Makes save_episode() near-instant. More info in the documentation: https://huggingface.co/docs/lerobot/streaming_video_encoding
     streaming_encoding: bool = False

src/lerobot/rollout/context.py

@@ -332,7 +332,7 @@ def build_rollout_context(
                 cfg.dataset.repo_id,
                 root=cfg.dataset.root,
                 batch_encoding_size=cfg.dataset.video_encoding_batch_size,
-                vcodec=cfg.dataset.vcodec,
+                camera_encoder_config=cfg.dataset.camera_encoder_config,
                 streaming_encoding=cfg.dataset.streaming_encoding,
                 encoder_queue_maxsize=cfg.dataset.encoder_queue_maxsize,
                 encoder_threads=cfg.dataset.encoder_threads,
@@ -367,7 +367,7 @@ def build_rollout_context(
                 image_writer_threads=cfg.dataset.num_image_writer_threads_per_camera
                 * len(robot.cameras if hasattr(robot, "cameras") else []),
                 batch_encoding_size=cfg.dataset.video_encoding_batch_size,
-                vcodec=cfg.dataset.vcodec,
+                camera_encoder_config=cfg.dataset.camera_encoder_config,
                 streaming_encoding=cfg.dataset.streaming_encoding,
                 encoder_queue_maxsize=cfg.dataset.encoder_queue_maxsize,
                 encoder_threads=cfg.dataset.encoder_threads,