Update README and streaming_turn_model.py to implement half-open interval ownership for fixed-grid AV frames. Adjust verification parameters to 1 for testing, and enhance documentation for clarity on audio slicing and frame selection. Add runtime checks to prevent overlapping temporal coordinates in open-stream intervals.

streaming_turn_model.py

@@ -167,7 +167,13 @@ class FixedGridAV:
         )
 
     def frames(self, start: float, end: float) -> list[Any]:
-        """Return fixed-grid frames whose timestamps lie in [start, end]."""
+        """Return fixed-grid frames whose timestamps lie in ``[start, end)``.
+
+        Half-open ownership is essential at native block boundaries. For
+        example, the frame at exactly 2.0 s belongs to ``[2.0, 4.0)`` and must
+        not also be committed in ``[0.0, 2.0)``. Audio slicing below follows
+        the same convention.
+        """
 
         import numpy as np
         from PIL import Image
@@ -175,7 +181,7 @@ class FixedGridAV:
         first = max(0, int(math.ceil(start * self.fps - 1e-7)))
         last = min(
             self.num_frames - 1,
-            int(math.floor(end * self.fps + 1e-7)),
+            int(math.ceil(end * self.fps - 1e-7)) - 1,
         )
         if first > last:
             # This can occur only when a caller starts between global visual
@@ -1255,11 +1261,32 @@ class OpenStreamReplayExtractor:
             manual_audios=manual_audios,
             video_fps=self.config.video_fps,
         )
-        return _open_media_pieces(
+        pieces = _open_media_pieces(
             self.model,
             inputs,
             use_audio_in_video=use_audio_in_video,
         )
+        # A standalone tail is at most one native 2 s block. Its temporal
+        # TMRoPE coordinates must therefore stay inside one 50-position chunk.
+        # This catches endpoint-inclusive frame selection (or another
+        # preprocessing regression) before overlapping coordinates are
+        # committed to the next block.
+        duration = interval[1] - interval[0]
+        if duration <= self.config.native_block_seconds + 1e-6:
+            temporal_positions = pieces.payload_position_ids[0]
+            temporal_span = int(
+                temporal_positions.max().item()
+                - temporal_positions.min().item()
+            )
+            positions_per_chunk = _tmrope_positions_per_chunk(self.model)
+            if temporal_span >= positions_per_chunk:
+                raise RuntimeError(
+                    "One open-stream AV interval spans multiple native TMRoPE "
+                    f"chunks: interval={interval}, temporal_span={temporal_span}, "
+                    f"chunk_size={positions_per_chunk}. Check frame-boundary "
+                    "ownership and audio preprocessing."
+                )
+        return pieces
 
     def state_from_scratch(
         self,
@@ -1812,6 +1839,11 @@ def main() -> None:
             if fixed_grid_av is not None
             else "qwen_utility_adaptive_sampling"
         ),
+        "media_interval_policy": (
+            "half_open_[start,end)"
+            if fixed_grid_av is not None
+            else "qwen_utility_defined"
+        ),
         "open_stream_policy": (
             {
                 "commit": "completed_2s_av_payload_only",