From d815b59def96b1dfc06cb035de7cf69d669fda39 Mon Sep 17 00:00:00 2001
From: Xin Wang <your-email@example.com>
Date: Mon, 17 Aug 2026 22:59:02 +0800
Subject: [PATCH] Refactor README and streaming_turn_model.py to clarify
 fixed-grid frame ownership and update documentation. Remove merge conflict
 markers and enhance explanations regarding session launching conditions and
 audio slicing behavior.

---
 README.md               |  6 ------
 streaming_turn_model.py | 10 ----------
 2 files changed, 16 deletions(-)

diff --git a/README.md b/README.md
index 51de4e2..c122bb3 100644
--- a/README.md
+++ b/README.md
@@ -584,17 +584,11 @@ python streaming_turn_model.py \
   --output features/Session_1_first_4s_check.pt
 ```
 
-<<<<<<< HEAD
 Do not launch all sessions unless `cache_replay` cosine is nearly 1. For
 `open-stream-replay`, a materially lower `continuous_window_semantics` cosine
 means that the custom payload stitching is not equivalent to one continuous
 Qwen input; it must not be dismissed as a media-turn-boundary effect because
 this mode intentionally keeps a single media turn open.
-=======
-Do not launch all sessions unless `cache_replay` cosine is nearly 1. The
-`continuous_window_semantics` cosine answers a different question and may be
-lower because blockwise media preprocessing changes the representation.
->>>>>>> 8145be410866dd0675038d92347aea34d24b84d5
 
 Video can be sampled at 2 FPS while predictions remain at 5 Hz. Audio and the
 causal boundary update every 200 ms; consecutive prediction times may use the
diff --git a/streaming_turn_model.py b/streaming_turn_model.py
index a3268e1..72018a5 100644
--- a/streaming_turn_model.py
+++ b/streaming_turn_model.py
@@ -243,7 +243,6 @@ class FixedGridAV:
             raise RuntimeError(f"Decoded audio is empty: {self.path}")
 
     def frames(self, start: float, end: float) -> list[Any]:
-<<<<<<< HEAD
         """Return fixed-grid frames whose timestamps lie in ``[start, end)``.
 
         Half-open ownership is essential at native block boundaries. For
@@ -251,23 +250,14 @@ class FixedGridAV:
         not also be committed in ``[0.0, 2.0)``. Audio slicing below follows
         the same convention.
         """
-=======
-        """Return fixed-grid frames whose timestamps lie in [start, end)."""
->>>>>>> 8145be410866dd0675038d92347aea34d24b84d5
 
         import numpy as np
         from PIL import Image
 
         first = max(0, int(math.ceil(start * self.fps - 1e-7)))
-<<<<<<< HEAD
-        last = min(
-            self.num_frames - 1,
-            int(math.ceil(end * self.fps - 1e-7)) - 1,
-=======
         last_exclusive = min(
             self.num_frames,
             int(math.ceil(end * self.fps - 1e-7)),
->>>>>>> 8145be410866dd0675038d92347aea34d24b84d5
         )
         last = last_exclusive - 1
         if first > last: