Add caching mechanism for completed AV blocks in streaming model. Introduce CompletedBlockPieceCache class to manage reusable blocks during strict-window replay, enhancing efficiency. Update profiling hooks for cache operations and refine README documentation to reflect changes in block handling and replay strategies.

README.md

@@ -477,7 +477,9 @@ two practical changes for this dataset:
 1. the current 0--2 second partial block is evaluated speculatively every
    0.2 seconds and discarded unless it reaches a complete block boundary;
 2. the KV history is bounded and rebuilt from recent complete blocks rather
-   than accumulating for an entire multi-minute session.
+   than accumulating for an entire multi-minute session. Complete-block AV
+   embeddings are retained in a bounded ring, so rolling rebuilds rerun only
+   the Thinker and do not rerun the processor, audio tower, or video tower.
 
 It should therefore be described as **bounded Qwen-style open streaming**, not
 as bit-for-bit reproduction of an unbounded official serving session.
@@ -522,7 +524,10 @@ prediction is emitted every 0.2 seconds.
 budget it rebuilds the open cache from the latest nine completed blocks
 (18 seconds) when a new block starts, then adds the current 0--2 second tail.
 Its effective history therefore varies from 18 to 20 seconds and never drops
-to an empty 0.2-second context at a 20-second boundary.
+to an empty 0.2-second context at a 20-second boundary. The nine blocks'
+prepared AV embeddings and local TMRoPE coordinates are cached once; strict
+window replay still recomputes the Thinker KV so retained blocks no longer
+carry indirect influence from observations that fell out of the window.
 
 For a short native-stream fidelity check, set `--memory-seconds` to at least
 the tested clip duration. For example, the options