Fix multi-turn replay fidelity: track realized output tokens across all components

The replayer and proxy were building multi-turn prompts from trace tokens,
but the model generates different output tokens. Subsequent turns had wrong
prefix tokens, causing cache misses and invalid experimental measurements.

- replay.py: min_tokens=max_tokens for deterministic length, return_token_ids
  to capture actual output, _apply_realized_prefix for next-turn correction
- proxy: extract output token_ids from SSE, record prompt+output as realized
  prefix in shadow cache, extract _handle_local_request to deduplicate
- bench.sh/launch_elastic_p2p.sh: default elastic mode to unified policy
- mooncake_connector: only send prompt blocks (not stale output blocks),
  track failed_recving_block_ids for error recovery

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

scripts/launch_elastic_p2p.sh

@@ -90,6 +90,7 @@ $PYTHON "$PROJECT_DIR/scripts/cache_aware_proxy.py" \
     --combined $combined_args \
     --bootstrap-ports "$bootstrap_ports" \
     --offload \
+    --policy unified \
     --heavy-threshold $HEAVY_THRESHOLD \
     --port $PROXY_PORT &
 sleep 5