Add Qwen tail and chunk ablations

PROJECT_CONTEXT.md

@@ -81,6 +81,12 @@ All are pending in that log; Omni LoRA is deferred and no semantic gate is compl
 
 ### Implemented but not GPU-verified
 
+- Qwen2.5-Omni now has two matched chunk-handling controls around the existing
+  5 Hz partial-tail path: native completed 2-second blocks held between
+  boundaries, and non-native 200-ms payload commits. Both preserve dense causal
+  alignment and save state-age/processing diagnostics, but still require the
+  documented real-GPU smoke test before a full run. See
+  [`docs/qwen_tail_chunk_ablation.md`](docs/qwen_tail_chunk_ablation.md).
 - MiniCPM-o 4.5 input-only feature extraction has two unmeasured modes: a
   native 1 Hz state causally held on the 5 Hz grid, and a 5 Hz completed-cache
   plus temporary-partial-tail branch. The latter refuses the normal