Update for S=256 bundle (no truncation)

README.md

@@ -46,16 +46,17 @@ no KV cache).
 
 - `macos/` — Core AI `.aimodel` (GPU) + `tokenizer/` + `metadata.json`
 - `metadata.json` exposes the diffusion knobs (no recompile to retune):
-  - `seq` — canvas length (this **v1 preview** is `128` ⇒ answers up to ~80 tokens; a longer-context build is planned)
+  - `seq` — canvas length (`256` ⇒ answers up to ~210 tokens). No KV cache ⇒ the whole prompt+answer
+    lives in `S`; per-step cost is ~linear in `S` (a larger canvas = fuller answers but slower steps).
   - `block_size` `32`, `threshold` `1.0` — the entropy threshold trades steps for speed; lower = more gradual, higher = fewer forwards (faster), too high degrades quality
 
 ## Performance (M4 Max, GPU)
 
 | metric | value |
 |---|---|
-| throughput | **≈38 tok/s** (threshold 1.0) |
-| TTFT | ~0.2 s |
-| forwards (NFE) | ~11 for an 83-token answer |
+| throughput | **≈40 tok/s** (threshold 1.0, S=256) |
+| TTFT | ~0.3 s |
+| forwards (NFE) | ~22 for a full 210-token answer |
 | size | 4.9 GB (int4 + int8 head) |
 
 The per-step cost is a full bidirectional forward over the whole canvas (no KV cache) — the