frank-large: roll back to gufo Qwen3.8-27B Q4_K_XL, one session x 262144 f16 KV

frank-small: llama.cpp CUDA (master, sm_86) on MiMo Q6_K GGUF, 2 x 262144,
asymmetric KV (f16 K + q8_0 V, flash-attn pinned for the V quant)

scripts/autoresearch-bench.py

@@ -84,7 +84,8 @@ def stream_completion(url: str, model: str, prompt: str):
                 d = ch.get("delta") or {}
                 # reasoning AND content deltas both arrive token by token;
                 # count either so greedy text length drives the rate.
-                if d.get("content") or d.get("reasoning"):
+                # (llama.cpp names the thinking field reasoning_content.)
+                if d.get("content") or d.get("reasoning") or d.get("reasoning_content"):
                     now = time.perf_counter()
                     if first is None:
                         first = now