frank-small: wire SPEC_DRAFT_N_MAX and POLL_LEVEL knobs

Both were implicit build defaults (3 and 50); the throughput sweep needs
to move them without editing the exec line each time. Defaults preserve
current behavior exactly. Additive only.

scripts/frank-small.env

@@ -90,8 +90,12 @@ NGL=999
 FLASH_ATTN=on
 
 # Speculative decoding: the MTP sidecar (draft context) chained with the
-# draftless ngram-mod matcher. Draft depth stays llama.cpp's default of 3.
+# draftless ngram-mod matcher. Draft depth and busy-wait level are made
+# explicit here for tuning (both were the implicit build defaults: 3 and 50;
+# the Gemma4 sidecar carries 4 nextn layers).
 SPEC_TYPE=draft-mtp,ngram-mod
+SPEC_DRAFT_N_MAX=3
+POLL_LEVEL=50
 
 # Greedy default (fleet contract); reasoning is extracted into
 # reasoning_content with an unlimited budget (the model decides).