dankclaw: bench cycle 1 - switch spec to ngram-mod; draft flags conditional

DFlash causes premature EOS on a generating slot when another task lands
with high LCP prompt reuse (shared draft ctx corruption, reproduced
2026-08-14 3x). Benching ngram-mod vs MTP sidecar to pick the
replacement. serve script now passes --spec-draft-model only for
draft-* spec types.

scripts/serve-llama-frank-large.sh

@@ -48,16 +48,25 @@ LLAMA_SERVER="${LLAMA_SERVER:-/home/dank/llama.cpp/build/bin/llama-server}"
 MODEL="$MODEL_DIR/$MODEL_FILE"
 DRAFT="$MODEL_DIR/$DRAFT_FILE"
 
-for f in "$MODEL" "$DRAFT"; do
-    if [[ ! -f "$f" ]]; then
-        echo "missing required file: $f" >&2
+if [[ ! -f "$MODEL" ]]; then
+    echo "missing required file: $MODEL" >&2
+    exit 1
+fi
+
+# Draft-model flags apply only to spec types that use a draft file
+# (draft-dflash, draft-mtp, draft-eagle3). ngram-mod is draftless.
+SPEC_ARGS=()
+if [[ "$SPEC_TYPE" == *draft-* ]]; then
+    if [[ ! -f "$DRAFT" ]]; then
+        echo "missing required file: $DRAFT" >&2
         exit 1
     fi
-done
+    SPEC_ARGS+=(--spec-draft-model "$DRAFT")
+fi
 
 exec "$LLAMA_SERVER" \
     --model "$MODEL" \
-    --spec-draft-model "$DRAFT" \
+    "${SPEC_ARGS[@]}" \
     --spec-type "$SPEC_TYPE" \
     --spec-draft-n-max "$SPEC_DRAFT_N_MAX" \
     --spec-ngram-mod-n-min "$SPEC_NGRAM_MOD_N_MIN" \