frank-large: deployer spec gate must accept the sharded MTP layout

The 2026-10-01 first deploy refused /home/dank/models/Qwen3.5-9B because
the handler checked for a single model.safetensors (the dflash layout);
the Qwen3.5-9B MTP head ships 4 shards behind model.safetensors.index.json.
Same dual-layout acceptance as the serve script, now mirrored and gated by
the seam. The gate fired before the stop, so the live gufo unit was never
touched (health 200 throughout).

tests/frank_large_unit.bats

@@ -191,6 +191,9 @@ FETCH_MTPSRC="$REPO_ROOT/scripts/download-frank-large-qwen35.sh"
     grep -q 'FRANK_LARGE_IMAGE' "$REMOTE_DEPLOY"
     grep -q "podman images --format '{{.RepoDigests}}'" "$REMOTE_DEPLOY"
     grep -q 'FRANK_LARGE_MODEL_SHARDS' "$REMOTE_DEPLOY"
+    # The deployer's draft gate must accept the SHARDED MTP layout too —
+    # the 2026-10-01 first deploy died on exactly this single-file check.
+    grep -q 'spec_dir/model.safetensors.index.json' "$REMOTE_DEPLOY"
     grep -q 'FRANK_LARGE_SPEC=' "$REMOTE_DEPLOY"
     grep -q 'wait_port_free 7770' "$REMOTE_DEPLOY"
     grep -q 'MainPID --value frank-large.service' "$REMOTE_DEPLOY"