From 82ff9dda20377baaa9986506636017ee4ae4c82c Mon Sep 17 00:00:00 2001
From: Frank <frank@dankware>
Date: Sat, 26 Sep 2026 20:58:53 -0700
Subject: [PATCH] frank-primary + frank-large: export /metrics, raise primary
 log verbosity to 4

Both b11030 serve scripts never passed --metrics, so /metrics answered
501 and Prometheus could not scrape frank-large (silently down since
its deploy) or frank-primary. frank-primary also gets -lv 4 (VERBOSITY
env tunable, default 4) for the full per-buffer load breakdown.
---
 scripts/serve-frank-large.sh   | 1 +
 scripts/serve-frank-primary.sh | 3 +++
 2 files changed, 4 insertions(+)

diff --git a/scripts/serve-frank-large.sh b/scripts/serve-frank-large.sh
index 0c518fa..6daf828 100755
--- a/scripts/serve-frank-large.sh
+++ b/scripts/serve-frank-large.sh
@@ -81,6 +81,7 @@ ARGS=(
     --parallel "$PARALLEL_SLOTS"
     --n-gpu-layers 999
     --jinja
+    --metrics
     --chat-template-file "$TEMPLATE_FILE"
     --chat-template-kwargs '{"preserve_thinking":true}'
     --cache-type-k q8_0
diff --git a/scripts/serve-frank-primary.sh b/scripts/serve-frank-primary.sh
index 6fd1f4d..d91748d 100755
--- a/scripts/serve-frank-primary.sh
+++ b/scripts/serve-frank-primary.sh
@@ -56,6 +56,7 @@ fi
 : "${BATCH_SIZE:=8192}"
 : "${UBATCH_SIZE:=512}"
 : "${CACHE_RAM:=16384}"
+: "${VERBOSITY:=4}"
 
 SERVER_BIN="$RUNTIME_DIR/llama-server"
 MODEL_PARTS=(
@@ -99,6 +100,8 @@ ARGS=(
     --alias frank-primary
     --ctx-size "$CONTEXT_SIZE"
     --parallel "$PARALLEL_SLOTS"
+    -lv "$VERBOSITY"
+    --metrics
     --n-gpu-layers "$NGL"
     --tensor-split "$TENSOR_SPLIT"
     --jinja