From 5108af11aa45316ebb11a9f552fa443cae1ff4f4 Mon Sep 17 00:00:00 2001
From: Frank <frank@dankware>
Date: Mon, 17 Aug 2026 16:50:23 -0700
Subject: [PATCH] frank-default-small: enable tool calling
 (--enable-auto-tool-choice --tool-call-parser qwen3_xml)

Clients send tool_choice=auto; without these flags vLLM rejects with
HTTP 400. The Avesed chat template renders the Qwen3 XML tool format,
so qwen3_xml is the matching parser.
---
 scripts/frank-default-small.env |  7 +++++++
 scripts/serve-frank-small.sh    | 11 ++++++++++-
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/scripts/frank-default-small.env b/scripts/frank-default-small.env
index e5efc30..5ad2769 100644
--- a/scripts/frank-default-small.env
+++ b/scripts/frank-default-small.env
@@ -39,6 +39,13 @@ NGRAM_LOOKUP_MAX=5
 NGRAM_LOOKUP_MIN=1
 NUM_SPEC_TOKENS=5
 
+# Tool calling. Clients (pi, OpenWebUI) send tool_choice=auto; without
+# --enable-auto-tool-choice vLLM rejects it with HTTP 400. The Avesed
+# chat template renders tools in the Qwen3 XML format, so the qwen3_xml
+# parser is the matching one.
+ENABLE_AUTO_TOOL_CHOICE=1
+TOOL_CALL_PARSER=qwen3_xml
+
 # RDNA flash-attention for the vision encoder (and general FA paths).
 # Without this, the mm encoder falls back to torch SDPA and the warmup
 # OOMs (256 GiB score matrix at max_model_len; measured 2026-08-17).
diff --git a/scripts/serve-frank-small.sh b/scripts/serve-frank-small.sh
index 48472a7..150e72f 100755
--- a/scripts/serve-frank-small.sh
+++ b/scripts/serve-frank-small.sh
@@ -33,12 +33,20 @@ fi
 : "${NGRAM_LOOKUP_MAX:=5}"
 : "${NGRAM_LOOKUP_MIN:=1}"
 : "${NUM_SPEC_TOKENS:=5}"
+: "${ENABLE_AUTO_TOOL_CHOICE:=1}"
+: "${TOOL_CALL_PARSER:=qwen3_xml}"
 
 if [[ ! -x "$VLLM_BIN" ]]; then
     echo "missing vllm binary: $VLLM_BIN" >&2
     exit 1
 fi
 
+TOOL_ARGS=()
+if [[ "${ENABLE_AUTO_TOOL_CHOICE}" == "1" ]]; then
+    TOOL_ARGS+=(--enable-auto-tool-choice)
+    TOOL_ARGS+=(--tool-call-parser "${TOOL_CALL_PARSER}")
+fi
+
 exec "$VLLM_BIN" serve "$MODEL" \
     --host "$BIND_ADDR" \
     --port "$LISTEN_PORT" \
@@ -50,4 +58,5 @@ exec "$VLLM_BIN" serve "$MODEL" \
     --gpu-memory-utilization "$GPU_MEMORY_UTILIZATION" \
     --speculative-config "{\"method\":\"ngram\",\"prompt_lookup_max\":$NGRAM_LOOKUP_MAX,\"prompt_lookup_min\":$NGRAM_LOOKUP_MIN,\"num_speculative_tokens\":$NUM_SPEC_TOKENS}" \
     --reasoning-parser qwen3 \
-    --trust-remote-code
+    --trust-remote-code \
+    "${TOOL_ARGS[@]}"