frank-default-small: use the repo chat_template.jinja so tools render in Qwen3 XML

The Avesed tokenizer_config.json ships no chat_template, so vLLM used its
built-in template, which does not render the <tool_call> instructions;
the model then emitted malformed XML (arguments baked into the function
name) and the qwen3_xml parser could not extract clean calls.

scripts/serve-frank-small.sh

@@ -35,6 +35,10 @@ fi
 : "${NUM_SPEC_TOKENS:=5}"
 : "${ENABLE_AUTO_TOOL_CHOICE:=1}"
 : "${TOOL_CALL_PARSER:=qwen3_xml}"
+# The Avesed tokenizer_config.json has no chat_template; vLLM would use its
+# built-in template which does not render the model's XML tool format. Use
+# the repo's chat_template.jinja (ships the <tool_call> instructions).
+: "${CHAT_TEMPLATE:=/home/dank/models/avesed-qwen36-chat_template.jinja}"
 
 if [[ ! -x "$VLLM_BIN" ]]; then
     echo "missing vllm binary: $VLLM_BIN" >&2
@@ -59,4 +63,5 @@ exec "$VLLM_BIN" serve "$MODEL" \
     --speculative-config "{\"method\":\"ngram\",\"prompt_lookup_max\":$NGRAM_LOOKUP_MAX,\"prompt_lookup_min\":$NGRAM_LOOKUP_MIN,\"num_speculative_tokens\":$NUM_SPEC_TOKENS}" \
     --reasoning-parser qwen3 \
     --trust-remote-code \
+    --chat-template "$CHAT_TEMPLATE" \
     "${TOOL_ARGS[@]}"