llm-inference-multimodel: fix tool-calling support (jinja template + gpu-layers=20 for VRAM fit)

ansible/roles/llm-inference-multimodel/tasks/models.yml

@@ -70,3 +70,30 @@
     msg:
       - "Aux model:        {{ llm_aux_model_path }}"
       - "Tool-calling model: {{ llm_toolcall_model_path }}"
+
+# --- Tool-calling chat template override -------------------------------------
+# Mistral-Small-24B-Instruct-2501's own embedded/tokenizer_config chat template
+# has NO tool-call handling ([AVAILABLE_TOOLS]/[TOOL_CALLS] blocks) — confirmed
+# via /props chat_template_caps.supports_tools=false against the stock
+# template. Mistral-Nemo-Instruct-2407 ships a template with full tool-calling
+# support and the same Mistral instruct format family, so we serve it via
+# --chat-template-file instead of relying on GGUF-embedded metadata.
+# See docs/validation-log.md for the investigation and probe results.
+
+- name: Create chat templates directory
+  ansible.builtin.file:
+    path: "{{ llm_toolcall_chat_template_file | dirname }}"
+    state: directory
+    owner: "{{ llm_service_user }}"
+    group: "{{ llm_service_user }}"
+    mode: "0755"
+  become: true
+
+- name: Deploy tool-calling-capable chat template (from Mistral-Nemo-Instruct-2407)
+  ansible.builtin.copy:
+    src: mistral-small-tool-use.jinja
+    dest: "{{ llm_toolcall_chat_template_file }}"
+    owner: "{{ llm_service_user }}"
+    group: "{{ llm_service_user }}"
+    mode: "0644"
+  become: true