Add Qwen3-8B no-think variant — dual thinking deployment (t_664289a0)

Part A: qwen3-no-think.jinja.j2 Ansible template
  - New template: templates/qwen3-no-think.jinja.j2
    Standard Qwen3 chat template with enable_thinking unconditionally false
    (hardcoded empty <think></think> prefix at add_generation_prompt step).
    Deployed to /opt/models/templates/qwen3-no-think.jinja on astro-orbiter.
  - tasks/models.yml: deploy templates dir + qwen3-no-think.jinja via
    ansible.builtin.template task (tags: models, chat_templates).

Part B: INI preset template — two Qwen3-8B sections
  - templates/llama-server-router-preset.ini.j2:
    [Qwen3-8B-Q4_K_M] — thinking variant, same GGUF, baked-in template.
    [Qwen3-8B-Q4_K_M-no_think] — no-think variant, same GGUF,
    chat-template-file = /opt/models/templates/qwen3-no-think.jinja.
    Both sections: n-gpu-layers=99, ctx-size=32768, flash-attn=true,
    q4_0 KV cache, sleep-idle-seconds=60.

Part C: defaults/main.yml — llama-swap models + matrix
  - llm_swapmode_models: added Qwen3-8B-Q4_K_M (port 8106, GPU) and
    Qwen3-8B-Q4_K_M-no_think (port 8107, GPU, chat_template_file set).
  - llm_swapmode_matrix_rows: row5 (Qwen3-8B thinking + embed),
    row6 (Qwen3-8B no_think + embed). Neither co-resident with Qwen3.8-27B.
  - templates/llama-swap-config.yaml.j2: added chat_template_file support
    (--chat-template-file flag conditional on model.chat_template_file).
  - tasks/swapmode.yml: GATE 2 assert updated 5 -> 7 models.

Part D: war-machine config.yaml (not tracked in git)
  - custom_providers.astro-orbiter.models: added Qwen3-8B-Q4_K_M-no_think
    (context_length: 32768).
  - Reassigned 5 latency-sensitive aux tasks from Meta-Llama-3.1-8B to
    Qwen3-8B-Q4_K_M-no_think: skills_hub, approval, mcp, title_generation,
    profile_describer. Rationale: GPU-resident, lower latency, json_schema OK.
  - web_extract and compression remain on Phi-3.5-mini (long scrapes).

VRAM: both Qwen3-8B variants co-reside with nomic-embed only (~10.4GB +
84MB). Cannot co-reside with Qwen3.8-27B (17.8GB); LRU eviction applies.

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

@@ -74,3 +74,30 @@
   loop_control:
     loop_var: staged_model
   tags: [models]
+
+# --- Chat template overrides ---------------------------------------------------
+# Deploy per-model chat template files used by llama-server via chat-template-file.
+# These are static files dropped into {{ llm_models_dir }}/templates/.
+# t_664289a0: qwen3-no-think.jinja — Qwen3 template with enable_thinking=false
+#   hardcoded. Used by [Qwen3-8B-Q4_K_M-no_think] in the router preset INI and
+#   the llama-swap config. The companion [Qwen3-8B-Q4_K_M] section uses the GGUF's
+#   baked-in template (thinking ON by default).
+- name: Ensure chat template directory exists at {{ llm_models_dir }}/templates
+  ansible.builtin.file:
+    path: "{{ llm_models_dir }}/templates"
+    state: directory
+    owner: "{{ llm_service_user }}"
+    group: "{{ llm_service_user }}"
+    mode: "0755"
+  become: true
+  tags: [models, chat_templates]
+
+- name: Deploy qwen3-no-think.jinja (thinking=false hard-switch for Qwen3-8B no_think variant)
+  ansible.builtin.template:
+    src: qwen3-no-think.jinja.j2
+    dest: "{{ llm_models_dir }}/templates/qwen3-no-think.jinja"
+    owner: "{{ llm_service_user }}"
+    group: "{{ llm_service_user }}"
+    mode: "0644"
+  become: true
+  tags: [models, chat_templates]