From 75cb93f25c3e18971e561b1d8538a3845dfe6f00 Mon Sep 17 00:00:00 2001
From: Hermes Agent service account
 <hermes@carousel-of-progress.local.mk-labs.cloud>
Date: Thu, 6 Aug 2026 09:10:06 -0500
Subject: [PATCH] llm-inference-multimodel: enable Qwen2.5-14B shadow instance
 (port 8002) for shadow-test window

Mistral (llama-server-toolcall, 8001) stopped temporarily on astro-orbiter to
free ~6.2GB VRAM headroom for this test window per Ryan/JARVIS approval.
Not a permanent decommission of Mistral.
---
 ansible/roles/llm-inference-multimodel/defaults/main.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ansible/roles/llm-inference-multimodel/defaults/main.yml b/ansible/roles/llm-inference-multimodel/defaults/main.yml
index 377659c..74ef9e8 100644
--- a/ansible/roles/llm-inference-multimodel/defaults/main.yml
+++ b/ansible/roles/llm-inference-multimodel/defaults/main.yml
@@ -71,7 +71,7 @@ llm_toolcall_model_id: mistral-small-24b-instruct-2501
 # (either free VRAM by stopping llama-server-toolcall for the shadow window,
 # or reduce ctx-size). llm_qwen_service_enabled defaults to false so a normal
 # playbook run will template the unit but NOT start it.
-llm_qwen_service_enabled: false
+llm_qwen_service_enabled: true
 llm_qwen_port: 8002
 llm_qwen_model_path: "{{ llm_models_dir }}/Qwen2.5-14B-Instruct-Q5_K_M.gguf"
 llm_qwen_model_url: "https://huggingface.co/bartowski/Qwen2.5-14B-Instruct-GGUF/resolve/main/Qwen2.5-14B-Instruct-Q5_K_M.gguf"