ai: unload llama's model from the engine row

The llama.cpp row offers Unload while a model is loaded. It posts to the
router's /models/unload, which frees the VRAM and leaves llama-server up,
so its web UI stays available; the engines themselves are still never
stopped from here. The answer is not read: the next poll shows the row
without a model, or with it if the unload failed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

1 files changed, 7 insertions, 0 deletions

diff --git a/desktop/modules/ai/AiModule.qml b/desktop/modules/ai/AiModule.qml
index 6df3d6b..d58ebfe 100644
--- a/desktop/modules/ai/AiModule.qml
+++ b/desktop/modules/ai/AiModule.qml
@@ -85,6 +85,13 @@ Module {
         exec(["sh", "-c", 'pkill -TERM -P "$1"; kill -TERM "$1"', "sh", app.detail]);
     }
 
+    // The router frees the model's VRAM; the next request for it loads it
+    // again. Its answer is not read, the next poll shows whether it worked.
+    function unload(model) {
+        exec(["curl", "-s", "-m", "30", "-X", "POST", "-H", "Content-Type: application/json",
+              "-d", JSON.stringify({ model: model }), "http://127.0.0.1:8181/models/unload"]);
+    }
+
     // Detached, so a start outlives a quickshell reload. No exit code comes
     // back; the next poll shows whether it worked.
     function exec(cmd) {