feat(llm): add sparse llm_advanced settings for Ollama tuning (T5.2)

src-tauri/src/models.rs

@@ -192,6 +192,10 @@ pub struct Settings {
     pub llm_provider: String, // ollama|custom|off
     pub llm_endpoint: String,
     pub llm_model: String,
+    /// Advanced Ollama tuning (T5.2): `{ system?, think?, keep_alive?, options: {…} }`.
+    /// Sparse — only user-overridden values are stored; `Null`/absent = all defaults.
+    #[serde(default)]
+    pub llm_advanced: serde_json::Value,
     pub preferred_backend: String, // auto|npu|nvidia|amd|intel|cpu
     pub whisper_model: String,     // ModelInfo.id, e.g. "base.en-q5_1"
     pub low_overhead: bool,