Reduce session logging and background churn

app/src/settings/ai.rs

@@ -1000,7 +1000,7 @@ pub enum OpenAIProviderKind {
 ///
 /// Multiple providers can be configured simultaneously. Each provider has its own endpoint,
 /// credentials, and model list.
-#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, schemars::JsonSchema)]
+#[derive(Clone, Serialize, Deserialize, PartialEq, schemars::JsonSchema)]
 #[schemars(description = "Configuration for a direct model provider endpoint.")]
 pub struct OpenAIProviderConfig {
     #[serde(default)]
@@ -1027,6 +1027,22 @@ pub struct OpenAIProviderConfig {
     pub models: Vec<OpenAIModelConfig>,
 }
 
+impl std::fmt::Debug for OpenAIProviderConfig {
+    fn fmt(&self, formatter: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        formatter
+            .debug_struct("OpenAIProviderConfig")
+            .field("kind", &self.kind)
+            .field("enabled", &self.enabled)
+            .field("name", &self.name)
+            .field("base_url", &self.base_url)
+            .field("api_key_configured", &self.api_key.is_some())
+            .field("project_id", &self.project_id)
+            .field("location", &self.location)
+            .field("models", &self.models)
+            .finish()
+    }
+}
+
 impl settings_value::SettingsValue for OpenAIProviderConfig {}
 
 fn default_acp_agent_id() -> String {

app/src/settings/ai_tests.rs

@@ -391,6 +391,9 @@ fn native_provider_settings_roundtrip_with_vertex_configuration() {
     }))
     .expect("Native OpenAI provider settings should deserialize");
     assert_eq!(native_openai.kind, OpenAIProviderKind::OpenAI);
+    let debug_output = format!("{native_openai:?}");
+    assert!(!debug_output.contains("sk-test"));
+    assert!(debug_output.contains("api_key_configured: true"));
 }
 
 #[test]