fix: disable storage for Codex responses requests (#3192)

Co-authored-by: honor2030 <honor2030@users.noreply.github.com>

src/openhuman/inference/provider/compatible.rs

@@ -269,6 +269,7 @@ impl OpenAiCompatibleProvider {
             input,
             instructions,
             stream: Some(false),
+            store: Some(false),
         };
 
         let url = self.responses_url();

src/openhuman/inference/provider/compatible_tests.rs

@@ -1,7 +1,7 @@
 use super::*;
 use sentry::test::TestTransport;
 use std::sync::Arc;
-use wiremock::matchers::{method, path};
+use wiremock::matchers::{body_json, method, path};
 use wiremock::{Mock, MockServer, ResponseTemplate};
 
 fn make_provider(name: &str, url: &str, key: Option<&str>) -> OpenAiCompatibleProvider {
@@ -354,6 +354,15 @@ async fn responses_api_primary_posts_directly_to_responses() {
     let server = MockServer::start().await;
     Mock::given(method("POST"))
         .and(path("/backend-api/codex/responses"))
+        .and(body_json(serde_json::json!({
+            "model": "gpt-5.5",
+            "input": [{
+                "role": "user",
+                "content": [{"type": "input_text", "text": "hello"}]
+            }],
+            "stream": false,
+            "store": false
+        })))
         .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!({
             "output_text": "hello from responses",
             "output": []

src/openhuman/inference/provider/compatible_types.rs

@@ -93,6 +93,8 @@ pub(crate) struct ResponsesRequest {
     pub(crate) instructions: Option<String>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub(crate) stream: Option<bool>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub(crate) store: Option<bool>,
 }
 
 #[derive(Debug, Serialize)]