fix(compact): 移除 OpenAI Compact 请求中不受支持的 store 参数

- 在 OpenAI Compact 请求规范化流程中剥离 `store`
- 将 compact 默认 body rules 与 Codex CLI 默认规则拆分
- 补充 same-format 和转换链路的 compact 回归测试

apps/aether-gateway/src/ai_pipeline/planner/standard/codex/tests.rs

@@ -26,7 +26,7 @@ fn applies_codex_defaults_when_body_rules_do_not_handle_fields() {
 }
 
 #[test]
-fn defers_to_user_body_rules_for_handled_fields() {
+fn strips_store_for_compact_even_when_body_rules_handle_it() {
     let body_rules = json!([
         {"action":"set","path":"store","value":true},
         {"action":"set","path":"instructions","value":"Keep custom"},
@@ -51,7 +51,7 @@ fn defers_to_user_body_rules_for_handled_fields() {
     );
 
     assert!(body.get("max_output_tokens").is_none());
-    assert_eq!(body["store"], true);
+    assert!(body.get("store").is_none());
     assert_eq!(body["instructions"], "Keep custom");
     assert_eq!(body["metadata"]["mode"], "custom");
     assert_eq!(body["top_p"], 0.5);

apps/aether-gateway/src/ai_pipeline/planner/standard/mod.rs

@@ -267,4 +267,32 @@ mod tests {
         assert_eq!(converted["store"], false);
         assert_eq!(converted["instructions"], "You are GPT-5.");
     }
+
+    #[test]
+    fn strips_store_for_openai_compact_requests() {
+        let request = json!({
+            "model": "gpt-5",
+            "messages": [{
+                "role": "user",
+                "content": "Hello from OpenAI Chat"
+            }],
+            "store": true
+        });
+
+        let converted = build_standard_request_body(
+            &request,
+            "openai:chat",
+            "gpt-5",
+            "openai",
+            "openai:compact",
+            "/v1/chat/completions",
+            false,
+            None,
+            None,
+        )
+        .expect("openai chat should convert to openai compact");
+
+        assert_eq!(converted["model"], "gpt-5");
+        assert!(converted.get("store").is_none());
+    }
 }

apps/aether-gateway/src/ai_pipeline/planner/standard/normalize/chat.rs

@@ -1,6 +1,5 @@
 use serde_json::Value;
 
-use super::super::codex::apply_codex_openai_cli_special_body_edits;
 use crate::ai_pipeline::conversion::{request_conversion_kind, RequestConversionKind};
 use crate::ai_pipeline::transport::apply_local_body_rules;
 use crate::ai_pipeline::transport::url::{
@@ -8,6 +7,7 @@ use crate::ai_pipeline::transport::url::{
     build_openai_cli_url, build_passthrough_path_url,
 };
 use crate::ai_pipeline::{
+    apply_codex_openai_cli_special_body_edits, apply_openai_compact_special_body_edits,
     build_cross_format_openai_chat_request_body as pipeline_build_cross_format_openai_chat_request_body,
     build_local_openai_chat_request_body as pipeline_build_local_openai_chat_request_body,
     GatewayProviderTransportSnapshot,
@@ -74,6 +74,7 @@ pub(crate) fn build_cross_format_openai_chat_request_body(
         body_rules,
         user_api_key_id,
     );
+    apply_openai_compact_special_body_edits(&mut provider_request_body, provider_api_format);
     Some(provider_request_body)
 }
 

apps/aether-gateway/src/ai_pipeline/planner/standard/normalize/cli.rs

@@ -3,7 +3,6 @@ use std::collections::BTreeMap;
 use serde_json::Value;
 use url::form_urlencoded;
 
-use super::super::codex::apply_codex_openai_cli_special_body_edits;
 use crate::ai_pipeline::conversion::{request_conversion_kind, RequestConversionKind};
 use crate::ai_pipeline::transport::antigravity::{
     build_antigravity_v1internal_url, AntigravityRequestUrlAction,
@@ -14,6 +13,7 @@ use crate::ai_pipeline::transport::url::{
     build_openai_cli_url, build_passthrough_path_url,
 };
 use crate::ai_pipeline::{
+    apply_codex_openai_cli_special_body_edits, apply_openai_compact_special_body_edits,
     build_cross_format_openai_cli_request_body as pipeline_build_cross_format_openai_cli_request_body,
     build_local_openai_cli_request_body as pipeline_build_local_openai_cli_request_body,
     GatewayProviderTransportSnapshot,
@@ -40,6 +40,7 @@ pub(crate) fn build_local_openai_cli_request_body(
         body_rules,
         user_api_key_id,
     );
+    apply_openai_compact_special_body_edits(&mut provider_request_body, provider_api_format);
     Some(provider_request_body)
 }
 
@@ -70,6 +71,7 @@ pub(crate) fn build_cross_format_openai_cli_request_body(
         body_rules,
         user_api_key_id,
     );
+    apply_openai_compact_special_body_edits(&mut provider_request_body, provider_api_format);
     Some(provider_request_body)
 }
 

apps/aether-gateway/src/ai_pipeline/planner/standard/normalize/tests.rs

@@ -81,6 +81,28 @@ fn local_openai_cli_wrapper_preserves_body_order_after_edits() {
     );
 }
 
+#[test]
+fn local_openai_compact_wrapper_strips_store_for_same_format_requests() {
+    let body_json = json!({
+        "model": "gpt-5.4",
+        "input": [],
+        "store": true
+    });
+
+    let provider_request_body = build_local_openai_cli_request_body(
+        &body_json,
+        "gpt-5.4",
+        false,
+        "openai",
+        "openai:compact",
+        None,
+        None,
+    )
+    .expect("local openai compact body should build");
+
+    assert!(provider_request_body.get("store").is_none());
+}
+
 #[test]
 fn strips_metadata_for_codex_openai_cli_requests() {
     let body_json = json!({

apps/aether-gateway/src/ai_pipeline/pure/mod.rs

@@ -3,15 +3,15 @@ pub(crate) use aether_ai_pipeline::api::{
     aggregate_openai_chat_stream_sync_response, aggregate_openai_cli_stream_sync_response,
     aggregate_standard_chat_stream_sync_response, aggregate_standard_cli_stream_sync_response,
     apply_codex_openai_cli_special_body_edits, apply_codex_openai_cli_special_headers,
-    augment_sync_report_context, build_core_error_body_for_client_format,
-    build_cross_format_openai_chat_request_body, build_cross_format_openai_cli_request_body,
-    build_generated_tool_call_id, build_kiro_final_message_sse_events,
-    build_kiro_initial_sse_events, build_kiro_stream_error_sse_events,
-    build_local_openai_chat_request_body, build_local_openai_cli_request_body,
-    build_local_success_background_report, build_local_success_conversion_background_report,
-    build_openai_cli_response, build_standard_request_body,
-    build_standard_request_body_from_canonical, build_standard_upstream_url,
-    calculate_kiro_context_input_tokens, canonicalize_tool_arguments,
+    apply_openai_compact_special_body_edits, augment_sync_report_context,
+    build_core_error_body_for_client_format, build_cross_format_openai_chat_request_body,
+    build_cross_format_openai_cli_request_body, build_generated_tool_call_id,
+    build_kiro_final_message_sse_events, build_kiro_initial_sse_events,
+    build_kiro_stream_error_sse_events, build_local_openai_chat_request_body,
+    build_local_openai_cli_request_body, build_local_success_background_report,
+    build_local_success_conversion_background_report, build_openai_cli_response,
+    build_standard_request_body, build_standard_request_body_from_canonical,
+    build_standard_upstream_url, calculate_kiro_context_input_tokens, canonicalize_tool_arguments,
     convert_claude_chat_response_to_openai_chat, convert_claude_cli_response_to_openai_cli,
     convert_gemini_chat_response_to_openai_chat, convert_gemini_cli_response_to_openai_cli,
     convert_openai_chat_request_to_claude_request, convert_openai_chat_request_to_gemini_request,