feat: 扩展 cache creation token 细分统计与 effective_input_tokens 计费逻辑

- 新增 cache_creation_ephemeral_5m/1h_input_tokens 字段，区分不同 TTL 的缓存写入 token
- 引入 effective_input_tokens（扣除 cache read 后的有效输入 token），暴露给 usage 接口
- billing 规则生成器支持 5m/1h ephemeral cache 独立定价与分级计费
- usage_mapper 增加 Claude/Anthropic 格式映射，修复 OpenAI responses 格式字段兼容性
- 迁移逻辑增强：支持 checksum 容错、applied/pending 数量日志、逐步执行信息输出
- executor 抽离 LocalExecutionRequestOutcome 类型，统一 sync/stream 路径返回语义
- provider-transport auth 层新增 complete passthrough headers 构建逻辑
- 前端 usage 类型全面补充 effective_input_tokens、cache_creation_tokens、total_input_context 字段

crates/aether-ai-pipeline/src/planner/standard/codex.rs

@@ -184,6 +184,7 @@ pub fn apply_codex_openai_cli_special_headers(
     if let Some(account_id) = extract_codex_account_id(decrypted_auth_config_raw) {
         provider_request_headers.insert("chatgpt-account-id".to_string(), account_id);
     }
+
     if !provider_request_headers
         .get("x-client-request-id")
         .map(|value| !value.trim().is_empty())
@@ -200,6 +201,7 @@ pub fn apply_codex_openai_cli_special_headers(
         .and_then(Value::as_str)
         .map(str::trim)
         .filter(|value| !value.is_empty());
+
     let Some(short_id) = prompt_cache_key.and_then(build_short_codex_header_id) else {
         return;
     };
@@ -213,6 +215,7 @@ pub fn apply_codex_openai_cli_special_headers(
         .eq_ignore_ascii_case("openai:compact")
         && !header_map_has_non_empty_value(original_headers, "conversation_id")
     {
-        provider_request_headers.insert("conversation_id".to_string(), short_id);
+        let session_id = provider_request_headers.get("session_id").unwrap();
+        provider_request_headers.insert("conversation_id".to_string(), session_id.clone());
     }
 }

crates/aether-ai-pipeline/src/planner/standard/normalize.rs

@@ -124,8 +124,18 @@ pub fn build_cross_format_openai_cli_request_body(
 
 #[cfg(test)]
 mod tests {
+    use super::build_local_openai_cli_request_body;
     use super::{build_cross_format_openai_cli_request_body, build_local_openai_chat_request_body};
-    use serde_json::json;
+    use serde_json::{json, Value};
+
+    fn object_keys(value: &Value) -> Vec<&str> {
+        value
+            .as_object()
+            .expect("json object")
+            .keys()
+            .map(String::as_str)
+            .collect()
+    }
 
     #[test]
     fn builds_openai_chat_cross_format_request_body_from_openai_cli_source() {
@@ -148,6 +158,29 @@ mod tests {
         assert_eq!(provider_request_body["messages"][0]["content"], "hello");
     }
 
+    #[test]
+    fn local_openai_cli_request_body_preserves_original_field_order() {
+        let body_json: Value = serde_json::from_str(
+            r#"{
+                "model": "gpt-5",
+                "include": ["reasoning.encrypted_content"],
+                "input": [],
+                "instructions": "Keep order"
+            }"#,
+        )
+        .expect("request json should parse");
+
+        let provider_request_body =
+            build_local_openai_cli_request_body(&body_json, "gpt-5-upstream", false)
+                .expect("openai cli body should build");
+
+        assert_eq!(
+            object_keys(&provider_request_body),
+            vec!["model", "include", "input", "instructions"]
+        );
+        assert_eq!(provider_request_body["model"], "gpt-5-upstream");
+    }
+
     #[test]
     fn builds_streaming_local_openai_chat_request_body_with_include_usage() {
         let body_json = json!({