diff --git a/server-rs/crates/platform-image/src/image_provider/runtime/executor.rs b/server-rs/crates/platform-image/src/image_provider/runtime/executor.rs
index c6508dd7b..22e35dc90 100644
--- a/server-rs/crates/platform-image/src/image_provider/runtime/executor.rs
+++ b/server-rs/crates/platform-image/src/image_provider/runtime/executor.rs
@@ -12,7 +12,7 @@ use crate::image_provider::{
     constants::{
         GPT_IMAGE_2_5_EDIT_MODEL, GPT_IMAGE_2_5_GENERATION_MODEL, GPT_IMAGE_2_C_MODEL,
         GPT_IMAGE_2_MODEL, VECTOR_ENGINE_IMAGE_EDIT_MAX_REFERENCE_IMAGES,
-        VECTOR_ENGINE_NANOBANANA_MAX_REFERENCE_IMAGES, VECTOR_ENGINE_PROVIDER,
+        VECTOR_ENGINE_NANOBANANA_MAX_REFERENCE_IMAGES,
     },
     curl_transport::{
         map_curl_error, send_image_json_request_with_curl,
@@ -143,6 +143,7 @@ pub async fn create_image_generation_with_model(
                     attempt,
                 ) {
                     if retry_image_upstream_status_after_delay(
+                        settings.provider,
                         "generation",
                         request_url.as_str(),
                         attempt,
@@ -165,6 +166,7 @@ pub async fn create_image_generation_with_model(
             Err(error) => {
                 if should_retry_image_curl_send_error(&error, attempt) {
                     if retry_image_send_after_delay(
+                        settings.provider,
                         "generation",
                         request_url.as_str(),
                         "request_send",
@@ -205,7 +207,7 @@ pub async fn create_image_generation_with_model(
         };
         let response_status = response.status;
         tracing::info!(
-            provider = VECTOR_ENGINE_PROVIDER,
+            provider = settings.provider.as_str(),
             endpoint = %request_url,
             status = response_status,
             image_model = upstream_model,
@@ -271,7 +273,7 @@ pub async fn create_nanobanana_generate_content(
     })?;
     if reference_images.len() > VECTOR_ENGINE_NANOBANANA_MAX_REFERENCE_IMAGES {
         return Err(PlatformImageError::InvalidRequest {
-            provider: VECTOR_ENGINE_PROVIDER,
+            provider: settings.provider.as_str(),
             message: format!(
                 "{failure_context}：参考图最多允许 {VECTOR_ENGINE_NANOBANANA_MAX_REFERENCE_IMAGES} 张，当前提交 {} 张。",
                 reference_images.len()
@@ -334,6 +336,7 @@ pub async fn create_nanobanana_generate_content(
                     attempt,
                 ) {
                     if retry_image_upstream_status_after_delay(
+                        ImageProvider::VectorEngine,
                         "nanobanana_generate_content",
                         request_url.as_str(),
                         attempt,
@@ -356,6 +359,7 @@ pub async fn create_nanobanana_generate_content(
             Err(error) => {
                 if should_retry_image_curl_send_error(&error, attempt) {
                     if retry_image_send_after_delay(
+                        ImageProvider::VectorEngine,
                         "nanobanana_generate_content",
                         request_url.as_str(),
                         "request_send",
@@ -394,7 +398,7 @@ pub async fn create_nanobanana_generate_content(
     };
     let response_status = response.status;
     tracing::info!(
-        provider = VECTOR_ENGINE_PROVIDER,
+        provider = settings.provider.as_str(),
         endpoint = %request_url,
         status = response_status,
         image_model = model,
@@ -495,13 +499,13 @@ pub async fn create_image_edit_with_references_and_model(
     })?;
     if reference_images.is_empty() {
         return Err(PlatformImageError::InvalidRequest {
-            provider: VECTOR_ENGINE_PROVIDER,
+            provider: settings.provider.as_str(),
             message: format!("{failure_context}：缺少参考图，图片编辑需要至少一张参考图。"),
         });
     }
     if reference_images.len() > VECTOR_ENGINE_IMAGE_EDIT_MAX_REFERENCE_IMAGES {
         return Err(PlatformImageError::InvalidRequest {
-            provider: VECTOR_ENGINE_PROVIDER,
+            provider: settings.provider.as_str(),
             message: format!(
                 "{failure_context}：参考图最多允许 {VECTOR_ENGINE_IMAGE_EDIT_MAX_REFERENCE_IMAGES} 张，当前提交 {} 张。",
                 reference_images.len()
@@ -529,7 +533,7 @@ pub async fn create_image_edit_with_references_and_model(
             reference_images,
         );
         tracing::info!(
-            provider = VECTOR_ENGINE_PROVIDER,
+            provider = settings.provider.as_str(),
             endpoint = %request_url,
             image_model = upstream_model,
             requested_image_model = requested_model,
@@ -586,6 +590,7 @@ pub async fn create_image_edit_with_references_and_model(
                     attempt,
                 ) {
                     if retry_image_upstream_status_after_delay(
+                        settings.provider,
                         "edit",
                         request_url.as_str(),
                         attempt,
@@ -608,6 +613,7 @@ pub async fn create_image_edit_with_references_and_model(
             Err(error) => {
                 if should_retry_image_curl_send_error(&error, attempt) {
                     if retry_image_send_after_delay(
+                        settings.provider,
                         "edit",
                         request_url.as_str(),
                         "request_send",
@@ -648,7 +654,7 @@ pub async fn create_image_edit_with_references_and_model(
         };
         let response_status = response.status;
         tracing::info!(
-            provider = VECTOR_ENGINE_PROVIDER,
+            provider = settings.provider.as_str(),
             endpoint = %request_url,
             status = response_status,
             image_model = upstream_model,
@@ -760,6 +766,7 @@ fn should_retry_image_upstream_response(status: u16, raw_body: &str, attempt: u3
 }
 
 async fn retry_image_send_after_delay(
+    provider: ImageProvider,
     request_kind: &'static str,
     request_url: &str,
     failure_stage: &'static str,
@@ -775,11 +782,12 @@ async fn retry_image_send_after_delay(
     request_params: Option<&serde_json::Value>,
     request_deadline: Option<Instant>,
 ) -> bool {
+    let provider_label = provider.as_str();
     let delay_ms =
         image_provider_send_retry_delay_ms(attempt, image_provider_send_retry_jitter_ms());
     if !retry_delay_fits_request_deadline(request_deadline, delay_ms) {
         tracing::warn!(
-            provider = VECTOR_ENGINE_PROVIDER,
+            provider = provider_label,
             endpoint = %request_url,
             request_kind,
             failure_stage = "request_budget",
@@ -800,7 +808,7 @@ async fn retry_image_send_after_delay(
         return false;
     }
     tracing::warn!(
-        provider = VECTOR_ENGINE_PROVIDER,
+        provider = provider_label,
         endpoint = %request_url,
         request_kind,
         failure_stage,
@@ -826,6 +834,7 @@ async fn retry_image_send_after_delay(
 }
 
 async fn retry_image_upstream_status_after_delay(
+    provider: ImageProvider,
     request_kind: &'static str,
     request_url: &str,
     attempt: u32,
@@ -837,11 +846,12 @@ async fn retry_image_upstream_status_after_delay(
     request_params: Option<&serde_json::Value>,
     request_deadline: Option<Instant>,
 ) -> bool {
+    let provider_label = provider.as_str();
     let delay_ms =
         image_provider_send_retry_delay_ms(attempt, image_provider_send_retry_jitter_ms());
     if !retry_delay_fits_request_deadline(request_deadline, delay_ms) {
         tracing::warn!(
-            provider = VECTOR_ENGINE_PROVIDER,
+            provider = provider_label,
             endpoint = %request_url,
             request_kind,
             failure_stage = "request_budget",
@@ -858,7 +868,7 @@ async fn retry_image_upstream_status_after_delay(
         return false;
     }
     tracing::warn!(
-        provider = VECTOR_ENGINE_PROVIDER,
+        provider = provider_label,
         endpoint = %request_url,
         request_kind,
         failure_stage = "upstream_status",