diff --git a/.dockerignore b/.dockerignore
index a88c7d61641..95ed9e268e4 100644
--- a/.dockerignore
+++ b/.dockerignore
@@ -63,7 +63,7 @@ dist
 
 # Gatsby files
 .cache/
-public
+
 
 # Vuepress build output
 .vuepress/dist
diff --git a/.env.template b/.env.template
index 166cc4ef4e4..d53c1be6caa 100644
--- a/.env.template
+++ b/.env.template
@@ -2,7 +2,7 @@
 # Your openai api key. (required)
 OPENAI_API_KEY=sk-xxxx
 
-# Access passsword, separated by comma. (optional)
+# Access password, separated by comma. (optional)
 CODE=your-password
 
 # You can start service behind a proxy
diff --git a/app/api/common.ts b/app/api/common.ts
index ca8406bb361..a75f2de5cfa 100644
--- a/app/api/common.ts
+++ b/app/api/common.ts
@@ -43,10 +43,6 @@ export async function requestOpenai(req: NextRequest) {
 
   console.log("[Proxy] ", path);
   console.log("[Base Url]", baseUrl);
-  // this fix [Org ID] undefined in server side if not using custom point
-  if (serverConfig.openaiOrgId !== undefined) {
-    console.log("[Org ID]", serverConfig.openaiOrgId);
-  }
 
   const timeoutId = setTimeout(
     () => {
@@ -116,18 +112,37 @@ export async function requestOpenai(req: NextRequest) {
   try {
     const res = await fetch(fetchUrl, fetchOptions);
 
+  // Extract the OpenAI-Organization header from the response
+  const openaiOrganizationHeader = res.headers.get("OpenAI-Organization");
+
+  // Check if serverConfig.openaiOrgId is defined and not an empty string
+  if (serverConfig.openaiOrgId && serverConfig.openaiOrgId.trim() !== "") {
+    // If openaiOrganizationHeader is present, log it; otherwise, log that the header is not present
+    console.log("[Org ID]", openaiOrganizationHeader);
+  } else {
+    console.log("[Org ID] is not set up.");
+  }
+
     // to prevent browser prompt for credentials
     const newHeaders = new Headers(res.headers);
     newHeaders.delete("www-authenticate");
     // to disable nginx buffering
     newHeaders.set("X-Accel-Buffering", "no");
 
+
+    // Conditionally delete the OpenAI-Organization header from the response if [Org ID] is undefined or empty (not setup in ENV)
+    // Also, this is to prevent the header from being sent to the client
+    if (!serverConfig.openaiOrgId || serverConfig.openaiOrgId.trim() === "") {
+      newHeaders.delete("OpenAI-Organization");
+    }
+
     // The latest version of the OpenAI API forced the content-encoding to be "br" in json response
     // So if the streaming is disabled, we need to remove the content-encoding header
     // Because Vercel uses gzip to compress the response, if we don't remove the content-encoding header
     // The browser will try to decode the response with brotli and fail
     newHeaders.delete("content-encoding");
 
+
     return new Response(res.body, {
       status: res.status,
       statusText: res.statusText,
diff --git a/app/client/platforms/openai.ts b/app/client/platforms/openai.ts
index 78e628ad771..408ee704e1c 100644
--- a/app/client/platforms/openai.ts
+++ b/app/client/platforms/openai.ts
@@ -228,19 +228,21 @@ export class ChatGPTApi implements LLMApi {
             }
             const text = msg.data;
             try {
-              const json = JSON.parse(text) as {
-                choices: Array<{
-                  delta: {
-                    content: string;
-                  };
-                }>;
-              };
-              const delta = json.choices[0]?.delta?.content;
+              const json = JSON.parse(text);
+              const choices = json.choices as Array<{ delta: { content: string } }>;
+              const delta = choices[0]?.delta?.content;
+              const textmoderation = json?.prompt_filter_results;
+
               if (delta) {
                 remainText += delta;
               }
+
+              if (textmoderation && textmoderation.length > 0 && ServiceProvider.Azure) {
+                const contentFilterResults = textmoderation[0]?.content_filter_results;
+                console.log(`[${ServiceProvider.Azure}] [Text Moderation] flagged categories result:`, contentFilterResults);
+              }
             } catch (e) {
-              console.error("[Request] parse error", text);
+              console.error("[Request] parse error", text, msg);
             }
           },
           onclose() {
diff --git a/app/components/message-selector.tsx b/app/components/message-selector.tsx
index 840e480cba7..8198a3cd4eb 100644
--- a/app/components/message-selector.tsx
+++ b/app/components/message-selector.tsx
@@ -227,7 +227,7 @@ export function MessageSelector(props: {
               </div>
 
               <div className={styles["checkbox"]}>
-                <input type="checkbox" checked={isSelected}></input>
+                <input type="checkbox" checked={isSelected} readOnly></input>
               </div>
             </div>
           );
diff --git a/app/store/chat.ts b/app/store/chat.ts
index f97d7d7255e..029c12a74be 100644
--- a/app/store/chat.ts
+++ b/app/store/chat.ts
@@ -557,6 +557,7 @@ export const useChatStore = createPersistStore(
             messages: topicMessages,
             config: {
               model: getSummarizeModel(session.mask.modelConfig.model),
+              stream: false,
             },
             onFinish(message) {
               get().updateCurrentSession(
@@ -600,6 +601,10 @@ export const useChatStore = createPersistStore(
           historyMsgLength > modelConfig.compressMessageLengthThreshold &&
           modelConfig.sendMemory
         ) {
+          /** Destruct max_tokens while summarizing
+           * this param is just shit
+           **/
+          const { max_tokens, ...modelcfg } = modelConfig;
           api.llm.chat({
             messages: toBeSummarizedMsgs.concat(
               createMessage({
@@ -609,7 +614,7 @@ export const useChatStore = createPersistStore(
               }),
             ),
             config: {
-              ...modelConfig,
+              ...modelcfg,
               stream: true,
               model: getSummarizeModel(session.mask.modelConfig.model),
             },