1417 completion timeout (#2374)

* Refactor handleDefaultStreamResponseV2 function for better error handling

* run yarn lint

* small error handling changes

* update error handling flow and scope of vars

* add back space

---------

Co-authored-by: Roman <rrojaski@gmail.com>

server/utils/helpers/chat/responses.js

@@ -22,41 +22,55 @@ function handleDefaultStreamResponseV2(response, stream, responseProps) {
     const handleAbort = () => clientAbortedHandler(resolve, fullText);
     response.on("close", handleAbort);
 
-    for await (const chunk of stream) {
-      const message = chunk?.choices?.[0];
-      const token = message?.delta?.content;
-
-      if (token) {
-        fullText += token;
-        writeResponseChunk(response, {
-          uuid,
-          sources: [],
-          type: "textResponseChunk",
-          textResponse: token,
-          close: false,
-          error: false,
-        });
-      }
-
-      // LocalAi returns '' and others return null on chunks - the last chunk is not "" or null.
-      // Either way, the key `finish_reason` must be present to determine ending chunk.
-      if (
-        message?.hasOwnProperty("finish_reason") && // Got valid message and it is an object with finish_reason
-        message.finish_reason !== "" &&
-        message.finish_reason !== null
-      ) {
-        writeResponseChunk(response, {
-          uuid,
-          sources,
-          type: "textResponseChunk",
-          textResponse: "",
-          close: true,
-          error: false,
-        });
-        response.removeListener("close", handleAbort);
-        resolve(fullText);
-        break; // Break streaming when a valid finish_reason is first encountered
+    // Now handle the chunks from the streamed response and append to fullText.
+    try {
+      for await (const chunk of stream) {
+        const message = chunk?.choices?.[0];
+        const token = message?.delta?.content;
+
+        if (token) {
+          fullText += token;
+          writeResponseChunk(response, {
+            uuid,
+            sources: [],
+            type: "textResponseChunk",
+            textResponse: token,
+            close: false,
+            error: false,
+          });
+        }
+
+        // LocalAi returns '' and others return null on chunks - the last chunk is not "" or null.
+        // Either way, the key `finish_reason` must be present to determine ending chunk.
+        if (
+          message?.hasOwnProperty("finish_reason") && // Got valid message and it is an object with finish_reason
+          message.finish_reason !== "" &&
+          message.finish_reason !== null
+        ) {
+          writeResponseChunk(response, {
+            uuid,
+            sources,
+            type: "textResponseChunk",
+            textResponse: "",
+            close: true,
+            error: false,
+          });
+          response.removeListener("close", handleAbort);
+          resolve(fullText);
+          break; // Break streaming when a valid finish_reason is first encountered
+        }
       }
+    } catch (e) {
+      console.log(`\x1b[43m\x1b[34m[STREAMING ERROR]\x1b[0m ${e.message}`);
+      writeResponseChunk(response, {
+        uuid,
+        type: "abort",
+        textResponse: null,
+        sources: [],
+        close: true,
+        error: e.message,
+      });
+      resolve(fullText); // Return what we currently have - if anything.
     }
   });
 }