Merge pull request #5759 from ConnectAI-E/feature/onfinish

Feature/onfinish

app/client/api.ts

@@ -70,7 +70,7 @@ export interface ChatOptions {
   config: LLMConfig;
 
   onUpdate?: (message: string, chunk: string) => void;
-  onFinish: (message: string) => void;
+  onFinish: (message: string, responseRes: Response) => void;
   onError?: (err: Error) => void;
   onController?: (controller: AbortController) => void;
   onBeforeTool?: (tool: ChatMessageTool) => void;

app/client/platforms/alibaba.ts

@@ -143,6 +143,7 @@ export class QwenApi implements LLMApi {
         let responseText = "";
         let remainText = "";
         let finished = false;
+        let responseRes: Response;
 
         // animate response to make it looks smooth
         function animateResponseText() {
@@ -172,7 +173,7 @@ export class QwenApi implements LLMApi {
         const finish = () => {
           if (!finished) {
             finished = true;
-            options.onFinish(responseText + remainText);
+            options.onFinish(responseText + remainText, responseRes);
           }
         };
 
@@ -188,6 +189,7 @@ export class QwenApi implements LLMApi {
               "[Alibaba] request response content type: ",
               contentType,
             );
+            responseRes = res;
 
             if (contentType?.startsWith("text/plain")) {
               responseText = await res.clone().text();
@@ -254,7 +256,7 @@ export class QwenApi implements LLMApi {
 
         const resJson = await res.json();
         const message = this.extractMessage(resJson);
-        options.onFinish(message);
+        options.onFinish(message, res);
       }
     } catch (e) {
       console.log("[Request] failed to make a chat request", e);

app/client/platforms/anthropic.ts

@@ -317,13 +317,14 @@ export class ClaudeApi implements LLMApi {
       };
 
       try {
-        controller.signal.onabort = () => options.onFinish("");
+        controller.signal.onabort = () =>
+          options.onFinish("", new Response(null, { status: 400 }));
 
         const res = await fetch(path, payload);
         const resJson = await res.json();
 
         const message = this.extractMessage(resJson);
-        options.onFinish(message);
+        options.onFinish(message, res);
       } catch (e) {
         console.error("failed to chat", e);
         options.onError?.(e as Error);

app/client/platforms/baidu.ts

@@ -162,6 +162,7 @@ export class ErnieApi implements LLMApi {
         let responseText = "";
         let remainText = "";
         let finished = false;
+        let responseRes: Response;
 
         // animate response to make it looks smooth
         function animateResponseText() {
@@ -191,7 +192,7 @@ export class ErnieApi implements LLMApi {
         const finish = () => {
           if (!finished) {
             finished = true;
-            options.onFinish(responseText + remainText);
+            options.onFinish(responseText + remainText, responseRes);
           }
         };
 
@@ -204,7 +205,7 @@ export class ErnieApi implements LLMApi {
             clearTimeout(requestTimeoutId);
             const contentType = res.headers.get("content-type");
             console.log("[Baidu] request response content type: ", contentType);
-
+            responseRes = res;
             if (contentType?.startsWith("text/plain")) {
               responseText = await res.clone().text();
               return finish();
@@ -267,7 +268,7 @@ export class ErnieApi implements LLMApi {
 
         const resJson = await res.json();
         const message = resJson?.result;
-        options.onFinish(message);
+        options.onFinish(message, res);
       }
     } catch (e) {
       console.log("[Request] failed to make a chat request", e);

app/client/platforms/bytedance.ts

@@ -130,6 +130,7 @@ export class DoubaoApi implements LLMApi {
         let responseText = "";
         let remainText = "";
         let finished = false;
+        let responseRes: Response;
 
         // animate response to make it looks smooth
         function animateResponseText() {
@@ -159,7 +160,7 @@ export class DoubaoApi implements LLMApi {
         const finish = () => {
           if (!finished) {
             finished = true;
-            options.onFinish(responseText + remainText);
+            options.onFinish(responseText + remainText, responseRes);
           }
         };
 
@@ -175,7 +176,7 @@ export class DoubaoApi implements LLMApi {
               "[ByteDance] request response content type: ",
               contentType,
             );
-
+            responseRes = res;
             if (contentType?.startsWith("text/plain")) {
               responseText = await res.clone().text();
               return finish();
@@ -241,7 +242,7 @@ export class DoubaoApi implements LLMApi {
 
         const resJson = await res.json();
         const message = this.extractMessage(resJson);
-        options.onFinish(message);
+        options.onFinish(message, res);
       }
     } catch (e) {
       console.log("[Request] failed to make a chat request", e);

app/client/platforms/glm.ts

@@ -177,7 +177,7 @@ export class ChatGLMApi implements LLMApi {
 
         const resJson = await res.json();
         const message = this.extractMessage(resJson);
-        options.onFinish(message);
+        options.onFinish(message, res);
       }
     } catch (e) {
       console.log("[Request] failed to make a chat request", e);

app/client/platforms/google.ts

@@ -274,7 +274,7 @@ export class GeminiProApi implements LLMApi {
           );
         }
         const message = apiClient.extractMessage(resJson);
-        options.onFinish(message);
+        options.onFinish(message, res);
       }
     } catch (e) {
       console.log("[Request] failed to make a chat request", e);

app/client/platforms/iflytek.ts

@@ -117,6 +117,7 @@ export class SparkApi implements LLMApi {
         let responseText = "";
         let remainText = "";
         let finished = false;
+        let responseRes: Response;
 
         // Animate response text to make it look smooth
         function animateResponseText() {
@@ -143,7 +144,7 @@ export class SparkApi implements LLMApi {
         const finish = () => {
           if (!finished) {
             finished = true;
-            options.onFinish(responseText + remainText);
+            options.onFinish(responseText + remainText, responseRes);
           }
         };
 
@@ -156,7 +157,7 @@ export class SparkApi implements LLMApi {
             clearTimeout(requestTimeoutId);
             const contentType = res.headers.get("content-type");
             console.log("[Spark] request response content type: ", contentType);
-
+            responseRes = res;
             if (contentType?.startsWith("text/plain")) {
               responseText = await res.clone().text();
               return finish();
@@ -231,7 +232,7 @@ export class SparkApi implements LLMApi {
 
         const resJson = await res.json();
         const message = this.extractMessage(resJson);
-        options.onFinish(message);
+        options.onFinish(message, res);
       }
     } catch (e) {
       console.log("[Request] failed to make a chat request", e);

app/client/platforms/moonshot.ts

@@ -180,7 +180,7 @@ export class MoonshotApi implements LLMApi {
 
         const resJson = await res.json();
         const message = this.extractMessage(resJson);
-        options.onFinish(message);
+        options.onFinish(message, res);
       }
     } catch (e) {
       console.log("[Request] failed to make a chat request", e);

app/client/platforms/openai.ts

@@ -361,7 +361,7 @@ export class ChatGPTApi implements LLMApi {
 
         const resJson = await res.json();
         const message = await this.extractMessage(resJson);
-        options.onFinish(message);
+        options.onFinish(message, res);
       }
     } catch (e) {
       console.log("[Request] failed to make a chat request", e);

app/client/platforms/tencent.ts

@@ -142,6 +142,7 @@ export class HunyuanApi implements LLMApi {
         let responseText = "";
         let remainText = "";
         let finished = false;
+        let responseRes: Response;
 
         // animate response to make it looks smooth
         function animateResponseText() {
@@ -171,7 +172,7 @@ export class HunyuanApi implements LLMApi {
         const finish = () => {
           if (!finished) {
             finished = true;
-            options.onFinish(responseText + remainText);
+            options.onFinish(responseText + remainText, responseRes);
           }
         };
 
@@ -187,7 +188,7 @@ export class HunyuanApi implements LLMApi {
               "[Tencent] request response content type: ",
               contentType,
             );
-
+            responseRes = res;
             if (contentType?.startsWith("text/plain")) {
               responseText = await res.clone().text();
               return finish();
@@ -253,7 +254,7 @@ export class HunyuanApi implements LLMApi {
 
         const resJson = await res.json();
         const message = this.extractMessage(resJson);
-        options.onFinish(message);
+        options.onFinish(message, res);
       }
     } catch (e) {
       console.log("[Request] failed to make a chat request", e);

app/client/platforms/xai.ts

@@ -173,7 +173,7 @@ export class XAIApi implements LLMApi {
 
         const resJson = await res.json();
         const message = this.extractMessage(resJson);
-        options.onFinish(message);
+        options.onFinish(message, res);
       }
     } catch (e) {
       console.log("[Request] failed to make a chat request", e);

app/store/chat.ts

@@ -649,13 +649,14 @@ export const useChatStore = createPersistStore(
               stream: false,
               providerName,
             },
-            onFinish(message) {
-              if (!isValidMessage(message)) return;
-              get().updateCurrentSession(
-                (session) =>
-                  (session.topic =
-                    message.length > 0 ? trimTopic(message) : DEFAULT_TOPIC),
-              );
+            onFinish(message, responseRes) {
+              if (responseRes?.status === 200) {
+                get().updateCurrentSession(
+                  (session) =>
+                    (session.topic =
+                      message.length > 0 ? trimTopic(message) : DEFAULT_TOPIC),
+                );
+              }
             },
           });
         }
@@ -669,7 +670,7 @@ export const useChatStore = createPersistStore(
 
         const historyMsgLength = countMessages(toBeSummarizedMsgs);
 
-        if (historyMsgLength > modelConfig?.max_tokens ?? 4000) {
+        if (historyMsgLength > (modelConfig?.max_tokens || 4000)) {
           const n = toBeSummarizedMsgs.length;
           toBeSummarizedMsgs = toBeSummarizedMsgs.slice(
             Math.max(0, n - modelConfig.historyMessageCount),
@@ -715,22 +716,20 @@ export const useChatStore = createPersistStore(
             onUpdate(message) {
               session.memoryPrompt = message;
             },
-            onFinish(message) {
-              console.log("[Memory] ", message);
-              get().updateCurrentSession((session) => {
-                session.lastSummarizeIndex = lastSummarizeIndex;
-                session.memoryPrompt = message; // Update the memory prompt for stored it in local storage
-              });
+            onFinish(message, responseRes) {
+              if (responseRes?.status === 200) {
+                console.log("[Memory] ", message);
+                get().updateCurrentSession((session) => {
+                  session.lastSummarizeIndex = lastSummarizeIndex;
+                  session.memoryPrompt = message; // Update the memory prompt for stored it in local storage
+                });
+              }
             },
             onError(err) {
               console.error("[Summarize] ", err);
             },
           });
         }
-
-        function isValidMessage(message: any): boolean {
-          return typeof message === "string" && !message.startsWith("```json");
-        }
       },
 
       updateStat(message: ChatMessage) {

app/utils.ts

@@ -266,7 +266,9 @@ export function isVisionModel(model: string) {
     model.includes("gpt-4-turbo") && !model.includes("preview");
 
   return (
-    visionKeywords.some((keyword) => model.includes(keyword)) || isGpt4Turbo
+    visionKeywords.some((keyword) => model.includes(keyword)) ||
+    isGpt4Turbo ||
+    isDalle3(model)
   );
 }
 

app/utils/chat.ts

@@ -174,6 +174,7 @@ export function stream(
   let finished = false;
   let running = false;
   let runTools: any[] = [];
+  let responseRes: Response;
 
   // animate response to make it looks smooth
   function animateResponseText() {
@@ -272,7 +273,7 @@ export function stream(
       }
       console.debug("[ChatAPI] end");
       finished = true;
-      options.onFinish(responseText + remainText);
+      options.onFinish(responseText + remainText, responseRes); // 将res传递给onFinish
     }
   };
 
@@ -304,6 +305,7 @@ export function stream(
         clearTimeout(requestTimeoutId);
         const contentType = res.headers.get("content-type");
         console.log("[Request] response content type: ", contentType);
+        responseRes = res;
 
         if (contentType?.startsWith("text/plain")) {
           responseText = await res.clone().text();

app/utils/stream.ts

@@ -19,7 +19,7 @@ type StreamResponse = {
   headers: Record<string, string>;
 };
 
-export function fetch(url: string, options?: RequestInit): Promise<any> {
+export function fetch(url: string, options?: RequestInit): Promise<Response> {
   if (window.__TAURI__) {
     const {
       signal,