V4.14.4 dev (#6058)

* perf: faq

* index

* delete dataset

* delete dataset

* perf: delete dataset

* init

* fix: outLink UID (#6048)

* perf: query extension

* fix: s3 configs (#6050)

* fix: s3 configs

* s3

---------

Co-authored-by: archer <[email protected]>

* s3 valid string check

* perf: completion api

* fix: model test

* perf: init

* fix: init

* fix: init shell

* fix: faq

---------

Co-authored-by: Roy <[email protected]>

Author: c121914yu

document/content/docs/introduction/development/openapi/share.mdx

@@ -15,20 +15,20 @@ description: FastGPT 分享链接身份鉴权
 
 ### 接口统一响应格式
 
-```json
+```jsonc
 {
   "success": true,
   "message": "错误提示",
   "msg": "同message, 错误提示",
   "data": {
-    "uid": "用户唯一凭证"
+    "uid": "用户唯一凭证" // 必须返回
   }
 }
 ```
 
 `FastGPT` 将会判断`success`是否为`true`决定是允许用户继续操作。`message`与`msg`是等同的，你可以选择返回其中一个，当`success`不为`true`时，将会提示这个错误。
 
-`uid`是用户的唯一凭证，将会用于拉取对话记录以及保存对话记录。可参考下方实践案例。
+`uid` 是用户的唯一凭证，必须返回该 ID 且 ID 的格式为不包含 "|"、"/“、"\" 字符的、长度小于等于 255 的字符串，否则会返回 `Invalid UID` 的错误。`uid` 将会用于拉取对话记录以及保存对话记录，可参考下方实践案例。
 
 ### 触发流程
 

document/content/docs/upgrading/4-14/4144.mdx

@@ -30,6 +30,7 @@ curl --location --request POST 'https://{{host}}/api/admin/initv4144' \
 4. 通过 API 上传本地文件至知识库，保存至 S3。同时将旧版 Gridfs 代码全部移除。
 5. 新版订阅套餐逻辑。
 6. 支持配置对话文件白名单。
+7. S3 支持 pathStyle 配置。
 
 ## ⚙️ 优化
 
@@ -38,6 +39,8 @@ curl --location --request POST 'https://{{host}}/api/admin/initv4144' \
 3. 用户通知，支持中英文，以及优化模板。
 4. 删除知识库采用队列异步删除模式。
 5. LLM 请求时，图片无效报错提示。
+6. completions 接口，非 stream 模式， detail=false 时，增加返回 reason_content。
+7. 增加对于无效的 S3 key 检测。
 
 ## 🐛 修复
 
@@ -47,6 +50,9 @@ curl --location --request POST 'https://{{host}}/api/admin/initv4144' \
 4. 工作台卡片在名字过长时错位。
 5. 分享链接中url query 中携带全局变量时，前端 UI 不会加载该值。
 6. window 下判断 CSV 文件异常。
+7. 模型测试时，如果模型未启动，会导致无法被测试。
+8. MCP header 中带特殊内容时，会抛错。
+9. 工作流引用其他 Agent 时，切换版本号后未及时更新 UI。
 
 ## 插件
 

document/data/doc-last-modified.json

@@ -34,7 +34,7 @@
   "document/content/docs/introduction/development/openapi/chat.mdx": "2025-11-14T13:21:17+08:00",
   "document/content/docs/introduction/development/openapi/dataset.mdx": "2025-09-29T11:34:11+08:00",
   "document/content/docs/introduction/development/openapi/intro.mdx": "2025-09-29T11:34:11+08:00",
-  "document/content/docs/introduction/development/openapi/share.mdx": "2025-08-05T23:20:39+08:00",
+  "document/content/docs/introduction/development/openapi/share.mdx": "2025-12-08T16:10:51+08:00",
   "document/content/docs/introduction/development/proxy/cloudflare.mdx": "2025-07-23T21:35:03+08:00",
   "document/content/docs/introduction/development/proxy/http_proxy.mdx": "2025-07-23T21:35:03+08:00",
   "document/content/docs/introduction/development/proxy/nginx.mdx": "2025-07-23T21:35:03+08:00",
@@ -118,7 +118,7 @@
   "document/content/docs/upgrading/4-14/4141.mdx": "2025-11-19T10:15:27+08:00",
   "document/content/docs/upgrading/4-14/4142.mdx": "2025-11-18T19:27:14+08:00",
   "document/content/docs/upgrading/4-14/4143.mdx": "2025-11-26T20:52:05+08:00",
-  "document/content/docs/upgrading/4-14/4144.mdx": "2025-12-08T01:44:15+08:00",
+  "document/content/docs/upgrading/4-14/4144.mdx": "2025-12-08T17:57:59+08:00",
   "document/content/docs/upgrading/4-8/40.mdx": "2025-08-02T19:38:37+08:00",
   "document/content/docs/upgrading/4-8/41.mdx": "2025-08-02T19:38:37+08:00",
   "document/content/docs/upgrading/4-8/42.mdx": "2025-08-02T19:38:37+08:00",

packages/service/common/s3/buckets/base.ts

@@ -50,6 +50,7 @@ export class S3BaseBucket {
         port: externalPort,
         accessKey: options.accessKey,
         secretKey: options.secretKey,
+        pathStyle: options.pathStyle,
         transportAgent: options.transportAgent
       });
     }

packages/service/common/s3/constants.ts

@@ -52,3 +52,9 @@ export const getSystemMaxFileSize = () => {
   const config = global.feConfigs?.uploadFileMaxSize || 1024; // MB, default 1024MB
   return config; // bytes
 };
+
+export const S3_KEY_PATH_INVALID_CHARS_MAP: Record<string, boolean> = {
+  '/': true,
+  '\\': true,
+  '|': true
+};

packages/service/common/s3/controller.ts

@@ -4,6 +4,7 @@ import { setCron } from '../system/cron';
 import { checkTimerLock } from '../system/timerLock/utils';
 import { TimerIdEnum } from '../system/timerLock/constants';
 import path from 'node:path';
+import { S3Error } from 'minio';
 
 export async function clearExpiredMinioFiles() {
   try {
@@ -56,6 +57,12 @@ export async function clearExpiredMinioFiles() {
           addLog.warn(`Bucket not found: ${file.bucketName}`);
         }
       } catch (error) {
+        if (
+          error instanceof S3Error &&
+          error.message.includes('Object name contains unsupported characters.')
+        ) {
+          await MongoS3TTL.deleteOne({ _id: file._id });
+        }
         fail++;
         addLog.error(`Failed to delete minio file: ${file.minioKey}`, error);
       }

packages/service/core/ai/functions/queryExtension.ts

@@ -13,7 +13,7 @@ import { useTextCosine } from '../hooks/useTextCosine';
   This module can eliminate referential ambiguity and expand queries based on context to improve retrieval.
   Submodular Optimization Mode: Generate multiple candidate queries, then use submodular algorithm to select the optimal query combination
 */
-const title = global.feConfigs?.systemTitle || 'FastAI';
+const title = global.feConfigs?.systemTitle || 'Nginx';
 const defaultPrompt = `## 你的任务
 你作为一个向量检索助手，你的任务是结合历史记录，为"原问题"生成{{count}}个不同版本的"检索词"。这些检索词应该从不同角度探索主题，以提高向量检索的语义丰富度和精度。
 
@@ -230,7 +230,7 @@ assistant: ${chatBg}
     .replace(/  /g, '');
 
   try {
-    const queries = json5.parse(jsonStr) as string[];
+    let queries = json5.parse(jsonStr) as string[];
 
     if (!Array.isArray(queries) || queries.length === 0) {
       return {
@@ -248,6 +248,8 @@ assistant: ${chatBg}
     const { lazyGreedyQuerySelection, embeddingModel: useEmbeddingModel } = useTextCosine({
       embeddingModel
     });
+    queries = queries.map((item) => String(item));
+
     const { selectedData: selectedQueries, embeddingTokens } = await lazyGreedyQuerySelection({
       originalText: query,
       candidates: queries,

packages/service/core/ai/llm/request.ts

@@ -81,14 +81,15 @@ export const createLLMResponse = async <T extends CompletionsBodyType>(
     return requestMessages;
   })();
 
-  const requestBody = await llmCompletionsBodyFormat({
+  const { requestBody, modelData } = await llmCompletionsBodyFormat({
     ...body,
     messages: rewriteMessages
   });
 
   // console.log(JSON.stringify(requestBody, null, 2));
   const { response, isStreamResponse, getEmptyResponseTip } = await createChatCompletion({
     body: requestBody,
+    modelData,
     userKey,
     options: {
       headers: {
@@ -491,10 +492,16 @@ const llmCompletionsBodyFormat = async <T extends CompletionsBodyType>({
   parallel_tool_calls,
   toolCallMode,
   ...body
-}: LLMRequestBodyType<T>): Promise<InferCompletionsBody<T>> => {
+}: LLMRequestBodyType<T>): Promise<{
+  requestBody: InferCompletionsBody<T>;
+  modelData: LLMModelItemType;
+}> => {
   const modelData = getLLMModel(body.model);
   if (!modelData) {
-    return body as unknown as InferCompletionsBody<T>;
+    return {
+      requestBody: body as unknown as InferCompletionsBody<T>,
+      modelData
+    };
   }
 
   const response_format = (() => {
@@ -548,7 +555,10 @@ const llmCompletionsBodyFormat = async <T extends CompletionsBodyType>({
     });
   }
 
-  return requestBody as unknown as InferCompletionsBody<T>;
+  return {
+    requestBody: requestBody as unknown as InferCompletionsBody<T>,
+    modelData
+  };
 };
 const createChatCompletion = async ({
   modelData,
@@ -579,6 +589,7 @@ const createChatCompletion = async ({
   try {
     // Rewrite model
     const modelConstantsData = modelData || getLLMModel(body.model);
+
     if (!modelConstantsData) {
       return Promise.reject(`${body.model} not found`);
     }

packages/service/core/dataset/controller.ts

@@ -115,6 +115,25 @@ export async function delDatasetRelevantData({
   // Delete vector data
   await deleteDatasetDataVector({ teamId, datasetIds });
 
+  // Delete dataset_data_texts in batches by datasetId
+  for (const datasetId of datasetIds) {
+    await MongoDatasetDataText.deleteMany({
+      teamId,
+      datasetId
+    }).maxTimeMS(300000); // Reduce timeout for single batch
+  }
+  // Delete dataset_datas in batches by datasetId
+  for (const datasetId of datasetIds) {
+    await MongoDatasetData.deleteMany({
+      teamId,
+      datasetId
+    }).maxTimeMS(300000);
+  }
+
+  await delCollectionRelatedSource({ collections });
+  // Delete vector data
+  await deleteDatasetDataVector({ teamId, datasetIds });
+
   // delete collections
   await MongoDatasetCollection.deleteMany({
     teamId,

packages/service/core/dataset/data/controller.ts

@@ -5,15 +5,11 @@ import { addDays } from 'date-fns';
 import { isS3ObjectKey, jwtSignS3ObjectKey } from '../../../common/s3/utils';
 
 export const formatDatasetDataValue = ({
-  teamId,
-  datasetId,
   q,
   a,
   imageId,
   imageDescMap
 }: {
-  teamId: string;
-  datasetId: string;
   q: string;
   a?: string;
   imageId?: string;
@@ -73,8 +69,6 @@ export const getFormatDatasetCiteList = (list: DatasetDataSchemaType[]) => {
   return list.map((item) => ({
     _id: item._id,
     ...formatDatasetDataValue({
-      teamId: item.teamId,
-      datasetId: item.datasetId,
       q: item.q,
       a: item.a,
       imageId: item.imageId