Update README.md

Update README_EN.md

.github/workflows/sync.yml

@@ -0,0 +1,48 @@
+name: Upstream Sync
+
+permissions:
+  contents: write
+  issues: write
+  actions: write
+
+on:
+  schedule:
+    - cron: '0 * * * *' # every hour
+  workflow_dispatch:
+
+jobs:
+  sync_latest_from_upstream:
+    name: Sync latest commits from upstream repo
+    runs-on: ubuntu-latest
+    if: ${{ github.event.repository.fork }}
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Clean issue notice
+        uses: actions-cool/issues-helper@v3
+        with:
+          actions: 'close-issues'
+          labels: '🚨 Sync Fail'
+
+      - name: Sync upstream changes
+        id: sync
+        uses: aormsby/Fork-Sync-With-Upstream-action@v3.4
+        with:
+          upstream_sync_repo: LLM-Red-Team/kimi-free-api
+          upstream_sync_branch: master
+          target_sync_branch: master
+          target_repo_token: ${{ secrets.GITHUB_TOKEN }} # automatically generated, no need to set
+          test_mode: false
+
+      - name: Sync check
+        if: failure()
+        uses: actions-cool/issues-helper@v3
+        with:
+          actions: 'create-issue'
+          title: '🚨 同步失败 | Sync Fail'
+          labels: '🚨 Sync Fail'
+          body: |
+            Due to a change in the workflow file of the LLM-Red-Team/kimi-free-api upstream repository, GitHub has automatically suspended the scheduled automatic update. You need to manually sync your fork. Please refer to the detailed [Tutorial][tutorial-en-US] for instructions.
+
+            由于 LLM-Red-Team/kimi-free-api 上游仓库的 workflow 文件变更，导致 GitHub 自动暂停了本次自动更新，你需要手动 Sync Fork 一次，

README.md

@@ -6,39 +6,50 @@
 <span>[ 中文 | <a href="README_EN.md">English</a> ]</span>
 
 
-![](https://img.shields.io/github/license/llm-red-team/kimi-free-api.svg)
+[![](https://img.shields.io/github/license/llm-red-team/kimi-free-api.svg)](LICENSE)
 ![](https://img.shields.io/github/stars/llm-red-team/kimi-free-api.svg)
 ![](https://img.shields.io/github/forks/llm-red-team/kimi-free-api.svg)
 ![](https://img.shields.io/docker/pulls/vinlic/kimi-free-api.svg)
 
-支持高速流式输出、支持多轮对话、支持联网搜索、支持长文档解读、支持图像解析，零配置部署，多路token支持，自动清理会话痕迹。
+支持高速流式输出、支持多轮对话、支持联网搜索、支持智能体对话、支持探索版、支持K1思考模型、支持长文档解读、支持图像解析，零配置部署，多路token支持，自动清理会话痕迹。
 
 与ChatGPT接口完全兼容。
 
-还有以下五个free-api欢迎关注：
+还有以下十个free-api欢迎关注：
 
 阶跃星辰 (跃问StepChat) 接口转API [step-free-api](https://github.com/LLM-Red-Team/step-free-api)
 
 阿里通义 (Qwen) 接口转API [qwen-free-api](https://github.com/LLM-Red-Team/qwen-free-api)
 
-ZhipuAI (智谱清言) 接口转API [glm-free-api](https://github.com/LLM-Red-Team/glm-free-api)
+智谱AI (智谱清言) 接口转API [glm-free-api](https://github.com/LLM-Red-Team/glm-free-api)
 
-秘塔AI (metaso) 接口转API [metaso-free-api](https://github.com/LLM-Red-Team/metaso-free-api)
+秘塔AI (Metaso) 接口转API [metaso-free-api](https://github.com/LLM-Red-Team/metaso-free-api)
 
-聆心智能 (Emohaa) 接口转API [emohaa-free-api](https://github.com/LLM-Red-Team/emohaa-free-api)
+字节跳动（豆包）接口转API [doubao-free-api](https://github.com/LLM-Red-Team/doubao-free-api)
+
+字节跳动（即梦AI）接口转API [jimeng-free-api](https://github.com/LLM-Red-Team/jimeng-free-api)
+
+讯飞星火（Spark）接口转API [spark-free-api](https://github.com/LLM-Red-Team/spark-free-api)
+
+MiniMax（海螺AI）接口转API [hailuo-free-api](https://github.com/LLM-Red-Team/hailuo-free-api)
+
+深度求索（DeepSeek）接口转API [deepseek-free-api](https://github.com/LLM-Red-Team/deepseek-free-api)
+
+聆心智能 (Emohaa) 接口转API [emohaa-free-api](https://github.com/LLM-Red-Team/emohaa-free-api)(当前不可用)
 
 ## 目录
 
 * [免责声明](#免责声明)
-* [在线体验](#在线体验)
 * [效果示例](#效果示例)
 * [接入准备](#接入准备)
   * [多账号接入](#多账号接入)
 * [Docker部署](#Docker部署)
   * [Docker-compose部署](#Docker-compose部署)
-* [Render部署](#Render部署)
-* [Vercel部署](#Vercel部署)
+  * [Render部署](#Render部署)
+  * [Vercel部署](#Vercel部署)
+  * [Zeabur部署](#Zeabur部署)
 * [原生部署](#原生部署)
+* [推荐使用客户端](#推荐使用客户端)
 * [接口列表](#接口列表)
   * [对话补全](#对话补全)
   * [文档解读](#文档解读)
@@ -46,9 +57,13 @@ ZhipuAI (智谱清言) 接口转API [glm-free-api](https://github.com/LLM-Red-Te
   * [refresh_token存活检测](#refresh_token存活检测)
 * [注意事项](#注意事项)
   * [Nginx反代优化](#Nginx反代优化)
+  * [Token统计](#Token统计)
+* [Star History](#star-history)
 
 ## 免责声明
 
+**逆向API是不稳定的，建议前往MoonshotAI官方 https://platform.moonshot.cn/ 付费使用API，避免封禁的风险。**
+
 **本组织和个人不接受任何资金捐助和交易，此项目是纯粹研究交流学习性质！**
 
 **仅限自用，禁止对外提供服务或商用，避免对官方造成服务压力，否则风险自担！**
@@ -57,12 +72,6 @@ ZhipuAI (智谱清言) 接口转API [glm-free-api](https://github.com/LLM-Red-Te
 
 **仅限自用，禁止对外提供服务或商用，避免对官方造成服务压力，否则风险自担！**
 
-## 在线体验
-
-此链接仅临时测试功能，不可长期使用，长期使用请自行部署。
-
-https://udify.app/chat/Po0F6BMJ15q5vu2P
-
 ## 效果示例
 
 ### 验明正身Demo
@@ -77,11 +86,17 @@ https://udify.app/chat/Po0F6BMJ15q5vu2P
 
 ![联网搜索](./doc/example-2.png)
 
+### 智能体对话Demo
+
+此处使用 [翻译通](https://kimi.moonshot.cn/chat/coo6l3pkqq4ri39f36bg) 智能体。
+
+![智能体对话](./doc/example-7.png)
+
 ### 长文档解读Demo
 
 ![长文档解读](./doc/example-5.png)
 
-### 图像解析Demo
+### 图像OCR Demo
 
 ![图像解析](./doc/example-3.png)
 
@@ -111,7 +126,7 @@ https://udify.app/chat/Po0F6BMJ15q5vu2P
 
 ## Docker部署
 
-请准备一台具有公网IP的服务器并将8000端口开放。
+请准备能够部署Docker镜像且能够访问网络的设备或服务器，并将8000端口开放。
 
 拉取镜像并启动服务
 
@@ -234,6 +249,14 @@ pm2 reload kimi-free-api
 pm2 stop kimi-free-api
 ```
 
+## 推荐使用客户端
+
+使用以下二次开发客户端接入free-api系列项目更快更简单，支持文档/图像上传！
+
+由 [Clivia](https://github.com/Yanyutin753/lobe-chat) 二次开发的LobeChat [https://github.com/Yanyutin753/lobe-chat](https://github.com/Yanyutin753/lobe-chat)
+
+由 [时光@](https://github.com/SuYxh) 二次开发的ChatGPT Web [https://github.com/SuYxh/chatgpt-web-sea](https://github.com/SuYxh/chatgpt-web-sea)
+
 ## 接口列表
 
 目前支持与openai兼容的 `/v1/chat/completions` 接口，可自行使用与openai或其他兼容的客户端接入接口，或者使用 [dify](https://dify.ai/) 等线上服务接入使用。
@@ -253,8 +276,19 @@ Authorization: Bearer [refresh_token]
 请求数据：
 ```json
 {
-    // 模型名称随意填写，如果不希望输出检索过程模型名称请包含silent_search
+    // 模型名称
+    // kimi：默认模型
+    // kimi-search：联网检索模型
+    // kimi-research：探索版模型
+    // kimi-k1：K1模型
+    // kimi-math：数学模型
+    // kimi-silent：不输出检索过程模型
+    // search/research/k1/math/silent：可自由组合使用
+    // 如果使用kimi+智能体，model请填写智能体ID，就是浏览器地址栏上尾部的一串英文+数字20个字符的ID
     "model": "kimi",
+    // 目前多轮对话基于消息合并实现，某些场景可能导致能力下降且受单轮最大Token数限制
+    // 如果您想获得原生的多轮对话体验，可以传入首轮消息获得的id，来接续上下文，注意如果使用这个，首轮必须传none，否则第二轮会空响应！
+    // "conversation_id": "cnndivilnl96vah411dg",
     "messages": [
         {
             "role": "user",
@@ -271,6 +305,7 @@ Authorization: Bearer [refresh_token]
 响应数据：
 ```json
 {
+    // 如果想获得原生多轮对话体验，此id，你可以传入到下一轮对话的conversation_id来接续上下文
     "id": "cnndivilnl96vah411dg",
     "model": "kimi",
     "object": "chat.completion",
@@ -308,7 +343,15 @@ Authorization: Bearer [refresh_token]
 请求数据：
 ```json
 {
-    // 模型名称随意填写，如果不希望输出检索过程模型名称请包含silent_search
+    // 模型名称
+    // kimi：默认模型
+    // kimi-search：联网检索模型
+    // kimi-research：探索版模型
+    // kimi-k1：K1模型
+    // kimi-math：数学模型
+    // kimi-silent：不输出检索过程模型
+    // search/research/k1/math/silent：可自由组合使用
+    // 如果使用kimi+智能体，model请填写智能体ID，就是浏览器地址栏上尾部的一串英文+数字20个字符的ID
     "model": "kimi",
     "messages": [
         {
@@ -357,7 +400,7 @@ Authorization: Bearer [refresh_token]
 }
 ```
 
-### 图像解析
+### 图像OCR
 
 提供一个可访问的图像URL或者BASE64_URL进行解析。
 
@@ -374,7 +417,15 @@ Authorization: Bearer [refresh_token]
 请求数据：
 ```json
 {
-    // 模型名称随意填写，如果不希望输出检索过程模型名称请包含silent_search
+    // 模型名称
+    // kimi：默认模型
+    // kimi-search：联网检索模型
+    // kimi-research：探索版模型
+    // kimi-k1：K1模型
+    // kimi-math：数学模型
+    // kimi-silent：不输出检索过程模型
+    // search/research/k1/math/silent：可自由组合使用
+    // 如果使用kimi+智能体，model请填写智能体ID，就是浏览器地址栏上尾部的一串英文+数字20个字符的ID
     "model": "kimi",
     "messages": [
         {
@@ -425,7 +476,7 @@ Authorization: Bearer [refresh_token]
 
 ### refresh_token存活检测
 
-检测refresh_token是否存活，如果存活live未true，否则为false，请不要频繁（小于10分钟）调用此接口。
+检测refresh_token是否存活，如果存活live为true，否则为false，请不要频繁（小于10分钟）调用此接口。
 
 **POST /token/check**
 

README_EN.md

@@ -1,6 +1,9 @@
 # KIMI AI Free Service
 
-![](https://img.shields.io/github/license/llm-red-team/kimi-free-api.svg)
+
+<hr>
+
+[![](https://img.shields.io/github/license/llm-red-team/kimi-free-api.svg)](LICENSE)
 ![](https://img.shields.io/github/stars/llm-red-team/kimi-free-api.svg)
 ![](https://img.shields.io/github/forks/llm-red-team/kimi-free-api.svg)
 ![](https://img.shields.io/docker/pulls/vinlic/kimi-free-api.svg)
@@ -9,37 +12,46 @@ Supports high-speed streaming output, multi-turn dialogues, internet search, lon
 
 Fully compatible with the ChatGPT interface.
 
-Also, the following four free APIs are available for your attention:
+Also, the following free APIs are available for your attention:
 
-Step to the Stars (StepChat) API to API [step-free-api](https://github.com/LLM-Red-Team/step-free-api)
+StepFun (StepChat) API to API [step-free-api](https://github.com/LLM-Red-Team/step-free-api)
 
 Ali Tongyi (Qwen) API to API [qwen-free-api](https://github.com/LLM-Red-Team/qwen-free-api)
 
-ZhipuAI (Wisdom Map Clear Words) API to API [glm-free-api](https://github.com/LLM-Red-Team/glm-free-api)
+ZhipuAI (ChatGLM) API to API [glm-free-api](https://github.com/LLM-Red-Team/glm-free-api)
 
-MetaAI (metaso) 接口转API [metaso-free-api](https://github.com/LLM-Red-Team/metaso-free-api)
+Meta Sota (metaso) API to API [metaso-free-api](https://github.com/LLM-Red-Team/metaso-free-api)
 
-Listening Intelligence (Emohaa) API to API [emohaa-free-api](https://github.com/LLM-Red-Team/emohaa-free-api)
+Iflytek Spark (Spark) API to API [spark-free-api](https://github.com/LLM-Red-Team/spark-free-api)
+
+Lingxin Intelligence (Emohaa) API to API [emohaa-free-api](https://github.com/LLM-Red-Team/emohaa-free-api) (OUT OF ORDER)
 
 ## Table of Contents
 
-* [Disclaimer](#disclaimer)
-*[Online experience](#在线experience)
-* [Effect Example](#EffectExample)
-* [Access preparation](#access preparation)
-   * [Multiple account access](#multiple account access)
-* [Docker Deployment](#DockerDeployment)
-   * [Docker-compose deployment](#Docker-compose deployment)
-* [Native Deployment](#nativedeployment)
-* [Interface List](#Interface List)
-   * [Dialogue completion](#dialogue completion)
-   * [Document Interpretation](#document interpretation)
-   * [Image analysis](#imageanalysis)
-   * [refresh_token survival detection](#refresh_token survival detection)
-* [Note](# NOTE)
-   * [Nginx anti-generation optimization](#Nginx anti-generation optimization)
+* [Announcement](#Announcement)
+* [Online experience](#Online-Experience)
+* [Effect Examples](#Effect-Examples)
+* [Access preparation](#Access-Preparation)
+    * [Multiple account access](#Multi-Account-Access)
+* [Docker Deployment](#Docker-Deployment)
+    * [Docker-compose Deployment](#Docker-compose-Deployment)
+    * [Render Deployment](Render-Deployment)
+    * [Vercel Deployment](#Vercel-Deployment)
+    * [Zeabur Deployment](#Zeabur-Deployment)
+* [Native Deployment](#Native-Deployment)
+* [Interface List](#Interface-List)
+    * [Conversation completion](#conversation-completion)
+    * [Document Interpretation](#document-interpretation)
+    * [Image analysis](#image-analysis)
+    * [refresh_token survival detection](#refresh_token-survival-detection)
+* [Precautions](#Precautions)
+    * [Nginx anti-generation optimization](#Nginx-anti-generation-optimization)
+    * [Token statistics](#Token-statistics)
+* [Star History](#star-history)
+  
+## Announcement
 
-## Disclaimer
+**This API is unstable. So we highly recommend you go to the [MoonshotAI](https://platform.moonshot.cn/) use the offical API, avoiding banned.**
 
 **This organization and individuals do not accept any financial donations and transactions. This project is purely for research, communication, and learning purposes!**
 
@@ -123,13 +135,13 @@ Restart service
 docker restart kimi-free-api
 ```
 
-Out of service
+Shut down service
 
 ```shell
 docker stop kimi-free-api
 ```
 
-### Docker-compose deployment
+### Docker-compose Deployment
 
 ```yaml
 version: '3'
@@ -145,7 +157,37 @@ services:
       - TZ=Asia/Shanghai
 ```
 
-## Native deployment
+### Render Deployment
+
+**Attention: Some deployment regions may not be able to connect to Kimi. If container logs show request timeouts or connection failures (Singapore has been tested and found unavailable), please switch to another deployment region!**
+
+**Attention Container instances for free accounts will automatically stop after a period of inactivity, which may result in a 50-second or longer delay during the next request. It is recommended to check [Render Container Keepalive](https://github.com/LLM-Red-Team/free-api-hub/#Render%E5%AE%B9%E5%99%A8%E4%BF%9D%E6%B4%BB)**
+
+1. Fork this project to your GitHub account.
+
+2. Visit [Render](https://dashboard.render.com/) and log in with your GitHub account.
+
+3. Build your Web Service (New+ -> Build and deploy from a Git repository -> Connect your forked project -> Select deployment region -> Choose instance type as Free -> Create Web Service).
+
+4. After the build is complete, copy the assigned domain and append the URL to access it.
+
+### Vercel Deployment
+**Note: Vercel free accounts have a request response timeout of 10 seconds, but interface responses are usually longer, which may result in a 504 timeout error from Vercel!**
+
+Please ensure that Node.js environment is installed first.
+```shell
+npm i -g vercel --registry http://registry.npmmirror.com
+vercel login
+git clone https://github.com/LLM-Red-Team/kimi-free-api
+cd kimi-free-api
+vercel --prod
+```
+
+### Zeabur Deployment
+
+[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/templates/GRFYBP)
+
+## Native Deployment
 
 Please prepare a server with a public IP and open port 8000.
 
@@ -187,15 +229,19 @@ Restart service
 pm2 reload kimi-free-api
 ```
 
-Out of service
+Shut down service
 
 ```shell
 pm2 stop kimi-free-api
 ```
 
-## Zeabur Deployment
+## Recommended Clients
 
-[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/templates/GRFYBP)
+Using the following second-developed clients for free-api series projects is faster and easier, and supports document/image uploads!
+
+[Clivia](https://github.com/Yanyutin753/lobe-chat)'s modified LobeChat [https://github.com/Yanyutin753/lobe-chat](https://github.com/Yanyutin753/lobe-chat)
+
+[Time@](https://github.com/SuYxh)'s modified ChatGPT Web [https://github.com/SuYxh/chatgpt-web-sea](https://github.com/SuYxh/chatgpt-web-sea)
 
 ## interface list
 
@@ -215,7 +261,15 @@ Authorization: Bearer [refresh_token]
 Request data:
 ```json
 {
-     // Fill in the model name as you like. If you do not want to output the retrieval process model name, please include silent_search.
+    // Model name
+    // kimi: default model
+    // kimi-search: online search model
+    // kimi-research: exploration version model
+    // kimi-k1: K1 model
+    // kimi-math: math model
+    // kimi-silent: model without search process output
+    // search/research/k1/math/silent: can be freely combined
+    // If using kimi+agent, fill in the agent ID for model, which is the 20-character ID of letters and numbers at the end of the browser address bar
      "model": "kimi",
      "messages": [
          {
@@ -271,27 +325,35 @@ Authorization: Bearer [refresh_token]
 Request data:
 ```json
 {
-     // Fill in the model name as you like. If you do not want to output the retrieval process model name, please include silent_search.
-     "model": "kimi",
-     "messages": [
-         {
-             "role": "user",
-             "content": [
-                 {
-                     "type": "file",
-                     "file_url": {
-                         "url": "https://mj101-1317487292.cos.ap-shanghai.myqcloud.com/ai/test.pdf"
-                     }
-                 },
-                 {
-                     "type": "text",
-                     "text": "What does the document say?"
-                 }
-             ]
-         }
-     ],
-     // It is recommended to turn off online search to prevent interference in interpreting results.
-     "use_search": false
+    // Model name
+    // kimi: default model
+    // kimi-search: online search model
+    // kimi-research: exploration version model
+    // kimi-k1: K1 model
+    // kimi-math: math model
+    // kimi-silent: model without search process output
+    // search/research/k1/math/silent: can be freely combined
+    // If using kimi+agent, fill in the agent ID for model, which is the 20-character ID of letters and numbers at the end of the browser address bar
+    "model": "kimi",
+    "messages": [
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "file",
+                    "file_url": {
+                        "url": "https://mj101-1317487292.cos.ap-shanghai.myqcloud.com/ai/test.pdf"
+                    }
+                },
+                {
+                    "type": "text",
+                    "text": "What does the document say?"
+                }
+            ]
+        }
+    ],
+    // It is recommended to turn off online search to prevent interference in interpreting results.
+    "use_search": false
 }
 ```
 
@@ -337,7 +399,15 @@ Authorization: Bearer [refresh_token]
 Request data:
 ```json
 {
-     // Fill in the model name as you like. If you do not want to output the retrieval process model name, please include silent_search.
+    // Model name
+    // kimi: default model
+    // kimi-search: online search model
+    // kimi-research: exploration version model
+    // kimi-k1: K1 model
+    // kimi-math: math model
+    // kimi-silent: model without search process output
+    // search/research/k1/math/silent: can be freely combined
+    // If using kimi+agent, fill in the agent ID for model, which is the 20-character ID of letters and numbers at the end of the browser address bar
      "model": "kimi",
      "messages": [
          {
@@ -406,7 +476,7 @@ Response data:
 }
 ```
 
-## Precautions
+## Notification
 
 ### Nginx anti-generation optimization
 
@@ -431,4 +501,4 @@ Since the inference side is not in kimi-free-api, the token cannot be counted an
 
 ## Star History
 
-[![Star History Chart](https://api.star-history.com/svg?repos=LLM-Red-Team/kimi-free-api&type=Date)](https://star-history.com/ #LLM-Red-Team/kimi-free-api&Date)
+[![Star History Chart](https://api.star-history.com/svg?repos=LLM-Red-Team/kimi-free-api&type=Date)](https://star-history.com/#LLM-Red-Team/kimi-free-api&Date)

package.json

@@ -1,6 +1,6 @@
 {
   "name": "kimi-free-api",
-  "version": "0.0.28",
+  "version": "0.0.36",
   "description": "Kimi Free API Server",
   "type": "module",
   "main": "dist/index.js",
@@ -13,8 +13,8 @@
     "dist/"
   ],
   "scripts": {
-    "dev": "tsup src/index.ts --format cjs,esm --sourcemap --dts --publicDir public --watch --onSuccess \"node dist/index.js\"",
-    "start": "node dist/index.js",
+    "dev": "tsup src/index.ts --format cjs,esm --sourcemap --dts --publicDir public --watch --onSuccess \"node --enable-source-maps --no-node-snapshot dist/index.js\"",
+    "start": "node --enable-source-maps --no-node-snapshot dist/index.js",
     "build": "tsup src/index.ts --format cjs,esm --sourcemap --dts --clean --publicDir public"
   },
   "author": "Vinlic",

src/api/consts/exceptions.ts

@@ -5,5 +5,6 @@ export default {
     API_TOKEN_EXPIRES: [-2002, 'Token已失效'],
     API_FILE_URL_INVALID: [-2003, '远程文件URL非法'],
     API_FILE_EXECEEDS_SIZE: [-2004, '远程文件超出大小'],
-    API_CHAT_STREAM_PUSHING: [-2005, '已有对话流正在输出']
+    API_CHAT_STREAM_PUSHING: [-2005, '已有对话流正在输出'],
+    API_RESEARCH_EXCEEDS_LIMIT: [-2006, '探索版使用量已达到上限']
 }

src/api/controllers/chat.ts

@@ -2,8 +2,9 @@ import { PassThrough } from "stream";
 import path from 'path';
 import _ from 'lodash';
 import mime from 'mime';
-import axios, { AxiosResponse } from 'axios';
+import axios, { AxiosRequestConfig, AxiosResponse } from 'axios';
 
+import type IStreamMessage from "../interfaces/IStreamMessage.ts";
 import APIException from "@/lib/exceptions/APIException.ts";
 import EX from "@/api/consts/exceptions.ts";
 import { createParser } from 'eventsource-parser'
@@ -12,27 +13,39 @@ import util from '@/lib/util.ts';
 
 // 模型名称
 const MODEL_NAME = 'kimi';
+// 设备ID
+const DEVICE_ID = Math.random() * 999999999999999999 + 7000000000000000000;
+// SessionID
+const SESSION_ID = Math.random() * 99999999999999999 + 1700000000000000000;
 // access_token有效期
 const ACCESS_TOKEN_EXPIRES = 300;
 // 最大重试次数
 const MAX_RETRY_COUNT = 3;
 // 重试延迟
 const RETRY_DELAY = 5000;
+// 基础URL
+const BASE_URL = 'https://kimi.moonshot.cn';
 // 伪装headers
 const FAKE_HEADERS = {
   'Accept': '*/*',
   'Accept-Encoding': 'gzip, deflate, br, zstd',
-  'Accept-Language': 'zh-CN,zh;q=0.9',
-  'Origin': 'https://kimi.moonshot.cn',
+  'Accept-Language': 'zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7',
+  'Cache-Control': 'no-cache',
+  'Pragma': 'no-cache',
+  'Origin': BASE_URL,
   'Cookie': util.generateCookie(),
   'R-Timezone': 'Asia/Shanghai',
-  'Sec-Ch-Ua': '"Google Chrome";v="123", "Not:A-Brand";v="8", "Chromium";v="123"',
+  'Sec-Ch-Ua': '"Google Chrome";v="131", "Chromium";v="131", "Not_A Brand";v="24"',
   'Sec-Ch-Ua-Mobile': '?0',
   'Sec-Ch-Ua-Platform': '"Windows"',
   'Sec-Fetch-Dest': 'empty',
   'Sec-Fetch-Mode': 'cors',
   'Sec-Fetch-Site': 'same-origin',
-  'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36'
+  'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
+  'Priority': 'u=1, i',
+  'X-Msh-Device-Id': `${DEVICE_ID}`,
+  'X-Msh-Platform': 'web',
+  'X-Msh-Session-Id': `${SESSION_ID}`
 };
 // 文件最大大小
 const FILE_MAX_SIZE = 100 * 1024 * 1024;
@@ -54,23 +67,10 @@ async function requestToken(refreshToken: string) {
   accessTokenRequestQueueMap[refreshToken] = [];
   logger.info(`Refresh token: ${refreshToken}`);
   const result = await (async () => {
-    const result = await axios.get('https://kimi.moonshot.cn/api/auth/token/refresh', {
+    const result = await axios.get(`${BASE_URL}/api/auth/token/refresh`, {
       headers: {
-        Accept: '*/*',
-        'Accept-Encoding': 'gzip, deflate, br, zstd',
-        'Accept-Language': 'zh-CN,zh;q=0.9',
         Authorization: `Bearer ${refreshToken}`,
-        'Cache-Control': 'no-cache',
-        'Cookie': util.generateCookie(),
-        Pragma: 'no-cache',
-        Referer: 'https://kimi.moonshot.cn/',
-        'Sec-Ch-Ua': '"Google Chrome";v="123", "Not:A-Brand";v="8", "Chromium";v="123"',
-        'Sec-Ch-Ua-Mobile': '?0',
-        'Sec-Ch-Ua-Platform': '"Windows"',
-        'Sec-Fetch-Dest': 'empty',
-        'Sec-Fetch-Mode': 'cors',
-        'Sec-Fetch-Site': 'same-origin',
-        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36'
+        ...FAKE_HEADERS,
       },
       timeout: 15000,
       validateStatus: () => true
@@ -79,9 +79,18 @@ async function requestToken(refreshToken: string) {
       access_token,
       refresh_token
     } = checkResult(result, refreshToken);
-    const { id: userId } = await getUserInfo(access_token, refreshToken);
+    const userResult = await axios.get(`${BASE_URL}/api/user`, {
+      headers: {
+        Authorization: `Bearer ${access_token}`,
+        ...FAKE_HEADERS,
+      },
+      timeout: 15000,
+      validateStatus: () => true
+    });
+    if(!userResult.data.id)
+      throw new APIException(EX.API_REQUEST_FAILED, '获取用户信息失败');
     return {
-      userId,
+      userId: userResult.data.id,
       accessToken: access_token,
       refreshToken: refresh_token,
       refreshTime: util.unixTimestamp() + ACCESS_TOKEN_EXPIRES
@@ -96,6 +105,7 @@ async function requestToken(refreshToken: string) {
       return result;
     })
     .catch(err => {
+      logger.error(err);
       if (accessTokenRequestQueueMap[refreshToken]) {
         accessTokenRequestQueueMap[refreshToken].forEach(resolve => resolve(err));
         delete accessTokenRequestQueueMap[refreshToken];
@@ -128,19 +138,32 @@ async function acquireToken(refreshToken: string): Promise<any> {
 }
 
 /**
- * 获取用户信息
- * 
- * @param refreshToken 用于刷新access_token的refresh_token
+ * 发送请求
  */
-async function getUserInfo(accessToken: string, refreshToken: string) {
-  const result = await axios.get('https://kimi.moonshot.cn/api/user', {
+export async function request(
+  method: string,
+  uri: string,
+  refreshToken: string,
+  options: AxiosRequestConfig = {}
+) {
+  const {
+    accessToken,
+    userId
+  } = await acquireToken(refreshToken);
+  logger.info(`url: ${uri}`);
+  const result = await axios({
+    method,
+    url: `${BASE_URL}${uri}`,
+    params: options.params,
+    data: options.data,
     headers: {
       Authorization: `Bearer ${accessToken}`,
-      Referer: 'https://kimi.moonshot.cn/',
-      'X-Traffic-Id': `7${util.generateRandomString({ length: 18, charset: 'numeric' })}`,
-      ...FAKE_HEADERS
+      'X-Traffic-Id': userId,
+      ...FAKE_HEADERS,
+      ...(options.headers || {})
     },
-    timeout: 15000,
+    timeout: options.timeout || 15000,
+    responseType: options.responseType,
     validateStatus: () => true
   });
   return checkResult(result, refreshToken);
@@ -153,27 +176,17 @@ async function getUserInfo(accessToken: string, refreshToken: string) {
  * 
  * @param refreshToken 用于刷新access_token的refresh_token
  */
-async function createConversation(name: string, refreshToken: string) {
-  const {
-    accessToken,
-    userId
-  } = await acquireToken(refreshToken);
-  const result = await axios.post('https://kimi.moonshot.cn/api/chat', {
-    is_example: false,
-    name
-  }, {
-    headers: {
-      Authorization: `Bearer ${accessToken}`,
-      Referer: 'https://kimi.moonshot.cn/',
-      'X-Traffic-Id': userId,
-      ...FAKE_HEADERS
-    },
-    timeout: 15000,
-    validateStatus: () => true
-  });
+async function createConversation(model: string, name: string, refreshToken: string) {
   const {
     id: convId
-  } = checkResult(result, refreshToken);
+  } = await request('POST', '/api/chat', refreshToken, {
+    data: {
+      enter_method: 'new_chat',
+      is_example: false,
+      kimiplus_id: /^[0-9a-z]{20}$/.test(model) ? model : 'kimi',
+      name
+    }
+  });
   return convId;
 }
 
@@ -185,49 +198,77 @@ async function createConversation(name: string, refreshToken: string) {
  * @param refreshToken 用于刷新access_token的refresh_token
  */
 async function removeConversation(convId: string, refreshToken: string) {
-  const {
-    accessToken,
-    userId
-  } = await acquireToken(refreshToken);
-  const result = await axios.delete(`https://kimi.moonshot.cn/api/chat/${convId}`, {
-    headers: {
-      Authorization: `Bearer ${accessToken}`,
-      Referer: `https://kimi.moonshot.cn/chat/${convId}`,
-      'X-Traffic-Id': userId,
-      ...FAKE_HEADERS
-    },
-    timeout: 15000,
-    validateStatus: () => true
-  });
-  checkResult(result, refreshToken);
+  return await request('DELETE', `/api/chat/${convId}`, refreshToken);
 }
 
 /**
- * prompt片段提交
+ * 获取建议
  * 
- * @param query prompt
  * @param refreshToken 用于刷新access_token的refresh_token
  */
-async function promptSnippetSubmit(query: string, refreshToken: string) {
-  const {
-    accessToken,
-    userId
-  } = await acquireToken(refreshToken);
-  const result = await axios.post('https://kimi.moonshot.cn/api/prompt-snippet/instance', {
-    "offset": 0,
-    "size": 10,
-    "query": query.replace('user:', '').replace('assistant:', '')
-  }, {
-    headers: {
-      Authorization: `Bearer ${accessToken}`,
-      Referer: 'https://kimi.moonshot.cn/',
-      'X-Traffic-Id': userId,
-      ...FAKE_HEADERS
-    },
-    timeout: 15000,
-    validateStatus: () => true
+async function getSuggestion(query: string, refreshToken: string) {
+  return await request('POST', '/api/suggestion', refreshToken, {
+    data: {
+      offset: 0,
+      page_referer: 'chat',
+      query: query.replace('user:', '').replace('assistant:', ''),
+      scene: 'first_round',
+      size: 10
+    }
   });
-  checkResult(result, refreshToken);
+}
+
+/**
+ * 预处理N2S
+ * 
+ * 预处理N2S，用于获取搜索结果
+ * 
+ * @param model 模型名称
+ * @param messages 参考gpt系列消息格式，多轮对话请完整提供上下文
+ * @param refs 引用文件ID列表
+ * @param refreshToken 用于刷新access_token的refresh_token
+ * @param refConvId 引用会话ID
+ */
+async function preN2s(model: string, messages: { role: string, content: string }[], refs: string[], refreshToken: string, refConvId?: string) {
+  const isSearchModel = model.indexOf('search') != -1;
+  return await request('POST', `/api/chat/${refConvId}/pre-n2s`, refreshToken, {
+    data: {
+      is_pro_search: false,
+      kimiplus_id: /^[0-9a-z]{20}$/.test(model) ? model : 'kimi',
+      messages,
+      refs,
+      use_search: isSearchModel
+    }
+  });
+}
+
+/**
+ * token计数
+ * 
+ * @param query 查询内容
+ * @param refreshToken 用于刷新access_token的refresh_token
+ * @param refConvId 引用会话ID
+ */
+async function tokenSize(query: string, refs: string[], refreshToken: string, refConvId: string) {
+  return await request('POST', `/api/chat/${refConvId}/token_size`, refreshToken, {
+    data: {
+      content: query,
+      refs: []
+    }
+  });
+}
+
+/**
+ * 获取探索版使用量
+ * 
+ * @param refreshToken 用于刷新access_token的refresh_token
+ */
+async function getResearchUsage(refreshToken: string): Promise<{
+  remain,
+  total,
+  used
+}> {
+  return await request('GET', '/api/chat/research/usage', refreshToken);
 }
 
 /**
@@ -236,56 +277,110 @@ async function promptSnippetSubmit(query: string, refreshToken: string) {
  * @param model 模型名称
  * @param messages 参考gpt系列消息格式，多轮对话请完整提供上下文
  * @param refreshToken 用于刷新access_token的refresh_token
- * @param useSearch 是否开启联网搜索
+ * @param refConvId 引用会话ID
  * @param retryCount 重试次数
  */
-async function createCompletion(model = MODEL_NAME, messages: any[], refreshToken: string, useSearch = true, retryCount = 0) {
+async function createCompletion(model = MODEL_NAME, messages: any[], refreshToken: string, refConvId?: string, retryCount = 0, segmentId?: string): Promise<IStreamMessage> {
   return (async () => {
     logger.info(messages);
 
+    // 创建会话
+    const convId = /[0-9a-zA-Z]{20}/.test(refConvId) ? refConvId : await createConversation(model, "未命名会话", refreshToken);
+
     // 提取引用文件URL并上传kimi获得引用的文件ID列表
     const refFileUrls = extractRefFileUrls(messages);
-    const refs = refFileUrls.length ? await Promise.all(refFileUrls.map(fileUrl => uploadFile(fileUrl, refreshToken))) : [];
+    const refResults = refFileUrls.length ? await Promise.all(refFileUrls.map(fileUrl => uploadFile(fileUrl, refreshToken, convId))) : [];
+    const refs = refResults.map(result => result.id);
+    const refsFile = refResults.map(result => ({
+      detail: result,
+      done: true,
+      file: {},
+      file_info: result,
+      id: result.id,
+      name: result.name,
+      parse_status: 'success',
+      size: result.size,
+      upload_progress: 100,
+      upload_status: 'success'
+    }));
 
     // 伪装调用获取用户信息
     fakeRequest(refreshToken)
       .catch(err => logger.error(err));
 
-    // 创建会话
-    const convId = await createConversation("未命名会话", refreshToken);
+    // 消息预处理
+    const sendMessages = messagesPrepare(messages, !!refConvId);
 
-    // 请求流
-    const {
-      accessToken,
-      userId
-    } = await acquireToken(refreshToken);
-    const sendMessages = messagesPrepare(messages);
-    const result = await axios.post(`https://kimi.moonshot.cn/api/chat/${convId}/completion/stream`, {
-      messages: sendMessages,
-      refs,
-      use_search: useSearch
-    }, {
-      headers: {
-        Authorization: `Bearer ${accessToken}`,
-        Referer: `https://kimi.moonshot.cn/chat/${convId}`,
-        'X-Traffic-Id': userId,
-        ...FAKE_HEADERS
+    !segmentId && preN2s(model, sendMessages, refs, refreshToken, convId)
+      .catch(err => logger.error(err));
+    getSuggestion(sendMessages[0].content, refreshToken)
+      .catch(err => logger.error(err));
+    tokenSize(sendMessages[0].content, refs, refreshToken, convId)
+      .catch(err => logger.error(err));
+    
+    const isMath = model.indexOf('math') != -1;
+    const isSearchModel = model.indexOf('search') != -1;
+    const isResearchModel = model.indexOf('research') != -1;
+    const isK1Model = model.indexOf('k1') != -1;
+
+    logger.info(`使用模型: ${model}，是否联网检索: ${isSearchModel}，是否探索版: ${isResearchModel}，是否K1模型: ${isK1Model}，是否数学模型: ${isMath}`);
+
+    if(segmentId)
+      logger.info(`继续请求，segmentId: ${segmentId}`);
+
+    // 检查探索版使用量
+    if(isResearchModel) {
+      const {
+        total,
+        used
+      } = await getResearchUsage(refreshToken);
+      if(used >= total)
+        throw new APIException(EX.API_RESEARCH_EXCEEDS_LIMIT, `探索版使用量已达到上限`);
+      logger.info(`探索版当前额度: ${used}/${total}`);
+    }
+
+    const kimiplusId = isK1Model ? 'crm40ee9e5jvhsn7ptcg' : (/^[0-9a-z]{20}$/.test(model) ? model : 'kimi');
+    
+    // 请求补全流
+    const stream = await request('POST', `/api/chat/${convId}/completion/stream`, refreshToken, {
+      data: segmentId ? {
+        segment_id: segmentId,
+        action: 'continue',
+        messages: [{ role: 'user', content: ' ' }],
+        kimiplus_id: kimiplusId,
+        extend: { sidebar: true }
+      } : {
+        kimiplus_id: kimiplusId,
+        messages: sendMessages,
+        refs,
+        refs_file: refsFile,
+        use_math: isMath,
+        use_research: isResearchModel,
+        use_search: isSearchModel,
+        extend: { sidebar: true }
+      },
+      headers: {
+        Referer: `https://kimi.moonshot.cn/chat/${convId}`
       },
-      // 120秒超时
-      timeout: 120000,
-      validateStatus: () => true,
       responseType: 'stream'
     });
 
     const streamStartTime = util.timestamp();
+
     // 接收流为输出文本
-    const answer = await receiveStream(model, convId, result.data);
+    const answer = await receiveStream(model, convId, stream);
+
+    // 如果上次请求生成长度超限，则继续请求
+    if(answer.choices[0].finish_reason == 'length' && answer.segment_id) {
+      const continueAnswer = await createCompletion(model, [], refreshToken, convId, retryCount, answer.segment_id);
+      answer.choices[0].message.content += continueAnswer.choices[0].message.content;
+    }
+  
     logger.success(`Stream has completed transfer ${util.timestamp() - streamStartTime}ms`);
 
     // 异步移除会话，如果消息不合规，此操作可能会抛出数据库错误异常，请忽略
-    removeConversation(convId, refreshToken)
-      .catch(err => console.error(err));
-    promptSnippetSubmit(sendMessages[0].content, refreshToken)
+    // 如果引用会话将不会清除，因为我们不知道什么时候你会结束会话
+    !refConvId && removeConversation(convId, refreshToken)
       .catch(err => console.error(err));
 
     return answer;
@@ -296,7 +391,7 @@ async function createCompletion(model = MODEL_NAME, messages: any[], refreshToke
         logger.warn(`Try again after ${RETRY_DELAY / 1000}s...`);
         return (async () => {
           await new Promise(resolve => setTimeout(resolve, RETRY_DELAY));
-          return createCompletion(model, messages, refreshToken, useSearch, retryCount + 1);
+          return createCompletion(model, messages, refreshToken, refConvId, retryCount + 1);
         })();
       }
       throw err;
@@ -309,54 +404,91 @@ async function createCompletion(model = MODEL_NAME, messages: any[], refreshToke
  * @param model 模型名称
  * @param messages 参考gpt系列消息格式，多轮对话请完整提供上下文
  * @param refreshToken 用于刷新access_token的refresh_token
- * @param useSearch 是否开启联网搜索
+ * @param refConvId 引用会话ID
  * @param retryCount 重试次数
  */
-async function createCompletionStream(model = MODEL_NAME, messages: any[], refreshToken: string, useSearch = true, retryCount = 0) {
+async function createCompletionStream(model = MODEL_NAME, messages: any[], refreshToken: string, refConvId?: string, retryCount = 0) {
   return (async () => {
     logger.info(messages);
 
+    // 创建会话
+    const convId = /[0-9a-zA-Z]{20}/.test(refConvId) ? refConvId : await createConversation(model, "未命名会话", refreshToken);
+
     // 提取引用文件URL并上传kimi获得引用的文件ID列表
     const refFileUrls = extractRefFileUrls(messages);
-    const refs = refFileUrls.length ? await Promise.all(refFileUrls.map(fileUrl => uploadFile(fileUrl, refreshToken))) : [];
+    const refResults = refFileUrls.length ? await Promise.all(refFileUrls.map(fileUrl => uploadFile(fileUrl, refreshToken, convId))) : [];
+    const refs = refResults.map(result => result.id);
+    const refsFile = refResults.map(result => ({
+      detail: result,
+      done: true,
+      file: {},
+      file_info: result,
+      id: result.id,
+      name: result.name,
+      parse_status: 'success',
+      size: result.size,
+      upload_progress: 100,
+      upload_status: 'success'
+    }));
 
     // 伪装调用获取用户信息
     fakeRequest(refreshToken)
       .catch(err => logger.error(err));
 
-    // 创建会话
-    const convId = await createConversation("未命名会话", refreshToken);
+    const sendMessages = messagesPrepare(messages, !!refConvId);
 
-    // 请求流
-    const {
-      accessToken,
-      userId
-    } = await acquireToken(refreshToken);
-    const sendMessages = messagesPrepare(messages);
-    const result = await axios.post(`https://kimi.moonshot.cn/api/chat/${convId}/completion/stream`, {
-      messages: sendMessages,
-      refs,
-      use_search: useSearch
-    }, {
-      // 120秒超时
-      timeout: 120000,
-      headers: {
-        Authorization: `Bearer ${accessToken}`,
-        Referer: `https://kimi.moonshot.cn/chat/${convId}`,
-        'X-Traffic-Id': userId,
-        ...FAKE_HEADERS
+    preN2s(model, sendMessages, refs, refreshToken, convId)
+      .catch(err => logger.error(err));
+    getSuggestion(sendMessages[0].content, refreshToken)
+      .catch(err => logger.error(err));
+    tokenSize(sendMessages[0].content, refs, refreshToken, convId)
+      .catch(err => logger.error(err));
+    
+    const isMath = model.indexOf('math') != -1;
+    const isSearchModel = model.indexOf('search') != -1;
+    const isResearchModel = model.indexOf('research') != -1;
+    const isK1Model = model.indexOf('k1') != -1;
+
+    logger.info(`使用模型: ${model}，是否联网检索: ${isSearchModel}，是否探索版: ${isResearchModel}，是否K1模型: ${isK1Model}，是否数学模型: ${isMath}`);
+
+    // 检查探索版使用量
+    if(isResearchModel) {
+      const {
+        total,
+        used
+      } = await getResearchUsage(refreshToken);
+      if(used >= total)
+        throw new APIException(EX.API_RESEARCH_EXCEEDS_LIMIT, `探索版使用量已达到上限`);
+      logger.info(`探索版当前额度: ${used}/${total}`);
+    }
+
+    const kimiplusId = isK1Model ? 'crm40ee9e5jvhsn7ptcg' : (/^[0-9a-z]{20}$/.test(model) ? model : 'kimi');
+
+    // 请求补全流
+    const stream = await request('POST', `/api/chat/${convId}/completion/stream`, refreshToken, {
+      data: {
+        kimiplus_id: kimiplusId,
+        messages: sendMessages,
+        refs,
+        refs_file: refsFile,
+        use_math: isMath,
+        use_research: isResearchModel,
+        use_search: isSearchModel,
+        extend: { sidebar: true }
+      },
+      headers: {
+        Referer: `https://kimi.moonshot.cn/chat/${convId}`
       },
-      validateStatus: () => true,
       responseType: 'stream'
     });
+
     const streamStartTime = util.timestamp();
     // 创建转换流将消息格式转换为gpt兼容格式
-    return createTransStream(model, convId, result.data, () => {
+    return createTransStream(model, convId, stream, () => {
       logger.success(`Stream has completed transfer ${util.timestamp() - streamStartTime}ms`);
       // 流传输结束后异步移除会话，如果消息不合规，此操作可能会抛出数据库错误异常，请忽略
-      removeConversation(convId, refreshToken)
-        .catch(err => console.error(err));
-      promptSnippetSubmit(sendMessages[0].content, refreshToken)
+      // 如果引用会话将不会清除，因为我们不知道什么时候你会结束会话
+      !refConvId && removeConversation(convId, refreshToken)
         .catch(err => console.error(err));
     });
   })()
@@ -366,7 +498,7 @@ async function createCompletionStream(model = MODEL_NAME, messages: any[], refre
         logger.warn(`Try again after ${RETRY_DELAY / 1000}s...`);
         return (async () => {
           await new Promise(resolve => setTimeout(resolve, RETRY_DELAY));
-          return createCompletionStream(model, messages, refreshToken, useSearch, retryCount + 1);
+          return createCompletionStream(model, messages, refreshToken, refConvId, retryCount + 1);
         })();
       }
       throw err;
@@ -381,32 +513,29 @@ async function createCompletionStream(model = MODEL_NAME, messages: any[], refre
  * @param refreshToken 用于刷新access_token的refresh_token
  */
 async function fakeRequest(refreshToken: string) {
-  const {
-    accessToken,
-    userId
-  } = await acquireToken(refreshToken);
-  const options = {
-    headers: {
-      Authorization: `Bearer ${accessToken}`,
-      Referer: `https://kimi.moonshot.cn/`,
-      'X-Traffic-Id': userId,
-      ...FAKE_HEADERS
-    }
-  };
   await [
-    () => axios.get('https://kimi.moonshot.cn/api/user', options),
-    () => axios.get('https://kimi.moonshot.cn/api/chat_1m/user/status', options),
-    () => axios.post('https://kimi.moonshot.cn/api/chat/list', {
-      offset: 0,
-      size: 50
-    }, options),
-    () => axios.post('https://kimi.moonshot.cn/api/show_case/list', {
-      offset: 0,
-      size: 4,
-      enable_cache: true,
-      order: "asc"
-    }, options)
-  ][Math.floor(Math.random() * 4)]();
+    () => request('GET', '/api/user', refreshToken),
+    () => request('POST', '/api/user/usage', refreshToken, {
+      data: {
+        usage: ['kimiv', 'math']
+      }
+    }),
+    () => request('GET', '/api/chat_1m/user/status', refreshToken),
+    () => request('GET', '/api/kimi_mv/user/status', refreshToken),
+    () => request('POST', '/api/kimiplus/history', refreshToken),
+    () => request('POST', '/api/kimiplus/search', refreshToken, {
+      data: {
+        offset: 0,
+        size: 20
+      }
+    }),
+    () => request('POST', '/api/chat/list', refreshToken, {
+      data: {
+        offset: 0,
+        size: 50
+      }
+    }),
+  ][Math.floor(Math.random() * 7)]();
 }
 
 /**
@@ -447,14 +576,28 @@ function extractRefFileUrls(messages: any[]) {
  * user:新消息
  * 
  * @param messages 参考gpt系列消息格式，多轮对话请完整提供上下文
+ * @param isRefConv 是否为引用会话
  */
-function messagesPrepare(messages: any[]) {
-  // 注入消息提升注意力
-  let latestMessage = messages[messages.length - 1];
-  let hasFileOrImage = Array.isArray(latestMessage.content)
-    && latestMessage.content.some(v => (typeof v === 'object' && ['file', 'image_url'].includes(v['type'])));
-  // 第二轮开始注入system prompt
-  if (messages.length > 2) {
+function messagesPrepare(messages: any[], isRefConv = false) {
+  let content;
+  if (isRefConv || messages.length < 2) {
+    content = messages.reduce((content, message) => {
+      if (_.isArray(message.content)) {
+        return message.content.reduce((_content, v) => {
+          if (!_.isObject(v) || v['type'] != 'text') return _content;
+          return _content + `${v["text"] || ""}\n`;
+        }, content);
+      }
+      return content += `${message.role == 'user' ? wrapUrlsToTags(message.content) : message.content}\n`;
+    }, '')
+    logger.info("\n透传内容：\n" + content);
+  }
+  else {
+    // 注入消息提升注意力
+    let latestMessage = messages[messages.length - 1];
+    let hasFileOrImage = Array.isArray(latestMessage.content)
+      && latestMessage.content.some(v => (typeof v === 'object' && ['file', 'image_url'].includes(v['type'])));
+    // 第二轮开始注入system prompt
     if (hasFileOrImage) {
       let newFileMessage = {
         "content": "关注用户最新发送文件和消息",
@@ -470,18 +613,18 @@ function messagesPrepare(messages: any[]) {
       messages.splice(messages.length - 1, 0, newTextMessage);
       logger.info("注入提升尾部消息注意力system prompt");
     }
+    content = messages.reduce((content, message) => {
+      if (_.isArray(message.content)) {
+        return message.content.reduce((_content, v) => {
+          if (!_.isObject(v) || v['type'] != 'text') return _content;
+          return _content + `${message.role || "user"}:${v["text"] || ""}\n`;
+        }, content);
+      }
+      return content += `${message.role || "user"}:${message.role == 'user' ? wrapUrlsToTags(message.content) : message.content}\n`;
+    }, '')
+    logger.info("\n对话合并：\n" + content);
   }
 
-  const content = messages.reduce((content, message) => {
-    if (Array.isArray(message.content)) {
-      return message.content.reduce((_content, v) => {
-        if (!_.isObject(v) || v['type'] != 'text') return _content;
-        return _content + `${message.role || "user"}:${v["text"] || ""}\n`;
-      }, content);
-    }
-    return content += `${message.role || "user"}:${message.role == 'user' ? wrapUrlsToTags(message.content) : message.content}\n`;
-  }, '');
-  logger.info("\n对话合并：\n" + content);
   return [
     { role: 'user', content }
   ]
@@ -504,13 +647,13 @@ function wrapUrlsToTags(content: string) {
  * @param filename 文件名称
  * @param refreshToken 用于刷新access_token的refresh_token
  */
-async function preSignUrl(filename: string, refreshToken: string) {
+async function preSignUrl(action: string, filename: string, refreshToken: string) {
   const {
     accessToken,
     userId
   } = await acquireToken(refreshToken);
   const result = await axios.post('https://kimi.moonshot.cn/api/pre-sign-url', {
-    action: 'file',
+    action,
     name: filename
   }, {
     timeout: 15000,
@@ -552,8 +695,9 @@ async function checkFileUrl(fileUrl: string) {
  * 
  * @param fileUrl 文件URL
  * @param refreshToken 用于刷新access_token的refresh_token
+ * @param refConvId 引用会话ID
  */
-async function uploadFile(fileUrl: string, refreshToken: string) {
+async function uploadFile(fileUrl: string, refreshToken: string, refConvId?: string) {
   // 预检查远程文件URL可用性
   await checkFileUrl(fileUrl);
 
@@ -577,11 +721,14 @@ async function uploadFile(fileUrl: string, refreshToken: string) {
     }));
   }
 
+  const fileType = (mimeType || '').includes('image') ? 'image' : 'file';
+
   // 获取预签名文件URL
-  const {
+  let {
     url: uploadUrl,
-    object_name: objectName
-  } = await preSignUrl(filename, refreshToken);
+    object_name: objectName,
+    file_id: fileId
+  } = await preSignUrl(fileType, filename, refreshToken);
 
   // 获取文件的MIME类型
   mimeType = mimeType || mime.getType(filename);
@@ -609,37 +756,58 @@ async function uploadFile(fileUrl: string, refreshToken: string) {
   });
   checkResult(result, refreshToken);
 
-  // 获取文件上传结果
-  result = await axios.post('https://kimi.moonshot.cn/api/file', {
-    type: 'file',
-    name: filename,
-    object_name: objectName,
-    timeout: 15000
-  }, {
-    headers: {
-      Authorization: `Bearer ${accessToken}`,
-      Referer: `https://kimi.moonshot.cn/`,
-      'X-Traffic-Id': userId,
-      ...FAKE_HEADERS
-    }
-  });
-  const { id: fileId } = checkResult(result, refreshToken);
+  let status, startTime = Date.now();
+  let fileDetail;
+  while (status != 'initialized' && status != 'parsed') {
+    if (Date.now() - startTime > 30000)
+      throw new Error('文件等待处理超时');
+    // 获取文件上传结果
+    result = await axios.post('https://kimi.moonshot.cn/api/file', fileType == 'image' ? {
+      type: 'image',
+      file_id: fileId,
+      name: filename
+    } : {
+      type: 'file',
+      name: filename,
+      object_name: objectName,
+      file_id: '',
+      chat_id: refConvId
+    }, {
+      headers: {
+        Authorization: `Bearer ${accessToken}`,
+        Referer: `https://kimi.moonshot.cn/`,
+        'X-Traffic-Id': userId,
+        ...FAKE_HEADERS
+      }
+    });
+    fileDetail = checkResult(result, refreshToken);
+    ({ id: fileId, status } = fileDetail);
+  }
 
-  // 处理文件转换
-  result = await axios.post('https://kimi.moonshot.cn/api/file/parse_process', {
-    ids: [fileId],
-    timeout: 120000
-  }, {
-    headers: {
-      Authorization: `Bearer ${accessToken}`,
-      Referer: `https://kimi.moonshot.cn/`,
-      'X-Traffic-Id': userId,
-      ...FAKE_HEADERS
-    }
-  });
-  checkResult(result, refreshToken);
+  startTime = Date.now();
+  let parseFinish = status == 'parsed';
+  while (!parseFinish) {
+    if (Date.now() - startTime > 30000)
+      throw new Error('文件等待处理超时');
+    // 处理文件转换
+    parseFinish = await new Promise(resolve => {
+      axios.post('https://kimi.moonshot.cn/api/file/parse_process', {
+        ids: [fileId],
+        timeout: 120000
+      }, {
+        headers: {
+          Authorization: `Bearer ${accessToken}`,
+          Referer: `https://kimi.moonshot.cn/`,
+          'X-Traffic-Id': userId,
+          ...FAKE_HEADERS
+        }
+      })
+        .then(() => resolve(true))
+        .catch(() => resolve(false));
+    });
+  }
 
-  return fileId;
+  return fileDetail;
 }
 
 /**
@@ -672,7 +840,9 @@ function checkResult(result: AxiosResponse, refreshToken: string) {
  * @param convId 会话ID
  * @param stream 消息流
  */
-async function receiveStream(model: string, convId: string, stream: any) {
+async function receiveStream(model: string, convId: string, stream: any): Promise<IStreamMessage> {
+  let webSearchCount = 0;
+  let temp = Buffer.from('');
   return new Promise((resolve, reject) => {
     // 消息初始化
     const data = {
@@ -683,10 +853,11 @@ async function receiveStream(model: string, convId: string, stream: any) {
         { index: 0, message: { role: 'assistant', content: '' }, finish_reason: 'stop' }
       ],
       usage: { prompt_tokens: 1, completion_tokens: 1, total_tokens: 2 },
+      segment_id: '',
       created: util.unixTimestamp()
     };
     let refContent = '';
-    const silentSearch = model.indexOf('silent_search') != -1;
+    const silentSearch = model.indexOf('silent') != -1;
     const parser = createParser(event => {
       try {
         if (event.type !== "event") return;
@@ -696,8 +867,16 @@ async function receiveStream(model: string, convId: string, stream: any) {
           throw new Error(`Stream response invalid: ${event.data}`);
         // 处理消息
         if (result.event == 'cmpl' && result.text) {
-          const exceptCharIndex = result.text.indexOf("<22>");
-          data.choices[0].message.content += result.text.substring(0, exceptCharIndex == -1 ? result.text.length : exceptCharIndex);
+          data.choices[0].message.content += result.text;
+        }
+        // 处理请求ID
+        else if(result.event == 'req') {
+          data.segment_id = result.id;
+        }
+        // 处理超长文本
+        else if(result.event == 'length') {
+          logger.warn('此次生成达到max_tokens，稍候将继续请求拼接完整响应');
+          data.choices[0].finish_reason = 'length';
         }
         // 处理结束或错误
         else if (result.event == 'all_done' || result.event == 'error') {
@@ -706,8 +885,10 @@ async function receiveStream(model: string, convId: string, stream: any) {
           resolve(data);
         }
         // 处理联网搜索
-        else if (!silentSearch && result.event == 'search_plus' && result.msg && result.msg.type == 'get_res')
-          refContent += `${result.msg.title} - ${result.msg.url}\n`;
+        else if (!silentSearch && result.event == 'search_plus' && result.msg && result.msg.type == 'get_res') {
+          webSearchCount += 1;
+          refContent += `【检索 ${webSearchCount}】 [${result.msg.title}](${result.msg.url})\n\n`;
+        }
         // else
         //   logger.warn(result.event, result);
       }
@@ -717,7 +898,20 @@ async function receiveStream(model: string, convId: string, stream: any) {
       }
     });
     // 将流数据喂给SSE转换器
-    stream.on("data", buffer => parser.feed(buffer.toString()));
+    stream.on("data", buffer => {
+      // 检查buffer是否以完整UTF8字符结尾
+      if (buffer.toString().indexOf('<27>') != -1) {
+        // 如果不完整则累积buffer直到收到完整字符
+        temp = Buffer.concat([temp, buffer]);
+        return;
+      }
+      // 将之前累积的不完整buffer拼接
+      if (temp.length > 0) {
+        buffer = Buffer.concat([temp, buffer]);
+        temp = Buffer.from('');
+      }
+      parser.feed(buffer.toString());
+    });
     stream.once("error", err => reject(err));
     stream.once("close", () => resolve(data));
   });
@@ -738,8 +932,11 @@ function createTransStream(model: string, convId: string, stream: any, endCallba
   const created = util.unixTimestamp();
   // 创建转换流
   const transStream = new PassThrough();
+  let webSearchCount = 0;
   let searchFlag = false;
-  const silentSearch = model.indexOf('silent_search') != -1;
+  let lengthExceed = false;
+  let segmentId = '';
+  const silentSearch = model.indexOf('silent') != -1;
   !transStream.closed && transStream.write(`data: ${JSON.stringify({
     id: convId,
     model,
@@ -747,6 +944,7 @@ function createTransStream(model: string, convId: string, stream: any, endCallba
     choices: [
       { index: 0, delta: { role: 'assistant', content: '' }, finish_reason: null }
     ],
+    segment_id: '',
     created
   })}\n\n`);
   const parser = createParser(event => {
@@ -767,12 +965,21 @@ function createTransStream(model: string, convId: string, stream: any, endCallba
           choices: [
             { index: 0, delta: { content: (searchFlag ? '\n' : '') + chunk }, finish_reason: null }
           ],
+          segment_id: segmentId,
           created
         })}\n\n`;
         if (searchFlag)
           searchFlag = false;
         !transStream.closed && transStream.write(data);
       }
+      // 处理请求ID
+      else if(result.event == 'req') {
+        segmentId = result.id;
+      }
+      // 处理超长文本
+      else if (result.event == 'length') {
+        lengthExceed = true;
+      }
       // 处理结束或错误
       else if (result.event == 'all_done' || result.event == 'error') {
         const data = `data: ${JSON.stringify({
@@ -783,10 +990,11 @@ function createTransStream(model: string, convId: string, stream: any, endCallba
             {
               index: 0, delta: result.event == 'error' ? {
                 content: '\n[内容由于不合规被停止生成，我们换个话题吧]'
-              } : {}, finish_reason: 'stop'
+              } : {}, finish_reason: lengthExceed ? 'length' : 'stop'
             }
           ],
           usage: { prompt_tokens: 1, completion_tokens: 1, total_tokens: 2 },
+          segment_id: segmentId,
           created
         })}\n\n`;
         !transStream.closed && transStream.write(data);
@@ -797,6 +1005,7 @@ function createTransStream(model: string, convId: string, stream: any, endCallba
       else if (!silentSearch && result.event == 'search_plus' && result.msg && result.msg.type == 'get_res') {
         if (!searchFlag)
           searchFlag = true;
+        webSearchCount += 1;
         const data = `data: ${JSON.stringify({
           id: convId,
           model,
@@ -804,10 +1013,11 @@ function createTransStream(model: string, convId: string, stream: any, endCallba
           choices: [
             {
               index: 0, delta: {
-                content: `检索 ${result.msg.title} - ${result.msg.url} ...\n`
+                content: `【检索 ${webSearchCount}】 [${result.msg.title}](${result.msg.url})\n`
               }, finish_reason: null
             }
           ],
+          segment_id: segmentId,
           created
         })}\n\n`;
         !transStream.closed && transStream.write(data);

src/api/interfaces/IStreamMessage.ts

@@ -0,0 +1,20 @@
+export default interface IStreamMessage {
+  id: string;
+  model: string;
+  object: string;
+  choices: {
+    index: number;
+    message: {
+      role: string;
+      content: string;
+    };
+    finish_reason: string;
+  }[];
+  usage: {
+    prompt_tokens: number;
+    completion_tokens: number;
+    total_tokens: number;
+  };
+  segment_id?: string;
+  created: number;
+}

src/api/routes/chat.ts

@@ -13,22 +13,26 @@ export default {
 
         '/completions': async (request: Request) => {
             request
+                .validate('body.conversation_id', v => _.isUndefined(v) || _.isString(v))
                 .validate('body.messages', _.isArray)
                 .validate('headers.authorization', _.isString)
             // refresh_token切分
             const tokens = chat.tokenSplit(request.headers.authorization);
             // 随机挑选一个refresh_token
             const token = _.sample(tokens);
-            const model = request.body.model;
-            const messages =  request.body.messages;
-            if (request.body.stream) {
-                const stream = await chat.createCompletionStream(model, messages, token, request.body.use_search);
+            let { model, conversation_id: convId, messages, stream, use_search } = request.body;
+
+            if(use_search)
+                model = 'kimi-search';
+
+            if (stream) {
+                const stream = await chat.createCompletionStream(model, messages, token, convId);
                 return new Response(stream, {
                     type: "text/event-stream"
                 });
             }
             else
-                return await chat.createCompletion(model, messages, token, request.body.use_search);
+                return await chat.createCompletion(model, messages, token, convId);
         }
 
     }

src/api/routes/index.ts

@@ -4,6 +4,7 @@ import Response from '@/lib/response/Response.ts';
 import chat from "./chat.ts";
 import ping from "./ping.ts";
 import token from './token.ts';
+import models from './models.ts';
 
 export default [
     {
@@ -21,5 +22,6 @@ export default [
     },
     chat,
     ping,
-    token
+    token,
+    models
 ];

src/api/routes/models.ts

@@ -0,0 +1,41 @@
+import _ from 'lodash';
+
+export default {
+
+    prefix: '/v1',
+
+    get: {
+        '/models': async () => {
+            return {
+                "data": [
+                    {
+                        "id": "moonshot-v1",
+                        "object": "model",
+                        "owned_by": "kimi-free-api"
+                    },
+                    {
+                        "id": "moonshot-v1-8k",
+                        "object": "model",
+                        "owned_by": "kimi-free-api"
+                    },
+                    {
+                        "id": "moonshot-v1-32k",
+                        "object": "model",
+                        "owned_by": "kimi-free-api"
+                    },
+                    {
+                        "id": "moonshot-v1-128k",
+                        "object": "model",
+                        "owned_by": "kimi-free-api"
+                    },
+                    {
+                        "id": "moonshot-v1-vision",
+                        "object": "model",
+                        "owned_by": "kimi-free-api"
+                    }
+                ]
+            };
+        }
+
+    }
+}