perf: deploy (#6972)

* perf: deploy * doc

perf: deploy (#6972)
* perf: deploy * doc
f33c80a6 · Archer · GitHub · 14373770 · f33c80a6 · f33c80a6
Commit f33c80a6 authored May 24, 2026 by Archer Committed by GitHub May 24, 2026
54 changed files
--- a/deploy/README.md
+++ b/deploy/README.md
@@ -2,59 +2,36 @@
 ### 正常更新（不动服务，只改版本）
-1. 更新 `args.json` 中的版本号
+1. 更新 `version/{version}/args.json` 中的版本号，例如 `version/v4.14/args.json` 或 `version/main/args.json`
-2. 在 `FastGPT` 目录执行 `pnpm run gen:deploy` 即可
+2. 在 `FastGPT` 目录执行 `node deploy/init.mjs` 即可
+3. 脚本会同时更新 `deploy/dev`、`document/public/deploy/install.sh` 和 `document/public/deploy/docker/{version}` 下的 Docker 部署文件
+### 加版本
+比如要添加 `v4.15` 稳定版：
+1. 创建 `version/v4.15`
+2. 添加 `version/v4.15/args.json`
+3. 添加 `version/v4.15/docker-compose.template.yml`
+4. 执行 `node deploy/init.mjs`，脚本会自动扫描并生成 `document/public/deploy/docker/v4.15`
 ### 加服务
 比如要添加 `example` 服务:
 1. `init.mjs` 的 `Services Enum` 中添加 fastgptExample: fastgpt-example
-2. 在 `args.json` 中添加 image 和 tag, 注意 `args.json` 的 `key` 值，要和 `init.mjs` 的 `value` 值一致。
+2. 在所有 `version/*/args.json` 中添加 image 和 tag, 注意 `args` 的 `key` 值，要和 `init.mjs` 的 `value` 值一致。
-3. 更新 templates/docker-compose.[dev|prod].yml 文件，把服务的相关配置加进去，并且：服务的 image 改为 ${{example.image}}:${{example.tag}}
+3. 更新所有需要生效的 `version/*/docker-compose.template.yml` 文件，把服务的相关配置加进去，并且：服务的 image 改为 ${{example.image}}:${{example.tag}}
+4. 如需同步开发环境，再更新 `templates/docker-compose.dev.yml`
+5. 执行 `node deploy/init.mjs` 重新生成部署文件
 ### 加向量库
 比如添加 `exampleDB` 向量库:
 1. 添加 vector service 配置在 `templates/vector` 下面，例如 `templates/vector/exampleDB.txt` 内容可以参考其他 txt，注意缩进，image 名字也要替换成 ${{exampleDB.image}}:${{exampleDB:tag}}, service name 必须是 `vectorDB`
-2. 在 `args.json` 中添加 `exampleDB` 的配置
+2. 在所有 `version/*/args.json` 中添加 `exampleDB` 的配置
-3. init.mjs vector enum 中添加 `vector`
+3. 添加连接配置片段，例如 `templates/vector/exampleDB.config.txt`
-4. init.mjs 中添加 vector 的相关配置:
+4. 如需额外 `configs`，添加 `templates/vector/exampleDB.extra.txt`
+5. 在 `templates/vector/config.json` 中添加向量库配置，声明输出文件名、service 片段、连接配置和 extra 片段
-```ts
+6. 执行 `node deploy/init.mjs` 重新生成部署文件
-const vector = {
-  // pg, milvus, ob ...
-  vector: {
-    db: '', // 空即可
-    config: `/
-  VECTOR_URL:vectordb://xxxxx
-    `, //注意 第一行反引号后面的 / 不能少（去除首个换行符）; 左边的两个空格的缩进不能变，否则会语法错误
-    extra: `` // 额外的配置，可以看 ob 的那个，需要一个 config 字段引入 init.sql
-  }
-}
-```
-5. init.mjs 读入 vector 配置
-```json
-{ // 这是个块作用域, 直接搜 read in Vectors
-// read in Vectors
-// pg, ob ....
-const vectordb = fs.readFileSync(path.join(process.cwd(), 'templates', 'vector', 'vector.txt'));
-vector.vector.db = String(vectordb);
-}
-```
-6. init.mjs 最后生成的时候，需要添加
-```ts
-    fs.promises.writeFile(
-      path.join(process.cwd(), 'docker', 'cn', 'docker-compose.vector.yml'),
-      replace(template, 'cn', VectorEnum.vector)
-    ),
-    fs.promises.writeFile(
-      path.join(process.cwd(), 'docker', 'global', 'docker-compose.zilliz.yml'),
-      replace(template, 'global', VectorEnum.vector)
-    ),
-```
 ## yaml 的锚点和引用

--- a/deploy/dev/docker-compose.cn.yml
+++ b/deploy/dev/docker-compose.cn.yml
@@ -174,7 +174,7 @@ services:
      retries: 3
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.15.0-beta1
    ports:
      - 3002:3000
    networks:
@@ -220,7 +220,7 @@ services:
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.15.0-beta1
    ports:
      - 3003:3000
    networks:
@@ -281,7 +281,7 @@ services:
      retries: 5
  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
  opensandbox-agent-sandbox-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.2.0
    profiles:
      - prepull
  opensandbox-execd-image:
@@ -294,7 +294,7 @@ services:
      - prepull
  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
  fastgpt-volume-manager:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.2.0
    container_name: fastgpt-volume-manager
    restart: always
    ports:
@@ -323,7 +323,7 @@ services:
  # AI Proxy
  fastgpt-aiproxy:
-    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.6
+    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    ports:

--- a/deploy/dev/docker-compose.yml
+++ b/deploy/dev/docker-compose.yml
@@ -174,7 +174,7 @@ services:
      retries: 3
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.20
+    image: ghcr.io/labring/fastgpt-code-sandbox:v4.15.0-beta1
    ports:
      - 3002:3000
    networks:
@@ -220,7 +220,7 @@ services:
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.20
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.15.0-beta1
    ports:
      - 3003:3000
    networks:
@@ -281,7 +281,7 @@ services:
      retries: 5
  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
  opensandbox-agent-sandbox-image:
-    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1
+    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.2.0
    profiles:
      - prepull
  opensandbox-execd-image:
@@ -294,7 +294,7 @@ services:
      - prepull
  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
  fastgpt-volume-manager:
-    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1
+    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.2.0
    container_name: fastgpt-volume-manager
    restart: always
    ports:
@@ -323,7 +323,7 @@ services:
  # AI Proxy
  fastgpt-aiproxy:
-    image: ghcr.io/labring/aiproxy:v0.5.6
+    image: ghcr.io/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    ports:

--- a/deploy/init.mjs
+++ b/deploy/init.mjs
@@ -10,18 +10,6 @@ const RegionEnum = {
  global: 'global'
 };
-/**
- * @enum {String} VectorEnum
- */
-const VectorEnum = {
-  pg: 'pg',
-  milvus: 'milvus',
-  zilliz: 'zilliz',
-  ob: 'ob',
-  seekdb: 'seekdb',
-  opengauss: 'opengauss'
-};
 // make sure the cwd
 const basePath = process.cwd();
 if (!basePath.endsWith('deploy')) {
@@ -29,16 +17,148 @@ if (!basePath.endsWith('deploy')) {
 }
 /**
+ * 扫描 `deploy/version/*` 获取所有可发布版本。
+ *
+ * 每个版本目录必须包含 `args.json` 和 `docker-compose.template.yml`。`main`
+ * 固定作为迭代版展示，其余目录名都作为稳定版展示；这里仅负责发现和排序。
+ *
+ * @returns {Promise<string[]>}
+ */
+const loadDeployVersions = async () => {
+  const versionRoot = path.join(process.cwd(), 'version');
+  const entries = await fs.promises.readdir(versionRoot, { withFileTypes: true });
+  const versions = [];
+  for (const entry of entries) {
+    if (!entry.isDirectory()) {
+      continue;
+    }
+    const version = entry.name;
+    const versionPath = path.join(versionRoot, version);
+    const requiredFiles = ['args.json', 'docker-compose.template.yml'];
+    const exists = await Promise.all(
+      requiredFiles.map((file) =>
+        fs.promises
+          .access(path.join(versionPath, file))
+          .then(() => true)
+          .catch(() => false)
+      )
+    );
+    if (exists.every(Boolean)) {
+      versions.push(version);
+    }
+  }
+  if (versions.length === 0) {
+    throw new Error('No deploy versions found in deploy/version');
+  }
+  return versions.sort((a, b) => {
+    if (a === 'main') return 1;
+    if (b === 'main') return -1;
+    return a.localeCompare(b, undefined, { numeric: true });
+  });
+};
+/**
+ * 将扫描到的版本列表写入安装脚本。
+ *
+ * `install.sh` 会被用户单独下载执行，版本列表不能依赖另一个运行时请求。
+ * 这里用固定标记替换生成片段，保持脚本入口和 deploy/version 目录一致。
+ *
+ * @param {string[]} deployVersions
+ */
+const syncInstallScriptVersions = async (deployVersions) => {
+  const installScriptPath = path.join(
+    process.cwd(),
+    '..',
+    'document',
+    'public',
+    'deploy',
+    'install.sh'
+  );
+  const begin = '# BEGIN GENERATED DEPLOY VERSIONS';
+  const end = '# END GENERATED DEPLOY VERSIONS';
+  const escapeRegExp = (value) => value.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
+  const shellQuote = (value) =>
+    `"${String(value)
+      .replace(/\\/g, '\\\\')
+      .replace(/"/g, '\\"')
+      .replace(/\$/g, '\\$')
+      .replace(/`/g, '\\`')}"`;
+  const versionsBlock = [
+    begin,
+    'DEPLOY_VERSIONS=(',
+    ...deployVersions.map((version) => `    ${shellQuote(version)}`),
+    ')',
+    end
+  ].join('\n');
+  const source = await fs.promises.readFile(installScriptPath, 'utf8');
+  const blockPattern = new RegExp(`${escapeRegExp(begin)}[\\s\\S]*?${escapeRegExp(end)}`);
+  if (!blockPattern.test(source)) {
+    throw new Error('Can not find generated deploy versions block in install.sh');
+  }
+  await fs.promises.writeFile(installScriptPath, source.replace(blockPattern, versionsBlock));
+};
+/**
+ * 读取共享向量库模板配置。
+ *
+ * `deploy/templates/vector/config.json` 维护向量库输出文件名、服务片段、连接配置
+ * 和额外 configs。版本模板只通过 `${{vec.*}}` 引用这些共享片段。
+ *
+ * @returns {Promise<Record<string, { filename: string, db: string, config: string, extra: string }>>}
+ */
+const loadVectorConfigs = async () => {
+  const vectorRoot = path.join(process.cwd(), 'templates', 'vector');
+  const vectorConfig = JSON.parse(
+    await fs.promises.readFile(path.join(vectorRoot, 'config.json'), 'utf8')
+  );
+  const vectors = {};
+  for (const [name, config] of Object.entries(vectorConfig)) {
+    const readOptionalFile = async (file) => {
+      if (!file) {
+        return '';
+      }
+      return (await fs.promises.readFile(path.join(vectorRoot, file), 'utf8')).replace(/\n$/, '');
+    };
+    vectors[name] = {
+      filename: config.filename,
+      db: await readOptionalFile(config.dbFile),
+      config: await readOptionalFile(config.configFile),
+      extra: await readOptionalFile(config.extraFile)
+    };
+    vectors[name].extraBlock = vectors[name].extra ? `configs:\n  ${vectors[name].extra}` : '';
+  }
+  return vectors;
+};
+/**
 * @typedef {{ tag: String, image: {cn: String, global: String} }} ArgItemType
 */
-/** format the args
+/**
- * @type {Record<Services, ArgItemType>}
+ * 读取指定部署版本的镜像参数。
+ *
+ * dev 默认使用 main 的参数；prod 按版本目录分别读取，避免稳定版 tag 被 main
+ * 分支的迭代镜像意外覆盖。
+ *
+ * @param {string} version
+ * @returns {Record<Services, ArgItemType>}
 */
-const args = (() => {
+const loadArgs = (version) => {
  /**
   * @type {{tags: Record<Services, string>, images: Record<Services, Record<string, string>>}}
   */
-  const obj = JSON.parse(fs.readFileSync(path.join(process.cwd(), 'args.json')));
+  const obj = JSON.parse(fs.readFileSync(path.join(process.cwd(), 'version', version, 'args.json')));
  const args = {};
  for (const key of Object.keys(obj.tags)) {
    args[key] = {
@@ -50,65 +170,18 @@ const args = (() => {
    };
  }
  return args;
-})();
-const vector = {
-  pg: {
-    db: '',
-    config: `\
-  PG_URL: postgresql://username:password@fastgpt-vector:5432/postgres`,
-    extra: ''
-  },
-  milvus: {
-    db: '',
-    config: `\
-  MILVUS_ADDRESS: http://fastgpt-vector:19530
-  MILVUS_TOKEN: none
-    `,
-    extra: ''
-  },
-  zilliz: {
-    db: '',
-    config: `\
-  MILVUS_ADDRESS: zilliz_cloud_address
-  MILVUS_TOKEN: zilliz_cloud_token`,
-    extra: ''
-  },
-  ob: {
-    db: '',
-    config: `\
-  OCEANBASE_URL: mysql://root%40tenantname:tenantpassword@fastgpt-vector:2881/mysql
-`,
-    extra: `\
-init_sql:
-    name: init_sql
-    content: |
-      ALTER SYSTEM SET ob_vector_memory_limit_percentage = 30;
-    `
-  },
-  seekdb: {
-    db: '',
-    config: `\
-  SEEKDB_URL: mysql://root:seekdbpassword@fastgpt-vector:2881/mysql
-`,
-    extra: ``
-  },
-  opengauss: {
-    db: '',
-    config: `\
-  OPENGAUSS_URL: postgresql://gaussdb:FastGPT@123@fastgpt-vector:5432/fastgpt`,
-    extra: ''
-  },
 };
 /**
 * replace all ${{}}
 * @param {string} source
 * @param {RegionEnum} region
- * @param {VectorEnum} vec
+ * @param {string | undefined} vec
+ * @param {Record<Services, ArgItemType>} args
+ * @param {Record<string, { filename: string, db: string, config: string, extra: string }>} vectors
 * @returns {string}
 */
-const replace = (source, region, vec) => {
+const replace = (source, region, vec, args, vectors) => {
  // Match ${{expr}}, capture "expr" inside {{}}
  return source.replace(/\$\{\{([^}]*)\}\}/g, (_, expr) => {
    // expr: a.b
@@ -117,10 +190,14 @@ const replace = (source, region, vec) => {
     */
    const [a, b] = expr.split('.');
    if (a === 'vec') {
+      if (!vectors[vec]) {
+        throw new Error(`Unknown vector config: ${vec}`);
+      }
      if (b === 'db') {
-        return replace(vector[vec].db, region, vec);
+        return replace(vectors[vec].db, region, vec, args, vectors);
      } else {
-        return vector[vec][b];
+        return vectors[vec][b];
      }
    }
@@ -131,113 +208,81 @@ const replace = (source, region, vec) => {
    }
  });
 };
-{
-  // read in Vectors
-  const pg = fs.readFileSync(path.join(process.cwd(), 'templates', 'vector', 'pg.txt'));
-  vector.pg.db = String(pg);
-  const milvus = fs.readFileSync(path.join(process.cwd(), 'templates', 'vector', 'milvus.txt'));
-  vector.milvus.db = String(milvus);
-  const ob = fs.readFileSync(path.join(process.cwd(), 'templates', 'vector', 'ob.txt'));
-  vector.ob.db = String(ob);
-  const seekdb = fs.readFileSync(path.join(process.cwd(), 'templates', 'vector', 'seekdb.txt'));
+const formatYamlOutput = (source) => `${source.trimEnd()}\n`;
-  vector.seekdb.db = String(seekdb);
-  const opengauss = fs.readFileSync(path.join(process.cwd(), 'templates', 'vector', 'opengauss.txt'));
+const generateDevFile = async (deployVersions, vectors) => {
-  vector.opengauss.db = String(opengauss);
-}
-const generateDevFile = async () => {
  console.log('generating dev/docker-compose.yml');
  // 1. read template
  const template = await fs.promises.readFile(
    path.join(process.cwd(), 'templates', 'docker-compose.dev.yml'),
    'utf8'
  );
+  const defaultDevVersion = deployVersions.includes('main') ? 'main' : deployVersions[0];
+  const args = loadArgs(defaultDevVersion);
  await Promise.all([
    fs.promises.writeFile(
      path.join(process.cwd(), 'dev', 'docker-compose.cn.yml'),
-      replace(template, 'cn')
+      formatYamlOutput(replace(template, 'cn', undefined, args, vectors))
    ),
    fs.promises.writeFile(
      path.join(process.cwd(), 'dev', 'docker-compose.yml'),
-      replace(template, 'global')
+      formatYamlOutput(replace(template, 'global', undefined, args, vectors))
    )
  ]);
  console.log('success geenrate dev files');
 };
-const generateProdFile = async () => {
+/**
-  console.log('generating prod/docker-compose.yml');
+ * 生成公开下载的 Docker Compose 部署文件。
-  const template = await fs.promises.readFile(
+ *
-    path.join(process.cwd(), 'templates', 'docker-compose.prod.yml'),
+ * 每个版本使用自己的模板和镜像参数；向量库片段保持共享。
-    'utf8'
+ */
+const generateProdFile = async (deployVersions, vectors) => {
+  console.log('generating public prod docker-compose.yml files');
+  const outputRoot = path.join(process.cwd(), '..', 'document', 'public', 'deploy', 'docker');
+  const regions = Object.values(RegionEnum);
+  const versionArgs = Object.fromEntries(deployVersions.map((version) => [version, loadArgs(version)]));
+  const versionTemplates = Object.fromEntries(
+    await Promise.all(
+      deployVersions.map(async (version) => [
+        version,
+        await fs.promises.readFile(
+          path.join(process.cwd(), 'version', version, 'docker-compose.template.yml'),
+          'utf8'
+        )
+      ])
+    )
  );
-  await Promise.all([
+  await fs.promises.rm(outputRoot, { recursive: true, force: true });
-    fs.promises.writeFile(
+  await fs.promises.mkdir(outputRoot, { recursive: true });
-      path.join(process.cwd(), 'docker', 'cn', 'docker-compose.pg.yml'),
-      replace(template, 'cn', VectorEnum.pg)
+  for (const version of deployVersions) {
-    ),
+    for (const region of regions) {
-    fs.promises.writeFile(
+      await fs.promises.mkdir(path.join(outputRoot, version, region), { recursive: true });
-      path.join(process.cwd(), 'docker', 'global', 'docker-compose.pg.yml'),
+    }
-      replace(template, 'global', VectorEnum.pg)
+  }
-    ),
-    fs.promises.writeFile(
+  await Promise.all(
-      path.join(process.cwd(), 'docker', 'cn', 'docker-compose.milvus.yml'),
+    deployVersions.flatMap((version) =>
-      replace(template, 'cn', VectorEnum.milvus)
+      regions.flatMap((region) =>
-    ),
+        Object.entries(vectors).map(([vector, { filename }]) =>
-    fs.promises.writeFile(
+          fs.promises.writeFile(
-      path.join(process.cwd(), 'docker', 'global', 'docker-compose.milvus.yml'),
+            path.join(outputRoot, version, region, `docker-compose.${filename}.yml`),
-      replace(template, 'global', VectorEnum.milvus)
+            formatYamlOutput(replace(versionTemplates[version], region, vector, versionArgs[version], vectors))
-    ),
+          )
-    fs.promises.writeFile(
+        )
-      path.join(process.cwd(), 'docker', 'cn', 'docker-compose.zilliz.yml'),
+      )
-      replace(template, 'cn', VectorEnum.zilliz)
-    ),
-    fs.promises.writeFile(
-      path.join(process.cwd(), 'docker', 'global', 'docker-compose.zilliz.yml'),
-      replace(template, 'global', VectorEnum.zilliz)
-    ),
-    fs.promises.writeFile(
-      path.join(process.cwd(), 'docker', 'cn', 'docker-compose.oceanbase.yml'),
-      replace(template, 'cn', VectorEnum.ob)
-    ),
-    fs.promises.writeFile(
-      path.join(process.cwd(), 'docker', 'global', 'docker-compose.oceanbase.yml'),
-      replace(template, 'global', VectorEnum.ob)
-    ),
-    fs.promises.writeFile(
-      path.join(process.cwd(), 'docker', 'cn', 'docker-compose.seekdb.yml'),
-      replace(template, 'cn', VectorEnum.seekdb)
-    ),
-    fs.promises.writeFile(
-      path.join(process.cwd(), 'docker', 'global', 'docker-compose.seekdb.yml'),
-      replace(template, 'global', VectorEnum.seekdb)
-    ),
-    fs.promises.writeFile(
-      path.join(process.cwd(), 'docker', 'cn', 'docker-compose.opengauss.yml'),
-      replace(template, 'cn', VectorEnum.opengauss)
-    ),
-    fs.promises.writeFile(
-      path.join(process.cwd(), 'docker', 'global', 'docker-compose.opengauss.yml'),
-      replace(template, 'global', VectorEnum.opengauss)
    )
-  ]);
+  );
  console.log('success geenrate prod files');
 };
-await Promise.all([generateDevFile(), generateProdFile()]);
+const deployVersions = await loadDeployVersions();
+await syncInstallScriptVersions(deployVersions);
-console.log('copy the docker dir to ../document/public');
+const vectors = await loadVectorConfigs();
+await Promise.all([generateDevFile(deployVersions, vectors), generateProdFile(deployVersions, vectors)]);
-await fs.promises.cp(
-  path.join(process.cwd(), 'docker'),
-  path.join(process.cwd(), '..', 'document', 'public', 'deploy', 'docker'),
-  { recursive: true }
-);
--- a/deploy/templates/vector/config.json
+++ b/deploy/templates/vector/config.json
+{
+  "pg": {
+    "filename": "pg",
+    "dbFile": "pg.txt",
+    "configFile": "pg.config.txt"
+  },
+  "milvus": {
+    "filename": "milvus",
+    "dbFile": "milvus.txt",
+    "configFile": "milvus.config.txt"
+  },
+  "zilliz": {
+    "filename": "zilliz",
+    "configFile": "zilliz.config.txt"
+  },
+  "ob": {
+    "filename": "oceanbase",
+    "dbFile": "ob.txt",
+    "configFile": "ob.config.txt",
+    "extraFile": "ob.extra.txt"
+  },
+  "seekdb": {
+    "filename": "seekdb",
+    "dbFile": "seekdb.txt",
+    "configFile": "seekdb.config.txt"
+  },
+  "opengauss": {
+    "filename": "opengauss",
+    "dbFile": "opengauss.txt",
+    "configFile": "opengauss.config.txt"
+  }
+}
--- a/deploy/templates/vector/milvus.config.txt
+++ b/deploy/templates/vector/milvus.config.txt
+  MILVUS_ADDRESS: http://fastgpt-vector:19530
+  MILVUS_TOKEN: none
--- a/deploy/templates/vector/ob.config.txt
+++ b/deploy/templates/vector/ob.config.txt
+  OCEANBASE_URL: mysql://root%40tenantname:tenantpassword@fastgpt-vector:2881/mysql
--- a/deploy/templates/vector/ob.extra.txt
+++ b/deploy/templates/vector/ob.extra.txt
+init_sql:
+    name: init_sql
+    content: |
+      ALTER SYSTEM SET ob_vector_memory_limit_percentage = 30;
--- a/deploy/templates/vector/opengauss.config.txt
+++ b/deploy/templates/vector/opengauss.config.txt
+  OPENGAUSS_URL: postgresql://gaussdb:FastGPT@123@fastgpt-vector:5432/fastgpt
--- a/deploy/templates/vector/pg.config.txt
+++ b/deploy/templates/vector/pg.config.txt
+  PG_URL: postgresql://username:password@fastgpt-vector:5432/postgres
--- a/deploy/templates/vector/seekdb.config.txt
+++ b/deploy/templates/vector/seekdb.config.txt
+  SEEKDB_URL: mysql://root:seekdbpassword@fastgpt-vector:2881/mysql
--- a/deploy/templates/vector/zilliz.config.txt
+++ b/deploy/templates/vector/zilliz.config.txt
+  MILVUS_ADDRESS: zilliz_cloud_address
+  MILVUS_TOKEN: zilliz_cloud_token
--- a/deploy/args.json
+++ b/deploy/args.json
 {
  "tags": {
-    "fastgpt": "v4.14.20",
+    "fastgpt": "v4.15.0-beta1",
-    "fastgpt-code-sandbox": "v4.14.20",
+    "fastgpt-code-sandbox": "v4.15.0-beta1",
-    "fastgpt-mcp_server": "v4.14.20",
+    "fastgpt-mcp_server": "v4.15.0-beta1",
    "fastgpt-plugin": "v0.6.2",
-    "volume-manager": "v0.1",
+    "volume-manager": "v0.2.0",
-    "agent-sandbox-image": "v0.1",
+    "agent-sandbox-image": "v0.2.0",
+    "aiproxy": "v0.5.8",
    "opensandbox-server": "v0.1.9",
    "opensandbox-execd": "v1.0.7",
    "opensandbox-egress": "v1.0.3",
-    "aiproxy": "v0.5.6",
    "aiproxy-pg": "0.8.0-pg15",
    "mongo": "5.0.32",
    "redis": "7.2-alpine",

--- a/deploy/version/main/docker-compose.template.yml
+++ b/deploy/version/main/docker-compose.template.yml
+# 用于部署的 docker-compose 文件:
+# - FastGPT 端口映射为 3000:3000
+# - FastGPT-mcp-server 端口映射 3005:3000
+# - 建议修改账密后再运行
+# root 默认密码（重启后会强制重置该密码成环境变量值）
+x-default-root-psw: &x-default-root-psw '1234'
+# 系统最高密钥凭证
+x-system-key: &x-system-key 'fastgpt-xxx'
+# plugin auth token
+x-plugin-auth-token: &x-plugin-auth-token 'token'
+# code sandbox token
+x-code-sandbox-token: &x-code-sandbox-token 'codesandbox'
+# aiproxy token
+x-aiproxy-token: &x-aiproxy-token 'token'
+# 数据库连接相关配置
+x-share-db-config: &x-share-db-config
+  MONGODB_URI: mongodb://myusername:mypassword@fastgpt-mongo:27017/fastgpt?authSource=admin
+  DB_MAX_LINK: 100
+  REDIS_URL: redis://default:mypassword@fastgpt-redis:6379
+  # @see https://doc.fastgpt.cn/self-host/config/object-storage
+  STORAGE_VENDOR: minio # minio | aws-s3 | cos | oss
+  STORAGE_REGION: us-east-1
+  STORAGE_ACCESS_KEY_ID: minioadmin
+  STORAGE_SECRET_ACCESS_KEY: minioadmin
+  STORAGE_PUBLIC_BUCKET: fastgpt-public
+  STORAGE_PRIVATE_BUCKET: fastgpt-private
+  STORAGE_EXTERNAL_ENDPOINT: http://192.168.0.2:9000 # 一个服务器和客户端均可访问到存储桶的地址，可以是固定的宿主机 IP 或者域名，注意不要填写成 127.0.0.1 或者 localhost 等本地回环地址(因为容器里无法使用)
+  STORAGE_S3_ENDPOINT: http://fastgpt-minio:9000 # 协议://域名(IP):端口
+  STORAGE_S3_FORCE_PATH_STYLE: true
+  STORAGE_S3_MAX_RETRIES: 3
+# Log 配置
+x-log-config: &x-log-config
+  LOG_ENABLE_CONSOLE: true
+  LOG_CONSOLE_LEVEL: debug
+  LOG_ENABLE_OTEL: false
+  LOG_OTEL_LEVEL: info
+  LOG_OTEL_URL: http://localhost:4318/v1/logs
+# 向量库相关配置
+x-vec-config: &x-vec-config
+${{vec.config}}
+services:
+  # Vector DB
+${{vec.db}}
+  fastgpt-mongo:
+    image: ${{mongo.image}}:${{mongo.tag}} # cpu 不支持 AVX 时候使用 4.4.29
+    container_name: fastgpt-mongo
+    restart: always
+    networks:
+      - data
+    command: mongod --keyFile /data/mongodb.key --replSet rs0
+    environment:
+      - MONGO_INITDB_ROOT_USERNAME=myusername
+      - MONGO_INITDB_ROOT_PASSWORD=mypassword
+    volumes:
+      - fastgpt-mongo:/data/db
+    healthcheck:
+      test: ['CMD', 'mongo', '-u', 'myusername', '-p', 'mypassword', '--authenticationDatabase', 'admin', '--eval', "db.adminCommand('ping')"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+      start_period: 30s
+    entrypoint:
+      - bash
+      - -c
+      - |
+        openssl rand -base64 128 > /data/mongodb.key
+        chmod 400 /data/mongodb.key
+        chown 999:999 /data/mongodb.key
+        echo 'const isInited = rs.status().ok === 1
+        if(!isInited){
+          rs.initiate({
+              _id: "rs0",
+              members: [
+                  { _id: 0, host: "fastgpt-mongo:27017" }
+              ]
+          })
+        }' > /data/initReplicaSet.js
+        # 启动MongoDB服务
+        exec docker-entrypoint.sh "$$@" &
+        # 等待MongoDB服务启动
+        until mongo -u myusername -p mypassword --authenticationDatabase admin --eval "print('waited for connection')"; do
+          echo "Waiting for MongoDB to start..."
+          sleep 2
+        done
+        # 执行初始化副本集的脚本
+        mongo -u myusername -p mypassword --authenticationDatabase admin /data/initReplicaSet.js
+        # 等待docker-entrypoint.sh脚本执行的MongoDB服务进程
+        wait $$!
+  fastgpt-redis:
+    image: ${{redis.image}}:${{redis.tag}}
+    container_name: fastgpt-redis
+    networks:
+      - data
+    restart: always
+    command: |
+      redis-server --requirepass mypassword --loglevel warning --maxclients 10000 --appendonly yes --save 60 10 --maxmemory 4gb --maxmemory-policy noeviction
+    healthcheck:
+      test: ['CMD', 'redis-cli', '-a', 'mypassword', 'ping']
+      interval: 10s
+      timeout: 3s
+      retries: 3
+      start_period: 30s
+    volumes:
+      - fastgpt-redis:/data
+  fastgpt-minio:
+    image: ${{minio.image}}:${{minio.tag}}
+    container_name: fastgpt-minio
+    restart: always
+    ports:
+      - 9000:9000
+      - 9001:9001
+    networks:
+      - data
+    environment:
+      - MINIO_ROOT_USER=minioadmin
+      - MINIO_ROOT_PASSWORD=minioadmin
+    volumes:
+      - fastgpt-minio:/data
+    command: server /data --console-address ":9001"
+    healthcheck:
+      test: ['CMD', 'curl', '-f', 'http://localhost:9000/minio/health/live']
+      interval: 30s
+      timeout: 20s
+      retries: 3
+  fastgpt-app:
+    container_name: fastgpt-app
+    image: ${{fastgpt.image}}:${{fastgpt.tag}}
+    ports:
+      - 3000:3000
+    networks:
+      - data
+      - app
+      - codesandbox
+      - aiproxy
+    depends_on:
+      fastgpt-mongo:
+        condition: service_healthy
+      fastgpt-vector:
+        condition: service_healthy
+      fastgpt-redis:
+        condition: service_healthy
+      fastgpt-minio:
+        condition: service_healthy
+      fastgpt-code-sandbox:
+        condition: service_healthy
+      fastgpt-plugin:
+        condition: service_healthy
+    restart: always
+    environment:
+      # 完整变量请参考: https://github.com/labring/FastGPT/blob/main/projects/app/.env.template
+      <<: [*x-share-db-config, *x-vec-config, *x-log-config]
+      HOSTNAME: 0.0.0.0
+      # ==================== 基础配置 ====================
+      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
+      FE_DOMAIN:
+      # root key（最高权限）
+      ROOT_KEY: *x-system-key
+      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
+      DEFAULT_ROOT_PSW: *x-default-root-psw
+      # 数据库最大连接数
+      DB_MAX_LINK: 5
+      # 自动同步索引
+      SYNC_INDEX: true
+      TOKEN_KEY: fastgpt
+      # 文件阅读时的密钥
+      FILE_TOKEN_KEY: filetokenkey
+      # 密钥加密 key
+      AES256_SECRET_KEY: fastgptsecret
+      # 强制将图片转成 base64 传递给模型
+      MULTIPLE_DATA_TO_BASE64: true
+      # ==================== 服务地址与集成 ====================
+      # plugin 地址
+      PLUGIN_BASE_URL: http://fastgpt-plugin:3000
+      PLUGIN_TOKEN: *x-plugin-auth-token
+      # code-sandbox 地址
+      CODE_SANDBOX_URL: http://fastgpt-code-sandbox:3000
+      CODE_SANDBOX_TOKEN: *x-code-sandbox-token
+      # AI Proxy 的地址，如果配了该地址，优先使用
+      AIPROXY_API_ENDPOINT: http://fastgpt-aiproxy:3000
+      # AI Proxy 的 Admin Token，与 AI Proxy 中的环境变量 ADMIN_KEY
+      AIPROXY_API_TOKEN: *x-aiproxy-token
+      # ==================== 日志与监控 ====================
+      # 传递给 OTLP 收集器的服务名称
+      LOG_OTEL_SERVICE_NAME: fastgpt-client
+    volumes:
+      - ./config.json:/app/data/config.json
+  fastgpt-code-sandbox:
+    container_name: fastgpt-code-sandbox
+    image: ${{fastgpt-code-sandbox.image}}:${{fastgpt-code-sandbox.tag}}
+    networks:
+      - codesandbox
+    restart: always
+    environment:
+      <<: [*x-log-config]
+      LOG_OTEL_SERVICE_NAME: fastgpt-code-sandbox
+      SANDBOX_TOKEN: *x-code-sandbox-token
+      # ===== Resource Limits =====
+      # Execution timeout per request (ms)
+      SANDBOX_MAX_TIMEOUT: 60000
+      # Maximum allowed memory per user code execution (MB)
+      # Note: System automatically adds 50MB for runtime overhead
+      # Actual process limit = SANDBOX_MAX_MEMORY_MB + 50MB
+      SANDBOX_MAX_MEMORY_MB: 256
+      # ===== Process Pool =====
+      # Number of pre-warmed worker processes (JS + Python)
+      SANDBOX_POOL_SIZE: 20
+      # ===== Network Request Limits =====
+      # Whether to check if the request is to a private network
+      CHECK_INTERNAL_IP: false
+      # Maximum number of HTTP requests per execution
+      SANDBOX_REQUEST_MAX_COUNT: 30
+      # Timeout for each outbound HTTP request (ms)
+      SANDBOX_REQUEST_TIMEOUT: 60000
+      # Maximum response body size for outbound requests
+      SANDBOX_REQUEST_MAX_RESPONSE_MB: 10
+      # Maximum request body size for outbound requests (MB)
+      SANDBOX_REQUEST_MAX_BODY_MB: 5
+      # ===== Module Control =====
+      # JS allowed modules whitelist (comma-separated)
+      SANDBOX_JS_ALLOWED_MODULES: lodash,dayjs,moment,uuid,crypto-js,qs,url,querystring
+      # Python allowed modules whitelist (comma-separated)
+      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
+    healthcheck:
+      test: [
+        'CMD',
+        'bun',
+        '-e',
+        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
+      ]
+      interval: 30s
+      timeout: 20s
+      retries: 3
+  fastgpt-mcp-server:
+    container_name: fastgpt-mcp-server
+    image: ${{fastgpt-mcp_server.image}}:${{fastgpt-mcp_server.tag}}
+    networks:
+      - app
+    ports:
+      - 3003:3000
+    restart: always
+    environment:
+      <<: [*x-log-config]
+      FASTGPT_ENDPOINT: http://fastgpt-app:3000
+  fastgpt-plugin:
+    image: ${{fastgpt-plugin.image}}:${{fastgpt-plugin.tag}}
+    container_name: fastgpt-plugin
+    restart: always
+    networks:
+      - data
+      - app
+    environment:
+      <<: [*x-share-db-config, *x-log-config]
+      AUTH_TOKEN: *x-plugin-auth-token
+      # 工具网络请求，最大请求和响应体
+      SERVICE_REQUEST_MAX_CONTENT_LENGTH: 10
+      # 最大 API 请求体大小
+      MAX_API_SIZE: 10
+      # 传递给 OTLP 收集器的服务名称
+      LOG_OTEL_SERVICE_NAME: fastgpt-plugin
+    depends_on:
+      fastgpt-mongo:
+        condition: service_healthy
+      fastgpt-minio:
+        condition: service_healthy
+    healthcheck:
+      test: ['CMD', 'curl', '-f', 'http://localhost:3000/health']
+      interval: 30s
+      timeout: 20s
+      retries: 3
+  # AI Proxy
+  fastgpt-aiproxy:
+    image: ${{aiproxy.image}}:${{aiproxy.tag}}
+    container_name: fastgpt-aiproxy
+    restart: unless-stopped
+    depends_on:
+      fastgpt-aiproxy-pg:
+        condition: service_healthy
+    networks:
+      - aiproxy
+    environment:
+      # 对应 fastgpt 里的AIPROXY_API_TOKEN
+      ADMIN_KEY: *x-aiproxy-token
+      # 错误日志详情保存时间（小时）
+      LOG_DETAIL_STORAGE_HOURS: 1
+      # 数据库连接地址
+      SQL_DSN: postgres://postgres:aiproxy@fastgpt-aiproxy-pg:5432/aiproxy
+      # 最大重试次数
+      RETRY_TIMES: 3
+      # 不需要计费
+      BILLING_ENABLED: false
+      # 不需要严格检测模型
+      DISABLE_MODEL_CONFIG: true
+    healthcheck:
+      test: ['CMD', 'curl', '-f', 'http://localhost:3000/api/status']
+      interval: 5s
+      timeout: 5s
+      retries: 10
+  fastgpt-aiproxy-pg:
+    image: ${{aiproxy-pg.image}}:${{aiproxy-pg.tag}} # docker hub
+    restart: unless-stopped
+    container_name: fastgpt-aiproxy-pg
+    volumes:
+      - fastgpt-aiproxy_pg:/var/lib/postgresql/data
+    networks:
+      - aiproxy
+    environment:
+      TZ: Asia/Shanghai
+      POSTGRES_USER: postgres
+      POSTGRES_DB: aiproxy
+      POSTGRES_PASSWORD: aiproxy
+    healthcheck:
+      test: ['CMD', 'pg_isready', '-U', 'postgres', '-d', 'aiproxy']
+      interval: 5s
+      timeout: 5s
+      retries: 10
+networks:
+  data:
+    name: fastgpt_data
+  app:
+    name: fastgpt_app
+  codesandbox:
+    name: fastgpt_codesandbox
+  aiproxy:
+    name: fastgpt_aiproxy
+volumes:
+  fastgpt-pg:
+  fastgpt-mongo:
+  fastgpt-redis:
+  fastgpt-minio:
+  fastgpt-milvus-minio:
+  fastgpt-milvus-etcd:
+  fastgpt-milvus-data:
+  fastgpt-ob-data:
+  fastgpt-ob-config:
+  fastgpt-seekdb-data:
+  fastgpt-seekdb-config:
+  fastgpt-aiproxy_pg:
+${{vec.extraBlock}}
--- a/deploy/version/v4.14/args.json
+++ b/deploy/version/v4.14/args.json
+{
+  "tags": {
+    "fastgpt": "v4.14.22",
+    "fastgpt-code-sandbox": "v4.14.22",
+    "fastgpt-mcp_server": "v4.14.22",
+    "fastgpt-plugin": "v0.6.2",
+    "volume-manager": "v0.1.2",
+    "agent-sandbox-image": "v0.1.2",
+    "aiproxy": "v0.5.8",
+    "opensandbox-server": "v0.1.9",
+    "opensandbox-execd": "v1.0.7",
+    "opensandbox-egress": "v1.0.3",
+    "aiproxy-pg": "0.8.0-pg15",
+    "mongo": "5.0.32",
+    "redis": "7.2-alpine",
+    "minio": "RELEASE.2025-09-07T16-13-09Z",
+    "pg": "0.8.0-pg15",
+    "milvus-minio": "RELEASE.2023-03-20T20-16-18Z",
+    "milvus-etcd": "v3.5.5",
+    "milvus-standalone": "v2.4.3",
+    "oceanbase": "4.3.5-lts",
+    "seekdb": "1.0.1.0-100000392025122619"
+  },
+  "images": {
+    "cn": {
+      "fastgpt": "registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt",
+      "fastgpt-plugin": "registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-plugin",
+      "fastgpt-code-sandbox": "registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox",
+      "fastgpt-mcp_server": "registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server",
+      "volume-manager": "registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager",
+      "agent-sandbox-image": "registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox",
+      "opensandbox-server": "registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-server",
+      "opensandbox-execd": "registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-execd",
+      "opensandbox-egress": "registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-egress",
+      "aiproxy": "registry.cn-hangzhou.aliyuncs.com/labring/aiproxy",
+      "aiproxy-pg": "registry.cn-hangzhou.aliyuncs.com/fastgpt/pgvector",
+      "mongo": "registry.cn-hangzhou.aliyuncs.com/fastgpt/mongo",
+      "redis": "registry.cn-hangzhou.aliyuncs.com/fastgpt/redis",
+      "minio": "registry.cn-hangzhou.aliyuncs.com/fastgpt/minio",
+      "pg": "registry.cn-hangzhou.aliyuncs.com/fastgpt/pgvector",
+      "milvus-minio": "minio/minio",
+      "milvus-etcd": "quay.io/coreos/etcd",
+      "milvus-standalone": "milvusdb/milvus",
+      "oceanbase": "oceanbase/oceanbase-ce",
+      "seekdb": "oceanbase/seekdb"
+    },
+    "global": {
+      "fastgpt": "ghcr.io/labring/fastgpt",
+      "fastgpt-plugin": "ghcr.io/labring/fastgpt-plugin",
+      "fastgpt-code-sandbox": "ghcr.io/labring/fastgpt-code-sandbox",
+      "fastgpt-mcp_server": "ghcr.io/labring/fastgpt-mcp_server",
+      "volume-manager": "ghcr.io/labring/fastgpt-agent-volume-manager",
+      "agent-sandbox-image": "ghcr.io/labring/fastgpt-agent-sandbox",
+      "opensandbox-server": "opensandbox/server",
+      "opensandbox-execd": "opensandbox/execd",
+      "opensandbox-egress": "opensandbox/egress",
+      "aiproxy": "ghcr.io/labring/aiproxy",
+      "aiproxy-pg": "pgvector/pgvector",
+      "mongo": "mongo",
+      "redis": "redis",
+      "minio": "minio/minio",
+      "pg": "pgvector/pgvector",
+      "milvus-minio": "minio/minio",
+      "milvus-etcd": "quay.io/coreos/etcd",
+      "milvus-standalone": "milvusdb/milvus",
+      "oceanbase": "oceanbase/oceanbase-ce",
+      "seekdb": "oceanbase/seekdb"
+    }
+  }
+}
--- a/deploy/templates/docker-compose.prod.yml
+++ b/deploy/templates/docker-compose.prod.yml
@@ -133,7 +133,7 @@ ${{vec.db}}
  fastgpt-app:
    container_name: fastgpt-app
-    image: ${{fastgpt.image}}:${{fastgpt.tag}} 
+    image: ${{fastgpt.image}}:${{fastgpt.tag}}
    ports:
      - 3000:3000
    networks:
@@ -162,7 +162,7 @@ ${{vec.db}}
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -204,6 +204,7 @@ ${{vec.db}}
      AGENT_SANDBOX_ENABLE_VOLUME: true
      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
+      AGENT_SANDBOX_VOLUME_MANAGER_MOUNT_PATH: /workspace
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
@@ -251,11 +252,11 @@ ${{vec.db}}
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3

--- a/document/content/self-host/deploy/docker.en.mdx
+++ b/document/content/self-host/deploy/docker.en.mdx
@@ -65,6 +65,7 @@ SeekDB is a high-performance vector database based on MySQL protocol, fully comp
 <Alert icon="🤖" context="success">
 SeekDB uses MySQL protocol, fully compatible with OceanBase:
 - Supports 1536-dimensional vector retrieval
 - Built-in HNSW index algorithm
 - Batch insert and query optimization
@@ -124,7 +125,8 @@ bash <(curl -fsSL https://doc.fastgpt.cn/deploy/install.sh)
 ```
 #### Method 2: Manual Download
-If your environment is non-*nix or can't access external networks, manually download `docker-compose.yml`.
+If your environment is non-\*nix or can't access external networks, manually download `docker-compose.yml`.
 1. Download the `docker-compose.yml` file:
@@ -132,27 +134,29 @@ If your environment is non-*nix or can't access external networks, manually down
 <summary>Click to view docker-compose config file download links for different databases</summary>
 - **Pgvector**
-  - China mirror (Alibaba Cloud): [docker-compose.pg.yml](https://doc.fastgpt.cn/deploy/docker/cn/docker-compose.pg.yml)
+  - China mirror (Alibaba Cloud): [docker-compose.pg.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/cn/docker-compose.pg.yml)
-  - Global mirror (dockerhub, ghcr): [docker-compose.pg.yml](https://doc.fastgpt.cn/deploy/docker/global/docker-compose.pg.yml)
+  - Global mirror (dockerhub, ghcr): [docker-compose.pg.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/global/docker-compose.pg.yml)
 - **Oceanbase**
-  - China mirror (Alibaba Cloud): [docker-compose.oceanbase.yml](https://doc.fastgpt.cn/deploy/docker/cn/docker-compose.oceanbase.yml)
+  - China mirror (Alibaba Cloud): [docker-compose.oceanbase.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/cn/docker-compose.oceanbase.yml)
-  - Global mirror (dockerhub, ghcr): [docker-compose.oceanbase.yml](https://doc.fastgpt.cn/deploy/docker/global/docker-compose.oceanbase.yml)
+  - Global mirror (dockerhub, ghcr): [docker-compose.oceanbase.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/global/docker-compose.oceanbase.yml)
 - **Milvus**
-  - China mirror (Alibaba Cloud): [docker-compose.milvus.yml](https://doc.fastgpt.cn/deploy/docker/cn/docker-compose.milvus.yml)
+  - China mirror (Alibaba Cloud): [docker-compose.milvus.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/cn/docker-compose.milvus.yml)
-  - Global mirror (dockerhub, ghcr): [docker-compose.milvus.yml](https://doc.fastgpt.cn/deploy/docker/global/docker-compose.milvus.yml)
+  - Global mirror (dockerhub, ghcr): [docker-compose.milvus.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/global/docker-compose.milvus.yml)
 - **Zilliz**
-  - China mirror (Alibaba Cloud): [docker-compose.zilliz.yml](https://doc.fastgpt.cn/deploy/docker/cn/docker-compose.zilliz.yml)
+  - China mirror (Alibaba Cloud): [docker-compose.zilliz.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/cn/docker-compose.zilliz.yml)
-  - Global mirror (dockerhub, ghcr): [docker-compose.zilliz.yml](https://doc.fastgpt.cn/deploy/docker/global/docker-compose.zilliz.yml)
+  - Global mirror (dockerhub, ghcr): [docker-compose.zilliz.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/global/docker-compose.zilliz.yml)
 - **SeekDB**
-  - China mirror (Alibaba Cloud): [docker-compose.seekdb.yml](https://doc.fastgpt.cn/deploy/docker/cn/docker-compose.seekdb.yml)
+  - China mirror (Alibaba Cloud): [docker-compose.seekdb.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/cn/docker-compose.seekdb.yml)
-  - Global mirror (dockerhub, ghcr): [docker-compose.seekdb.yml](https://doc.fastgpt.cn/deploy/docker/global/docker-compose.seekdb.yml)
+  - Global mirror (dockerhub, ghcr): [docker-compose.seekdb.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/global/docker-compose.seekdb.yml)
 2. Download the `config.json` file:
 - [config.json](https://doc.fastgpt.cn/deploy/config/config.json)
 </details>
 Download config.json file:
 - [config.json](https://doc.fastgpt.cn/deploy/config/config.json)
 ### 2. Modify Environment Variables
@@ -165,7 +169,7 @@ These ports must be accessible:
 1. Port 3000 (FastGPT main service)
 2. Port 9000 (S3 service)
-1. Port 3005 (FastGPT SSE MCP server service)
+3. Port 3005 (FastGPT SSE MCP server service)
 ### 4. Start Containers
@@ -192,9 +196,9 @@ Each container restart automatically initializes the root user with password `12
 Starting from V4.14.0, the fastgpt-plugin image only provides the runtime environment without pre-installed system plugins. All FastGPT systems must manually install system plugins.
-* Install via the plugin marketplace — by default it fetches from the public FastGPT Marketplace.
+- Install via the plugin marketplace — by default it fetches from the public FastGPT Marketplace.
-* If your FastGPT can't access the marketplace, visit [FastGPT Plugin Marketplace](https://marketplace.fastgpt.cn/), download .pkg files, and import them via file upload.
+- If your FastGPT can't access the marketplace, visit [FastGPT Plugin Marketplace](https://marketplace.fastgpt.cn/), download .pkg files, and import them via file upload.
-* You can also sort tools, set default installations, and manage tags.
+- You can also sort tools, set default installations, and manage tags.
 ![alt text](../../../public/imgs/image-121.png)
@@ -204,9 +208,9 @@ Starting from V4.14.0, the fastgpt-plugin image only provides the runtime enviro
 | FastGPT-plugin Version | FastGPT Main Service |
 | ---------------------- | -------------------- |
-|   0.6.x      |     >= 4.14.11         |
+| 0.6.x                  | >= 4.14.11           |
-|   0.5.x      |     >= 4.14.6, < 4.14.11        |
+| 0.5.x                  | >= 4.14.6, < 4.14.11 |
-|  < 0.5.0      |   < 4.14.6       
+| < 0.5.0                | < 4.14.6             |
 ### S3 Connection Issues

--- a/document/content/self-host/deploy/docker.mdx
+++ b/document/content/self-host/deploy/docker.mdx
@@ -18,13 +18,13 @@ import { Alert } from '@/components/docs/Alert';
 - MongoDB：用于存储除了向量外的各类数据
 - PostgreSQL/Milvus/Oceanbase/SeekDB：存储向量数据
- AIProxy: 聚合各类 AI API，支持多模型调用 （任何模型问题，先自行通过 OneAPI 测试校验）
+- AIProxy: 聚合各类 AI API，支持多模型调用（任何模型问题，先自行通过 OneAPI 测试校验）
 </Alert>
 ## 推荐配置
-### PgVector版本
+### PgVector 版本
 非常轻量，适合知识库索引量在 5000 万以下。
@@ -34,7 +34,7 @@ import { Alert } from '@/components/docs/Alert';
 | 100w 组向量                      | 4c8g 50GB          | 4c16g 50GB   |
 | 500w 组向量                      | 8c32g 200GB        | 16c64g 200GB |
-### Milvus版本
+### Milvus 版本
 对于亿级以上向量性能更优秀。
@@ -46,13 +46,13 @@ import { Alert } from '@/components/docs/Alert';
 | 100w 组向量 | 未测试             |          |
 | 500w 组向量 |                    |          |
-### zilliz cloud版本
+### zilliz cloud 版本
 Zilliz Cloud 由 Milvus 原厂打造，是全托管的 SaaS 向量数据库服务，性能优于 Milvus 并提供 SLA，点击使用 [Zilliz Cloud](https://zilliz.com.cn/)。
 由于向量库使用了 Cloud，无需占用本地资源，无需太关注。
-### SeekDB版本
+### SeekDB 版本
 SeekDB 是基于 MySQL 协议的高性能向量数据库，与 OceanBase 协议完全兼容，支持高效的向量检索。
@@ -65,6 +65,7 @@ SeekDB 鈭 MySQL 悅扯摨 OceanBase 悅
 <Alert icon="🤖" context="success">
 SeekDB 使用 MySQL 协议，与 OceanBase 完全兼容：
 - 支持 1536 维向量检索
 - 内置 HNSW 索引算法
 - 提供批量插入和查询优化
@@ -117,14 +118,15 @@ brew install orbstack
 #### 方法一：使用交互式脚本部署
-需要在 Linux/MacOS/Windows WSL 环境下执行，引导用户选择部署环境、向量库版本，IP地址等。
+需要在 Linux/MacOS/Windows WSL 环境下执行，引导用户选择部署环境、向量库版本，IP 地址等。
 ```bash
 bash <(curl -fsSL https://doc.fastgpt.cn/deploy/install.sh)
 ```
 #### 方法二：手动下载部署
-如果部署环境为非 *nix 环境或无法访问外网，需要手动下载 `docker-compose.yml` 进行部署
+如果部署环境为非 \*nix 环境或无法访问外网，需要手动下载 `docker-compose.yml` 进行部署
 1. 下载 `docker-compose.yml` 文件：
@@ -132,27 +134,29 @@ bash <(curl -fsSL https://doc.fastgpt.cn/deploy/install.sh)
 <summary>点击展开查看不同数据库的 docker-compose 配置文件下载地址</summary>
 - **Pgvector**
-  - 中国大陆地区镜像源(阿里云)：[docker-compose.pg.yml](https://doc.fastgpt.cn/deploy/docker/cn/docker-compose.pg.yml)
+  - 中国大陆地区镜像源(阿里云)：[docker-compose.pg.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/cn/docker-compose.pg.yml)
-  - 全球镜像源(dockerhub, ghcr)：[docker-compose.pg.yml](https://doc.fastgpt.cn/deploy/docker/global/docker-compose.pg.yml)
+  - 全球镜像源(dockerhub, ghcr)：[docker-compose.pg.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/global/docker-compose.pg.yml)
 - **Oceanbase**
-  - 中国大陆地区镜像源(阿里云)：[docker-compose.oceanbase.yml](https://doc.fastgpt.cn/deploy/docker/cn/docker-compose.oceanbase.yml)
+  - 中国大陆地区镜像源(阿里云)：[docker-compose.oceanbase.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/cn/docker-compose.oceanbase.yml)
-  - 全球镜像源(dockerhub, ghcr)：[docker-compose.oceanbase.yml](https://doc.fastgpt.cn/deploy/docker/global/docker-compose.oceanbase.yml)
+  - 全球镜像源(dockerhub, ghcr)：[docker-compose.oceanbase.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/global/docker-compose.oceanbase.yml)
 - **Milvus**
-  - 中国大陆地区镜像源(阿里云)：[docker-compose.milvus.yml](https://doc.fastgpt.cn/deploy/docker/cn/docker-compose.milvus.yml)
+  - 中国大陆地区镜像源(阿里云)：[docker-compose.milvus.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/cn/docker-compose.milvus.yml)
-  - 全球镜像源(dockerhub, ghcr)：[docker-compose.milvus.yml](https://doc.fastgpt.cn/deploy/docker/global/docker-compose.milvus.yml)
+  - 全球镜像源(dockerhub, ghcr)：[docker-compose.milvus.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/global/docker-compose.milvus.yml)
 - **Zilliz**
-  - 中国大陆地区镜像源(阿里云)：[docker-compose.zilliz.yml](https://doc.fastgpt.cn/deploy/docker/cn/docker-compose.zilliz.yml)
+  - 中国大陆地区镜像源(阿里云)：[docker-compose.zilliz.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/cn/docker-compose.zilliz.yml)
-  - 全球镜像源(dockerhub, ghcr)：[docker-compose.zilliz.yml](https://doc.fastgpt.cn/deploy/docker/global/docker-compose.zilliz.yml)
+  - 全球镜像源(dockerhub, ghcr)：[docker-compose.zilliz.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/global/docker-compose.zilliz.yml)
 - **SeekDB**
-  - 中国大陆地区镜像源(阿里云)：[docker-compose.seekdb.yml](https://doc.fastgpt.cn/deploy/docker/cn/docker-compose.seekdb.yml)
+  - 中国大陆地区镜像源(阿里云)：[docker-compose.seekdb.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/cn/docker-compose.seekdb.yml)
-  - 全球镜像源(dockerhub, ghcr)：[docker-compose.seekdb.yml](https://doc.fastgpt.cn/deploy/docker/global/docker-compose.seekdb.yml)
+  - 全球镜像源(dockerhub, ghcr)：[docker-compose.seekdb.yml](https://doc.fastgpt.cn/deploy/docker/v4.14/global/docker-compose.seekdb.yml)
 2. 下载 `config.json` 文件：
 - [config.json](https://doc.fastgpt.cn/deploy/config/config.json)
 </details>
 下载 config.json 文件
 - [config.json](https://doc.fastgpt.cn/deploy/config/config.json)
 ### 2. 修改环境变量
@@ -165,11 +169,11 @@ bash <(curl -fsSL https://doc.fastgpt.cn/deploy/install.sh)
 1. 3000 端口（FastGPT 主服务）
 2. 9000 端口（S3 服务）
-1. 3005 端口（FastGPT SSE MCP server 服务）
+3. 3005 端口（FastGPT SSE MCP server 服务）
 ### 4. 启动容器
-在 docker-compose.yml 同级目录下执行。请确保`docker-compose`版本最好在2.17以上，否则可能无法执行自动化命令。
+在 docker-compose.yml 同级目录下执行。请确保 `docker-compose` 版本最好在 2.17 以上，否则可能无法执行自动化命令。
 ```bash
 # 启动容器
@@ -179,23 +183,21 @@ docker compose --profile prepull pull opensandbox-agent-sandbox-image opensandbo
 ### 5. 访问 FastGPT
-可通过第二步开放的端口/域名访问 FastGPT。
+可通过第二步开放的端口/域名访问 FastGPT。登录用户名为 `root`，密码为 `docker-compose.yml` 环境变量里设置的 `DEFAULT_ROOT_PSW`。每次重启容器，都会自动初始化 root 用户，密码为 `1234`（与环境变量中的 `DEFAULT_ROOT_PSW` 一致）。
-登录用户名为 `root`，密码为`docker-compose.yml`环境变量里设置的 `DEFAULT_ROOT_PSW`。
-每次重启容器，都会自动初始化 root 用户，密码为 `1234`（与环境变量中的`DEFAULT_ROOT_PSW`一致）。
 ### 6. 配置模型
- 首次登录FastGPT后，系统会提示未配置`语言模型`和`索引模型`，并自动跳转模型配置页面。系统必须至少有这两类模型才能正常使用。
+- 首次登录 FastGPT 后，系统会提示未配置 `语言模型` 和 `索引模型`，并自动跳转模型配置页面。系统必须至少有这两类模型才能正常使用。
- 如果系统未正常跳转，可以在`账号-模型提供商`页面，进行模型配置。[点击查看相关教程](../config/model/intro.mdx)
+- 如果系统未正常跳转，可以在 `账号-模型提供商` 页面，进行模型配置。[点击查看相关教程](../config/model/intro.mdx)
- 目前已知可能问题：首次进入系统后，整个浏览器 tab 无法响应。此时需要删除该tab，重新打开一次即可。
+- 目前已知可能问题：首次进入系统后，整个浏览器 tab 无法响应。此时需要删除该 tab，重新打开一次即可。
 ### 7. 按需安装系统插件
 从 V4.14.0 版本开始，fastgpt-plugin 镜像仅提供运行环境，不再预装系统插件，所有 FastGPT 系统需手动安装系统插件。
-* 通过插件市场安装，默认会向公开的 FastGPT Marketplace 获取数据进行安装。
+- 通过插件市场安装，默认会向公开的 FastGPT Marketplace 获取数据进行安装。
-* 如果你的 FastGPT 无法访问插件市场，则可以手动访问[FastGPT 插件市场](https://marketplace.fastgpt.cn/)，先下载 .pkg 文件，再通过文件导入的方式安装到系统里。
+- 如果你的 FastGPT 无法访问插件市场，则可以手动访问 [FastGPT 插件市场](https://marketplace.fastgpt.cn/)，先下载 .pkg 文件，再通过文件导入的方式安装到系统里。
-* 除了安装外，还可对工具进行排序、默认安装、标签管理等。
+- 除了安装外，还可对工具进行排序、默认安装、标签管理等。
 ![alt text](../../../public/imgs/image-121.png)
@@ -203,26 +205,25 @@ docker compose --profile prepull pull opensandbox-agent-sandbox-image opensandbo
 ### FastGPT 和 FastGPT-plugin 版本对应
-| FastGPT-plugin 版本  |  FastGPT 主服务 |
+| FastGPT-plugin 版本 | FastGPT 主服务       |
-| ------------------- | ---------------- |
+| ------------------- | -------------------- |
-|   0.6.x      |     >= 4.14.11         |
+| 0.6.x               | >= 4.14.11           |
-|   0.5.x      |     >= 4.14.6, < 4.14.11        |
+| 0.5.x               | >= 4.14.6, < 4.14.11 |
-|  < 0.5.0      |   < 4.14.6        |
+| < 0.5.0             | < 4.14.6             |
 ### S3 无法正常连接
+检查 `STORAGE_EXTERNAL_ENDPOINT` 变量，需设置成客户端和 FastGPT 服务均可访问的地址。
-检查`STORAGE_EXTERNAL_ENDPOINT`变量，需设置成客户端和 FastGPT 服务均可访问的地址。
 **重要：**
-> 填入的地址不可为`127.0.0.1`或者`localhost`等本地回环地址，可填 Docker 部署时的宿主机本地IP，但是需要把宿主机固定为静态 IP；或者统一为一个固定域名；目的是为了避免对象存储签名 URL 时，签发与上传的 URL 不一致导致的 403 错误。
+> 填入的地址不可为 `127.0.0.1` 或者 `localhost` 等本地回环地址，可填 Docker 部署时的宿主机本地 IP，但是需要把宿主机固定为静态 IP；或者统一为一个固定域名；目的是为了避免对象存储签名 URL 时，签发与上传的 URL 不一致导致的 403 错误。
 >
 > 具体查看 [对象存储配置及常见问题](../config/object-storage.mdx)
 ### 登录系统后，浏览器无法响应
-无法点击任何内容，刷新也无效。此时需要删除该tab，重新打开一次即可。
+无法点击任何内容，刷新也无效。此时需要删除该 tab，重新打开一次即可。
 ### Mongo 副本集自动初始化失败
@@ -230,7 +231,7 @@ docker compose --profile prepull pull opensandbox-agent-sandbox-image opensandbo
 如果是由于，无法自动初始化副本集合，可以手动初始化副本集：
-1. 终端中执行下面命令，创建mongo密钥：
+1. 终端中执行下面命令，创建 mongo 密钥：
 ```bash
 openssl rand -base64 756 > ./mongodb.key
@@ -289,12 +290,11 @@ rs.initiate({
 rs.status()
 ```
-### 如何修改API地址和密钥
+### 如何修改 API 地址和密钥
-默认是写了OneAPi的连接地址和密钥，可以通过修改`docker-compose.yml`中，fastgpt容器的环境变量实现。
+默认是写了 OneAPi 的连接地址和密钥，可以通过修改 `docker-compose.yml` 中，fastgpt 容器的环境变量实现。
-`OPENAI_BASE_URL`（API 接口的地址，需要加/v1）
+`OPENAI_BASE_URL`（API 接口的地址，需要加/v1）`CHAT_API_KEY`（API 接口的凭证）。
-`CHAT_API_KEY`（API 接口的凭证）。
 修改完后重启：
@@ -317,27 +317,27 @@ docker compose up -d
 ### 如何自定义配置文件？
-修改`config.json`文件，并执行`docker compose down`再执行`docker compose up -d`重起容器。具体配置，参考[配置详解](../config/json.mdx)。
+修改 `config.json` 文件，并执行 `docker compose down` 再执行 `docker compose up -d` 重起容器。具体配置，参考[配置详解](../config/json.mdx)。
 ### 如何检查自定义配置文件是否挂载
 1. `docker logs fastgpt` 可以查看日志，在启动容器后，第一次请求网页，会进行配置文件读取，可以看看有没有读取成功以及有无错误日志。
-2. `docker exec -it fastgpt sh` 进入 FastGPT 容器，可以通过`ls data`查看目录下是否成功挂载`config.json`文件。可通过`cat data/config.json`查看配置文件。
+2. `docker exec -it fastgpt sh` 进入 FastGPT 容器，可以通过 `ls data` 查看目录下是否成功挂载 `config.json` 文件。可通过 `cat data/config.json` 查看配置文件。
 **可能不生效的原因**
 1. 挂载目录不正确
-2. 配置文件不正确，日志中会提示`invalid json`，配置文件需要是标准的 JSON 文件。
+2. 配置文件不正确，日志中会提示 `invalid json`，配置文件需要是标准的 JSON 文件。
-3. 修改后，没有`docker compose down`再`docker compose up -d`，restart是不会重新挂载文件的。
+3. 修改后，没有 `docker compose down` 再 `docker compose up -d`，restart 是不会重新挂载文件的。
 ### 如何检查环境变量是否正常加载
 1. `docker exec -it fastgpt sh` 进入 FastGPT 容器。
-2. 直接输入`env`命令查看所有环境变量。
+2. 直接输入 `env` 命令查看所有环境变量。
-### 为什么无法连接`本地模型`镜像
+### 为什么无法连接 `本地模型` 镜像
-`docker-compose.yml`中使用了桥接的模式建立了`fastgpt`网络，如想通过0.0.0.0或镜像名访问其它镜像，需将其它镜像也加入到网络中。
+`docker-compose.yml` 中使用了桥接的模式建立了 `fastgpt` 网络，如想通过 0.0.0.0 或镜像名访问其它镜像，需将其它镜像也加入到网络中。
 ### 端口冲突怎么解决？
@@ -345,7 +345,7 @@ docker-compose 蝡臬摰蛹嚗垢:餈垢`
 桥接模式下，容器运行端口不会有冲突，但是会有映射端口冲突，只需将映射端口修改成不同端口即可。
-如果`容器1`需要连接`容器2`，使用`容器2:运行端口`来进行连接即可。
+如果 `容器1` 需要连接 `容器2`，使用 `容器2:运行端口` 来进行连接即可。
 （自行补习 docker 基本知识）
@@ -361,21 +361,21 @@ PG 摨瓷銝/仃韐伐隞交敹astGPT 隡
 可能原因：
-1. arm架构。需要使用 Mongo 官方镜像： mongo:5.0.18
+1. arm 架构。需要使用 Mongo 官方镜像：mongo:5.0.18
 2. cpu 不支持 AVX，无法用 mongo5，需要换成 mongo4.x。把 mongo 的 image 换成: mongo:4.4.29
 ### Operation `auth_codes.findOne()` buffering timed out after 10000ms
-mongo连接失败，查看mongo的运行状态**对应日志**。
+mongo 连接失败，查看 mongo 的运行状态**对应日志**。
 可能原因：
-1. mongo 服务有没有起来（有些 cpu 不支持 AVX，无法用 mongo5，需要换成 mongo4.x，可以docker hub找个最新的4.x，修改镜像版本，重新运行）
+1. mongo 服务有没有起来（有些 cpu 不支持 AVX，无法用 mongo5，需要换成 mongo4.x，可以 docker hub 找个最新的 4.x，修改镜像版本，重新运行）
-2. 连接数据库的环境变量填写错误（账号密码，注意host和port，非容器网络连接，需要用公网ip并加上 directConnection=true）
+2. 连接数据库的环境变量填写错误（账号密码，注意 host 和 port，非容器网络连接，需要用公网 ip 并加上 directConnection=true）
 3. 副本集启动失败。导致容器一直重启。
-4. `Illegal instruction.... Waiting for MongoDB to start`: cpu 不支持 AVX，无法用 mongo5，需要换成 mongo4.x
+4. `Illegal instruction.... Waiting for MongoDB to start` : cpu 不支持 AVX，无法用 mongo5，需要换成 mongo4.x
-### 首次部署，root用户提示未注册
+### 首次部署，root 用户提示未注册
 日志会有错误提示。大概率是没有启动 Mongo 副本集模式。
@@ -392,15 +392,16 @@ mongo餈憭梯揖嚗ongo**撖孵敹**
 ### 如何修改密码
-修改`docker-compose.yml`文件中`DEFAULT_ROOT_PSW`并重启即可，密码会自动更新。
+修改 `docker-compose.yml` 文件中 `DEFAULT_ROOT_PSW` 并重启即可，密码会自动更新。
 ### 部署 Zilliz 版本，获取账号和密钥
-打开 [Zilliz Cloud](https://zilliz.com.cn/), 创建实例并获取相关秘钥。
+打开 [Zilliz Cloud](https://zilliz.com.cn/) , 创建实例并获取相关秘钥。
 ![zilliz_key](../../../public/imgs/zilliz_key.png)
 <Alert icon="🤖" context="success">
-1. 修改`MILVUS_ADDRESS`和`MILVUS_TOKEN`链接参数，分别对应 `zilliz` 的 `Public Endpoint` 和 `Api key`，记得把自己ip加入白名单。
+1. 修改 `MILVUS_ADDRESS` 和 `MILVUS_TOKEN` 链接参数，分别对应 `zilliz` 的 `Public Endpoint` 和 `Api key`，记得把自己 ip 加入白名单。
 </Alert>
--- a/document/content/self-host/upgrading/4-14/41410.en.mdx
+++ b/document/content/self-host/upgrading/4-14/41410.en.mdx
@@ -9,7 +9,7 @@ description: 'FastGPT V4.14.10 Release Notes'
 The following configuration adjustments are for `docker compose` deployments. `sealos` commercial users can contact support for an online sandbox service solution.
-Open the [latest yml deployment file](https://github.com/labring/FastGPT/blob/main/deploy/docker/global/docker-compose.pg.yml) and add the following:
+Open the [latest yml deployment file](https://github.com/labring/FastGPT/blob/main/document/public/deploy/docker/v4.14/global/docker-compose.pg.yml) and add the following:
 1. Add the `x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'` variable configuration at the top of the file.
 2. Add 3 new services: `opensandbox-server`, `volume-manager`, and `agent-sandbox-image`.

--- a/document/content/self-host/upgrading/4-14/41410.mdx
+++ b/document/content/self-host/upgrading/4-14/41410.mdx
@@ -9,7 +9,7 @@ description: 'FastGPT V4.14.10 更新说明'
 以下针对的是 `docker compose` 部署方案的配置调整，使用 `sealos` 的商业版用户，可私信支持人员，提供在线的沙盒服务方案。
-参考[最新 yml 部署文件](https://github.com/labring/FastGPT/blob/main/deploy/docker/cn/docker-compose.pg.yml)，调整本地 yml 文件，加入以下内容：
+参考[最新 yml 部署文件](https://github.com/labring/FastGPT/blob/main/document/public/deploy/docker/v4.14/cn/docker-compose.pg.yml)，调整本地 yml 文件，加入以下内容：
 1. 在文件顶部增加 `x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'` 变量配置。
 2. 增加 5 组 services: `opensandbox-server` , `opensandbox-agent-sandbox-image` , `opensandbox-execd-image` , `opensandbox-egress-image` , `fastgpt-volume-manager`

--- a/document/content/self-host/upgrading/outdated/4100.en.mdx
+++ b/document/content/self-host/upgrading/outdated/4100.en.mdx
@@ -7,7 +7,7 @@ description: 'FastGPT V4.10.0 Update Notes'
 ### Docker Deployment
- Refer to the latest [docker-compose.yml](https://github.com/labring/FastGPT/blob/main/deploy/docker/docker-compose-pgvector.yml) file to add the `fastgpt-plugin` and `minio` services.
+- Refer to the latest [docker-compose.yml](https://github.com/labring/FastGPT/blob/main/document/public/deploy/docker/main/global/docker-compose.pg.yml) file to add the `fastgpt-plugin` and `minio` services.
 - Set the `fastgpt-plugin` environment variable `AUTH_TOKEN` to a sufficiently complex value.
 - Set the `fastgpt-plugin` environment variable `MINIO_CUSTOM_ENDPOINT` to `http://ip:port` or a relevant domain name that is accessible to FastGPT users.
 - Update the environment variables for the `fastgpt` and `fastgpt-pro` (commercial edition) containers:
@@ -16,6 +16,7 @@ description: 'FastGPT V4.10.0 Update Notes'
 PLUGIN_BASE_URL=http://fastgpt-plugin:3000
 PLUGIN_TOKEN=the AUTH_TOKEN value you just set
 ```
 - Update the `fastgpt` and `fastgpt-pro` image tags to: v4.10.0-fix
 - Run `docker-compose up -d` to start/update all services.

--- a/document/content/self-host/upgrading/outdated/4100.mdx
+++ b/document/content/self-host/upgrading/outdated/4100.mdx
@@ -7,25 +7,26 @@ description: 'FastGPT V4.10.0 更新说明'
 ### Docker 版本
- 参考最新的[docker-compose.yml](https://github.com/labring/FastGPT/blob/main/deploy/docker/docker-compose-pgvector.yml)文件，加入`fastgpt-plugin`和`minio`服务。
+- 参考最新的 [docker-compose.yml](https://github.com/labring/FastGPT/blob/main/document/public/deploy/docker/main/global/docker-compose.pg.yml) 文件，加入 `fastgpt-plugin` 和 `minio` 服务。
- 修改`fastgpt-plugin`环境变量`AUTH_TOKEN`为较复杂的值。
+- 修改 `fastgpt-plugin` 环境变量 `AUTH_TOKEN` 为较复杂的值。
- 修改`fastgpt-plugin`环境变量`MINIO_CUSTOM_ENDPOINT`为`http://ip:port` 或相关域名，要求fastgpt 用户可访问。
+- 修改 `fastgpt-plugin` 环境变量 `MINIO_CUSTOM_ENDPOINT` 为 `http://ip:port` 或相关域名，要求 fastgpt 用户可访问。
- 更新`fastgpt`和`fastgpt-pro`(商业版)容器的环境变量:
+- 更新 `fastgpt` 和 `fastgpt-pro` (商业版)容器的环境变量:
 ```
 PLUGIN_BASE_URL=http://fastgpt-plugin:3000
 PLUGIN_TOKEN=刚修改的 AUTH_TOKEN 值
 ```
- 更新`fastgpt`和`fastgpt-pro`镜像 tag: v4.10.0-fix
- `docker-compose up -d`启动/更新所有服务。
+- 更新 `fastgpt` 和 `fastgpt-pro` 镜像 tag: v4.10.0-fix
+- `docker-compose up -d` 启动/更新所有服务。
 ### Sealos 版本
- 在 Sealos 桌面的`对象存储`中，新建一个存储桶，设置`publicRead`权限。并获取相关密钥：
+- 在 Sealos 桌面的 `对象存储` 中，新建一个存储桶，设置 `publicRead` 权限。并获取相关密钥：
 ![](../../../../public/imgs/sealos-s3.png)
- 部署`fastgpt-plugin`服务，镜像`registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-plugin:v0.1.0`，内网暴露端口3000，无需公网访问，设置环境变量:
+- 部署 `fastgpt-plugin` 服务，镜像 `registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-plugin:v0.1.0`，内网暴露端口 3000，无需公网访问，设置环境变量:
 ```
 AUTH_TOKEN=鉴权 token
@@ -43,7 +44,7 @@ MINIO_SECRET_KEY=Secret Key
 MINIO_BUCKET=存储桶名
 ```
- 更新`fastgpt`和`fastgpt-pro`(商业版)容器的环境变量以及镜像 tag: v4.10.0-fix
+- 更新 `fastgpt` 和 `fastgpt-pro` (商业版)容器的环境变量以及镜像 tag: v4.10.0-fix
 ```
 PLUGIN_BASE_URL=fastgpt-plugin 服务的内网地址

--- a/document/content/self-host/upgrading/outdated/482.en.mdx
+++ b/document/content/self-host/upgrading/outdated/482.en.mdx
@@ -16,7 +16,7 @@ SANDBOX_URL=internal-network-address
 ## Docker Deployment
-You can pull the latest [docker-compose.yml](https://github.com/labring/FastGPT/blob/main/deploy/docker/docker-compose.yml) file for reference.
+You can pull the latest [docker-compose.yml](https://github.com/labring/FastGPT/blob/main/document/public/deploy/docker/main/global/docker-compose.pg.yml) file for reference.
 1. Add a new `sandbox` container.
 2. Add the `SANDBOX_URL` environment variable to the fastgpt and fastgpt-pro (commercial edition) containers.

--- a/document/content/self-host/upgrading/outdated/482.mdx
+++ b/document/content/self-host/upgrading/outdated/482.mdx
@@ -6,7 +6,7 @@ description: FastGPT V4.8.2 更新说明
 ## Sealos 升级说明
 1. 在应用管理中新建一个应用，镜像为：registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.8.1
-2. 无需外网访问地址，端口号为3000
+2. 无需外网访问地址，端口号为 3000
 3. 部署完后，复制应用的内网地址
 4. 点击变更`FastGPT - 修改环境变量，增加下面的环境变量即可
@@ -16,7 +16,7 @@ SANDBOX_URL=内网地址
 ## Docker 部署
-可以拉取最新 [docker-compose.yml](https://github.com/labring/FastGPT/blob/main/deploy/docker/docker-compose.yml) 文件参考
+可以拉取最新 [docker-compose.yml](https://github.com/labring/FastGPT/blob/main/document/public/deploy/docker/main/global/docker-compose.pg.yml) 文件参考
 1. 新增一个容器 `sandbox`
 2. fastgpt 和 fastgpt-pro(商业版) 容器新增环境变量: `SANDBOX_URL`
@@ -24,7 +24,7 @@ SANDBOX_URL=内网地址
 ## V4.8.2 更新说明
-1. 新增 - js代码运行节点（更完整的type提醒，后续继续完善）
+1. 新增 - js 代码运行节点（更完整的 type 提醒，后续继续完善）
 2. 新增 - 内容提取节点支持数据类型选择
 3. 修复 - 新增的站点同步无法使用
 4. 修复 - 定时任务无法输入内容
--- a/document/content/self-host/upgrading/outdated/483.en.mdx
+++ b/document/content/self-host/upgrading/outdated/483.en.mdx
@@ -11,7 +11,7 @@ description: FastGPT V4.8.3 Release Notes
 ## V4.8.3 Release Notes
-1. New - Milvus database support. See the latest [docker-compose-milvus.yml](https://github.com/labring/FastGPT/blob/main/deploy/docker/docker-compose-milvus.yml) for reference.
+1. New - Milvus database support. See the latest [docker-compose-milvus.yml](https://github.com/labring/FastGPT/blob/main/document/public/deploy/docker/main/global/docker-compose.milvus.yml) for reference.
 2. New - Added logging for empty answers in the chat API to help troubleshoot model issues.
 3. New - If/Else conditional node now supports regex for string matching.
 4. New - Code execution node now supports console.log for debug output.

--- a/document/content/self-host/upgrading/outdated/483.mdx
+++ b/document/content/self-host/upgrading/outdated/483.mdx
@@ -11,8 +11,8 @@ description: FastGPT V4.8.3 更新说明
 ## V4.8.3 更新说明
-1. 新增 - 支持 Milvus 数据库， 可参考最新的 [docker-compose-milvus.yml](https://github.com/labring/FastGPT/blob/main/deploy/docker/docker-compose-milvus.yml).
+1. 新增 - 支持 Milvus 数据库，可参考最新的 [docker-compose-milvus.yml](https://github.com/labring/FastGPT/blob/main/document/public/deploy/docker/main/global/docker-compose.milvus.yml) .
 2. 新增 - 给 chat 接口 empty answer 增加 log，便于排查模型问题。
-3. 新增 - ifelse判断器，字符串支持正则。
+3. 新增 - ifelse 判断器，字符串支持正则。
 4. 新增 - 代码运行支持 console.log 输出调试。
 5. 修复 - 变量更新在 Debug 模式下出错。
--- a/document/content/self-host/upgrading/outdated/490.en.mdx
+++ b/document/content/self-host/upgrading/outdated/490.en.mdx
@@ -12,7 +12,7 @@ description: FastGPT V4.9.0 Release Notes
 - Update FastGPT image tag: v4.9.0
 - Update FastGPT Pro image tag: v4.9.0
 - Sandbox image: no update required
- Update PG container to v0.8.0-pg15. See the [latest yml](https://raw.githubusercontent.com/labring/FastGPT/main/deploy/docker/docker-compose-pgvector.yml)
+- Update PG container to v0.8.0-pg15. See the [latest yml](https://raw.githubusercontent.com/labring/FastGPT/main/document/public/deploy/docker/main/global/docker-compose.pg.yml)
 ### 3. Replace OneAPI (Optional)
@@ -20,7 +20,7 @@ Follow this step if you want to replace OneAPI with [AI Proxy](https://github.co
 #### 1. Modify the yml File
-Refer to the [latest yml](https://raw.githubusercontent.com/labring/FastGPT/main/deploy/docker/docker-compose-pgvector.yml) file. OneAPI has been removed and AI Proxy configuration has been added, including one service and one PgSQL database. Append the `aiproxy` configuration after the OneAPI configuration (don't remove OneAPI yet — the initialization process will automatically sync OneAPI's configuration).
+Refer to the [latest yml](https://raw.githubusercontent.com/labring/FastGPT/main/document/public/deploy/docker/main/global/docker-compose.pg.yml) file. OneAPI has been removed and AI Proxy configuration has been added, including one service and one PgSQL database. Append the `aiproxy` configuration after the OneAPI configuration (don't remove OneAPI yet — the initialization process will automatically sync OneAPI's configuration).
 <details>
 <summary>AI Proxy Yml Configuration</summary>

--- a/document/content/self-host/upgrading/outdated/490.mdx
+++ b/document/content/self-host/upgrading/outdated/490.mdx
@@ -12,7 +12,7 @@ description: FastGPT V4.9.0 更新说明
 - 更新 FastGPT 镜像 tag: v4.9.0
 - 更新 FastGPT 商业版镜像 tag: v4.9.0
 - Sandbox 镜像，可以不更新
- 更新 PG 容器为 v0.8.0-pg15, 可以查看[最新的 yml](https://raw.githubusercontent.com/labring/FastGPT/main/deploy/docker/docker-compose-pgvector.yml)
+- 更新 PG 容器为 v0.8.0-pg15, 可以查看[最新的 yml](https://raw.githubusercontent.com/labring/FastGPT/main/document/public/deploy/docker/main/global/docker-compose.pg.yml)
 ### 3. 替换 OneAPI（可选）
@@ -20,7 +20,7 @@ description: FastGPT V4.9.0 更新说明
 #### 1. 修改 yml 文件
-参考[最新的 yml](https://raw.githubusercontent.com/labring/FastGPT/main/deploy/docker/docker-compose-pgvector.yml) 文件。里面已移除 OneAPI 并添加了 AIProxy配置。包含一个服务和一个 PgSQL 数据库。将 `aiproxy` 的配置`追加`到 OneAPI 的配置后面（先不要删除 OneAPI，有一个初始化会自动同步 OneAPI 的配置）
+参考[最新的 yml](https://raw.githubusercontent.com/labring/FastGPT/main/document/public/deploy/docker/main/global/docker-compose.pg.yml) 文件。里面已移除 OneAPI 并添加了 AIProxy 配置。包含一个服务和一个 PgSQL 数据库。将 `aiproxy` 的配置 `追加` 到 OneAPI 的配置后面（先不要删除 OneAPI，有一个初始化会自动同步 OneAPI 的配置）
 <details>
 <summary>AI Proxy Yml 配置</summary>
@@ -92,7 +92,7 @@ description: FastGPT V4.9.0 更新说明
 `docker-compose down` 停止服务，然后 `docker-compose up -d` 启动服务，此时会追加 `aiproxy` 服务，并修改 FastGPT 的配置。
-#### 4. 执行OneAPI迁移AI proxy脚本
+#### 4. 执行 OneAPI 迁移 AI proxy 脚本
 - 可联网方案:
@@ -111,7 +111,7 @@ curl --location --request POST 'http://localhost:3000/api/channels/import/oneapi
 # 返回 {"data":[],"success":true} 代表成功
 ```
- 无法联网时，可打开`aiproxy`的外网暴露端口，然后在本地执行脚本。
+- 无法联网时，可打开 `aiproxy` 的外网暴露端口，然后在本地执行脚本。
 aiProxy 暴露端口：3003:3000，修改后重新 `docker-compose up -d` 启动服务。
@@ -128,9 +128,9 @@ curl --location --request POST 'http://localhost:3003/api/channels/import/oneapi
 - 如果不熟悉 docker 操作，建议不要走脚本迁移，直接删除 OneAPI 所有内容，然后手动重新添加渠道。
-#### 5. 进入 FastGPT 检查`AI Proxy` 服务是否正常启动。
+#### 5. 进入 FastGPT 检查 `AI Proxy` 服务是否正常启动。
-登录 root 账号后，在`账号-模型提供商`页面，可以看到多出了`模型渠道`和`调用日志`两个选项，打开模型渠道，可以看到之前 OneAPI 的渠道，说明迁移完成，此时可以手动再检查下渠道是否正常。
+登录 root 账号后，在 `账号-模型提供商` 页面，可以看到多出了 `模型渠道` 和 `调用日志` 两个选项，打开模型渠道，可以看到之前 OneAPI 的渠道，说明迁移完成，此时可以手动再检查下渠道是否正常。
 #### 6. 删除 OneAPI 服务
@@ -144,7 +144,7 @@ docker-compose up -d
 ### 4. 运行 FastGPT 升级脚本
-从任意终端，发起 1 个 HTTP 请求。其中 `{{rootkey}}` 替换成环境变量里的 `rootkey`；`{{host}}` 替换成**FastGPT 域名**。
+从任意终端，发起 1 个 HTTP 请求。其中 `{{rootkey}}` 替换成环境变量里的 `rootkey`；`{{host}}` 替换成 **FastGPT 域名**。
 ```bash
 curl --location --request POST 'https://{{host}}/api/admin/initv490' \
@@ -163,11 +163,11 @@ curl --location --request POST 'https://{{host}}/api/admin/initv490' \
 1. 弃用 - 之前私有化部署的自定义文件解析方案，请同步更新到最新的配置方案。[点击查看 PDF 增强解析配置](../../config/json.mdx#使用-doc2x-解析-pdf-文件)
 2. 弃用 - 弃用旧版本地文件上传 API：/api/core/dataset/collection/create/file（以前仅商业版可用的 API，该接口已放切换成：/api/core/dataset/collection/create/localFile）
 3. 停止维护，即将弃用 - 外部文件库相关 API，可通过 API 文件库替代。
-4. API更新 - 上传文件至知识库、创建连接集合、API 文件库、推送分块数据等带有 `trainingType` 字段的接口，`trainingType`字段未来仅支持`chunk`和`QA`两种模式。增强索引模式将设置单独字段：`autoIndexes`，目前仍有适配旧版`trainingType=auto`代码，但请尽快变更成新接口类型。具体可见：[知识库 OpenAPI 文档](../../../openapi/dataset.mdx)
+4. API 更新 - 上传文件至知识库、创建连接集合、API 文件库、推送分块数据等带有 `trainingType` 字段的接口，`trainingType` 字段未来仅支持 `chunk` 和 `QA` 两种模式。增强索引模式将设置单独字段：`autoIndexes`，目前仍有适配旧版 `trainingType=auto` 代码，但请尽快变更成新接口类型。具体可见：[知识库 OpenAPI 文档](../../../openapi/dataset.mdx)
 ## 🚀 新增内容
-1. PDF增强解析交互添加到页面上。同时内嵌 Doc2x 服务，可直接使用 Doc2x 服务解析 PDF 文件。
+1. PDF 增强解析交互添加到页面上。同时内嵌 Doc2x 服务，可直接使用 Doc2x 服务解析 PDF 文件。
 2. 图片自动标注，同时修改知识库文件上传部分数据逻辑和交互。
 3. pg vector 插件升级 0.8.0 版本，引入迭代搜索，减少部分数据无法被检索的情况。
 4. 新增 qwen-qwq 系列模型配置。

--- a/document/data/doc-last-modified.json
+++ b/document/data/doc-last-modified.json
@@ -278,7 +278,7 @@
  "content/self-host/upgrading/4-14/4149.en.mdx": "2026-04-26T21:08:47+08:00",
  "content/self-host/upgrading/4-14/4149.mdx": "2026-04-26T21:08:47+08:00",
  "content/self-host/upgrading/4-15/4150.mdx": "2026-05-20T17:52:26+08:00",
-  "content/self-host/upgrading/4-15/41502.mdx": "2026-05-23T22:47:02+08:00",
+  "content/self-host/upgrading/4-15/41502.mdx": "2026-05-23T23:33:02+08:00",
  "content/self-host/upgrading/outdated/40.en.mdx": "2026-04-26T21:08:47+08:00",
  "content/self-host/upgrading/outdated/40.mdx": "2026-04-26T21:08:47+08:00",
  "content/self-host/upgrading/outdated/41.en.mdx": "2026-04-26T21:08:47+08:00",

--- a/document/public/deploy/docker/cn/docker-compose.milvus.yml
+++ b/document/public/deploy/docker/cn/docker-compose.milvus.yml
@@ -11,8 +11,6 @@ x-system-key: &x-system-key 'fastgpt-xxx'
 x-plugin-auth-token: &x-plugin-auth-token 'token'
 # code sandbox token
 x-code-sandbox-token: &x-code-sandbox-token 'codesandbox'
-# volume manager auth token
-x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'
 # aiproxy token
 x-aiproxy-token: &x-aiproxy-token 'token'
 # 数据库连接相关配置
@@ -43,7 +41,6 @@ x-log-config: &x-log-config
 x-vec-config: &x-vec-config
  MILVUS_ADDRESS: http://fastgpt-vector:19530
  MILVUS_TOKEN: none
 services:
  # Vector DB
@@ -104,7 +101,6 @@ services:
    depends_on:
      - 'fastgpt-milvus-etcd'
      - 'fastgpt-milvus-minio'
  fastgpt-mongo:
    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -192,14 +188,13 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.20 
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.15.0-beta1
    ports:
      - 3000:3000
    networks:
      - data
      - app
      - codesandbox
-      - opensandbox
      - aiproxy
    depends_on:
      fastgpt-mongo:
@@ -221,7 +216,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -250,20 +245,6 @@ services:
      # AI Proxy 的 Admin Token，与 AI Proxy 中的环境变量 ADMIN_KEY
      AIPROXY_API_TOKEN: *x-aiproxy-token
-      # ==================== Agent sandbox 配置 ====================
-      AGENT_SANDBOX_PROVIDER: opensandbox
-      # OpenSandbox 配置（PROVIDER: opensandbox 时生效）
-      AGENT_SANDBOX_OPENSANDBOX_BASEURL: http://opensandbox-server:8090
-      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
-      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
-      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
-      # Volume 持久化配置（opensandbox provider 下可选）
-      AGENT_SANDBOX_ENABLE_VOLUME: true
-      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
-      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
      LOG_OTEL_SERVICE_NAME: fastgpt-client
@@ -271,7 +252,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.15.0-beta1
    networks:
      - codesandbox
    restart: always
@@ -310,17 +291,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.15.0-beta1
    networks:
      - app
    ports:
@@ -356,79 +337,9 @@ services:
      timeout: 20s
      retries: 3
-  # 沙盒控制器：管理 Docker 容器的创建/执行/停止/删除
-  # runtime=docker 模式需要挂载 Docker socket
-  # 配置 docker.host_ip 为宿主机 LAN IP（容器内访问宿主机服务用）
-  opensandbox-server:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-server:v0.1.9
-    container_name: fastgpt-opensandbox-server
-    restart: always
-    networks:
-      - opensandbox
-    extra_hosts:
-      - 'host.docker.internal:host-gateway'
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    configs:
-      - source: opensandbox-config
-        target: /etc/opensandbox/config.toml
-    environment:
-      SANDBOX_CONFIG_PATH: /etc/opensandbox/config.toml
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'python',
-          '-c',
-          'import urllib.request,sys; sys.exit(0 if urllib.request.urlopen("http://localhost:8090/health",timeout=3).status==200 else 1)'
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
-  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
-  opensandbox-agent-sandbox-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1
-    profiles:
-      - prepull
-  opensandbox-execd-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-execd:v1.0.7
-    profiles:
-      - prepull
-  opensandbox-egress-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-egress:v1.0.3
-    profiles:
-      - prepull
-  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
-  fastgpt-volume-manager:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1
-    container_name: fastgpt-volume-manager
-    restart: always
-    networks:
-      - opensandbox
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    environment:
-      PORT: 3000
-      VM_RUNTIME: docker
-      VM_AUTH_TOKEN: *x-volume-manager-auth-token # 对应 AGENT_SANDBOX_VOLUME_MANAGER_TOKEN
-      VM_VOLUME_NAME_PREFIX: fastgpt-session # volume 名称前缀
-      VM_LOG_LEVEL: info
-      VM_DOCKER_API_VERSION: v1.44
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'bun',
-          '-e',
-          "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
  # AI Proxy
  fastgpt-aiproxy:
-    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.6
+    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -479,8 +390,6 @@ networks:
    name: fastgpt_app
  codesandbox:
    name: fastgpt_codesandbox
-  opensandbox:
-    name: fastgpt_opensandbox
  aiproxy:
    name: fastgpt_aiproxy
@@ -497,31 +406,3 @@ volumes:
  fastgpt-seekdb-data:
  fastgpt-seekdb-config:
  fastgpt-aiproxy_pg:
-configs:
-  opensandbox-config:
-    content: |
-      [server]
-      host = "0.0.0.0"
-      port = 8090
-      log_level = "INFO"
-      [runtime]
-      type = "docker"
-      execd_image = "registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-execd:v1.0.7"
-      [egress]
-      image = "registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-egress:v1.0.3"
-      [docker]
-      network_mode = "fastgpt_opensandbox"
-      # When server runs in a container, set host_ip to the host's IP or hostname so bridge-mode endpoints are reachable (e.g. host.docker.internal or the host LAN IP).
-      # It's required when server deployed with docker container under host.
-      host_ip = "host.docker.internal"
-      drop_capabilities = ["AUDIT_WRITE", "MKNOD", "NET_ADMIN", "NET_RAW", "SYS_ADMIN", "SYS_MODULE", "SYS_PTRACE", "SYS_TIME", "SYS_TTY_CONFIG"]
-      no_new_privileges = true
-      pids_limit = 512
-      [ingress]
-      mode = "direct"
--- a/document/public/deploy/docker/cn/docker-compose.oceanbase.yml
+++ b/document/public/deploy/docker/cn/docker-compose.oceanbase.yml
@@ -11,8 +11,6 @@ x-system-key: &x-system-key 'fastgpt-xxx'
 x-plugin-auth-token: &x-plugin-auth-token 'token'
 # code sandbox token
 x-code-sandbox-token: &x-code-sandbox-token 'codesandbox'
-# volume manager auth token
-x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'
 # aiproxy token
 x-aiproxy-token: &x-aiproxy-token 'token'
 # 数据库连接相关配置
@@ -43,7 +41,6 @@ x-log-config: &x-log-config
 x-vec-config: &x-vec-config
  OCEANBASE_URL: mysql://root%40tenantname:tenantpassword@fastgpt-vector:2881/mysql
 services:
  # Vector DB
  fastgpt-vector:
@@ -82,7 +79,6 @@ services:
      timeout: 10s
      retries: 1000
      start_period: 10s
  fastgpt-mongo:
    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -170,14 +166,13 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.20 
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.15.0-beta1
    ports:
      - 3000:3000
    networks:
      - data
      - app
      - codesandbox
-      - opensandbox
      - aiproxy
    depends_on:
      fastgpt-mongo:
@@ -199,7 +194,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -228,20 +223,6 @@ services:
      # AI Proxy 的 Admin Token，与 AI Proxy 中的环境变量 ADMIN_KEY
      AIPROXY_API_TOKEN: *x-aiproxy-token
-      # ==================== Agent sandbox 配置 ====================
-      AGENT_SANDBOX_PROVIDER: opensandbox
-      # OpenSandbox 配置（PROVIDER: opensandbox 时生效）
-      AGENT_SANDBOX_OPENSANDBOX_BASEURL: http://opensandbox-server:8090
-      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
-      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
-      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
-      # Volume 持久化配置（opensandbox provider 下可选）
-      AGENT_SANDBOX_ENABLE_VOLUME: true
-      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
-      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
      LOG_OTEL_SERVICE_NAME: fastgpt-client
@@ -249,7 +230,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.15.0-beta1
    networks:
      - codesandbox
    restart: always
@@ -288,17 +269,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.15.0-beta1
    networks:
      - app
    ports:
@@ -334,79 +315,9 @@ services:
      timeout: 20s
      retries: 3
-  # 沙盒控制器：管理 Docker 容器的创建/执行/停止/删除
-  # runtime=docker 模式需要挂载 Docker socket
-  # 配置 docker.host_ip 为宿主机 LAN IP（容器内访问宿主机服务用）
-  opensandbox-server:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-server:v0.1.9
-    container_name: fastgpt-opensandbox-server
-    restart: always
-    networks:
-      - opensandbox
-    extra_hosts:
-      - 'host.docker.internal:host-gateway'
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    configs:
-      - source: opensandbox-config
-        target: /etc/opensandbox/config.toml
-    environment:
-      SANDBOX_CONFIG_PATH: /etc/opensandbox/config.toml
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'python',
-          '-c',
-          'import urllib.request,sys; sys.exit(0 if urllib.request.urlopen("http://localhost:8090/health",timeout=3).status==200 else 1)'
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
-  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
-  opensandbox-agent-sandbox-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1
-    profiles:
-      - prepull
-  opensandbox-execd-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-execd:v1.0.7
-    profiles:
-      - prepull
-  opensandbox-egress-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-egress:v1.0.3
-    profiles:
-      - prepull
-  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
-  fastgpt-volume-manager:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1
-    container_name: fastgpt-volume-manager
-    restart: always
-    networks:
-      - opensandbox
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    environment:
-      PORT: 3000
-      VM_RUNTIME: docker
-      VM_AUTH_TOKEN: *x-volume-manager-auth-token # 对应 AGENT_SANDBOX_VOLUME_MANAGER_TOKEN
-      VM_VOLUME_NAME_PREFIX: fastgpt-session # volume 名称前缀
-      VM_LOG_LEVEL: info
-      VM_DOCKER_API_VERSION: v1.44
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'bun',
-          '-e',
-          "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
  # AI Proxy
  fastgpt-aiproxy:
-    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.6
+    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -457,8 +368,6 @@ networks:
    name: fastgpt_app
  codesandbox:
    name: fastgpt_codesandbox
-  opensandbox:
-    name: fastgpt_opensandbox
  aiproxy:
    name: fastgpt_aiproxy
@@ -477,33 +386,7 @@ volumes:
  fastgpt-aiproxy_pg:
 configs:
-  opensandbox-config:
-    content: |
-      [server]
-      host = "0.0.0.0"
-      port = 8090
-      log_level = "INFO"
-      [runtime]
-      type = "docker"
-      execd_image = "registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-execd:v1.0.7"
-      [egress]
-      image = "registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-egress:v1.0.3"
-      [docker]
-      network_mode = "fastgpt_opensandbox"
-      # When server runs in a container, set host_ip to the host's IP or hostname so bridge-mode endpoints are reachable (e.g. host.docker.internal or the host LAN IP).
-      # It's required when server deployed with docker container under host.
-      host_ip = "host.docker.internal"
-      drop_capabilities = ["AUDIT_WRITE", "MKNOD", "NET_ADMIN", "NET_RAW", "SYS_ADMIN", "SYS_MODULE", "SYS_PTRACE", "SYS_TIME", "SYS_TTY_CONFIG"]
-      no_new_privileges = true
-      pids_limit = 512
-      [ingress]
-      mode = "direct"
  init_sql:
    name: init_sql
    content: |
      ALTER SYSTEM SET ob_vector_memory_limit_percentage = 30;
--- a/document/public/deploy/docker/cn/docker-compose.opengauss.yml
+++ b/document/public/deploy/docker/cn/docker-compose.opengauss.yml
@@ -11,8 +11,6 @@ x-system-key: &x-system-key 'fastgpt-xxx'
 x-plugin-auth-token: &x-plugin-auth-token 'token'
 # code sandbox token
 x-code-sandbox-token: &x-code-sandbox-token 'codesandbox'
-# volume manager auth token
-x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'
 # aiproxy token
 x-aiproxy-token: &x-aiproxy-token 'token'
 # 数据库连接相关配置
@@ -152,14 +150,13 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.20 
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.15.0-beta1
    ports:
      - 3000:3000
    networks:
      - data
      - app
      - codesandbox
-      - opensandbox
      - aiproxy
    depends_on:
      fastgpt-mongo:
@@ -181,7 +178,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -210,20 +207,6 @@ services:
      # AI Proxy 的 Admin Token，与 AI Proxy 中的环境变量 ADMIN_KEY
      AIPROXY_API_TOKEN: *x-aiproxy-token
-      # ==================== Agent sandbox 配置 ====================
-      AGENT_SANDBOX_PROVIDER: opensandbox
-      # OpenSandbox 配置（PROVIDER: opensandbox 时生效）
-      AGENT_SANDBOX_OPENSANDBOX_BASEURL: http://opensandbox-server:8090
-      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
-      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
-      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
-      # Volume 持久化配置（opensandbox provider 下可选）
-      AGENT_SANDBOX_ENABLE_VOLUME: true
-      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
-      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
      LOG_OTEL_SERVICE_NAME: fastgpt-client
@@ -231,7 +214,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.15.0-beta1
    networks:
      - codesandbox
    restart: always
@@ -270,17 +253,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.15.0-beta1
    networks:
      - app
    ports:
@@ -316,79 +299,9 @@ services:
      timeout: 20s
      retries: 3
-  # 沙盒控制器：管理 Docker 容器的创建/执行/停止/删除
-  # runtime=docker 模式需要挂载 Docker socket
-  # 配置 docker.host_ip 为宿主机 LAN IP（容器内访问宿主机服务用）
-  opensandbox-server:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-server:v0.1.9
-    container_name: fastgpt-opensandbox-server
-    restart: always
-    networks:
-      - opensandbox
-    extra_hosts:
-      - 'host.docker.internal:host-gateway'
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    configs:
-      - source: opensandbox-config
-        target: /etc/opensandbox/config.toml
-    environment:
-      SANDBOX_CONFIG_PATH: /etc/opensandbox/config.toml
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'python',
-          '-c',
-          'import urllib.request,sys; sys.exit(0 if urllib.request.urlopen("http://localhost:8090/health",timeout=3).status==200 else 1)'
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
-  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
-  opensandbox-agent-sandbox-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1
-    profiles:
-      - prepull
-  opensandbox-execd-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-execd:v1.0.7
-    profiles:
-      - prepull
-  opensandbox-egress-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-egress:v1.0.3
-    profiles:
-      - prepull
-  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
-  fastgpt-volume-manager:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1
-    container_name: fastgpt-volume-manager
-    restart: always
-    networks:
-      - opensandbox
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    environment:
-      PORT: 3000
-      VM_RUNTIME: docker
-      VM_AUTH_TOKEN: *x-volume-manager-auth-token # 对应 AGENT_SANDBOX_VOLUME_MANAGER_TOKEN
-      VM_VOLUME_NAME_PREFIX: fastgpt-session # volume 名称前缀
-      VM_LOG_LEVEL: info
-      VM_DOCKER_API_VERSION: v1.44
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'bun',
-          '-e',
-          "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
  # AI Proxy
  fastgpt-aiproxy:
-    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.6
+    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -439,8 +352,6 @@ networks:
    name: fastgpt_app
  codesandbox:
    name: fastgpt_codesandbox
-  opensandbox:
-    name: fastgpt_opensandbox
  aiproxy:
    name: fastgpt_aiproxy
@@ -457,31 +368,3 @@ volumes:
  fastgpt-seekdb-data:
  fastgpt-seekdb-config:
  fastgpt-aiproxy_pg:
-configs:
-  opensandbox-config:
-    content: |
-      [server]
-      host = "0.0.0.0"
-      port = 8090
-      log_level = "INFO"
-      [runtime]
-      type = "docker"
-      execd_image = "registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-execd:v1.0.7"
-      [egress]
-      image = "registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-egress:v1.0.3"
-      [docker]
-      network_mode = "fastgpt_opensandbox"
-      # When server runs in a container, set host_ip to the host's IP or hostname so bridge-mode endpoints are reachable (e.g. host.docker.internal or the host LAN IP).
-      # It's required when server deployed with docker container under host.
-      host_ip = "host.docker.internal"
-      drop_capabilities = ["AUDIT_WRITE", "MKNOD", "NET_ADMIN", "NET_RAW", "SYS_ADMIN", "SYS_MODULE", "SYS_PTRACE", "SYS_TIME", "SYS_TTY_CONFIG"]
-      no_new_privileges = true
-      pids_limit = 512
-      [ingress]
-      mode = "direct"
--- a/document/public/deploy/docker/cn/docker-compose.pg.yml
+++ b/document/public/deploy/docker/cn/docker-compose.pg.yml
@@ -11,8 +11,6 @@ x-system-key: &x-system-key 'fastgpt-xxx'
 x-plugin-auth-token: &x-plugin-auth-token 'token'
 # code sandbox token
 x-code-sandbox-token: &x-code-sandbox-token 'codesandbox'
-# volume manager auth token
-x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'
 # aiproxy token
 x-aiproxy-token: &x-aiproxy-token 'token'
 # 数据库连接相关配置
@@ -63,7 +61,6 @@ services:
      interval: 5s
      timeout: 5s
      retries: 10
  fastgpt-mongo:
    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -151,14 +148,13 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.20 
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.15.0-beta1
    ports:
      - 3000:3000
    networks:
      - data
      - app
      - codesandbox
-      - opensandbox
      - aiproxy
    depends_on:
      fastgpt-mongo:
@@ -180,7 +176,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -209,20 +205,6 @@ services:
      # AI Proxy 的 Admin Token，与 AI Proxy 中的环境变量 ADMIN_KEY
      AIPROXY_API_TOKEN: *x-aiproxy-token
-      # ==================== Agent sandbox 配置 ====================
-      AGENT_SANDBOX_PROVIDER: opensandbox
-      # OpenSandbox 配置（PROVIDER: opensandbox 时生效）
-      AGENT_SANDBOX_OPENSANDBOX_BASEURL: http://opensandbox-server:8090
-      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
-      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
-      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
-      # Volume 持久化配置（opensandbox provider 下可选）
-      AGENT_SANDBOX_ENABLE_VOLUME: true
-      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
-      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
      LOG_OTEL_SERVICE_NAME: fastgpt-client
@@ -230,7 +212,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.15.0-beta1
    networks:
      - codesandbox
    restart: always
@@ -269,17 +251,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.15.0-beta1
    networks:
      - app
    ports:
@@ -315,79 +297,9 @@ services:
      timeout: 20s
      retries: 3
-  # 沙盒控制器：管理 Docker 容器的创建/执行/停止/删除
-  # runtime=docker 模式需要挂载 Docker socket
-  # 配置 docker.host_ip 为宿主机 LAN IP（容器内访问宿主机服务用）
-  opensandbox-server:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-server:v0.1.9
-    container_name: fastgpt-opensandbox-server
-    restart: always
-    networks:
-      - opensandbox
-    extra_hosts:
-      - 'host.docker.internal:host-gateway'
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    configs:
-      - source: opensandbox-config
-        target: /etc/opensandbox/config.toml
-    environment:
-      SANDBOX_CONFIG_PATH: /etc/opensandbox/config.toml
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'python',
-          '-c',
-          'import urllib.request,sys; sys.exit(0 if urllib.request.urlopen("http://localhost:8090/health",timeout=3).status==200 else 1)'
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
-  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
-  opensandbox-agent-sandbox-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1
-    profiles:
-      - prepull
-  opensandbox-execd-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-execd:v1.0.7
-    profiles:
-      - prepull
-  opensandbox-egress-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-egress:v1.0.3
-    profiles:
-      - prepull
-  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
-  fastgpt-volume-manager:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1
-    container_name: fastgpt-volume-manager
-    restart: always
-    networks:
-      - opensandbox
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    environment:
-      PORT: 3000
-      VM_RUNTIME: docker
-      VM_AUTH_TOKEN: *x-volume-manager-auth-token # 对应 AGENT_SANDBOX_VOLUME_MANAGER_TOKEN
-      VM_VOLUME_NAME_PREFIX: fastgpt-session # volume 名称前缀
-      VM_LOG_LEVEL: info
-      VM_DOCKER_API_VERSION: v1.44
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'bun',
-          '-e',
-          "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
  # AI Proxy
  fastgpt-aiproxy:
-    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.6
+    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -438,8 +350,6 @@ networks:
    name: fastgpt_app
  codesandbox:
    name: fastgpt_codesandbox
-  opensandbox:
-    name: fastgpt_opensandbox
  aiproxy:
    name: fastgpt_aiproxy
@@ -456,31 +366,3 @@ volumes:
  fastgpt-seekdb-data:
  fastgpt-seekdb-config:
  fastgpt-aiproxy_pg:
-configs:
-  opensandbox-config:
-    content: |
-      [server]
-      host = "0.0.0.0"
-      port = 8090
-      log_level = "INFO"
-      [runtime]
-      type = "docker"
-      execd_image = "registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-execd:v1.0.7"
-      [egress]
-      image = "registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-egress:v1.0.3"
-      [docker]
-      network_mode = "fastgpt_opensandbox"
-      # When server runs in a container, set host_ip to the host's IP or hostname so bridge-mode endpoints are reachable (e.g. host.docker.internal or the host LAN IP).
-      # It's required when server deployed with docker container under host.
-      host_ip = "host.docker.internal"
-      drop_capabilities = ["AUDIT_WRITE", "MKNOD", "NET_ADMIN", "NET_RAW", "SYS_ADMIN", "SYS_MODULE", "SYS_PTRACE", "SYS_TIME", "SYS_TTY_CONFIG"]
-      no_new_privileges = true
-      pids_limit = 512
-      [ingress]
-      mode = "direct"
--- a/document/public/deploy/docker/cn/docker-compose.seekdb.yml
+++ b/document/public/deploy/docker/cn/docker-compose.seekdb.yml
@@ -11,8 +11,6 @@ x-system-key: &x-system-key 'fastgpt-xxx'
 x-plugin-auth-token: &x-plugin-auth-token 'token'
 # code sandbox token
 x-code-sandbox-token: &x-code-sandbox-token 'codesandbox'
-# volume manager auth token
-x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'
 # aiproxy token
 x-aiproxy-token: &x-aiproxy-token 'token'
 # 数据库连接相关配置
@@ -43,7 +41,6 @@ x-log-config: &x-log-config
 x-vec-config: &x-vec-config
  SEEKDB_URL: mysql://root:seekdbpassword@fastgpt-vector:2881/mysql
 services:
  # Vector DB
  fastgpt-vector:
@@ -69,7 +66,6 @@ services:
      timeout: 10s
      retries: 1000
      start_period: 10s
  fastgpt-mongo:
    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -157,14 +153,13 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.20 
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.15.0-beta1
    ports:
      - 3000:3000
    networks:
      - data
      - app
      - codesandbox
-      - opensandbox
      - aiproxy
    depends_on:
      fastgpt-mongo:
@@ -186,7 +181,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -215,20 +210,6 @@ services:
      # AI Proxy 的 Admin Token，与 AI Proxy 中的环境变量 ADMIN_KEY
      AIPROXY_API_TOKEN: *x-aiproxy-token
-      # ==================== Agent sandbox 配置 ====================
-      AGENT_SANDBOX_PROVIDER: opensandbox
-      # OpenSandbox 配置（PROVIDER: opensandbox 时生效）
-      AGENT_SANDBOX_OPENSANDBOX_BASEURL: http://opensandbox-server:8090
-      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
-      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
-      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
-      # Volume 持久化配置（opensandbox provider 下可选）
-      AGENT_SANDBOX_ENABLE_VOLUME: true
-      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
-      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
      LOG_OTEL_SERVICE_NAME: fastgpt-client
@@ -236,7 +217,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.15.0-beta1
    networks:
      - codesandbox
    restart: always
@@ -275,17 +256,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.15.0-beta1
    networks:
      - app
    ports:
@@ -321,79 +302,9 @@ services:
      timeout: 20s
      retries: 3
-  # 沙盒控制器：管理 Docker 容器的创建/执行/停止/删除
-  # runtime=docker 模式需要挂载 Docker socket
-  # 配置 docker.host_ip 为宿主机 LAN IP（容器内访问宿主机服务用）
-  opensandbox-server:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-server:v0.1.9
-    container_name: fastgpt-opensandbox-server
-    restart: always
-    networks:
-      - opensandbox
-    extra_hosts:
-      - 'host.docker.internal:host-gateway'
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    configs:
-      - source: opensandbox-config
-        target: /etc/opensandbox/config.toml
-    environment:
-      SANDBOX_CONFIG_PATH: /etc/opensandbox/config.toml
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'python',
-          '-c',
-          'import urllib.request,sys; sys.exit(0 if urllib.request.urlopen("http://localhost:8090/health",timeout=3).status==200 else 1)'
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
-  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
-  opensandbox-agent-sandbox-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1
-    profiles:
-      - prepull
-  opensandbox-execd-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-execd:v1.0.7
-    profiles:
-      - prepull
-  opensandbox-egress-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-egress:v1.0.3
-    profiles:
-      - prepull
-  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
-  fastgpt-volume-manager:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1
-    container_name: fastgpt-volume-manager
-    restart: always
-    networks:
-      - opensandbox
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    environment:
-      PORT: 3000
-      VM_RUNTIME: docker
-      VM_AUTH_TOKEN: *x-volume-manager-auth-token # 对应 AGENT_SANDBOX_VOLUME_MANAGER_TOKEN
-      VM_VOLUME_NAME_PREFIX: fastgpt-session # volume 名称前缀
-      VM_LOG_LEVEL: info
-      VM_DOCKER_API_VERSION: v1.44
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'bun',
-          '-e',
-          "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
  # AI Proxy
  fastgpt-aiproxy:
-    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.6
+    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -444,8 +355,6 @@ networks:
    name: fastgpt_app
  codesandbox:
    name: fastgpt_codesandbox
-  opensandbox:
-    name: fastgpt_opensandbox
  aiproxy:
    name: fastgpt_aiproxy
@@ -462,31 +371,3 @@ volumes:
  fastgpt-seekdb-data:
  fastgpt-seekdb-config:
  fastgpt-aiproxy_pg:
-configs:
-  opensandbox-config:
-    content: |
-      [server]
-      host = "0.0.0.0"
-      port = 8090
-      log_level = "INFO"
-      [runtime]
-      type = "docker"
-      execd_image = "registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-execd:v1.0.7"
-      [egress]
-      image = "registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-egress:v1.0.3"
-      [docker]
-      network_mode = "fastgpt_opensandbox"
-      # When server runs in a container, set host_ip to the host's IP or hostname so bridge-mode endpoints are reachable (e.g. host.docker.internal or the host LAN IP).
-      # It's required when server deployed with docker container under host.
-      host_ip = "host.docker.internal"
-      drop_capabilities = ["AUDIT_WRITE", "MKNOD", "NET_ADMIN", "NET_RAW", "SYS_ADMIN", "SYS_MODULE", "SYS_PTRACE", "SYS_TIME", "SYS_TTY_CONFIG"]
-      no_new_privileges = true
-      pids_limit = 512
-      [ingress]
-      mode = "direct"
--- a/document/public/deploy/docker/cn/docker-compose.zilliz.yml
+++ b/document/public/deploy/docker/cn/docker-compose.zilliz.yml
@@ -11,8 +11,6 @@ x-system-key: &x-system-key 'fastgpt-xxx'
 x-plugin-auth-token: &x-plugin-auth-token 'token'
 # code sandbox token
 x-code-sandbox-token: &x-code-sandbox-token 'codesandbox'
-# volume manager auth token
-x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'
 # aiproxy token
 x-aiproxy-token: &x-aiproxy-token 'token'
 # 数据库连接相关配置
@@ -134,14 +132,13 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.20 
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.15.0-beta1
    ports:
      - 3000:3000
    networks:
      - data
      - app
      - codesandbox
-      - opensandbox
      - aiproxy
    depends_on:
      fastgpt-mongo:
@@ -163,7 +160,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -192,20 +189,6 @@ services:
      # AI Proxy 的 Admin Token，与 AI Proxy 中的环境变量 ADMIN_KEY
      AIPROXY_API_TOKEN: *x-aiproxy-token
-      # ==================== Agent sandbox 配置 ====================
-      AGENT_SANDBOX_PROVIDER: opensandbox
-      # OpenSandbox 配置（PROVIDER: opensandbox 时生效）
-      AGENT_SANDBOX_OPENSANDBOX_BASEURL: http://opensandbox-server:8090
-      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
-      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
-      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
-      # Volume 持久化配置（opensandbox provider 下可选）
-      AGENT_SANDBOX_ENABLE_VOLUME: true
-      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
-      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
      LOG_OTEL_SERVICE_NAME: fastgpt-client
@@ -213,7 +196,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.15.0-beta1
    networks:
      - codesandbox
    restart: always
@@ -252,17 +235,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.15.0-beta1
    networks:
      - app
    ports:
@@ -298,79 +281,9 @@ services:
      timeout: 20s
      retries: 3
-  # 沙盒控制器：管理 Docker 容器的创建/执行/停止/删除
-  # runtime=docker 模式需要挂载 Docker socket
-  # 配置 docker.host_ip 为宿主机 LAN IP（容器内访问宿主机服务用）
-  opensandbox-server:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-server:v0.1.9
-    container_name: fastgpt-opensandbox-server
-    restart: always
-    networks:
-      - opensandbox
-    extra_hosts:
-      - 'host.docker.internal:host-gateway'
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    configs:
-      - source: opensandbox-config
-        target: /etc/opensandbox/config.toml
-    environment:
-      SANDBOX_CONFIG_PATH: /etc/opensandbox/config.toml
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'python',
-          '-c',
-          'import urllib.request,sys; sys.exit(0 if urllib.request.urlopen("http://localhost:8090/health",timeout=3).status==200 else 1)'
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
-  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
-  opensandbox-agent-sandbox-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1
-    profiles:
-      - prepull
-  opensandbox-execd-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-execd:v1.0.7
-    profiles:
-      - prepull
-  opensandbox-egress-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-egress:v1.0.3
-    profiles:
-      - prepull
-  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
-  fastgpt-volume-manager:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1
-    container_name: fastgpt-volume-manager
-    restart: always
-    networks:
-      - opensandbox
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    environment:
-      PORT: 3000
-      VM_RUNTIME: docker
-      VM_AUTH_TOKEN: *x-volume-manager-auth-token # 对应 AGENT_SANDBOX_VOLUME_MANAGER_TOKEN
-      VM_VOLUME_NAME_PREFIX: fastgpt-session # volume 名称前缀
-      VM_LOG_LEVEL: info
-      VM_DOCKER_API_VERSION: v1.44
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'bun',
-          '-e',
-          "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
  # AI Proxy
  fastgpt-aiproxy:
-    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.6
+    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -421,8 +334,6 @@ networks:
    name: fastgpt_app
  codesandbox:
    name: fastgpt_codesandbox
-  opensandbox:
-    name: fastgpt_opensandbox
  aiproxy:
    name: fastgpt_aiproxy
@@ -439,31 +350,3 @@ volumes:
  fastgpt-seekdb-data:
  fastgpt-seekdb-config:
  fastgpt-aiproxy_pg:
-configs:
-  opensandbox-config:
-    content: |
-      [server]
-      host = "0.0.0.0"
-      port = 8090
-      log_level = "INFO"
-      [runtime]
-      type = "docker"
-      execd_image = "registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-execd:v1.0.7"
-      [egress]
-      image = "registry.cn-hangzhou.aliyuncs.com/fastgpt/opensandbox-egress:v1.0.3"
-      [docker]
-      network_mode = "fastgpt_opensandbox"
-      # When server runs in a container, set host_ip to the host's IP or hostname so bridge-mode endpoints are reachable (e.g. host.docker.internal or the host LAN IP).
-      # It's required when server deployed with docker container under host.
-      host_ip = "host.docker.internal"
-      drop_capabilities = ["AUDIT_WRITE", "MKNOD", "NET_ADMIN", "NET_RAW", "SYS_ADMIN", "SYS_MODULE", "SYS_PTRACE", "SYS_TIME", "SYS_TTY_CONFIG"]
-      no_new_privileges = true
-      pids_limit = 512
-      [ingress]
-      mode = "direct"
--- a/document/public/deploy/docker/global/docker-compose.milvus.yml
+++ b/document/public/deploy/docker/global/docker-compose.milvus.yml
@@ -11,8 +11,6 @@ x-system-key: &x-system-key 'fastgpt-xxx'
 x-plugin-auth-token: &x-plugin-auth-token 'token'
 # code sandbox token
 x-code-sandbox-token: &x-code-sandbox-token 'codesandbox'
-# volume manager auth token
-x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'
 # aiproxy token
 x-aiproxy-token: &x-aiproxy-token 'token'
 # 数据库连接相关配置
@@ -43,7 +41,6 @@ x-log-config: &x-log-config
 x-vec-config: &x-vec-config
  MILVUS_ADDRESS: http://fastgpt-vector:19530
  MILVUS_TOKEN: none
 services:
  # Vector DB
@@ -104,7 +101,6 @@ services:
    depends_on:
      - 'fastgpt-milvus-etcd'
      - 'fastgpt-milvus-minio'
  fastgpt-mongo:
    image: mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -192,14 +188,13 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: ghcr.io/labring/fastgpt:v4.14.20 
+    image: ghcr.io/labring/fastgpt:v4.15.0-beta1
    ports:
      - 3000:3000
    networks:
      - data
      - app
      - codesandbox
-      - opensandbox
      - aiproxy
    depends_on:
      fastgpt-mongo:
@@ -221,7 +216,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -250,20 +245,6 @@ services:
      # AI Proxy 的 Admin Token，与 AI Proxy 中的环境变量 ADMIN_KEY
      AIPROXY_API_TOKEN: *x-aiproxy-token
-      # ==================== Agent sandbox 配置 ====================
-      AGENT_SANDBOX_PROVIDER: opensandbox
-      # OpenSandbox 配置（PROVIDER: opensandbox 时生效）
-      AGENT_SANDBOX_OPENSANDBOX_BASEURL: http://opensandbox-server:8090
-      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
-      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: ghcr.io/labring/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
-      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
-      # Volume 持久化配置（opensandbox provider 下可选）
-      AGENT_SANDBOX_ENABLE_VOLUME: true
-      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
-      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
      LOG_OTEL_SERVICE_NAME: fastgpt-client
@@ -271,7 +252,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.20
+    image: ghcr.io/labring/fastgpt-code-sandbox:v4.15.0-beta1
    networks:
      - codesandbox
    restart: always
@@ -310,17 +291,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.20
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.15.0-beta1
    networks:
      - app
    ports:
@@ -356,79 +337,9 @@ services:
      timeout: 20s
      retries: 3
-  # 沙盒控制器：管理 Docker 容器的创建/执行/停止/删除
-  # runtime=docker 模式需要挂载 Docker socket
-  # 配置 docker.host_ip 为宿主机 LAN IP（容器内访问宿主机服务用）
-  opensandbox-server:
-    image: opensandbox/server:v0.1.9
-    container_name: fastgpt-opensandbox-server
-    restart: always
-    networks:
-      - opensandbox
-    extra_hosts:
-      - 'host.docker.internal:host-gateway'
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    configs:
-      - source: opensandbox-config
-        target: /etc/opensandbox/config.toml
-    environment:
-      SANDBOX_CONFIG_PATH: /etc/opensandbox/config.toml
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'python',
-          '-c',
-          'import urllib.request,sys; sys.exit(0 if urllib.request.urlopen("http://localhost:8090/health",timeout=3).status==200 else 1)'
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
-  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
-  opensandbox-agent-sandbox-image:
-    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1
-    profiles:
-      - prepull
-  opensandbox-execd-image:
-    image: opensandbox/execd:v1.0.7
-    profiles:
-      - prepull
-  opensandbox-egress-image:
-    image: opensandbox/egress:v1.0.3
-    profiles:
-      - prepull
-  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
-  fastgpt-volume-manager:
-    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1
-    container_name: fastgpt-volume-manager
-    restart: always
-    networks:
-      - opensandbox
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    environment:
-      PORT: 3000
-      VM_RUNTIME: docker
-      VM_AUTH_TOKEN: *x-volume-manager-auth-token # 对应 AGENT_SANDBOX_VOLUME_MANAGER_TOKEN
-      VM_VOLUME_NAME_PREFIX: fastgpt-session # volume 名称前缀
-      VM_LOG_LEVEL: info
-      VM_DOCKER_API_VERSION: v1.44
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'bun',
-          '-e',
-          "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
  # AI Proxy
  fastgpt-aiproxy:
-    image: ghcr.io/labring/aiproxy:v0.5.6
+    image: ghcr.io/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -479,8 +390,6 @@ networks:
    name: fastgpt_app
  codesandbox:
    name: fastgpt_codesandbox
-  opensandbox:
-    name: fastgpt_opensandbox
  aiproxy:
    name: fastgpt_aiproxy
@@ -497,31 +406,3 @@ volumes:
  fastgpt-seekdb-data:
  fastgpt-seekdb-config:
  fastgpt-aiproxy_pg:
-configs:
-  opensandbox-config:
-    content: |
-      [server]
-      host = "0.0.0.0"
-      port = 8090
-      log_level = "INFO"
-      [runtime]
-      type = "docker"
-      execd_image = "opensandbox/execd:v1.0.7"
-      [egress]
-      image = "opensandbox/egress:v1.0.3"
-      [docker]
-      network_mode = "fastgpt_opensandbox"
-      # When server runs in a container, set host_ip to the host's IP or hostname so bridge-mode endpoints are reachable (e.g. host.docker.internal or the host LAN IP).
-      # It's required when server deployed with docker container under host.
-      host_ip = "host.docker.internal"
-      drop_capabilities = ["AUDIT_WRITE", "MKNOD", "NET_ADMIN", "NET_RAW", "SYS_ADMIN", "SYS_MODULE", "SYS_PTRACE", "SYS_TIME", "SYS_TTY_CONFIG"]
-      no_new_privileges = true
-      pids_limit = 512
-      [ingress]
-      mode = "direct"
--- a/document/public/deploy/docker/global/docker-compose.oceanbase.yml
+++ b/document/public/deploy/docker/global/docker-compose.oceanbase.yml
@@ -11,8 +11,6 @@ x-system-key: &x-system-key 'fastgpt-xxx'
 x-plugin-auth-token: &x-plugin-auth-token 'token'
 # code sandbox token
 x-code-sandbox-token: &x-code-sandbox-token 'codesandbox'
-# volume manager auth token
-x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'
 # aiproxy token
 x-aiproxy-token: &x-aiproxy-token 'token'
 # 数据库连接相关配置
@@ -43,7 +41,6 @@ x-log-config: &x-log-config
 x-vec-config: &x-vec-config
  OCEANBASE_URL: mysql://root%40tenantname:tenantpassword@fastgpt-vector:2881/mysql
 services:
  # Vector DB
  fastgpt-vector:
@@ -82,7 +79,6 @@ services:
      timeout: 10s
      retries: 1000
      start_period: 10s
  fastgpt-mongo:
    image: mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -170,14 +166,13 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: ghcr.io/labring/fastgpt:v4.14.20 
+    image: ghcr.io/labring/fastgpt:v4.15.0-beta1
    ports:
      - 3000:3000
    networks:
      - data
      - app
      - codesandbox
-      - opensandbox
      - aiproxy
    depends_on:
      fastgpt-mongo:
@@ -199,7 +194,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -228,20 +223,6 @@ services:
      # AI Proxy 的 Admin Token，与 AI Proxy 中的环境变量 ADMIN_KEY
      AIPROXY_API_TOKEN: *x-aiproxy-token
-      # ==================== Agent sandbox 配置 ====================
-      AGENT_SANDBOX_PROVIDER: opensandbox
-      # OpenSandbox 配置（PROVIDER: opensandbox 时生效）
-      AGENT_SANDBOX_OPENSANDBOX_BASEURL: http://opensandbox-server:8090
-      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
-      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: ghcr.io/labring/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
-      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
-      # Volume 持久化配置（opensandbox provider 下可选）
-      AGENT_SANDBOX_ENABLE_VOLUME: true
-      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
-      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
      LOG_OTEL_SERVICE_NAME: fastgpt-client
@@ -249,7 +230,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.20
+    image: ghcr.io/labring/fastgpt-code-sandbox:v4.15.0-beta1
    networks:
      - codesandbox
    restart: always
@@ -288,17 +269,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.20
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.15.0-beta1
    networks:
      - app
    ports:
@@ -334,79 +315,9 @@ services:
      timeout: 20s
      retries: 3
-  # 沙盒控制器：管理 Docker 容器的创建/执行/停止/删除
-  # runtime=docker 模式需要挂载 Docker socket
-  # 配置 docker.host_ip 为宿主机 LAN IP（容器内访问宿主机服务用）
-  opensandbox-server:
-    image: opensandbox/server:v0.1.9
-    container_name: fastgpt-opensandbox-server
-    restart: always
-    networks:
-      - opensandbox
-    extra_hosts:
-      - 'host.docker.internal:host-gateway'
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    configs:
-      - source: opensandbox-config
-        target: /etc/opensandbox/config.toml
-    environment:
-      SANDBOX_CONFIG_PATH: /etc/opensandbox/config.toml
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'python',
-          '-c',
-          'import urllib.request,sys; sys.exit(0 if urllib.request.urlopen("http://localhost:8090/health",timeout=3).status==200 else 1)'
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
-  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
-  opensandbox-agent-sandbox-image:
-    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1
-    profiles:
-      - prepull
-  opensandbox-execd-image:
-    image: opensandbox/execd:v1.0.7
-    profiles:
-      - prepull
-  opensandbox-egress-image:
-    image: opensandbox/egress:v1.0.3
-    profiles:
-      - prepull
-  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
-  fastgpt-volume-manager:
-    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1
-    container_name: fastgpt-volume-manager
-    restart: always
-    networks:
-      - opensandbox
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    environment:
-      PORT: 3000
-      VM_RUNTIME: docker
-      VM_AUTH_TOKEN: *x-volume-manager-auth-token # 对应 AGENT_SANDBOX_VOLUME_MANAGER_TOKEN
-      VM_VOLUME_NAME_PREFIX: fastgpt-session # volume 名称前缀
-      VM_LOG_LEVEL: info
-      VM_DOCKER_API_VERSION: v1.44
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'bun',
-          '-e',
-          "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
  # AI Proxy
  fastgpt-aiproxy:
-    image: ghcr.io/labring/aiproxy:v0.5.6
+    image: ghcr.io/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -457,8 +368,6 @@ networks:
    name: fastgpt_app
  codesandbox:
    name: fastgpt_codesandbox
-  opensandbox:
-    name: fastgpt_opensandbox
  aiproxy:
    name: fastgpt_aiproxy
@@ -477,33 +386,7 @@ volumes:
  fastgpt-aiproxy_pg:
 configs:
-  opensandbox-config:
-    content: |
-      [server]
-      host = "0.0.0.0"
-      port = 8090
-      log_level = "INFO"
-      [runtime]
-      type = "docker"
-      execd_image = "opensandbox/execd:v1.0.7"
-      [egress]
-      image = "opensandbox/egress:v1.0.3"
-      [docker]
-      network_mode = "fastgpt_opensandbox"
-      # When server runs in a container, set host_ip to the host's IP or hostname so bridge-mode endpoints are reachable (e.g. host.docker.internal or the host LAN IP).
-      # It's required when server deployed with docker container under host.
-      host_ip = "host.docker.internal"
-      drop_capabilities = ["AUDIT_WRITE", "MKNOD", "NET_ADMIN", "NET_RAW", "SYS_ADMIN", "SYS_MODULE", "SYS_PTRACE", "SYS_TIME", "SYS_TTY_CONFIG"]
-      no_new_privileges = true
-      pids_limit = 512
-      [ingress]
-      mode = "direct"
  init_sql:
    name: init_sql
    content: |
      ALTER SYSTEM SET ob_vector_memory_limit_percentage = 30;
--- a/document/public/deploy/docker/global/docker-compose.opengauss.yml
+++ b/document/public/deploy/docker/global/docker-compose.opengauss.yml
@@ -11,8 +11,6 @@ x-system-key: &x-system-key 'fastgpt-xxx'
 x-plugin-auth-token: &x-plugin-auth-token 'token'
 # code sandbox token
 x-code-sandbox-token: &x-code-sandbox-token 'codesandbox'
-# volume manager auth token
-x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'
 # aiproxy token
 x-aiproxy-token: &x-aiproxy-token 'token'
 # 数据库连接相关配置
@@ -152,14 +150,13 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: ghcr.io/labring/fastgpt:v4.14.20 
+    image: ghcr.io/labring/fastgpt:v4.15.0-beta1
    ports:
      - 3000:3000
    networks:
      - data
      - app
      - codesandbox
-      - opensandbox
      - aiproxy
    depends_on:
      fastgpt-mongo:
@@ -181,7 +178,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -210,20 +207,6 @@ services:
      # AI Proxy 的 Admin Token，与 AI Proxy 中的环境变量 ADMIN_KEY
      AIPROXY_API_TOKEN: *x-aiproxy-token
-      # ==================== Agent sandbox 配置 ====================
-      AGENT_SANDBOX_PROVIDER: opensandbox
-      # OpenSandbox 配置（PROVIDER: opensandbox 时生效）
-      AGENT_SANDBOX_OPENSANDBOX_BASEURL: http://opensandbox-server:8090
-      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
-      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: ghcr.io/labring/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
-      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
-      # Volume 持久化配置（opensandbox provider 下可选）
-      AGENT_SANDBOX_ENABLE_VOLUME: true
-      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
-      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
      LOG_OTEL_SERVICE_NAME: fastgpt-client
@@ -231,7 +214,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.20
+    image: ghcr.io/labring/fastgpt-code-sandbox:v4.15.0-beta1
    networks:
      - codesandbox
    restart: always
@@ -270,17 +253,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.20
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.15.0-beta1
    networks:
      - app
    ports:
@@ -316,79 +299,9 @@ services:
      timeout: 20s
      retries: 3
-  # 沙盒控制器：管理 Docker 容器的创建/执行/停止/删除
-  # runtime=docker 模式需要挂载 Docker socket
-  # 配置 docker.host_ip 为宿主机 LAN IP（容器内访问宿主机服务用）
-  opensandbox-server:
-    image: opensandbox/server:v0.1.9
-    container_name: fastgpt-opensandbox-server
-    restart: always
-    networks:
-      - opensandbox
-    extra_hosts:
-      - 'host.docker.internal:host-gateway'
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    configs:
-      - source: opensandbox-config
-        target: /etc/opensandbox/config.toml
-    environment:
-      SANDBOX_CONFIG_PATH: /etc/opensandbox/config.toml
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'python',
-          '-c',
-          'import urllib.request,sys; sys.exit(0 if urllib.request.urlopen("http://localhost:8090/health",timeout=3).status==200 else 1)'
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
-  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
-  opensandbox-agent-sandbox-image:
-    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1
-    profiles:
-      - prepull
-  opensandbox-execd-image:
-    image: opensandbox/execd:v1.0.7
-    profiles:
-      - prepull
-  opensandbox-egress-image:
-    image: opensandbox/egress:v1.0.3
-    profiles:
-      - prepull
-  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
-  fastgpt-volume-manager:
-    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1
-    container_name: fastgpt-volume-manager
-    restart: always
-    networks:
-      - opensandbox
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    environment:
-      PORT: 3000
-      VM_RUNTIME: docker
-      VM_AUTH_TOKEN: *x-volume-manager-auth-token # 对应 AGENT_SANDBOX_VOLUME_MANAGER_TOKEN
-      VM_VOLUME_NAME_PREFIX: fastgpt-session # volume 名称前缀
-      VM_LOG_LEVEL: info
-      VM_DOCKER_API_VERSION: v1.44
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'bun',
-          '-e',
-          "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
  # AI Proxy
  fastgpt-aiproxy:
-    image: ghcr.io/labring/aiproxy:v0.5.6
+    image: ghcr.io/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -439,8 +352,6 @@ networks:
    name: fastgpt_app
  codesandbox:
    name: fastgpt_codesandbox
-  opensandbox:
-    name: fastgpt_opensandbox
  aiproxy:
    name: fastgpt_aiproxy
@@ -457,31 +368,3 @@ volumes:
  fastgpt-seekdb-data:
  fastgpt-seekdb-config:
  fastgpt-aiproxy_pg:
-configs:
-  opensandbox-config:
-    content: |
-      [server]
-      host = "0.0.0.0"
-      port = 8090
-      log_level = "INFO"
-      [runtime]
-      type = "docker"
-      execd_image = "opensandbox/execd:v1.0.7"
-      [egress]
-      image = "opensandbox/egress:v1.0.3"
-      [docker]
-      network_mode = "fastgpt_opensandbox"
-      # When server runs in a container, set host_ip to the host's IP or hostname so bridge-mode endpoints are reachable (e.g. host.docker.internal or the host LAN IP).
-      # It's required when server deployed with docker container under host.
-      host_ip = "host.docker.internal"
-      drop_capabilities = ["AUDIT_WRITE", "MKNOD", "NET_ADMIN", "NET_RAW", "SYS_ADMIN", "SYS_MODULE", "SYS_PTRACE", "SYS_TIME", "SYS_TTY_CONFIG"]
-      no_new_privileges = true
-      pids_limit = 512
-      [ingress]
-      mode = "direct"
--- a/document/public/deploy/docker/global/docker-compose.pg.yml
+++ b/document/public/deploy/docker/global/docker-compose.pg.yml
@@ -11,8 +11,6 @@ x-system-key: &x-system-key 'fastgpt-xxx'
 x-plugin-auth-token: &x-plugin-auth-token 'token'
 # code sandbox token
 x-code-sandbox-token: &x-code-sandbox-token 'codesandbox'
-# volume manager auth token
-x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'
 # aiproxy token
 x-aiproxy-token: &x-aiproxy-token 'token'
 # 数据库连接相关配置
@@ -63,7 +61,6 @@ services:
      interval: 5s
      timeout: 5s
      retries: 10
  fastgpt-mongo:
    image: mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -151,14 +148,13 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: ghcr.io/labring/fastgpt:v4.14.20 
+    image: ghcr.io/labring/fastgpt:v4.15.0-beta1
    ports:
      - 3000:3000
    networks:
      - data
      - app
      - codesandbox
-      - opensandbox
      - aiproxy
    depends_on:
      fastgpt-mongo:
@@ -180,7 +176,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -209,20 +205,6 @@ services:
      # AI Proxy 的 Admin Token，与 AI Proxy 中的环境变量 ADMIN_KEY
      AIPROXY_API_TOKEN: *x-aiproxy-token
-      # ==================== Agent sandbox 配置 ====================
-      AGENT_SANDBOX_PROVIDER: opensandbox
-      # OpenSandbox 配置（PROVIDER: opensandbox 时生效）
-      AGENT_SANDBOX_OPENSANDBOX_BASEURL: http://opensandbox-server:8090
-      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
-      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: ghcr.io/labring/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
-      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
-      # Volume 持久化配置（opensandbox provider 下可选）
-      AGENT_SANDBOX_ENABLE_VOLUME: true
-      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
-      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
      LOG_OTEL_SERVICE_NAME: fastgpt-client
@@ -230,7 +212,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.20
+    image: ghcr.io/labring/fastgpt-code-sandbox:v4.15.0-beta1
    networks:
      - codesandbox
    restart: always
@@ -269,17 +251,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.20
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.15.0-beta1
    networks:
      - app
    ports:
@@ -315,79 +297,9 @@ services:
      timeout: 20s
      retries: 3
-  # 沙盒控制器：管理 Docker 容器的创建/执行/停止/删除
-  # runtime=docker 模式需要挂载 Docker socket
-  # 配置 docker.host_ip 为宿主机 LAN IP（容器内访问宿主机服务用）
-  opensandbox-server:
-    image: opensandbox/server:v0.1.9
-    container_name: fastgpt-opensandbox-server
-    restart: always
-    networks:
-      - opensandbox
-    extra_hosts:
-      - 'host.docker.internal:host-gateway'
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    configs:
-      - source: opensandbox-config
-        target: /etc/opensandbox/config.toml
-    environment:
-      SANDBOX_CONFIG_PATH: /etc/opensandbox/config.toml
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'python',
-          '-c',
-          'import urllib.request,sys; sys.exit(0 if urllib.request.urlopen("http://localhost:8090/health",timeout=3).status==200 else 1)'
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
-  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
-  opensandbox-agent-sandbox-image:
-    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1
-    profiles:
-      - prepull
-  opensandbox-execd-image:
-    image: opensandbox/execd:v1.0.7
-    profiles:
-      - prepull
-  opensandbox-egress-image:
-    image: opensandbox/egress:v1.0.3
-    profiles:
-      - prepull
-  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
-  fastgpt-volume-manager:
-    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1
-    container_name: fastgpt-volume-manager
-    restart: always
-    networks:
-      - opensandbox
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    environment:
-      PORT: 3000
-      VM_RUNTIME: docker
-      VM_AUTH_TOKEN: *x-volume-manager-auth-token # 对应 AGENT_SANDBOX_VOLUME_MANAGER_TOKEN
-      VM_VOLUME_NAME_PREFIX: fastgpt-session # volume 名称前缀
-      VM_LOG_LEVEL: info
-      VM_DOCKER_API_VERSION: v1.44
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'bun',
-          '-e',
-          "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
  # AI Proxy
  fastgpt-aiproxy:
-    image: ghcr.io/labring/aiproxy:v0.5.6
+    image: ghcr.io/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -438,8 +350,6 @@ networks:
    name: fastgpt_app
  codesandbox:
    name: fastgpt_codesandbox
-  opensandbox:
-    name: fastgpt_opensandbox
  aiproxy:
    name: fastgpt_aiproxy
@@ -456,31 +366,3 @@ volumes:
  fastgpt-seekdb-data:
  fastgpt-seekdb-config:
  fastgpt-aiproxy_pg:
-configs:
-  opensandbox-config:
-    content: |
-      [server]
-      host = "0.0.0.0"
-      port = 8090
-      log_level = "INFO"
-      [runtime]
-      type = "docker"
-      execd_image = "opensandbox/execd:v1.0.7"
-      [egress]
-      image = "opensandbox/egress:v1.0.3"
-      [docker]
-      network_mode = "fastgpt_opensandbox"
-      # When server runs in a container, set host_ip to the host's IP or hostname so bridge-mode endpoints are reachable (e.g. host.docker.internal or the host LAN IP).
-      # It's required when server deployed with docker container under host.
-      host_ip = "host.docker.internal"
-      drop_capabilities = ["AUDIT_WRITE", "MKNOD", "NET_ADMIN", "NET_RAW", "SYS_ADMIN", "SYS_MODULE", "SYS_PTRACE", "SYS_TIME", "SYS_TTY_CONFIG"]
-      no_new_privileges = true
-      pids_limit = 512
-      [ingress]
-      mode = "direct"
--- a/document/public/deploy/docker/global/docker-compose.seekdb.yml
+++ b/document/public/deploy/docker/global/docker-compose.seekdb.yml
@@ -11,8 +11,6 @@ x-system-key: &x-system-key 'fastgpt-xxx'
 x-plugin-auth-token: &x-plugin-auth-token 'token'
 # code sandbox token
 x-code-sandbox-token: &x-code-sandbox-token 'codesandbox'
-# volume manager auth token
-x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'
 # aiproxy token
 x-aiproxy-token: &x-aiproxy-token 'token'
 # 数据库连接相关配置
@@ -43,7 +41,6 @@ x-log-config: &x-log-config
 x-vec-config: &x-vec-config
  SEEKDB_URL: mysql://root:seekdbpassword@fastgpt-vector:2881/mysql
 services:
  # Vector DB
  fastgpt-vector:
@@ -69,7 +66,6 @@ services:
      timeout: 10s
      retries: 1000
      start_period: 10s
  fastgpt-mongo:
    image: mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -157,14 +153,13 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: ghcr.io/labring/fastgpt:v4.14.20 
+    image: ghcr.io/labring/fastgpt:v4.15.0-beta1
    ports:
      - 3000:3000
    networks:
      - data
      - app
      - codesandbox
-      - opensandbox
      - aiproxy
    depends_on:
      fastgpt-mongo:
@@ -186,7 +181,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -215,20 +210,6 @@ services:
      # AI Proxy 的 Admin Token，与 AI Proxy 中的环境变量 ADMIN_KEY
      AIPROXY_API_TOKEN: *x-aiproxy-token
-      # ==================== Agent sandbox 配置 ====================
-      AGENT_SANDBOX_PROVIDER: opensandbox
-      # OpenSandbox 配置（PROVIDER: opensandbox 时生效）
-      AGENT_SANDBOX_OPENSANDBOX_BASEURL: http://opensandbox-server:8090
-      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
-      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: ghcr.io/labring/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
-      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
-      # Volume 持久化配置（opensandbox provider 下可选）
-      AGENT_SANDBOX_ENABLE_VOLUME: true
-      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
-      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
      LOG_OTEL_SERVICE_NAME: fastgpt-client
@@ -236,7 +217,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.20
+    image: ghcr.io/labring/fastgpt-code-sandbox:v4.15.0-beta1
    networks:
      - codesandbox
    restart: always
@@ -275,17 +256,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.20
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.15.0-beta1
    networks:
      - app
    ports:
@@ -321,79 +302,9 @@ services:
      timeout: 20s
      retries: 3
-  # 沙盒控制器：管理 Docker 容器的创建/执行/停止/删除
-  # runtime=docker 模式需要挂载 Docker socket
-  # 配置 docker.host_ip 为宿主机 LAN IP（容器内访问宿主机服务用）
-  opensandbox-server:
-    image: opensandbox/server:v0.1.9
-    container_name: fastgpt-opensandbox-server
-    restart: always
-    networks:
-      - opensandbox
-    extra_hosts:
-      - 'host.docker.internal:host-gateway'
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    configs:
-      - source: opensandbox-config
-        target: /etc/opensandbox/config.toml
-    environment:
-      SANDBOX_CONFIG_PATH: /etc/opensandbox/config.toml
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'python',
-          '-c',
-          'import urllib.request,sys; sys.exit(0 if urllib.request.urlopen("http://localhost:8090/health",timeout=3).status==200 else 1)'
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
-  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
-  opensandbox-agent-sandbox-image:
-    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1
-    profiles:
-      - prepull
-  opensandbox-execd-image:
-    image: opensandbox/execd:v1.0.7
-    profiles:
-      - prepull
-  opensandbox-egress-image:
-    image: opensandbox/egress:v1.0.3
-    profiles:
-      - prepull
-  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
-  fastgpt-volume-manager:
-    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1
-    container_name: fastgpt-volume-manager
-    restart: always
-    networks:
-      - opensandbox
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    environment:
-      PORT: 3000
-      VM_RUNTIME: docker
-      VM_AUTH_TOKEN: *x-volume-manager-auth-token # 对应 AGENT_SANDBOX_VOLUME_MANAGER_TOKEN
-      VM_VOLUME_NAME_PREFIX: fastgpt-session # volume 名称前缀
-      VM_LOG_LEVEL: info
-      VM_DOCKER_API_VERSION: v1.44
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'bun',
-          '-e',
-          "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
  # AI Proxy
  fastgpt-aiproxy:
-    image: ghcr.io/labring/aiproxy:v0.5.6
+    image: ghcr.io/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -444,8 +355,6 @@ networks:
    name: fastgpt_app
  codesandbox:
    name: fastgpt_codesandbox
-  opensandbox:
-    name: fastgpt_opensandbox
  aiproxy:
    name: fastgpt_aiproxy
@@ -462,31 +371,3 @@ volumes:
  fastgpt-seekdb-data:
  fastgpt-seekdb-config:
  fastgpt-aiproxy_pg:
-configs:
-  opensandbox-config:
-    content: |
-      [server]
-      host = "0.0.0.0"
-      port = 8090
-      log_level = "INFO"
-      [runtime]
-      type = "docker"
-      execd_image = "opensandbox/execd:v1.0.7"
-      [egress]
-      image = "opensandbox/egress:v1.0.3"
-      [docker]
-      network_mode = "fastgpt_opensandbox"
-      # When server runs in a container, set host_ip to the host's IP or hostname so bridge-mode endpoints are reachable (e.g. host.docker.internal or the host LAN IP).
-      # It's required when server deployed with docker container under host.
-      host_ip = "host.docker.internal"
-      drop_capabilities = ["AUDIT_WRITE", "MKNOD", "NET_ADMIN", "NET_RAW", "SYS_ADMIN", "SYS_MODULE", "SYS_PTRACE", "SYS_TIME", "SYS_TTY_CONFIG"]
-      no_new_privileges = true
-      pids_limit = 512
-      [ingress]
-      mode = "direct"
--- a/document/public/deploy/docker/global/docker-compose.zilliz.yml
+++ b/document/public/deploy/docker/global/docker-compose.zilliz.yml
@@ -11,8 +11,6 @@ x-system-key: &x-system-key 'fastgpt-xxx'
 x-plugin-auth-token: &x-plugin-auth-token 'token'
 # code sandbox token
 x-code-sandbox-token: &x-code-sandbox-token 'codesandbox'
-# volume manager auth token
-x-volume-manager-auth-token: &x-volume-manager-auth-token 'vmtoken'
 # aiproxy token
 x-aiproxy-token: &x-aiproxy-token 'token'
 # 数据库连接相关配置
@@ -134,14 +132,13 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: ghcr.io/labring/fastgpt:v4.14.20 
+    image: ghcr.io/labring/fastgpt:v4.15.0-beta1
    ports:
      - 3000:3000
    networks:
      - data
      - app
      - codesandbox
-      - opensandbox
      - aiproxy
    depends_on:
      fastgpt-mongo:
@@ -163,7 +160,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -192,20 +189,6 @@ services:
      # AI Proxy 的 Admin Token，与 AI Proxy 中的环境变量 ADMIN_KEY
      AIPROXY_API_TOKEN: *x-aiproxy-token
-      # ==================== Agent sandbox 配置 ====================
-      AGENT_SANDBOX_PROVIDER: opensandbox
-      # OpenSandbox 配置（PROVIDER: opensandbox 时生效）
-      AGENT_SANDBOX_OPENSANDBOX_BASEURL: http://opensandbox-server:8090
-      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
-      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: ghcr.io/labring/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
-      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
-      # Volume 持久化配置（opensandbox provider 下可选）
-      AGENT_SANDBOX_ENABLE_VOLUME: true
-      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
-      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
      LOG_OTEL_SERVICE_NAME: fastgpt-client
@@ -213,7 +196,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.20
+    image: ghcr.io/labring/fastgpt-code-sandbox:v4.15.0-beta1
    networks:
      - codesandbox
    restart: always
@@ -252,17 +235,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.20
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.15.0-beta1
    networks:
      - app
    ports:
@@ -298,79 +281,9 @@ services:
      timeout: 20s
      retries: 3
-  # 沙盒控制器：管理 Docker 容器的创建/执行/停止/删除
-  # runtime=docker 模式需要挂载 Docker socket
-  # 配置 docker.host_ip 为宿主机 LAN IP（容器内访问宿主机服务用）
-  opensandbox-server:
-    image: opensandbox/server:v0.1.9
-    container_name: fastgpt-opensandbox-server
-    restart: always
-    networks:
-      - opensandbox
-    extra_hosts:
-      - 'host.docker.internal:host-gateway'
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    configs:
-      - source: opensandbox-config
-        target: /etc/opensandbox/config.toml
-    environment:
-      SANDBOX_CONFIG_PATH: /etc/opensandbox/config.toml
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'python',
-          '-c',
-          'import urllib.request,sys; sys.exit(0 if urllib.request.urlopen("http://localhost:8090/health",timeout=3).status==200 else 1)'
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
-  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
-  opensandbox-agent-sandbox-image:
-    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1
-    profiles:
-      - prepull
-  opensandbox-execd-image:
-    image: opensandbox/execd:v1.0.7
-    profiles:
-      - prepull
-  opensandbox-egress-image:
-    image: opensandbox/egress:v1.0.3
-    profiles:
-      - prepull
-  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
-  fastgpt-volume-manager:
-    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1
-    container_name: fastgpt-volume-manager
-    restart: always
-    networks:
-      - opensandbox
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock # Docker 模式必须挂载，需检查是否与主机的 socket 文件一致
-    environment:
-      PORT: 3000
-      VM_RUNTIME: docker
-      VM_AUTH_TOKEN: *x-volume-manager-auth-token # 对应 AGENT_SANDBOX_VOLUME_MANAGER_TOKEN
-      VM_VOLUME_NAME_PREFIX: fastgpt-session # volume 名称前缀
-      VM_LOG_LEVEL: info
-      VM_DOCKER_API_VERSION: v1.44
-    healthcheck:
-      test:
-        [
-          'CMD',
-          'bun',
-          '-e',
-          "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-        ]
-      interval: 10s
-      timeout: 5s
-      retries: 5
  # AI Proxy
  fastgpt-aiproxy:
-    image: ghcr.io/labring/aiproxy:v0.5.6
+    image: ghcr.io/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -421,8 +334,6 @@ networks:
    name: fastgpt_app
  codesandbox:
    name: fastgpt_codesandbox
-  opensandbox:
-    name: fastgpt_opensandbox
  aiproxy:
    name: fastgpt_aiproxy
@@ -439,31 +350,3 @@ volumes:
  fastgpt-seekdb-data:
  fastgpt-seekdb-config:
  fastgpt-aiproxy_pg:
-configs:
-  opensandbox-config:
-    content: |
-      [server]
-      host = "0.0.0.0"
-      port = 8090
-      log_level = "INFO"
-      [runtime]
-      type = "docker"
-      execd_image = "opensandbox/execd:v1.0.7"
-      [egress]
-      image = "opensandbox/egress:v1.0.3"
-      [docker]
-      network_mode = "fastgpt_opensandbox"
-      # When server runs in a container, set host_ip to the host's IP or hostname so bridge-mode endpoints are reachable (e.g. host.docker.internal or the host LAN IP).
-      # It's required when server deployed with docker container under host.
-      host_ip = "host.docker.internal"
-      drop_capabilities = ["AUDIT_WRITE", "MKNOD", "NET_ADMIN", "NET_RAW", "SYS_ADMIN", "SYS_MODULE", "SYS_PTRACE", "SYS_TIME", "SYS_TTY_CONFIG"]
-      no_new_privileges = true
-      pids_limit = 512
-      [ingress]
-      mode = "direct"
--- a/deploy/docker/cn/docker-compose.milvus.yml
+++ b/deploy/docker/cn/docker-compose.milvus.yml
@@ -43,7 +43,6 @@ x-log-config: &x-log-config
 x-vec-config: &x-vec-config
  MILVUS_ADDRESS: http://fastgpt-vector:19530
  MILVUS_TOKEN: none
 services:
  # Vector DB
@@ -104,7 +103,6 @@ services:
    depends_on:
      - 'fastgpt-milvus-etcd'
      - 'fastgpt-milvus-minio'
  fastgpt-mongo:
    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -192,7 +190,7 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.20 
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.22
    ports:
      - 3000:3000
    networks:
@@ -221,7 +219,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -257,12 +255,13 @@ services:
      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
+      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1.2
      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
      # Volume 持久化配置（opensandbox provider 下可选）
      AGENT_SANDBOX_ENABLE_VOLUME: true
      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
+      AGENT_SANDBOX_VOLUME_MANAGER_MOUNT_PATH: /workspace
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
@@ -271,7 +270,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.22
    networks:
      - codesandbox
    restart: always
@@ -310,17 +309,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.22
    networks:
      - app
    ports:
@@ -387,7 +386,7 @@ services:
      retries: 5
  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
  opensandbox-agent-sandbox-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1.2
    profiles:
      - prepull
  opensandbox-execd-image:
@@ -400,7 +399,7 @@ services:
      - prepull
  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
  fastgpt-volume-manager:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1.2
    container_name: fastgpt-volume-manager
    restart: always
    networks:
@@ -428,7 +427,7 @@ services:
  # AI Proxy
  fastgpt-aiproxy:
-    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.6
+    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -524,4 +523,3 @@ configs:
      [ingress]
      mode = "direct"
--- a/deploy/docker/cn/docker-compose.oceanbase.yml
+++ b/deploy/docker/cn/docker-compose.oceanbase.yml
@@ -43,7 +43,6 @@ x-log-config: &x-log-config
 x-vec-config: &x-vec-config
  OCEANBASE_URL: mysql://root%40tenantname:tenantpassword@fastgpt-vector:2881/mysql
 services:
  # Vector DB
  fastgpt-vector:
@@ -82,7 +81,6 @@ services:
      timeout: 10s
      retries: 1000
      start_period: 10s
  fastgpt-mongo:
    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -170,7 +168,7 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.20 
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.22
    ports:
      - 3000:3000
    networks:
@@ -199,7 +197,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -235,12 +233,13 @@ services:
      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
+      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1.2
      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
      # Volume 持久化配置（opensandbox provider 下可选）
      AGENT_SANDBOX_ENABLE_VOLUME: true
      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
+      AGENT_SANDBOX_VOLUME_MANAGER_MOUNT_PATH: /workspace
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
@@ -249,7 +248,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.22
    networks:
      - codesandbox
    restart: always
@@ -288,17 +287,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.22
    networks:
      - app
    ports:
@@ -365,7 +364,7 @@ services:
      retries: 5
  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
  opensandbox-agent-sandbox-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1.2
    profiles:
      - prepull
  opensandbox-execd-image:
@@ -378,7 +377,7 @@ services:
      - prepull
  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
  fastgpt-volume-manager:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1.2
    container_name: fastgpt-volume-manager
    restart: always
    networks:
@@ -406,7 +405,7 @@ services:
  # AI Proxy
  fastgpt-aiproxy:
-    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.6
+    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -506,4 +505,3 @@ configs:
    name: init_sql
    content: |
      ALTER SYSTEM SET ob_vector_memory_limit_percentage = 30;
--- a/deploy/docker/cn/docker-compose.opengauss.yml
+++ b/deploy/docker/cn/docker-compose.opengauss.yml
@@ -152,7 +152,7 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.20 
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.22
    ports:
      - 3000:3000
    networks:
@@ -181,7 +181,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -217,12 +217,13 @@ services:
      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
+      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1.2
      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
      # Volume 持久化配置（opensandbox provider 下可选）
      AGENT_SANDBOX_ENABLE_VOLUME: true
      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
+      AGENT_SANDBOX_VOLUME_MANAGER_MOUNT_PATH: /workspace
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
@@ -231,7 +232,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.22
    networks:
      - codesandbox
    restart: always
@@ -270,17 +271,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.22
    networks:
      - app
    ports:
@@ -347,7 +348,7 @@ services:
      retries: 5
  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
  opensandbox-agent-sandbox-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1.2
    profiles:
      - prepull
  opensandbox-execd-image:
@@ -360,7 +361,7 @@ services:
      - prepull
  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
  fastgpt-volume-manager:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1.2
    container_name: fastgpt-volume-manager
    restart: always
    networks:
@@ -388,7 +389,7 @@ services:
  # AI Proxy
  fastgpt-aiproxy:
-    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.6
+    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -484,4 +485,3 @@ configs:
      [ingress]
      mode = "direct"
--- a/deploy/docker/cn/docker-compose.pg.yml
+++ b/deploy/docker/cn/docker-compose.pg.yml
@@ -63,7 +63,6 @@ services:
      interval: 5s
      timeout: 5s
      retries: 10
  fastgpt-mongo:
    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -151,7 +150,7 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.20 
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.22
    ports:
      - 3000:3000
    networks:
@@ -180,7 +179,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -216,12 +215,13 @@ services:
      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
+      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1.2
      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
      # Volume 持久化配置（opensandbox provider 下可选）
      AGENT_SANDBOX_ENABLE_VOLUME: true
      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
+      AGENT_SANDBOX_VOLUME_MANAGER_MOUNT_PATH: /workspace
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
@@ -230,7 +230,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.22
    networks:
      - codesandbox
    restart: always
@@ -269,17 +269,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.22
    networks:
      - app
    ports:
@@ -346,7 +346,7 @@ services:
      retries: 5
  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
  opensandbox-agent-sandbox-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1.2
    profiles:
      - prepull
  opensandbox-execd-image:
@@ -359,7 +359,7 @@ services:
      - prepull
  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
  fastgpt-volume-manager:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1.2
    container_name: fastgpt-volume-manager
    restart: always
    networks:
@@ -387,7 +387,7 @@ services:
  # AI Proxy
  fastgpt-aiproxy:
-    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.6
+    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -483,4 +483,3 @@ configs:
      [ingress]
      mode = "direct"
--- a/deploy/docker/cn/docker-compose.seekdb.yml
+++ b/deploy/docker/cn/docker-compose.seekdb.yml
@@ -43,7 +43,6 @@ x-log-config: &x-log-config
 x-vec-config: &x-vec-config
  SEEKDB_URL: mysql://root:seekdbpassword@fastgpt-vector:2881/mysql
 services:
  # Vector DB
  fastgpt-vector:
@@ -69,7 +68,6 @@ services:
      timeout: 10s
      retries: 1000
      start_period: 10s
  fastgpt-mongo:
    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -157,7 +155,7 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.20 
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.22
    ports:
      - 3000:3000
    networks:
@@ -186,7 +184,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -222,12 +220,13 @@ services:
      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
+      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1.2
      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
      # Volume 持久化配置（opensandbox provider 下可选）
      AGENT_SANDBOX_ENABLE_VOLUME: true
      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
+      AGENT_SANDBOX_VOLUME_MANAGER_MOUNT_PATH: /workspace
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
@@ -236,7 +235,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.22
    networks:
      - codesandbox
    restart: always
@@ -275,17 +274,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.22
    networks:
      - app
    ports:
@@ -352,7 +351,7 @@ services:
      retries: 5
  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
  opensandbox-agent-sandbox-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1.2
    profiles:
      - prepull
  opensandbox-execd-image:
@@ -365,7 +364,7 @@ services:
      - prepull
  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
  fastgpt-volume-manager:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1.2
    container_name: fastgpt-volume-manager
    restart: always
    networks:
@@ -393,7 +392,7 @@ services:
  # AI Proxy
  fastgpt-aiproxy:
-    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.6
+    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -489,4 +488,3 @@ configs:
      [ingress]
      mode = "direct"
--- a/deploy/docker/cn/docker-compose.zilliz.yml
+++ b/deploy/docker/cn/docker-compose.zilliz.yml
@@ -134,7 +134,7 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.20 
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.14.22
    ports:
      - 3000:3000
    networks:
@@ -163,7 +163,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -199,12 +199,13 @@ services:
      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
+      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1.2
      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
      # Volume 持久化配置（opensandbox provider 下可选）
      AGENT_SANDBOX_ENABLE_VOLUME: true
      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
+      AGENT_SANDBOX_VOLUME_MANAGER_MOUNT_PATH: /workspace
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
@@ -213,7 +214,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-code-sandbox:v4.14.22
    networks:
      - codesandbox
    restart: always
@@ -252,17 +253,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.20
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-mcp_server:v4.14.22
    networks:
      - app
    ports:
@@ -329,7 +330,7 @@ services:
      retries: 5
  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
  opensandbox-agent-sandbox-image:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-sandbox:v0.1.2
    profiles:
      - prepull
  opensandbox-execd-image:
@@ -342,7 +343,7 @@ services:
      - prepull
  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
  fastgpt-volume-manager:
-    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1
+    image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-agent-volume-manager:v0.1.2
    container_name: fastgpt-volume-manager
    restart: always
    networks:
@@ -370,7 +371,7 @@ services:
  # AI Proxy
  fastgpt-aiproxy:
-    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.6
+    image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -466,4 +467,3 @@ configs:
      [ingress]
      mode = "direct"
--- a/deploy/docker/global/docker-compose.milvus.yml
+++ b/deploy/docker/global/docker-compose.milvus.yml
@@ -43,7 +43,6 @@ x-log-config: &x-log-config
 x-vec-config: &x-vec-config
  MILVUS_ADDRESS: http://fastgpt-vector:19530
  MILVUS_TOKEN: none
 services:
  # Vector DB
@@ -104,7 +103,6 @@ services:
    depends_on:
      - 'fastgpt-milvus-etcd'
      - 'fastgpt-milvus-minio'
  fastgpt-mongo:
    image: mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -192,7 +190,7 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: ghcr.io/labring/fastgpt:v4.14.20 
+    image: ghcr.io/labring/fastgpt:v4.14.22
    ports:
      - 3000:3000
    networks:
@@ -221,7 +219,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -257,12 +255,13 @@ services:
      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: ghcr.io/labring/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
+      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1.2
      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
      # Volume 持久化配置（opensandbox provider 下可选）
      AGENT_SANDBOX_ENABLE_VOLUME: true
      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
+      AGENT_SANDBOX_VOLUME_MANAGER_MOUNT_PATH: /workspace
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
@@ -271,7 +270,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.20
+    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.22
    networks:
      - codesandbox
    restart: always
@@ -310,17 +309,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.20
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.22
    networks:
      - app
    ports:
@@ -387,7 +386,7 @@ services:
      retries: 5
  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
  opensandbox-agent-sandbox-image:
-    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1
+    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1.2
    profiles:
      - prepull
  opensandbox-execd-image:
@@ -400,7 +399,7 @@ services:
      - prepull
  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
  fastgpt-volume-manager:
-    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1
+    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1.2
    container_name: fastgpt-volume-manager
    restart: always
    networks:
@@ -428,7 +427,7 @@ services:
  # AI Proxy
  fastgpt-aiproxy:
-    image: ghcr.io/labring/aiproxy:v0.5.6
+    image: ghcr.io/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -524,4 +523,3 @@ configs:
      [ingress]
      mode = "direct"
--- a/deploy/docker/global/docker-compose.oceanbase.yml
+++ b/deploy/docker/global/docker-compose.oceanbase.yml
@@ -43,7 +43,6 @@ x-log-config: &x-log-config
 x-vec-config: &x-vec-config
  OCEANBASE_URL: mysql://root%40tenantname:tenantpassword@fastgpt-vector:2881/mysql
 services:
  # Vector DB
  fastgpt-vector:
@@ -82,7 +81,6 @@ services:
      timeout: 10s
      retries: 1000
      start_period: 10s
  fastgpt-mongo:
    image: mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -170,7 +168,7 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: ghcr.io/labring/fastgpt:v4.14.20 
+    image: ghcr.io/labring/fastgpt:v4.14.22
    ports:
      - 3000:3000
    networks:
@@ -199,7 +197,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -235,12 +233,13 @@ services:
      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: ghcr.io/labring/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
+      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1.2
      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
      # Volume 持久化配置（opensandbox provider 下可选）
      AGENT_SANDBOX_ENABLE_VOLUME: true
      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
+      AGENT_SANDBOX_VOLUME_MANAGER_MOUNT_PATH: /workspace
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
@@ -249,7 +248,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.20
+    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.22
    networks:
      - codesandbox
    restart: always
@@ -288,17 +287,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.20
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.22
    networks:
      - app
    ports:
@@ -365,7 +364,7 @@ services:
      retries: 5
  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
  opensandbox-agent-sandbox-image:
-    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1
+    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1.2
    profiles:
      - prepull
  opensandbox-execd-image:
@@ -378,7 +377,7 @@ services:
      - prepull
  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
  fastgpt-volume-manager:
-    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1
+    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1.2
    container_name: fastgpt-volume-manager
    restart: always
    networks:
@@ -406,7 +405,7 @@ services:
  # AI Proxy
  fastgpt-aiproxy:
-    image: ghcr.io/labring/aiproxy:v0.5.6
+    image: ghcr.io/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -506,4 +505,3 @@ configs:
    name: init_sql
    content: |
      ALTER SYSTEM SET ob_vector_memory_limit_percentage = 30;
--- a/deploy/docker/global/docker-compose.opengauss.yml
+++ b/deploy/docker/global/docker-compose.opengauss.yml
@@ -152,7 +152,7 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: ghcr.io/labring/fastgpt:v4.14.20 
+    image: ghcr.io/labring/fastgpt:v4.14.22
    ports:
      - 3000:3000
    networks:
@@ -181,7 +181,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -217,12 +217,13 @@ services:
      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: ghcr.io/labring/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
+      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1.2
      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
      # Volume 持久化配置（opensandbox provider 下可选）
      AGENT_SANDBOX_ENABLE_VOLUME: true
      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
+      AGENT_SANDBOX_VOLUME_MANAGER_MOUNT_PATH: /workspace
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
@@ -231,7 +232,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.20
+    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.22
    networks:
      - codesandbox
    restart: always
@@ -270,17 +271,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.20
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.22
    networks:
      - app
    ports:
@@ -347,7 +348,7 @@ services:
      retries: 5
  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
  opensandbox-agent-sandbox-image:
-    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1
+    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1.2
    profiles:
      - prepull
  opensandbox-execd-image:
@@ -360,7 +361,7 @@ services:
      - prepull
  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
  fastgpt-volume-manager:
-    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1
+    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1.2
    container_name: fastgpt-volume-manager
    restart: always
    networks:
@@ -388,7 +389,7 @@ services:
  # AI Proxy
  fastgpt-aiproxy:
-    image: ghcr.io/labring/aiproxy:v0.5.6
+    image: ghcr.io/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -484,4 +485,3 @@ configs:
      [ingress]
      mode = "direct"
--- a/deploy/docker/global/docker-compose.pg.yml
+++ b/deploy/docker/global/docker-compose.pg.yml
@@ -63,7 +63,6 @@ services:
      interval: 5s
      timeout: 5s
      retries: 10
  fastgpt-mongo:
    image: mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -151,7 +150,7 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: ghcr.io/labring/fastgpt:v4.14.20 
+    image: ghcr.io/labring/fastgpt:v4.14.22
    ports:
      - 3000:3000
    networks:
@@ -180,7 +179,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -216,12 +215,13 @@ services:
      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: ghcr.io/labring/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
+      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1.2
      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
      # Volume 持久化配置（opensandbox provider 下可选）
      AGENT_SANDBOX_ENABLE_VOLUME: true
      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
+      AGENT_SANDBOX_VOLUME_MANAGER_MOUNT_PATH: /workspace
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
@@ -230,7 +230,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.20
+    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.22
    networks:
      - codesandbox
    restart: always
@@ -269,17 +269,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.20
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.22
    networks:
      - app
    ports:
@@ -346,7 +346,7 @@ services:
      retries: 5
  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
  opensandbox-agent-sandbox-image:
-    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1
+    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1.2
    profiles:
      - prepull
  opensandbox-execd-image:
@@ -359,7 +359,7 @@ services:
      - prepull
  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
  fastgpt-volume-manager:
-    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1
+    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1.2
    container_name: fastgpt-volume-manager
    restart: always
    networks:
@@ -387,7 +387,7 @@ services:
  # AI Proxy
  fastgpt-aiproxy:
-    image: ghcr.io/labring/aiproxy:v0.5.6
+    image: ghcr.io/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -483,4 +483,3 @@ configs:
      [ingress]
      mode = "direct"
--- a/deploy/docker/global/docker-compose.seekdb.yml
+++ b/deploy/docker/global/docker-compose.seekdb.yml
@@ -43,7 +43,6 @@ x-log-config: &x-log-config
 x-vec-config: &x-vec-config
  SEEKDB_URL: mysql://root:seekdbpassword@fastgpt-vector:2881/mysql
 services:
  # Vector DB
  fastgpt-vector:
@@ -69,7 +68,6 @@ services:
      timeout: 10s
      retries: 1000
      start_period: 10s
  fastgpt-mongo:
    image: mongo:5.0.32 # cpu 不支持 AVX 时候使用 4.4.29
    container_name: fastgpt-mongo
@@ -157,7 +155,7 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: ghcr.io/labring/fastgpt:v4.14.20 
+    image: ghcr.io/labring/fastgpt:v4.14.22
    ports:
      - 3000:3000
    networks:
@@ -186,7 +184,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -222,12 +220,13 @@ services:
      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: ghcr.io/labring/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
+      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1.2
      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
      # Volume 持久化配置（opensandbox provider 下可选）
      AGENT_SANDBOX_ENABLE_VOLUME: true
      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
+      AGENT_SANDBOX_VOLUME_MANAGER_MOUNT_PATH: /workspace
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
@@ -236,7 +235,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.20
+    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.22
    networks:
      - codesandbox
    restart: always
@@ -275,17 +274,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.20
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.22
    networks:
      - app
    ports:
@@ -352,7 +351,7 @@ services:
      retries: 5
  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
  opensandbox-agent-sandbox-image:
-    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1
+    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1.2
    profiles:
      - prepull
  opensandbox-execd-image:
@@ -365,7 +364,7 @@ services:
      - prepull
  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
  fastgpt-volume-manager:
-    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1
+    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1.2
    container_name: fastgpt-volume-manager
    restart: always
    networks:
@@ -393,7 +392,7 @@ services:
  # AI Proxy
  fastgpt-aiproxy:
-    image: ghcr.io/labring/aiproxy:v0.5.6
+    image: ghcr.io/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -489,4 +488,3 @@ configs:
      [ingress]
      mode = "direct"
--- a/deploy/docker/global/docker-compose.zilliz.yml
+++ b/deploy/docker/global/docker-compose.zilliz.yml
@@ -134,7 +134,7 @@ services:
  fastgpt-app:
    container_name: fastgpt-app
-    image: ghcr.io/labring/fastgpt:v4.14.20 
+    image: ghcr.io/labring/fastgpt:v4.14.22
    ports:
      - 3000:3000
    networks:
@@ -163,7 +163,7 @@ services:
      HOSTNAME: 0.0.0.0
      # ==================== 基础配置 ====================
      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
-      FE_DOMAIN: 
+      FE_DOMAIN:
      # root key（最高权限）
      ROOT_KEY: *x-system-key
      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
@@ -199,12 +199,13 @@ services:
      AGENT_SANDBOX_OPENSANDBOX_API_KEY:
      AGENT_SANDBOX_OPENSANDBOX_RUNTIME: docker
      AGENT_SANDBOX_OPENSANDBOX_IMAGE_REPO: ghcr.io/labring/fastgpt-agent-sandbox
-      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1
+      AGENT_SANDBOX_OPENSANDBOX_IMAGE_TAG: v0.1.2
      AGENT_SANDBOX_OPENSANDBOX_USE_SERVER_PROXY: true
      # Volume 持久化配置（opensandbox provider 下可选）
      AGENT_SANDBOX_ENABLE_VOLUME: true
      AGENT_SANDBOX_VOLUME_MANAGER_URL: http://fastgpt-volume-manager:3000
      AGENT_SANDBOX_VOLUME_MANAGER_TOKEN: *x-volume-manager-auth-token
+      AGENT_SANDBOX_VOLUME_MANAGER_MOUNT_PATH: /workspace
      # ==================== 日志与监控 ====================
      # 传递给 OTLP 收集器的服务名称
@@ -213,7 +214,7 @@ services:
      - ./config.json:/app/data/config.json
  fastgpt-code-sandbox:
    container_name: fastgpt-code-sandbox
-    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.20
+    image: ghcr.io/labring/fastgpt-code-sandbox:v4.14.22
    networks:
      - codesandbox
    restart: always
@@ -252,17 +253,17 @@ services:
      SANDBOX_PYTHON_ALLOWED_MODULES: math,cmath,decimal,fractions,random,statistics,collections,array,heapq,bisect,queue,copy,itertools,functools,operator,string,re,difflib,textwrap,unicodedata,codecs,datetime,time,calendar,_strptime,json,csv,base64,binascii,struct,hashlib,hmac,secrets,uuid,typing,abc,enum,dataclasses,contextlib,pprint,weakref,numpy,pandas,matplotlib
    healthcheck:
      test: [
-        'CMD',                                                                                                                                                        
+        'CMD',
-        'bun',                                                               
+        'bun',
        '-e',
        "fetch('http://localhost:3000/health').then((res) => { if (!res.ok) throw new Error(String(res.status)); })"
-      ]     
+      ]
      interval: 30s
      timeout: 20s
      retries: 3
  fastgpt-mcp-server:
    container_name: fastgpt-mcp-server
-    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.20
+    image: ghcr.io/labring/fastgpt-mcp_server:v4.14.22
    networks:
      - app
    ports:
@@ -329,7 +330,7 @@ services:
      retries: 5
  # Pre-pull only: not started by `docker compose up` (uses profile `prepull`).
  opensandbox-agent-sandbox-image:
-    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1
+    image: ghcr.io/labring/fastgpt-agent-sandbox:v0.1.2
    profiles:
      - prepull
  opensandbox-execd-image:
@@ -342,7 +343,7 @@ services:
      - prepull
  # 卷管理微服务：负责幂等创建/删除 Docker named volume 或 k8s PVC
  fastgpt-volume-manager:
-    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1
+    image: ghcr.io/labring/fastgpt-agent-volume-manager:v0.1.2
    container_name: fastgpt-volume-manager
    restart: always
    networks:
@@ -370,7 +371,7 @@ services:
  # AI Proxy
  fastgpt-aiproxy:
-    image: ghcr.io/labring/aiproxy:v0.5.6
+    image: ghcr.io/labring/aiproxy:v0.5.8
    container_name: fastgpt-aiproxy
    restart: unless-stopped
    depends_on:
@@ -466,4 +467,3 @@ configs:
      [ingress]
      mode = "direct"
--- a/document/public/deploy/install.sh
+++ b/document/public/deploy/install.sh
@@ -57,14 +57,70 @@ radio_select() {
 # 确保退出时恢复光标
 trap 'tput cnorm 2>/dev/null; exit' INT TERM
+# ========== 部署版本列表（由 deploy/init.mjs 自动生成） ==========
+# BEGIN GENERATED DEPLOY VERSIONS
+DEPLOY_VERSIONS=(
+    "v4.14"
+    "main"
+)
+# END GENERATED DEPLOY VERSIONS
+# 获取部署版本展示文案：main 为迭代版，其他版本均视为稳定版
+get_version_label() {
+    local version="$1"
+    if [ "$version" == "main" ]; then
+        echo "迭代版 main"
+    else
+        echo "稳定版 $version"
+    fi
+}
 # ========== 1. 选择镜像源 ==========
 radio_select "请选择镜像源 (↑↓ 选择, 回车确认):" "阿里云 (中国大陆)" "GitHub (全球)"
 case $RADIO_RESULT in
-    1) REGION="global" ;;
+    1)
-    *) REGION="cn" ;;
+        REGION="global"
+        BASE_URL="https://doc.fastgpt.io/deploy"
+        ;;
+    *)
+        REGION="cn"
+        BASE_URL="https://doc.fastgpt.cn/deploy"
+        ;;
 esac
-# ========== 2. 选择向量数据库 ==========
+# ========== 2. 选择部署版本 ==========
+if [ ${#DEPLOY_VERSIONS[@]} -eq 0 ]; then
+    echo "错误: 未配置部署版本"
+    exit 1
+fi
+if [ -n "$FASTGPT_DEPLOY_VERSION" ]; then
+    version_matched=false
+    for version in "${DEPLOY_VERSIONS[@]}"; do
+        if [ "$FASTGPT_DEPLOY_VERSION" == "$version" ]; then
+            version_matched=true
+            break
+        fi
+    done
+    if [ "$version_matched" = true ]; then
+        DEPLOY_VERSION="$FASTGPT_DEPLOY_VERSION"
+    else
+        echo "错误: 不支持的 FASTGPT_DEPLOY_VERSION: $FASTGPT_DEPLOY_VERSION"
+        echo "可选版本: ${DEPLOY_VERSIONS[*]}"
+        exit 1
+    fi
+else
+    VERSION_OPTIONS=()
+    for version in "${DEPLOY_VERSIONS[@]}"; do
+        VERSION_OPTIONS+=("$(get_version_label "$version")")
+    done
+    radio_select "请选择部署版本 (↑↓ 选择, 回车确认):" "${VERSION_OPTIONS[@]}"
+    DEPLOY_VERSION="${DEPLOY_VERSIONS[$RADIO_RESULT]}"
+fi
+# ========== 3. 选择向量数据库 ==========
 radio_select "请选择向量数据库 (↑↓ 选择, 回车确认):" "PostgreSQL + pgvector" "Milvus" "Zilliz" "OceanBase" "SeekDB"
 case $RADIO_RESULT in
    1) VECTOR="milvus" ;;
@@ -74,7 +130,7 @@ case $RADIO_RESULT in
    *) VECTOR="pg" ;;
 esac
-# ========== 3. 检测可用 IP ==========
+# ========== 4. 检测可用 IP ==========
 IP_LIST=()
 PRIMARY_IP=""
@@ -152,17 +208,19 @@ select_address() {
    fi
 }
-# ========== 4. 选择 S3 访问地址 (端口 9000) ==========
+# ========== 5. 选择 S3 访问地址 (端口 9000) ==========
 select_address "请选择 S3 访问地址 - 客户端和容器均需可访问 (↑↓ 选择, 回车确认, 通常默认第一个即可):" 9000
 S3_ADDR="$SELECTED_ADDR"
 S3_CUSTOM=$SELECTED_CUSTOM
-# ========== 5. 选择 SSE MCP 访问地址 (端口 3003) ==========
+# ========== 6. 选择 SSE MCP 访问地址 (端口 3003) ==========
 select_address "请选择 SSE MCP 访问地址 - 客户端和容器均需可访问 (↑↓ 选择, 回车确认, 通常默认第一个即可):" 3003
 MCP_ADDR="$SELECTED_ADDR"
 MCP_CUSTOM=$SELECTED_CUSTOM
 # ========== 确认配置 ==========
+DEPLOY_VERSION_LABEL="$(get_version_label "$DEPLOY_VERSION")"
 REGION_LABEL="阿里云 (中国大陆)"
 if [ "$REGION" == "global" ]; then
    REGION_LABEL="GitHub (全球)"
@@ -191,6 +249,7 @@ fi
 echo ""
 echo "=============================="
+echo "  部署版本:     $DEPLOY_VERSION_LABEL"
 echo "  镜像源:       $REGION_LABEL"
 echo "  向量数据库:   $VECTOR"
 echo "  S3 地址:      $S3_DISPLAY"
@@ -213,13 +272,7 @@ if [ "$REGION" == "global" ] && [ "$VECTOR" == "zilliz" ]; then
    VECTOR_FILE="zilliz"
 fi
-if [ "$REGION" == "cn" ]; then
+YML_URL="${BASE_URL}/docker/${DEPLOY_VERSION}/${REGION}/docker-compose.${VECTOR_FILE}.yml"
-    BASE_URL="https://doc.fastgpt.cn/deploy"
-    YML_URL="${BASE_URL}/docker/cn/docker-compose.${VECTOR_FILE}.yml"
-else
-    BASE_URL="https://doc.fastgpt.io/deploy"
-    YML_URL="${BASE_URL}/docker/global/docker-compose.${VECTOR_FILE}.yml"
-fi
 CONFIG_URL="${BASE_URL}/config/config.json"
@@ -316,69 +369,79 @@ else
    echo "警告: 未设置 MCP 地址，请手动编辑 config.json 中的 mcpServerProxyEndpoint"
 fi
-# ========== 检测并替换 docker.sock 路径 ==========
+if [ "$DEPLOY_VERSION" != "main" ]; then
-# 某些发行版 / Docker Desktop / rootless 模式下，宿主机 docker.sock 不在 /var/run/docker.sock
+    # ========== 检测并替换 docker.sock 路径 ==========
-# 若路径错误，Docker 会把挂载目标在容器内创建为空目录，导致 volume-manager / opensandbox 无法调用 Docker API
+    # 某些发行版 / Docker Desktop / rootless 模式下，宿主机 docker.sock 不在 /var/run/docker.sock
-detect_docker_sock() {
+    # 若路径错误，Docker 会把挂载目标在容器内创建为空目录，导致 volume-manager / opensandbox 无法调用 Docker API
-    # 1. DOCKER_HOST 环境变量
+    detect_docker_sock() {
-    if [ -n "$DOCKER_HOST" ] && [[ "$DOCKER_HOST" == unix://* ]]; then
+        # 1. DOCKER_HOST 环境变量
-        local sock="${DOCKER_HOST#unix://}"
+        if [ -n "$DOCKER_HOST" ] && [[ "$DOCKER_HOST" == unix://* ]]; then
-        [ -S "$sock" ] && { echo "$sock"; return 0; }
+            local sock="${DOCKER_HOST#unix://}"
-    fi
+            [ -S "$sock" ] && { echo "$sock"; return 0; }
+        fi
-    # 2. docker context 当前上下文
+        # 2. docker context 当前上下文
-    if command -v docker &>/dev/null; then
+        if command -v docker &>/dev/null; then
-        local ctx
+            local ctx
-        ctx=$(docker context inspect --format '{{ .Endpoints.docker.Host }}' 2>/dev/null)
+            ctx=$(docker context inspect --format '{{ .Endpoints.docker.Host }}' 2>/dev/null)
-        if [[ "$ctx" == unix://* ]]; then
+            if [[ "$ctx" == unix://* ]]; then
-            ctx="${ctx#unix://}"
+                ctx="${ctx#unix://}"
-            [ -S "$ctx" ] && { echo "$ctx"; return 0; }
+                [ -S "$ctx" ] && { echo "$ctx"; return 0; }
+            fi
        fi
-    fi
-    # 3. 常见路径依次探测
+        # 3. 常见路径依次探测
-    local candidates=(
+        local candidates=(
-        "/var/run/docker.sock"
+            "/var/run/docker.sock"
-        "/run/docker.sock"
+            "/run/docker.sock"
-        "$HOME/.docker/run/docker.sock"         # macOS Docker Desktop
+            "$HOME/.docker/run/docker.sock"         # macOS Docker Desktop
-        "$HOME/.docker/desktop/docker.sock"
+            "$HOME/.docker/desktop/docker.sock"
-        "/run/user/$(id -u 2>/dev/null)/docker.sock"  # rootless
+            "/run/user/$(id -u 2>/dev/null)/docker.sock"  # rootless
-    )
+        )
-    for p in "${candidates[@]}"; do
+        for p in "${candidates[@]}"; do
-        [ -S "$p" ] && { echo "$p"; return 0; }
+            [ -S "$p" ] && { echo "$p"; return 0; }
-    done
+        done
-    return 1
+        return 1
-}
+    }
-HOST_SOCK=$(detect_docker_sock)
+    HOST_SOCK=$(detect_docker_sock)
-if [ -n "$HOST_SOCK" ]; then
+    if [ -n "$HOST_SOCK" ]; then
-    if [ "$HOST_SOCK" != "/var/run/docker.sock" ]; then
+        if [ "$HOST_SOCK" != "/var/run/docker.sock" ]; then
-        # 只改宿主侧路径（冒号左边），容器内仍为 /var/run/docker.sock
+            # 只改宿主侧路径（冒号左边），容器内仍为 /var/run/docker.sock
-        ESCAPED_SOCK=$(printf '%s' "$HOST_SOCK" | sed -e 's/[\/&|]/\\&/g')
+            ESCAPED_SOCK=$(printf '%s' "$HOST_SOCK" | sed -e 's/[\/&|]/\\&/g')
-        if [[ "$OSTYPE" == "darwin"* ]]; then
+            if [[ "$OSTYPE" == "darwin"* ]]; then
-            sed -i '' "s|- /var/run/docker.sock:/var/run/docker.sock|- ${ESCAPED_SOCK}:/var/run/docker.sock|g" docker-compose.yml
+                sed -i '' "s|- /var/run/docker.sock:/var/run/docker.sock|- ${ESCAPED_SOCK}:/var/run/docker.sock|g" docker-compose.yml
+            else
+                sed -i "s|- /var/run/docker.sock:/var/run/docker.sock|- ${ESCAPED_SOCK}:/var/run/docker.sock|g" docker-compose.yml
+            fi
+            echo "已检测到 Docker socket: $HOST_SOCK，已更新 docker-compose.yml 挂载路径"
        else
-            sed -i "s|- /var/run/docker.sock:/var/run/docker.sock|- ${ESCAPED_SOCK}:/var/run/docker.sock|g" docker-compose.yml
+            echo "Docker socket 路径正常: /var/run/docker.sock"
        fi
-        echo "已检测到 Docker socket: $HOST_SOCK，已更新 docker-compose.yml 挂载路径"
    else
-        echo "Docker socket 路径正常: /var/run/docker.sock"
+        echo "警告: 未检测到 Docker socket。请确认 Docker 正在运行，"
+        echo "      并手动编辑 docker-compose.yml，将两处 '- /var/run/docker.sock:/var/run/docker.sock'"
+        echo "      左侧改成宿主机实际的 socket 路径。"
    fi
-else
-    echo "警告: 未检测到 Docker socket。请确认 Docker 正在运行，"
-    echo "      并手动编辑 docker-compose.yml，将两处 '- /var/run/docker.sock:/var/run/docker.sock'"
-    echo "      左侧改成宿主机实际的 socket 路径。"
 fi
 # ========== 完成 ==========
 echo ""
 echo "配置下载成功! 后续操作:"
-echo "  1. 预热沙盒:   docker compose --profile prepull pull opensandbox-agent-sandbox-image opensandbox-execd-image opensandbox-egress-image"
+if [ "$DEPLOY_VERSION" != "main" ]; then
-echo "  2. 启动服务:   docker compose up -d"
+    echo "  1. 预热沙盒:   docker compose --profile prepull pull opensandbox-agent-sandbox-image opensandbox-execd-image opensandbox-egress-image"
-echo "  3. 开放端口:   3000, 9000, 3003"
+    echo "  2. 启动服务:   docker compose up -d"
-echo "  4. 访问服务:   http://localhost:3000"
+    echo "  3. 开放端口:   3000, 9000, 3003"
-echo "  5. 登录服务:   默认账号为 'root', 密码为: '1234'"
+    echo "  4. 访问服务:   http://localhost:3000"
-echo "  6. 配置模型:   在 '账号-模型提供商' 页面，进行模型配置"
+    echo "  5. 登录服务:   默认账号为 'root', 密码为: '1234'"
+    echo "  6. 配置模型:   在 '账号-模型提供商' 页面，进行模型配置"
+else
+    echo "  1. 启动服务:   docker compose up -d"
+    echo "  2. 开放端口:   3000, 9000, 3003"
+    echo "  3. 访问服务:   http://localhost:3000"
+    echo "  4. 登录服务:   默认账号为 'root', 密码为: '1234'"
+    echo "  5. 配置模型:   在 '账号-模型提供商' 页面，进行模型配置"
+fi
 echo ""
 echo "详细文档: https://doc.fastgpt.cn/self-host/deploy/docker"