Gemini Code Assist 是 Google Cloud中依托 AI 技术的协作工具。如果您在创建工作站配置时选择了 Cloud Workstations Base Editor (Code OSS for Cloud Workstations)(基本编辑器 [Code OSS for Cloud Workstations]),Gemini 可以在基本编辑器中帮助您执行以下操作:
[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-08-11。"],[],[],null,["# Cloud Workstations overview\n\nCloud Workstations provides managed development environments on Google Cloud\nwith built-in security and preconfigured yet customizable development\nenvironments. Instead of requiring your developers to install software and run\nsetup scripts, you can create a workstation configuration that specifies your\nenvironment in a reproducible way. Any updates to a workstation configuration\nautomatically apply to workstations the next time they start. Developers access\nthe workstations through a browser-based IDE, from multiple local code editors\n(such as VSCode or JetBrains IDEs such as IntelliJ IDEA Ultimate and PyCharm\nProfessional), or through SSH.\n\nCloud Workstations uses the following Google Cloud resources to manage your\ndevelopment environments:\n\n- **Workstation clusters** define a group of workstations in a particular\n region and the VPC network they're attached to.\n Workstation clusters aren't related to\n [Google Kubernetes Engine (GKE)](/kubernetes-engine/docs/concepts/kubernetes-engine-overview)\n clusters.\n\n- **Workstation configurations** act as templates for workstations. The\n workstation configuration defines details such as the workstation virtual\n machine (VM) instance type, persistent storage, container image defining\n environment, which IDE or Code Editor to use, and more. Administrators and\n platform teams can also use\n [Identity and Access Management (IAM)](/iam/docs/overview)\n rules to grant access to teams or to individual developers.\n\n- **Workstations** are preconfigured development environments that provide a\n cloud IDE, language tooling, libraries, and more. Workstations can be\n started or stopped on demand, and run on\n [Compute Engine](/compute/docs/instances)\n VMs in your project, with a persistent disk attached to store data\n between sessions.\n\nAdministrators and platform teams create *workstation configurations* that they\nshare with their development team. Each developer creates a *workstation* based\non a workstation configuration.\n\n\nFigure 1. Cloud Workstations Concepts\n\n\u003cbr /\u003e\n\nWorkstation lifecycle\n---------------------\n\nWorkstations run on ephemeral Compute Engine VMs, and can be started or\nstopped on demand to improve cost savings. Additionally, administrators and\nplatform teams can configure an *idle timeout* or *running timeout* in the\n[workstation configuration](/workstations/docs/customize-development-environment#resource:-workstationconfig)\nto help make sure that workstations shut down when they are no longer used,\nwhich reduces costs. It also helps make sure that all workstations synchronize with\nthe latest changes applied to their workstation configuration when each\nworkstation restarts.\n\nPersistent storage\n------------------\n\nWhen a workstation stops, its ephemeral VM is deleted along with all workstation\nruntime data. Administrators and platform teams can optionally configure a\npersistent home directory on a workstation configuration, so all data saved to\nthe home directory persists between sessions. This persistent storage is\nimplemented as a\n[persistent disk](/persistent-disk) that\nis attached to the workstation VM when the session starts, and detached when the\nsession ends.\n\nWorkstation DNS hostnames\n-------------------------\n\nEvery workstation is given its own unique hostname. All workstations in a\nworkstation cluster share a common, cluster-specific domain name, and the\nworkstation cluster takes care of routing requests for this hostname to the\nrunning workstation. The workstation hostname can be used to connect to the\nworkstation through your browser.\n\nConfiguration updates\n---------------------\n\nUpdates to a workstation configuration automatically apply to workstations\nwhen each workstation restarts after the configuration update.\nFor example, changing the machine type in a workstation configuration changes\nthe machine type of the VMs used by the associated workstations the next time\neach workstation restarts. Administrators and platform teams can configure an\n*idle timeout* or *running timeout* in the\n[workstation configuration](/workstations/docs/customize-development-environment#resource:-workstationconfig)\nto help make sure that workstations synchronize with configuration updates\nwithin a bounded period of time.\n\nGemini Code Assist\n------------------\n\n[Gemini Code Assist](/gemini/docs/overview) is an AI-powered\ncollaborator in Google Cloud. If you select the Cloud Workstations **Base Editor (Code OSS for Cloud Workstations)**\nwhen you\n[create your workstation configuration](/workstations/docs/create-configuration#customize_environment),\nGemini can help you with the following in the base editor:\n\n- Provide guidance to help you solve problems with your code.\n\n- Generate code for your project.\n\n- Receive inline suggestions while you're coding.\n\nGemini provides source citations when suggestions directly\nquote at length from a source to help you comply with any license requirements.\nFor more information about using Gemini with Cloud Workstations, see\n[Code with Gemini Code Assist assistance](/workstations/docs/write-code-gemini).\n\nLearn [how and when Gemini\nfor Google Cloud uses your data](/gemini/docs/discover/data-governance).\n\nSoftware supply chain security\n------------------------------\n\nCloud Workstations is one of the Google Cloud components you\ncan use to protect your software supply chain. You can use\nCloud Workstations together with other Google Cloud products and\nfeatures to improve the security posture of developer workflows and tools,\nsoftware dependencies, CI/CD systems used to build and deploy your software,\nand runtime environments such as Google Kubernetes Engine and Cloud Run. To learn\nmore, see\n[Software supply chain security](/software-supply-chain-security/docs/overview)."]]