Follow Discord
Sweep 22 Oct 2026 · 21:04Z Build v2.1.309 528 read Stable v2.1.308 Latest v2.1.309 Next v2.1.309 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsSearch
Search the documentation

305 pages for sandbox.

Titles and paths first, then pages whose text carries it. Each row opens that page as this site last read it.

List Session Thread Events Claude Developer Platform · in the page api/beta/sessions/threads/events/list …olset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `type: "user.tool_result"` - `id: string`… Stream Session Thread Events Claude Developer Platform · in the page api/beta/sessions/threads/events/stream …olset tool execution. Only valid on `self_hosted` environments, where sandbox-routed tools are executed by the client rather than the server. - `type: "user.tool_result"` - `id: string`… claude-models-on-google-cloud-anthropic-managed-iam-permissions Claude Developer Platform · in the page api/claude-models-on-google-cloud-anthropic-managed-iam-permissions …and `roles/claude.admin` include every permission that a [self-hosted sandbox](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes) worker needs. `environments.processWork` author… claude-platform-on-aws-iam-actions Claude Developer Platform · in the page api/claude-platform-on-aws-iam-actions …</Note> <Note> `ProcessEnvironmentWork` authorizes a [self-hosted sandbox](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes) worker to poll for, acknowledge, heartbeat, sto… spans Claude Developer Platform · in the page api/opentelemetry/spans …gents. The API runs the agent toolset tools, except in a [self-hosted sandbox](https://platform.claude.com/docs/en/manage-claude/opentelemetry/sdk#trace-a-self-hosted-sandbox), where the environment w… overview Claude Developer Platform · in the page api/overview …aged-agents/sessions):** Run stateful agent sessions in managed cloud sandboxes (`POST /v1/sessions`, `GET /v1/sessions/{id}/events/stream`) * **[Environments API](https://platform.claude.com/docs/en/… anthropic-managed Claude Developer Platform · in the page build-with-claude/claude-models-on-google-cloud/anthropic-managed …aude.com/docs/en/managed-agents/scheduled-deployments) * [Self-hosted sandboxes](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes) Access is checked when a session or a deploy… claude-platform-on-aws Claude Developer Platform · in the page build-with-claude/claude-platform-on-aws …out of the box. * **Code execution:** Run code in Anthropic's managed sandbox using the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool). * **To… files Claude Developer Platform · in the page build-with-claude/files …ools/tool-use/code-execution-tool"> Run Python and Bash code in a sandboxed container to analyze data, generate files, and iterate on solutions. </Card> <Card title="Vision" icon="image" href… mid-conversation-effort-example Claude Developer Platform · in the page build-with-claude/mid-conversation-effort-example …mall throwaway fixture directory that is removed on exit. There is no sandbox here: the command runs with the permissions of the process that launched the example. For clarity this example runs each c… overview Claude Developer Platform · in the page build-with-claude/overview …ocs/en/agents-and-tools/tool-use/code-execution-tool) | Run code in a sandboxed environment for advanced data analysis, calculations, and file processing. Free when used with web search or web fetch.… skills-guide Claude Developer Platform · in the page build-with-claude/skills-guide …ools/tool-use/code-execution-tool"> Run Python and Bash code in a sandboxed container to analyze data, generate files, and iterate on solutions. </Card> </CardGroup> api-and-data-retention Claude Developer Platform · in the page manage-claude/api-and-data-retention …m. Applies to all Managed Agents sub-features, including [Self-hosted sandboxes](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes).… compliance-faq Claude Developer Platform · in the page manage-claude/compliance-faq …ncremental-reads). </Accordion> <Accordion title="How do I get a sandbox to test the Compliance API?"> To test only the [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compl… data-residency Claude Developer Platform · in the page manage-claude/data-residency …spects the Workspace geo configured in Console, and with [self-hosted sandboxes](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes), tool execution and the sandbox filesystem st… opentelemetry Claude Developer Platform · in the page manage-claude/opentelemetry …| | Tools in a [self-hosted sandbox](https://platform.claude.com/docs/en/manage-claude/opentelemetry/sdk#trace-a-self-hosted-sandbox) | ✅… sdk Claude Developer Platform · in the page manage-claude/opentelemetry/sdk …the call and the read loop. ## Tracing a Managed Agents self-hosted sandbox In a Managed Agents [self-hosted sandbox](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes), your… budgets Claude Developer Platform · in the page managed-agents/budgets …ason`) of `budget_reached`; it is not terminated, and its history and sandbox are preserved like any other idle session's. On the [event stream](https://platform.claude.com/docs/en/managed-agents/even… choosing-an-environment Claude Developer Platform · in the page managed-agents/choosing-an-environment …d code run in an Anthropic-managed cloud environment or a self-hosted sandbox, and see what changes if you switch. featureMetadata: topic: title: Managed Agents url: https://platform.claude.… DCF Model Rubric Claude Developer Platform · in the page managed-agents/define-outcomes …The agent writes output files to `/mnt/session/outputs/` inside the sandbox. To retrieve them, list files through the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) with th… environments Claude Developer Platform · in the page managed-agents/environments ….com/docs/en/managed-agents/environments description: Customize cloud sandboxes for your sessions. featureMetadata: topic: title: Managed Agents url: https://platform.claude.com/docs/en/mana… events-and-streaming Claude Developer Platform · in the page managed-agents/events-and-streaming …less the session is explicitly deleted. When a session goes idle, its sandbox is checkpointed. The checkpoint preserves the full sandbox state, including the filesystem, installed packages, and any fi… files Claude Developer Platform · in the page managed-agents/files …managed-agents/files description: Upload files and mount them in your sandbox for reading and processing. featureMetadata: topic: title: Managed Agents url: https://platform.claude.com/docs/… github Claude Developer Platform · in the page managed-agents/github …nts-2026-04-01 --- You can mount a GitHub repository to your session sandbox and connect to the GitHub MCP for making pull requests. GitHub repositories are cached, so future sessions that use the s… mcp-connector Claude Developer Platform · in the page managed-agents/mcp-connector …s (about 25,000 tokens), it is automatically written to a file in the sandbox. The model receives a truncated preview with the file path and can read the full content from there. ## Provide authentic… memory Claude Developer Platform · in the page managed-agents/memory …store to a session, it is mounted as a directory inside the session's sandbox. The agent reads and writes it with the same file tools it uses for the rest of the filesystem, and a note describing each… migration Claude Developer Platform · in the page managed-agents/migration …op back with `tool_result` messages. | Pre-built tools run inside the sandbox automatically. You only handle custom tools through `agent.custom_tool_use` events. | | You provision your own sandbox for… multiagent-orchestration Claude Developer Platform · in the page managed-agents/multiagent-orchestration …the-session-an-advisor). ### How it works All agents share the same sandbox, filesystem, and [vault credentials](https://platform.claude.com/docs/en/managed-agents/vaults), but each agent runs in it… overview Claude Developer Platform · in the page managed-agents/overview …** | Configuration for where sessions run: an Anthropic-managed cloud sandbox, or a self-hosted sandbox on your own infrastructure | | **Session** | A running agent instance within an environment,… quickstart Claude Developer Platform · in the page managed-agents/quickstart …** | Configuration for where sessions run: an Anthropic-managed cloud sandbox, or a self-hosted sandbox on your own infrastructure | | **Session** | A running agent instance within an environment,… reference Claude Developer Platform · in the page managed-agents/reference …ments](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes) only, your integration is responsible for providing `agent_toolset` results. The SDK helpers and CLI do this automatica… scheduled-deployments Claude Developer Platform · in the page managed-agents/scheduled-deployments …nment](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-memory) can attach memory stores; `file` and `github_repository` resources require a cloud environment. The Claude Conso… secure-deployment Claude Developer Platform · in the page managed-agents/secure-deployment …| Cloud or self-hosted sandbox | Cloud, unless tools must run on infrastructure you control… secure-deployment-monitoring Claude Developer Platform · in the page managed-agents/secure-deployment-monitoring …streaming#answer-tool-calls-that-pause-the-session). In a self-hosted sandbox, an `agent.tool_use` event can be waiting for your sandbox to return the tool's result. With workflow runs open, a tool ca… secure-deployment-risks Claude Developer Platform · in the page managed-agents/secure-deployment-risks --- title: Security risks and sandbox boundaries url: https://platform.claude.com/docs/en/managed-agents/secure-deployment-risks description: Why an agent's settings matter for security, and what the… session-operations Claude Developer Platform · in the page managed-agents/session-operations …is permanent. It deletes the session's record, events, and associated sandbox. A `running` session cannot be deleted; to delete one, send a [`user.interrupt` event](https://platform.claude.com/docs/en… sessions Claude Developer Platform · in the page managed-agents/sessions …registers the session but does not start any work; the environment's sandbox starts provisioning as soon as the session is created, so the first tool call does not wait on it. To delegate a task, sen… skills Claude Developer Platform · in the page managed-agents/skills …Mounting more skills increases the time it takes for the session's sandbox to start. Attach only the skills each agent needs for its task. </Note> Each entry in the `skills` (csharp, go: `Skills`)… tools Claude Developer Platform · in the page managed-agents/tools …| | Read | `read` | Read a file from the sandbox filesystem | | Write | `write` | Write a file to the sandbox filesystem | | Edit… tools-web-restrictions Claude Developer Platform · in the page managed-agents/tools-web-restrictions …`web_search` and `web_fetch` run on Anthropic's servers, not in the sandbox. A cloud environment with `limited` [networking](https://platform.claude.com/docs/en/managed-agents/environments#networkin… vaults Claude Developer Platform · in the page managed-agents/vaults …, go: `SecretName`) (the environment variable name) and stored in the sandbox as an opaque placeholder. When the agent initiates an outbound request, the opaque placeholder is substituted with the rea… webhooks Claude Developer Platform · in the page managed-agents/webhooks …items](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes) emit no webhook events. </Tab> <Tab title="Memory store events"> | Event | Trigger… workflow-runs Claude Developer Platform · in the page managed-agents/workflow-runs …urned. A run's agents also work with the same files, in the session's sandbox. * **Take the next step by itself:** An agent's result goes to the program, not to the agent that the session runs. The pr… overview Claude Developer Platform · in the page release-notes/overview …s reach a host, add it to `allowed_hosts`, which also opens it to the sandbox. `unrestricted` networking and self-hosted environments do not limit these tools. See [Environment networking](https://pla… mitigate-jailbreaks Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks …ge: don't give Claude access to secrets it doesn't need, run tools in sandboxed environments, and scope permissions as narrowly as possible. * **Screen tool outputs before Claude acts on them.** Appl… Set up Claude Code for your organization Claude Code CLI · in the page admin-setup …d integrations are allowed | [Permissions](/docs/en/permissions.md), [Sandboxing](/docs/en/sandboxing.md) | | [Set up usage visibility](#set-up-usage-visibility) | How you track spend and adoption | [… Use Claude Code features in the SDK Claude Code CLI · in the page agent-sdk/claude-code-features …s) in settings, or `ENABLE_CLAUDEAI_MCP_SERVERS=false` in `env` | | [`sandbox.credentials`](/docs/en/sandboxing#protect-credentials) `deny` entries and file `mask` entries in `~/.claude/settings.json`… Configure your agent Claude Code CLI · in the page agent-sdk/configuration …| [Effort level](/docs/en/agent-sdk/agent-loop.md#effort-level) | | `sandbox` | `sandbox` | Sandbox behavior for tool execution | [TypeScript](/docs/en/agent-sdk/typescript.md#sandbox-configuration)… Intercept and control agent behavior with hooks Claude Code CLI · in the page agent-sdk/hooks …mand, the hook doesn't run. To block Bash writes to a file where [the sandbox runs](/docs/en/sandboxing.md), see the sandbox configuration for [Python](/docs/en/agent-sdk/python.md#sandbox-configurati… Hosting the Agent SDK Claude Code CLI · in the page agent-sdk/hosting …observability, and multi-tenant isolation for Docker, Kubernetes, and sandbox providers. The Agent SDK spawns and supervises a `claude` CLI subprocess that owns a shell, a working directory, and sess…
Feedback