582 pages for environment.

wif-reference Claude Developer Platform · in the page manage-claude/wif-reference …/platform.claude.com/docs/en/manage-claude/wif-reference description: Environment variables, validation rules, profile configuration, and error reference for Workload Identity Federation. --- This pa… workload-identity-federation Claude Developer Platform · in the page manage-claude/workload-identity-federation …nce an internal hostname. You typically register one issuer for each environment: your production EKS cluster, your staging cluster, and GitHub Actions are three separate issuers. ### Federation rul… workspaces Claude Developer Platform · in the page manage-claude/workspaces …ithin an organization. Use workspaces to separate different projects, environments, or teams while maintaining centralized billing and administration. ## How workspaces work Every organization has a… agent-setup Claude Developer Platform · in the page managed-agents/agent-setup …xes. | Applicable endpoints: * `/v1/agents` * `/v1/sessions` * `/v1/environments` budgets Claude Developer Platform · in the page managed-agents/budgets …application/json" \ -d '{ "agent": "'"$AGENT_ID"'", "environment_id": "'"$ENVIRONMENT_ID"'", "budget": { "type": "limit", "max_list_cost": {"amount": "125", "cur… cloud-sandboxes-reference Claude Developer Platform · in the page managed-agents/cloud-sandboxes-reference …ithout any installation steps. These specifications apply to `cloud` environments. Self-hosted sandboxes run on your infrastructure with whatever your worker provides. ## Programming languages | La… DCF Model Rubric Claude Developer Platform · in the page managed-agents/define-outcomes …; using Anthropic.Models.Beta.Agents; using Anthropic.Models.Beta.Environments; using Anthropic.Models.Beta.Sessions; using Anthropic.Models.Beta.Sessions.Events; using Anthropic.Models.File… dreams Claude Developer Platform · in the page managed-agents/dreams …application/json" \ -d '{ "agent": "'"$agent_id"'", "environment_id": "'"$environment_id"'", "resources": [ { "type": "memory_store", "memory_store_id": "'"$output_store… event-deltas Claude Developer Platform · in the page managed-agents/event-deltas …xes. | Applicable endpoints: * `/v1/agents` * `/v1/sessions` * `/v1/environments` files Claude Developer Platform · in the page managed-agents/files …application/json" \ -d '{ "agent": "'"$AGENT_ID"'", "environment_id": "'"$ENVIRONMENT_ID"'", "resources": [ { "type": "file", "file_id": "'"$FILE_ID"… github Claude Developer Platform · in the page managed-agents/github …create a session that mounts the GitHub repository. With a `limited` [environment](https://platform.claude.com/docs/en/managed-agents/environments#networking), session creation fails with a 400 error… mcp-connector Claude Developer Platform · in the page managed-agents/mcp-connector …) for how to create vaults and manage credentials. With a `limited` [environment](https://platform.claude.com/docs/en/managed-agents/environments#networking), session creation fails with a 400 error… memory Claude Developer Platform · in the page managed-agents/memory …: beta note: On Claude Platform on AWS, sessions on self-hosted environments can't attach memory stores. Sending `managed-agents-2026-04-01` together with `agent-memory-2026-07-22` on a memory s… migration Claude Developer Platform · in the page managed-agents/migration …nt={"type": "agent", "id": agent.id, "version": agent.version}, environment_id=environment.id, ) with client.beta.sessions.events.stream(session.id) as stream: client.beta.sessions.ev… multiagent-orchestration Claude Developer Platform · in the page managed-agents/multiagent-orchestration …ication/json" \ -d '{ "agent": "'"$LEAD_AGENT_ID"'", "environment_id": "'"$ENVIRONMENT_ID"'" }' ``` ```bash CLI ant beta:sessions create \ --agent "$LEAD_AGENT_ID" \… onboarding Claude Developer Platform · in the page managed-agents/onboarding …e base Once your agent works as expected: 1. Copy the agent ID and [environment ID](https://platform.claude.com/docs/en/managed-agents/environments) from Console. 2. Reference them in your code when… overview Claude Developer Platform · in the page managed-agents/overview …own agent loop, tool execution, and runtime, you get a fully managed environment where Claude can read files, run commands, browse the web, and run code securely. The harness supports built-in prompt… permission-policies Claude Developer Platform · in the page managed-agents/permission-policies …xes. | Applicable endpoints: * `/v1/agents` * `/v1/sessions` * `/v1/environments` quickstart Claude Developer Platform · in the page managed-agents/quickstart …ta --- This guide walks you through creating an agent, setting up an environment, starting a session, and streaming agent responses. Let Claude Code set up your agent for you ```text /claude-api ma… reference Claude Developer Platform · in the page managed-agents/reference …| | `user.tool_result` | For sessions with `self_hosted` [environments](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes) only, your integration is responsible for… scheduled-deployments Claude Developer Platform · in the page managed-agents/scheduled-deployments …(https://platform.claude.com/docs/en/managed-agents/agent-setup) and [environment configuration](https://platform.claude.com/docs/en/managed-agents/environments), and optionally accept [files](https:/… secure-deployment Claude Developer Platform · in the page managed-agents/secure-deployment …| Environment `networking.type` | `limited`, with only the hosts the agent needs… secure-deployment-risks Claude Developer Platform · in the page managed-agents/secure-deployment-risks …| | `bash` and file tools | The sandbox. In a cloud environment, each session gets its own isolated Linux container | Environment networking, the tool se… spawn.sh: called once per claimed work item Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes …so the agent's code, filesystem, and network egress never leave your environment. Tool execution stays on your host: the filesystem the agent reads and writes, the processes it spawns, and the netwo… self-hosted-sandboxes-custom-tools Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-custom-tools …network egress you configured for the sandbox, and nothing more. The environment key authorizes posting custom tool results, so your Claude API key stays off the worker host. <Note> Serving custom… self-hosted-sandboxes-memory Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-memory …51101 - claude-sonnet-4-5-20250929 --- Sessions on a self-hosted environment attach [memory stores](https://platform.claude.com/docs/en/managed-agents/memory) exactly as sessions on cloud environ… self-hosted-sandboxes-operations Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-operations …ics and stop endpoints accept either your organization API key or the environment key. Call them from outside the worker host with your organization API key. Setting `ANTHROPIC_API_KEY` on the worker… self-hosted-sandboxes-reference Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-reference …scription: "Reference for self-hosted sandbox workers: ant CLI flags, environment variables, host requirements, filesystem paths, and SDK helper options." featureMetadata: topic: title: Managed… self-hosted-sandboxes-security Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-security …rity description: Shared responsibility model for self-hosted sandbox environments. featureMetadata: topic: title: Managed Agents url: https://platform.claude.com/docs/en/managed-agents/over… self-hosted-sandboxes-workers Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-workers …rence) for every CLI flag and SDK option. For more control, call the [Environments Work endpoints](https://platform.claude.com/docs/en/api/beta/environments/work) directly and implement your own worke… session-observability Claude Developer Platform · in the page managed-agents/session-observability …xes. | Applicable endpoints: * `/v1/agents` * `/v1/sessions` * `/v1/environments` session-operations Claude Developer Platform · in the page managed-agents/session-operations …delete the session once it’s `idle`. Memory stores, vaults, skills, environments, and agents are independent resources and are not affected by session deletion. Files you uploaded through the Files… session-threads Claude Developer Platform · in the page managed-agents/session-threads …xes. | Applicable endpoints: * `/v1/agents` * `/v1/sessions` * `/v1/environments` sessions Claude Developer Platform · in the page managed-agents/sessions …nthropic managed): beta --- A session is an agent instance within an environment. Each session references an [agent](https://platform.claude.com/docs/en/managed-agents/agent-setup) and an [environmen… skills Claude Developer Platform · in the page managed-agents/skills …plication/json" \ -d @- <<JSON { "agent": "$agent_id", "environment_id": "$environment_id", "resources": [ { "type": "github_repository", "url": "https://github… tools Claude Developer Platform · in the page managed-agents/tools …e in the [sandbox](https://platform.claude.com/docs/en/managed-agents/environments). The model receives a truncated preview with the file path and can read the full content from there. ## Configuring… tools-web-restrictions Claude Developer Platform · in the page managed-agents/tools-web-restrictions …d `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#networking) also applies i… vaults Claude Developer Platform · in the page managed-agents/vaults …that URL at session runtime, the token is injected automatically. * **Environment variables** (`environment_variable`): each credential is keyed by a `secret_name` (java, php: `secretName`; csharp, go… webhooks Claude Developer Platform · in the page managed-agents/webhooks …h an unrecoverable error, such as an archived subagent or an archived environment. Recoverable failures, including rate limits, don’t pause the deployment. See [Failure behavior](https://platform.clau… workflow-runs Claude Developer Platform · in the page managed-agents/workflow-runs …xes. | Applicable endpoints: * `/v1/agents` * `/v1/sessions` * `/v1/environments` migration-guide Claude Developer Platform · in the page models/haiku-5-5/migration-guide …olset_name` on results. Zoom is on by default in the toolset; if your environment doesn’t implement it, add `"configs": {"zoom": {"enabled": false}}`. If you send the `fine-grained-tool-streaming-2025… migration-guide Claude Developer Platform · in the page models/opus-5-5/migration-guide …-5#prompts-written-for-thinking-disabled). 3. **Test in a development environment** before switching production traffic. ## Migrating to Claude Opus 5.5 from Claude Opus 4.8 First work through [What… overview Claude Developer Platform · in the page release-notes/overview …ude/api-credits-for-subscribers). * In Claude Managed Agents, a cloud environment with `limited` networking now also applies its `allowed_hosts` to the `web_search` and `web_fetch` tools. A `web_fetch… mitigate-jailbreaks Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks …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.** Apply the same… Use Claude Code with a screen reader Claude Code CLI · in the page accessibility …or sessions started from one shell: set the `CLAUDE_AX_SCREEN_READER` environment variable to `1`. In Bash or Zsh, run `export CLAUDE_AX_SCREEN_READER=1`. In PowerShell, run `$env:CLAUDE_AX_SCREEN_REA… Set up Claude Code for your organization Claude Code CLI · in the page admin-setup …on-the-web.md) have their own admin surfaces on claude.ai: * **Cloud environments page**: Owners create [organization-shared environments](https://code.claude.com/docs/en/cloud-environments.md#organi… Escalate hard decisions with the advisor tool Claude Code CLI · in the page advisor …is ignored. The `--advisor` flag is accepted but has no effect. See [Environment variables](https://code.claude.com/docs/en/env-vars.md). ## Compare with related features The advisor is one of seve… How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …ns`. Can't be used when running as root on Unix. Use only in isolated environments where the agent's actions can't affect systems you care about | CI, containers, or other isolated environments | For… Configure your agent Claude Code CLI · in the page agent-sdk/configuration …figure Agent SDK sessions: compose the options object, set the model, environment, and limits, and find each feature option's page. An Agent SDK session reads configuration from settings files, envir… Track cost and usage Claude Code CLI · in the page agent-sdk/cost-tracking …`ENABLE_PROMPT_CACHING_1H`](https://code.claude.com/docs/en/env-vars) environment variable. You can export it in your shell or container environment, or pass it through `options.env`. The following e…