740 pages for term.

cmek-aws-kms Claude Developer Platform · in the page manage-claude/cmek-aws-kms …ars. After you click **Save**, click **Accept** on the data retention terms. </Step> </Steps> </Tab> <Tab title="Claude Enterprise"> On Claude Enterprise, CMEK applies to the whole… cmek-azure-key-vault Claude Developer Platform · in the page manage-claude/cmek-azure-key-vault …ars. After you click **Save**, click **Accept** on the data retention terms. </Step> </Steps> </Tab> <Tab title="Claude Enterprise"> On Claude Enterprise, CMEK applies to the whole… cmek-coverage-claude-enterprise Claude Developer Platform · in the page manage-claude/cmek-coverage-claude-enterprise …In organizations with HIPAA readiness, an Owner must first accept the terms for using them. | | Artifact publishing and sharing… cmek-data-retention Claude Developer Platform · in the page manage-claude/cmek-data-retention …e workspace to **Standard data retention**, accept the data retention terms, and attach your key to it. The workspace you switch can't be the default workspace, whose retention follows the organizatio… cmek-google-cloud-kms Claude Developer Platform · in the page manage-claude/cmek-google-cloud-kms …ars. After you click **Save**, click **Accept** on the data retention terms. </Step> </Steps> </Tab> <Tab title="Claude Enterprise"> On Claude Enterprise, CMEK applies to the whole… compliance-errors Claude Developer Platform · in the page manage-claude/compliance-errors …r, then retry. If the header is absent (for example, stripped by an intermediary), fall back to exponential backoff (start at 1 second, double up to 60 seconds). Do not advance your pagination cursor… compliance-faq Claude Developer Platform · in the page manage-claude/compliance-faq …ude Desktop that run on users' machines, Claude Code sessions (in the terminal, in Claude Desktop, or in an IDE extension), sessions in the Claude Science desktop app, Claude for Microsoft 365 session… before_id is the first_id from a previous response Claude Developer Platform · in the page manage-claude/compliance-integration-patterns …curity information and event management (SIEM) system, and where long-term copies of activity and content live. These choices are independent of the endpoints themselves; this page helps you evaluate… compliance-sessions Claude Developer Platform · in the page manage-claude/compliance-sessions …| | Claude Code in the terminal, in Claude Desktop, or in an IDE extension, running on the user's machine | Local sess… data-residency Claude Developer Platform · in the page manage-claude/data-residency …de Models on Google Cloud (Google managed), the inference region is determined by the endpoint URL or inference profile, so `inference_geo` is not applicable. On [Claude in Microsoft Foundry](https://… inference-hooks Claude Developer Platform · in the page manage-claude/inference-hooks …nd within the timeout, your organization's failure handling setting determines the outcome: block the request, or allow it to proceed without inspection. Sustained failures attributable to your server… inference-hooks-endpoint Claude Developer Platform · in the page manage-claude/inference-hooks-endpoint …xpose it at a public `https://` URL. For example, put it behind a TLS-terminating reverse proxy on a host you control, not a reverse-tunnel service (see [Receive a request](https://platform.claude.com… opentelemetry Claude Developer Platform · in the page manage-claude/opentelemetry …thropic, including the Beta Services section of the [Service Specific Terms](https://www.anthropic.com/legal/service-specific-terms). </Note> The Claude API and the SDK can trace your Messages API re… api Claude Developer Platform · in the page manage-claude/opentelemetry/api …OTLP/HTTP endpoint that you specify, in accordance with your provider terms and access controls. After delivery, the data is held by the service that you chose, outside Anthropic, under that service's… plugins-api Claude Developer Platform · in the page manage-claude/plugins-api …oad each build, test it, and then promote it. To have your pipeline determine when each build is served, pin the plugin once by setting `served_version_id` to its current version; from then on, promot… spend-limits-api Claude Developer Platform · in the page manage-claude/spend-limits-api …time. | Both `approved` and `denied` are terminal. A member has at most one `pending` request at a time. Approving with `POST /v1/organizations/spend_limit_increase_reque… wif-admin-api Claude Developer Platform · in the page manage-claude/wif-admin-api …d cannot perform every operation on this page. ### Interactive (your terminal) Log in with the [`ant` CLI](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/quickstart) under a dedicated pr… github-actions Claude Developer Platform · in the page manage-claude/wif-providers/github-actions …st this claim (and others, such as `repository_owner` and `ref`) to determine which workflow runs are allowed to authenticate. ## Prerequisites * Familiarity with [WIF concepts](https://platform.cla… Replace NODE_UID with the node's UID: Claude Developer Platform · in the page manage-claude/wif-providers/spiffe …d JWT-SVID) and the OIDC Discovery Provider's `domains` list (which determines the host the discovery document and JWKS are served from). That shared URL is what you register with Anthropic. The trus… wif-reference Claude Developer Platform · in the page manage-claude/wif-reference …t. ## OAuth scopes The `oauth_scope` you set on a federation rule determines which Claude API endpoints the minted access token can call. | Scope | Grants access to… budgets Claude Developer Platform · in the page managed-agents/budgets …cs/en/managed-agents/session-operations#session-statuses) rather than terminating; changing or removing the budget resumes the work that the budget paused. Deployments accept the same budget and apply… choosing-an-environment Claude Developer Platform · in the page managed-agents/choosing-an-environment …your own infrastructure. Claude still runs on Anthropic's side and determines which tool to call next. A program that you run, called a worker, carries out the agent's bash and file tool calls on you… cloud-sandboxes-reference Claude Developer Platform · in the page managed-agents/cloud-sandboxes-reference …nd YAML processing * `tar`, `zip`, `unzip` - Archive tools * `tmux` - Terminal multiplexer ### Development tools * `make`, `cmake` - Build systems * `docker` - Container management (limited availabi… DCF Model Rubric Claude Developer Platform · in the page managed-agents/define-outcomes …risk-free rate, and equity risk premium are sourced or justified ## Terminal Value - Uses either perpetuity growth or exit multiple method (stated which) - Terminal growth rate does not exceed long-… dreams Claude Developer Platform · in the page managed-agents/dreams …time. The session is archived (not deleted) when the dream reaches a terminal state, so the transcript remains available afterward. ## Use the output When `status` (csharp, go: `Status`) reaches `c… environments Claude Developer Platform · in the page managed-agents/environments …* **The agent acts on your behalf:** Its actions can violate a site's terms of service, or create accounts and records there. * **Model behavior is not a security control:** The agent can act on exter… multiagent-orchestration Claude Developer Platform · in the page managed-agents/multiagent-orchestration …itself. You decide which of these the agent can use, and the agent determines when to use them. To guide that choice, tell the agent in its system prompt when to use a workflow run. See [Tell the age… permission-policies Claude Developer Platform · in the page managed-agents/permission-policies …ll has one of three outcomes: * **The call runs.** When the server determines that the call is safe, the tool runs as it would under `always_allow`. * **The call is denied.** When the server evaluate… quickstart Claude Developer Platform · in the page managed-agents/quickstart …gents: 1. **Provisions a sandbox:** Your environment configuration determines how it's built. 2. **Runs the agent loop:** Claude determines which tools to use based on your message. 3. **Runs tools:*… reference Claude Developer Platform · in the page managed-agents/reference …| | `session.status_terminated` | Session ended, either because of an unrecoverable error or because it was archived.… scheduled-deployments Claude Developer Platform · in the page managed-agents/scheduled-deployments …(deployment.id) ``` </CodeGroup> **Archive**, unlike **pause**, is terminal: the schedule ends and the deployment cannot be modified. <CodeGroup> ```bash cURL curl --fail-with-body -sS -X POST… secure-deployment Claude Developer Platform · in the page managed-agents/secure-deployment …| Optional. A review of each session that went idle or terminated, on a schedule… secure-deployment-monitoring Claude Developer Platform · in the page managed-agents/secure-deployment-monitoring …| | Sessions that reach a budget or terminate | The `session.budget_reached` and `session.status_terminated` webhooks… spawn.sh: called once per claimed work item Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes …control plane (where Claude runs) so the model can see results and determine what to do next. The agent's [skills](https://platform.claude.com/docs/en/managed-agents/skills) and the contents of any [… self-hosted-sandboxes-custom-tools Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-custom-tools …const controller = new AbortController(); process.once("SIGTERM", () => controller.abort()); await new EnvironmentWorker({ client, environmentId, environmentK… self-hosted-sandboxes-operations Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-operations …rocess runs no teardown. To stop a worker cleanly: 1. **Make sure SIGTERM and SIGINT cancel the worker.** How depends on the worker: | Worker | What to do… self-hosted-sandboxes-reference Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-reference …queue and gives you each claimed session. | You determine what happens for each session, for example launching a sandbox rather than running tools in-process. | | [`client.beta.ses… self-hosted-sandboxes-security Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-security …em. * **Network egress controls.** Your sandbox's network access is determined by your VPC and firewall rules. Without egress restrictions, a compromised tool execution can reach arbitrary external ho… self-hosted-sandboxes-workers Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-workers ….get_running_loop() for signum in (signal.SIGINT, signal.SIGTERM): loop.add_signal_handler(signum, task.cancel) with contextlib.suppress(asyncio.CancelledError):… session-observability Claude Developer Platform · in the page managed-agents/session-observability …open the same viewer from the `ant` CLI or follow the session in your terminal. See [Connect to a Managed Agents session from your terminal](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/… session-operations Claude Developer Platform · in the page managed-agents/session-operations …| | `terminated` | Session has ended, either because of an unrecoverable error or because it was archived. A session that completes i… session-threads Claude Developer Platform · in the page managed-agents/session-threads …`budget_reached`, the interrupt is a no-op. An interrupt that names a terminated thread returns a 400 error. An interrupted child doesn't send the primary thread's agent the report it sends when a tur… tools Claude Developer Platform · in the page managed-agents/tools …cify what operations are available and what they return, and Claude determines when and how to call them. Claude does not run a custom tool itself. It emits a structured request, your code runs the o… webhooks Claude Developer Platform · in the page managed-agents/webhooks …| | `session.status_terminated` | The session terminated, either because of an unrecoverable error or because it was archived.… workflow-runs Claude Developer Platform · in the page managed-agents/workflow-runs …to the program, not to the agent that the session runs. The program determines which agents run next, and it writes their prompts. * **Repeat and choose:** Inside a phase, the program can repeat work… Or, for Claude Mythos 5.1, which offers the same capabilities to verified organizations: Claude Developer Platform · in the page models/fable-5-1/migration-guide …de/thinking) is always on, unchanged from Claude Fable 5. The model determines when and how much to think. No `thinking` configuration is required. Both `thinking: {type: "disabled"}` and manual exten… whats-new-fable-5-1 Claude Developer Platform · in the page models/fable-5-1/whats-new-fable-5-1 …able 5.1 and Claude Mythos 5.1 carries Anthropic's statistical text watermark on every platform where the model is available. Supported image, video, and audio files Claude produces (through the [code… overview Claude Developer Platform · in the page models/haiku-5-5/overview …laude.com/docs/en/build-with-claude/thinking"> Claude Haiku 5.5 determines when and how much to think. Steer depth with `effort`. </Card> <Card title="Context windows" icon="stack" href="http… whats-new-haiku-5-5 Claude Developer Platform · in the page models/haiku-5-5/whats-new-haiku-5-5 …rm.claude.com/docs/en/build-with-claude/thinking), Claude Haiku 5.5 determines when and how much to think. Adaptive thinking is on by default. Although you can still turn thinking off with `thinking:… migration-guide Claude Developer Platform · in the page models/opus-5-5/migration-guide …ehavior on Claude Opus 5.5. If you were using `temperature = 0` for determinism, note that it never guaranteed identical outputs on prior models. 3. **Thinking content omitted by default:** Thinking…