Docs search: force / page 5 of 10 / Source Intelligence

claude-opus-4 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4 …self-criticism, and avoids creating content that would support or reinforce self-destructive behavior even if they request this. In ambiguous cases, it tries to ensure the human is happy and is approa…

claude-opus-4-1 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-1 …self-criticism, and avoids creating content that would support or reinforce self-destructive behavior even if they request this. In ambiguous cases, it tries to ensure the human is happy and is approa…

claude-opus-4-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-5 …self-criticism, and avoids creating content that would support or reinforce self-destructive behavior even if the person requests this. In ambiguous cases, Claude tries to ensure the person is happy a…

claude-opus-4-6 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-6 …self-criticism, and avoids creating content that would support or reinforce self-destructive behavior even if the person requests this. Claude should not suggest techniques that use physical discomfor…

claude-opus-4-7 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-7 …self-criticism, and avoids creating content that would support or reinforce self-destructive behavior, even if the person requests this. Claude should not suggest techniques that use physical discomfo…

claude-opus-4-8 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-8 …self-criticism, and avoids creating content that would support or reinforce self-destructive behavior, even if the person requests this. Claude should not suggest techniques that use physical discomfo…

claude-opus-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-5 …self-criticism, and avoids creating content that would support or reinforce self-destructive behavior, even if the person requests this. Claude should not suggest techniques that use physical discomfo…

claude-opus-5-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-5-5 …f-criticism. Claude avoids creating content that could support or reinforce such behavior even if the person requests this. In ambiguous cases, Claude tries to ensure the person is happy and is approa…

claude-sonnet-3-7 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-3-7 …self-criticism, and avoids creating content that would support or reinforce self-destructive behavior even if they request this. In ambiguous cases, it tries to ensure the human is happy and is approa…

claude-sonnet-4 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-4 …self-criticism, and avoids creating content that would support or reinforce self-destructive behavior even if they request this. In ambiguous cases, it tries to ensure the human is happy and is approa…

claude-sonnet-4-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-4-5 …self-criticism, and avoids creating content that would support or reinforce self-destructive behavior even if the person requests this. In ambiguous cases, Claude tries to ensure the person is happy a…

claude-sonnet-4-6 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-4-6 …self-criticism, and avoids creating content that would support or reinforce self-destructive behavior even if the person requests this. Claude should not suggest techniques that use physical discomfor…

claude-sonnet-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-5 …self-criticism, and avoids creating content that would support or reinforce self-destructive behavior even if the person requests this. Claude does not suggest substitution techniques for self-harm th…

claude-sonnet-5-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-5-5 …self-criticism, and avoids creating content that would support or reinforce self-destructive behavior even if the person requests this. Claude does not suggest substitution techniques for self-harm th…

increase-consistency Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/increase-consistency …format you want. This trick bypasses Claude's friendly preamble and enforces your structure. <Accordion title="Example: Daily sales report"> ```text User wrap You're an insightful Sales Intellige…

Set up Claude Code for your organization Claude Code CLI · in the page admin-setup …oying Claude Code, covering API providers, managed settings, policy enforcement, usage monitoring, and data handling. Claude Code enforces organization policy through managed settings that take prece…

Escalate hard decisions with the advisor tool Claude Code CLI · in the page advisor …nsult the advisor before you continue`. There is no setting to cap or force advisor calls; if you want Claude to consult more or less often during a task, say so in your instructions. ## What you see…

How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …d Claude Code stops any background subagents still running. The cap-enforcement behaviors require Claude Code v2.1.217 or later. With [streaming input](/docs/en/agent-sdk/streaming-vs-single-mode.md)…

Give Claude custom tools Claude Code CLI · in the page agent-sdk/custom-tools …your process. Informational only. | Annotations are metadata, not enforcement. A tool marked `readOnlyHint: true` can still write to disk if that's what the handler does. Keep the annotation accurat…

Hosting the Agent SDK Claude Code CLI · in the page agent-sdk/hosting …For production, route outbound traffic through an egress proxy that enforces domain allowlists, injects credentials, and logs requests. See [Secure Deployment](/docs/en/agent-sdk/secure-deployment.md)…

Modifying system prompts Claude Code CLI · in the page agent-sdk/modifying-system-prompts …ocs/en/prompt-caching.md#how-the-cache-is-organized). Where the API enforces [preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking), Claude also loses its think…

Agent SDK reference - Python Claude Code CLI · in the page agent-sdk/python …"Claude Code CLI not found. Try reinstalling: pip install --force-reinstall claude-agent-sdk" ) # Catch ResultError before ProcessError, which it subclasses. Its message # ca…

Securely deploying AI agents Claude Code CLI · in the page agent-sdk/secure-deployment …s, [sandbox-runtime](https://github.com/anthropics/sandbox-runtime) enforces filesystem and network restrictions at the OS level. The main advantage is simplicity: no Docker configuration, container…

Get structured output from agents Claude Code CLI · in the page agent-sdk/structured-outputs …such as `"format": "email"`, is accepted as an annotation and isn't enforced by the SDK's validator. Before v2.1.205, any schema containing `format` was treated as invalid. ## Example: TODO tracking…

Subagents in the SDK Claude Code CLI · in the page agent-sdk/subagents …Code version that added each variable and the spend cap's subagent enforcement. Claude decides on its own when to spawn a subagent and how many to spawn. Each subagent makes its own API requests, wh…

Agent SDK reference - TypeScript Claude Code CLI · in the page agent-sdk/typescript …, for example `npm install @anthropic-ai/claude-agent-sdk-linux-x64 --force`. * On Windows, the binary subpath is `claude.exe`, for example `@anthropic-ai/claude-agent-sdk-win32-x64/claude.exe`. ###…

Orchestrate teams of Claude Code sessions Claude Code CLI · in the page agent-teams …n place of the first source. If you set [`CLAUDE_CODE_SUBAGENT_MODEL_FORCE=1`](/docs/en/sub-agents#run-every-subagent-on-one-model), the first two sources don't apply. Claude Code picks every teammat…

Manage multiple agents with agent view Claude Code CLI · in the page agent-view …t can't detect hyperlink support, for example over SSH or tmux. Set [`FORCE_HYPERLINK=0`](/docs/en/env-vars) to render the label as plain text. * After you send a follow-up to the session, Claude Code…

Claude Code on Amazon Bedrock Claude Code CLI · in the page amazon-bedrock …L_ACCESS_MEMORY=1`](/docs/en/env-vars). ### When your organization enforces a model allowlist If you set [`enforceAvailableModels`](/docs/en/model-config#enforce-the-allowlist-for-the-default-model)…

Authentication Claude Code CLI · in the page authentication …pt. * **Login restricted to an organization**: an administrator set [`forceLoginOrgUUID`](/docs/en/settings-reference#forceloginorguuid) in managed settings to [require logins from specific organizati…

Configure auto mode Claude Code CLI · in the page auto-mode-config …s a production deploy. The push's content is also still checked, so a force push, a secret entering the commit, or a change that would send secrets outside the repository when CI or a deploy pipeline…

Claude Code changelog Claude Code CLI · in the page changelog …ngs; under Claude Desktop, only in project settings * Changed exit to force-kill background commands still running 1.5 seconds after being asked to stop; in fullscreen mode they could previously be le…

Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry Claude Code CLI · in the page claude-apps-gateway …`managed` block](/docs/en/claude-apps-gateway-config#managed). Leave `forceLoginMethod` and `forceLoginOrgUUID` out of that block, or [some signed-in sessions exit at startup](/docs/en/claude-apps-gat…

Claude apps gateway configuration Claude Code CLI · in the page claude-apps-gateway-config …`admin`](#admin): Admin API auth and retention for spend limits * [`enforcement`](#enforcement): spend-limit fail-open or fail-closed behavior * [`pricing`](#pricing): contracted rates and a multiplie…

Claude apps gateway deployment and operations Claude Code CLI · in the page claude-apps-gateway-deploy …ent, plus the compute it runs on. * **Bypass**: the gateway doesn't enforce that the only route to a model goes through it. A developer with their own credential can still call the provider directly,…

Deploy Claude apps gateway on AWS Claude Code CLI · in the page claude-apps-gateway-on-aws …the database in the private subnets, and a parameter group with `rds.force_ssl=1` so the server rejects plaintext connections. The engine version is pinned once because the parameter group's family m…

Deploy Claude apps gateway on Google Cloud Claude Code CLI · in the page claude-apps-gateway-on-gcp …also satisfies projects where `constraints/sql.restrictPublicIp` is enforced: ```bash theme={null} VPC=cc-gateway-vpc gcloud compute networks create "$VPC" --subnet-mode=custom gcloud compute network…

Claude apps gateway spend limits Claude Code CLI · in the page claude-apps-gateway-spend-limits …y day, week, or month. Set limits with an Admin API and the gateway enforces them live on every request. Spend limits cap how much each developer can spend through your [Claude apps gateway](/docs/en…

Use Claude Code in the cloud Claude Code CLI · in the page claude-code-on-the-web …even when Claude Code would otherwise clone from the remote, set `CCR_FORCE_BUNDLE=1`: ```bash theme={null} CCR_FORCE_BUNDLE=1 claude --cloud "Run the test suite and fix any failures" ``` Bundled re…

Explore the .claude directory Claude Code CLI · in the page claude-directory …ession. Unlike CLAUDE.md, which Claude reads as guidance, these are enforced whether Claude follows them or not.', contains: [<><A href="/docs/en/permissions">permissions</A>: allow, deny, o…

Let Claude coordinate ongoing work with Projects Claude Code CLI · in the page claude-projects …e GitHub App doesn't cover yet or one in a GitHub organization that enforces SSO. **1. Connect your GitHub account** If you haven't used claude.ai/code before, your first visit walks you through con…

Scan your codebase for vulnerabilities Claude Code CLI · in the page claude-security …scanners | Language-specific rules, supply-chain checks, and policy enforcement | The plugin doesn't replace your existing source-code security tools. Run it alongside static analysis, dependency sca…

claude-tag Claude Code CLI · in the page claude-tag …"sr-only">Search...</span><svg data-search-item="trigger-icon" class="forced-colors:forced-color-adjust-none forced-colors:bg-[color:CanvasText]! h-4 w-4 bg-gray-500 dark:bg-gray-400 hover:bg-gray-600…

CLI reference Claude Code CLI · in the page cli-reference …pic account. Use `--email` to pre-fill your email address, `--sso` to force SSO authentication, and `--console` to sign in with Anthropic Console for API usage billing instead of a Claude subscription…

Configure cloud environments Claude Code CLI · in the page cloud-environments …s/en/model-config.md#surface-coverage) for how `availableModels` is enforced in cloud sessions. Settings deployed to your device through MDM or managed settings files don't apply, because the session…

Code Review Claude Code CLI · in the page code-review …e settling severity and writing the review. Put the rules you want enforced directly in `REVIEW.md`. #### What you can tune `REVIEW.md` is freeform markdown, so anything you can express as a review…

Customize Code Review Claude Code CLI · in the page code-review-customize …most five Nits per review. ## Do not report - Anything CI already enforces: lint, formatting, type errors - Generated files under `src/gen/` and any `*.lock` file - Test-only code that intentionally…

Commands Claude Code CLI · in the page commands …| | `/reload-plugins [--force]` | Reload all active [plugins](/docs/en/pl…