992 pages for start.

migration-guide Claude Developer Platform · in the page models/sonnet-5-5/migration-guide …ttings that return errors, thinking changes, and a checklist for each starting model. --- This guide lists the code changes for moving to Claude Sonnet 5.5 from Claude Sonnet 5, Claude Sonnet 4.6, Cl… whats-new-sonnet-5-5 Claude Developer Platform · in the page models/sonnet-5-5/whats-new-sonnet-5-5 …nnet 5. Re-run your effort sweep rather than carrying a setting over. Start at `high` unless your workload is agentic or latency-sensitive. For agentic coding and multistep tool use, start at `medium`… overview Claude Developer Platform · in the page release-notes/overview …CLI](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/quickstart) that send API version `2026-10-21` by default: Python SDK 2.0.0, TypeScript SDK 1.0.0, C# SDK 13.0.0, Go SDK 2.0.0, Java SD… claude-haiku-3-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-haiku-3-5 …honest", "I should be direct", and so on. Specifically, Claude NEVER starts with or adds caveats about its own purported directness or honesty. If Claude is asked to assist with tasks involving the… claude-opus-4 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4 …xplicitly tells the person what aspects it can't or won't with at the start of its response. If Claude provides bullet points in its response, it should use CommonMark standard markdown, and each bul… claude-opus-4-1 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-1 …xplicitly tells the person what aspects it can't or won't with at the start of its response. If Claude provides bullet points in its response, it should use CommonMark standard markdown, and each bul… claude-opus-4-7 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-7 …rred over asking the person to do the lookup themselves. Once Claude starts on a task, Claude sees it through to a complete answer rather than stopping partway. This means searching again if a search… claude-sonnet-3-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-3-5 …honest", "I should be direct", and so on. Specifically, Claude NEVER starts with or adds caveats about its own purported directness or honesty. If Claude provides bullet points in its response, each… claude-sonnet-4 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-4 …xplicitly tells the person what aspects it can't or won't with at the start of its response. If Claude provides bullet points in its response, it should use CommonMark standard markdown, and each bul… claude-sonnet-4-6 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-4-6 …d remains available for people who prefer it or want to continue work started with it. The person is able to switch models mid-conversation, so previous messages claiming to be from a different model… overview Claude Developer Platform · in the page release-notes/system-prompts/overview …de up-to-date information, such as the current date, to Claude at the start of every conversation. The system prompt also encourages certain behaviors, such as always providing code snippets in Markdo… develop-tests Claude Developer Platform · in the page test-and-evaluate/develop-tests …o LLM-based grading. --- Building a successful LLM-based application starts with clearly defining your success criteria and then designing evaluations to measure performance against them. This cycle… handle-streaming-refusals Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/handle-streaming-refusals …aming responses, and retry refused requests on a fallback model. --- Starting with Claude 4 models, streaming responses from Claude's API return **`stop_reason`: `"refusal"`** when streaming classifi… increase-consistency Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/increase-consistency …ntitrust lawsuits and regulatory actions - Talent poaching by startups and competitors </threats> </swot> <strategy>Focus on our agility and customization. Target TechGiant's slo… reduce-latency Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/reduce-latency …3. Stream responses Streaming is a feature that allows the model to start sending back its response before the full output is complete. This can significantly improve the perceived responsiveness of… Use Claude Code with a screen reader Claude Code CLI · in the page accessibility …: * For one session: run `claude --ax-screen-reader`. * For sessions started from one shell: set the `CLAUDE_AX_SCREEN_READER` environment variable to `1`. In Bash or Zsh, run `export CLAUDE_AX_SCREE… Set up Claude Code for your organization Claude Code CLI · in the page admin-setup …west | Windows only | Claude Code fetches server-managed settings at startup and refreshes them hourly during the session, with no endpoint infrastructure to deploy. Delivery through the claude.ai ad… Escalate hard decisions with the advisor tool Claude Code CLI · in the page advisor …main model [supports it](#choose-an-advisor-model). After the session starts, Claude Code shows an `Advisor Tool (experimental) is on and may use more tokens · /advisor` notification. To stop using th… How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …so most installs need no separate Claude Code install. See the [quickstart's install note](/docs/en/agent-sdk/quickstart.md) for the installs that do. When you start an agent, the SDK runs the same… Use Claude Code features in the SDK Claude Code CLI · in the page agent-sdk/claude-code-features …rojects/<project>/memory/` | Loaded into the system prompt at session start. The agent writes new memories there with the standard `Write` and `Edit` tools rather than a dedicated memory tool, so thos… Configure your agent Claude Code CLI · in the page agent-sdk/configuration …es, environment variables, and the `options` object you pass when you start it. This page shows how to compose the `options` object and what settings files and environment variables control. For ever… Track cost and usage Claude Code CLI · in the page agent-sdk/cost-tracking …r call totals rather than summing across results. The running totals start over each time your app sends one of those three commands, and inside a `query()` call nothing else resets them. Three resul… Examples Claude Code CLI · in the page agent-sdk/examples …minimal agent first If you haven't built anything with the SDK yet, start with one of these before a full application: * [Agent SDK quickstart](/docs/en/agent-sdk/quickstart.md): build your first w… Rewind file changes with checkpointing Claude Code CLI · in the page agent-sdk/file-checkpointing …ve_response(): # Update checkpoint before each agent turn starts # This overwrites the previous checkpoint. Only keep the latest if isinstance(message, UserMessage)… Intercept and control agent behavior with hooks Claude Code CLI · in the page agent-sdk/hooks …code in response to agent events, like a tool being called, a session starting, or execution stopping. With hooks, you can: * **Block dangerous operations** before they execute, like destructive shel… Hosting the Agent SDK Claude Code CLI · in the page agent-sdk/hosting …container's filesystem by default. None of them survive a container restart, a scale-down, or a move to a different node. | State | Default location | | - | - | | Session transcripts | `~/.claude/pro… Connect to external tools with MCP Claude Code CLI · in the page agent-sdk/mcp …Context Protocol (MCP)](https://modelcontextprotocol.io/docs/getting-started/intro) is an open standard for connecting AI agents to external tools and data sources. With MCP, your agent can query dat… Modifying system prompts Claude Code CLI · in the page agent-sdk/modifying-system-prompts …m prompts define Claude's behavior, capabilities, and response style. Start from the `claude_code` preset for CLI or IDE-like coding tools where a human watches and steers the work. Write your own pro… Observability with OpenTelemetry Claude Code CLI · in the page agent-sdk/observability …les in your shell, container, or orchestrator before your application starts. Every `query()` call picks them up automatically with no code change. This is the recommended approach for production depl… Agent SDK overview Claude Code CLI · in the page agent-sdk/overview …our language](https://platform.claude.com/docs/en/managed-agents/quickstart#install-the-sdk), the `ant` CLI, or the REST API. | To drive the same agent loop from a language other than Python or TypeS… Configure permissions Claude Code CLI · in the page agent-sdk/permissions …ing streaming sessions. With Claude Code v2.1.302 or later, your app starts in `default` mode unless you set a permission mode or it gets one from [`permissions.defaultMode`](/docs/en/settings-refere… Agent SDK reference - Python Claude Code CLI · in the page agent-sdk/python …ndows PowerShell, and API key setup, see [Setup in the Agent SDK quickstart](/docs/en/agent-sdk/quickstart.md#setup). ## Choosing between `query()` and `ClaudeSDKClient` The Python SDK provides two… Persist sessions to external storage Claude Code CLI · in the page agent-sdk/session-storage …ility.** Local containers are ephemeral. An external store survives restarts and redeploys. * **Compliance and audit.** Keep transcripts in storage you already govern, with your own retention rules, e… Work with sessions Claude Code CLI · in the page agent-sdk/sessions …with no ID handling. | | Pick up where you left off after a process restart | `continue_conversation=True` (Python) / `continue: true` (TypeScript). Resumes the most recent session in the directory, n… Extend agents with skills Claude Code CLI · in the page agent-sdk/skills …*: once filesystem settings load, the SDK discovers skill metadata at startup from user and project directories, and loads the full content when Claude invokes the skill * **Model-invoked**: Claude au… Stream responses in real-time Claude Code CLI · in the page agent-sdk/streaming-output …t types include: | Event Type | Description | | :- | :- | | `message_start` | Start of a new message | | `content_block_start` | Start of a new content block (text or tool use) | | `content_block_del… Get structured output from agents Claude Code CLI · in the page agent-sdk/structured-outputs …] > } > ``` > > Typed data you can use directly in your UI. ## Quick start To use structured outputs, define a [JSON Schema](https://json-schema.org/understanding-json-schema/about) describing the s… Subagents in the SDK Claude Code CLI · in the page agent-sdk/subagents …ontext isolation**: each subagent runs in its own conversation, which starts fresh unless the subagent is a [fork](/docs/en/sub-agents.md#fork-the-current-conversation). Either way, intermediate tool… Track todos Claude Code CLI · in the page agent-sdk/todo-tracking …task 2. **Activated**: Claude sets the todo to `in_progress` when it starts the work 3. **Completed**: Claude marks it completed when the task finishes successfully 4. **Removed**: Claude deletes a t… Troubleshoot the Agent SDK Claude Code CLI · in the page agent-sdk/troubleshooting …e Agent SDK > Fix Agent SDK errors when the Claude Code CLI fails to start, the CLI process exits, or a successful result arrives without structured output. This page covers Agent SDK errors in CLI… Agent SDK reference - TypeScript Claude Code CLI · in the page agent-sdk/typescript …bed the platform binary as a file asset, extract it to a real path at startup with `extractFromBunfs()`, and pass that path to [`pathToClaudeCodeExecutable`](#options). The `extractFromBunfs()` helpe… TypeScript SDK V2 session API (removed) Claude Code CLI · in the page agent-sdk/typescript-v2-preview …and streaming the response: * `createSession()` / `resumeSession()`: Start or continue a conversation * `session.send()`: Send a message * `session.stream()`: Get the response ## Installation Agent… Orchestrate teams of Claude Code sessions Claude Code CLI · in the page agent-teams …) or environment. Without that variable, no team is set up at session start, no team directories are written, and Claude does not spawn or propose teammates. Agent teams have [known limitations](#limi… Manage multiple agents with agent view Claude Code CLI · in the page agent-view …ns sessions on your machine and you dispatch each one; to have Claude start and track parallel sessions in the cloud from one conversation instead, see [Projects](/docs/en/claude-projects.md). > [!NO… Run agents in parallel Claude Code CLI · in the page agents …ongoing conversation at claude.ai/code or in the desktop app. Claude starts parallel sessions called threads, in the cloud or, when you ask, on your computer through Remote Control, gives each one th… Claude Code on Amazon Bedrock Claude Code CLI · in the page amazon-bedrock …ut. ## Sign in with Bedrock If you have AWS credentials and want to start using Claude Code through Amazon Bedrock, the login wizard walks you through it. You complete the AWS-side prerequisites onc… Track team usage with analytics Claude Code CLI · in the page analytics …tify adoption patterns, and find team members who can help others get started. #### Monitor adoption Track the Adoption chart and user counts to identify: * Active users who can share best practice… Share session output as artifacts Claude Code CLI · in the page artifacts …d scheduled task](/docs/en/scheduled-tasks.md) firing in your session started, rather than a prompt you typed | Asks before the first publish of each artifact | | Claude can't read the file without yo… Authentication Claude Code CLI · in the page authentication …accounts, give each account its own configuration directory. When you start `claude`, set the [`CLAUDE_CONFIG_DIR`](/docs/en/env-vars#variables) environment variable to the directory for the account y… Auto mode classifier request charges Claude Code CLI · in the page auto-mode-classifier-billing …hem there by setting `CLAUDE_CODE_AUTO_MODE_SERVER` to `0` before you start the session, in your shell or in the [`env` settings key](/docs/en/settings-reference#env): ```bash theme={null} export CLA…