174 pages for extract.

whats-new-sonnet-5-5 Claude Developer Platform · in the page models/sonnet-5-5/whats-new-sonnet-5-5 …t could help with the development of competing AI models. `"reasoning_extraction"` means it asks the model to reproduce its internal reasoning in the response text. `"general_harms"` means it falls un… overview Claude Developer Platform · in the page release-notes/overview …`stop_details.category` is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`, the categories where we measure low volumes of false positives. Mid-stream refusals were already billed. Refusals bi… develop-tests Claude Developer Platform · in the page test-and-evaluate/develop-tests …eCosineSimilarity(outputs: string[]): Promise<number> { const extractor = await pipeline("feature-extraction", "Xenova/all-MiniLM-L6-v2"); const embeddings = (await extractor(outputs,… mitigate-jailbreaks Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks …t is the body of an inbound email from an unknown sender, or OCR text extracted from a user-uploaded image. This context helps Claude calibrate how much to trust embedded directives. * **State the po… reduce-hallucinations Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/reduce-hallucinations …ng:** For tasks involving long documents (>20k tokens), ask Claude to extract word-for-word quotes first before performing its task. This grounds its responses in the actual text, reducing hallucinati… Intercept and control agent behavior with hooks Claude Code CLI · in the page agent-sdk/hooks …async def protect_env_files(input_data, tool_use_id, context): # Extract the file path from the tool's input arguments file_path = input_data["tool_input"].get("file_path", "") file_name… Hosting the Agent SDK Claude Code CLI · in the page agent-sdk/hosting …mple workloads include bug investigation and fix, invoice and receipt extraction, document translation, and media transformation. The container runs a one-shot entrypoint that reads the task from the… Agent SDK reference - Python Claude Code CLI · in the page agent-sdk/python …: int, # File size in bytes "count": int, # Number of pages extracted as images "outputDir": str, # Directory containing the extracted page images }, "firstPage": int | None… Stream responses in real-time Claude Code CLI · in the page agent-sdk/streaming-output …tinguish `StreamEvent` from other message types 2. For `StreamEvent`, extract the `event` field and check its `type` 3. Look for `content_block_delta` events where `delta.type` is `text_delta`, which… Get structured output from agents Claude Code CLI · in the page agent-sdk/structured-outputs …from "@anthropic-ai/claude-agent-sdk"; // Define structure for TODO extraction const todoSchema = { type: "object", properties: { todos: { type: "array", items: { type: "… Subagents in the SDK Claude Code CLI · in the page agent-sdk/subagents …o resume a subagent programmatically: 1. **Capture the session ID**: extract `session_id` from messages during the first query 2. **Extract the agent ID**: parse `agentId` from the Agent tool result… Agent SDK reference - TypeScript Claude Code CLI · in the page agent-sdk/typescript …nd`. To work around this, embed the platform binary as a file asset, extract it to a real path at startup with `extractFromBunfs()`, and pass that path to [`pathToClaudeCodeExecutable`](#options). T… TypeScript SDK V2 session API (removed) Claude Code CLI · in the page agent-sdk/typescript-v2-preview …ype SDKMessage } from "@anthropic-ai/claude-agent-sdk"; // Helper to extract text from assistant messages function getAssistantText(msg: SDKMessage): string | null { if (msg.type !== "assistant") r… Track team usage with analytics Claude Code CLI · in the page analytics …tribution process When a pull request is merged: 1. Added lines are extracted from the PR diff 2. Claude Code sessions that edited matching files within a time window are identified 3. PR lines are… Use Claude Code with Chrome Claude Code CLI · in the page chrome …to test web apps, debug with console logs, automate form filling, and extract data from web pages. Claude Code integrates with the [Claude in Chrome browser extension](https://chromewebstore.google.c… Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry Claude Code CLI · in the page claude-apps-gateway …. All structured-masking fields are dropped too, so a parent-supplied extract pattern can't displace a stricter mask another source sets for the same path. * **`envVars` entries with `mode: mask`**: n… Error reference Claude Code CLI · in the page errors …y-measures-flagged-a-cybersecurity-topic) | | `` Details: `[reasoning_extraction]` `` | [Request errors](#safeguards-flagged-a-request-for-claudes-reasoning) | | `API Error: Output blocked by content… Run Claude Code programmatically Claude Code CLI · in the page headless …the structured output in the `structured_output` field. This example extracts function names and returns them as an array of strings: ```bash theme={null} claude -p "Extract the main function names… Hooks reference Claude Code CLI · in the page hooks …} ] } } ``` The script reads the JSON input from stdin, extracts the command, and returns a `permissionDecision` of `"deny"` if it contains `rm -rf`. Save it to `.claude/hooks/block-rm.s… Automate actions with hooks Claude Code CLI · in the page hooks-guide …Write` matcher, so it runs only after file-editing tools. The command extracts the edited file path with [`jq`](https://jqlang.org/) and passes it to Prettier. Add this to `.claude/settings.json` in y… Monitoring Claude Code CLI · in the page monitoring-usage …ils.category` of `"cyber"`, `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`. `false` when the response carried no category or a value outside that set. Absent when `server_fallback_hop` is `tru… Host and maintain a marketplace Claude Code CLI · in the page plugins/host-marketplace …rchive downloads, the install fails when the zip exceeds any of these extraction limits: * **Entries**: 100,000 files and directories * **File size**: 512 MiB for any one file, uncompressed * **Total… Plugin loading reference Claude Code CLI · in the page plugins/loading …never copied. A `--plugin-url` archive or a `--plugin-dir` `.zip` is extracted into a session temp directory first * **Relative-path plugins in a marketplace you added from a local path**: the plugin… Plugin manifest reference Claude Code CLI · in the page plugins/manifest-reference …file as an `mcpServers` map | | MCP bundle path | `"./bundle.mcpb"` | Extracts the `.mcpb` or `.dxt` bundle into `.mcpb-cache/` under the plugin root and reads its server config | | MCP bundle URL | `… Marketplace reference Claude Code CLI · in the page plugins/marketplace-reference …k-local, or cloud-metadata host. For the size, timeout, redirect, and extraction limits on the download, see [Stay within the download limits for hosted files](/docs/en/plugins/host-marketplace.md#sta… Configure the sandboxed Bash tool Claude Code CLI · in the page sandboxing …cture, such as a `DATABASE_URL` connection string or a JWT, use the [`extract`, `decode`, `maskClaims`, and `onExtractNoMatch` fields](/docs/en/settings-reference#sandbox-credentials-envvars) so tools… Customize sessions in self-hosted environments Claude Code CLI · in the page self-hosted-environments-configuration …). | | `CCR_SESSION_ACCOUNT_EMAIL` | The session creator's email, pre-extracted by the runner from the token's `act.email` claim without signature verification. Suitable for labelling, such as commit… Verify session identity in self-hosted environments Claude Code CLI · in the page self-hosted-environments-identity …them from the printed JSON and compare them explicitly. This command extracts the creator identity, preferring the email address, then the creator's `act.sub` subject, `user:<id>` or `agent:<id>`: `… Claude Code settings Claude Code CLI · in the page settings …`path` or `name` and a `mode` of `mask` or `deny`, such as one whose `extract` pattern has no capturing group, is degraded to `mode: "deny"` with a warning, so the credential stays blocked, not masked… All settings Claude Code CLI · in the page settings-reference …`path` or `name` and a `mode` of `mask` or `deny`, such as one whose `extract` pattern has no capturing group, is degraded to `mode: "deny"` with a warning, so the credential stays blocked, not masked… Customize your status line Claude Code CLI · in the page statusline …/jqlang.org/), a command-line JSON parser you may need to install, to extract the model name, directory, and context percentage, then prints a formatted line. Save this to `~/.claude/statusline.sh` (… Create custom subagents Claude Code CLI · in the page sub-agents …t) via stdin to hook commands. The validation script reads this JSON, extracts the Bash command, and [exits with code 2](/docs/en/hooks.md#exit-code-2-behavior-per-event) to block write operations: `… Tools reference Claude Code CLI · in the page tools-reference …h tool behavior WebFetch takes a URL and a prompt describing what to extract. It fetches the page and converts the response to Markdown when the server returns HTML. For most fetches, it then runs th… Week 32 · August 3–7, 2026 Claude Code CLI · in the page whats-new/2026-w32 …substitutes the real value on egress; credential masking also gains `extract`, JWT-aware `decode`, and AWS SigV4 re-signing optionsMarketplaces can distribute a plugin as a [zip archive](/docs/en/plu… Lazy authentication for MCP servers Claude Documentation · in the page connectors/building/lazy-authentication …McpPost(req: Request, res: Response): Promise<void> { const token = extractBearer(req); const authed = isTokenValid(token); // The gate. initialize, tools/list, and public tool calls fall throu… Identity and access Claude Documentation · in the page government/tenant-admin/identity-and-access …a URL. Once SAML is active, the card shows the Entity ID and SSO URL extracted from your metadata so you can confirm the connection is pointing where you expect. ### Attribute mapping (advanced) Bo… Use Claude for Excel Claude Documentation · in the page office-agents/excel …ces can contain hidden instructions that manipulate the add-in into > extracting data, modifying records, or performing destructive actions. External files such as downloaded templates, vendor files,… Use Claude for PowerPoint Claude Documentation · in the page office-agents/powerpoint …ces can contain hidden instructions that manipulate the add-in into > extracting data, modifying records, or performing destructive actions. External files such as downloaded templates, vendor files,… Use Claude for Word Claude Documentation · in the page office-agents/word …ail can contain hidden instructions that manipulate the > add-in into extracting data, modifying records, or performing > destructive actions. Prompt injection attacks hide malicious instructions in… Create custom skills Claude Documentation · in the page skills/how-to …s common tasks, and a `scripts/` folder Claude runs to fill forms and extract tables, the pattern from [Add scripts](#add-scripts) * **[skill-creator](https://github.com/anthropics/skills/tree/main/sk… Web search and web fetch Claude Documentation · in the page third-party/claude-desktop/web-tools …`headersHelper` is the same key on every device, and a local user can extract it. The exposure is limited to billing abuse on that key (it grants no data access). For regulated environments, set spend… Build an MCP client Model Context Protocol · in the page docs/2024-11-05/develop/build-client ….call_tool` * Uses `chat` helper method to wrap Anthropic API calls * Extracts tool result content with `result.dig("result", "content")` * Passes tool results back to Claude for a final response ###… Client Best Practices Model Context Protocol · in the page docs/2024-11-05/develop/clients/client-best-practices …`any` or `string` and handle the unstructured output downstream. * **Extract a typed result using a fast model**, for single-shot calls outside loops. Expose a host-brokered `extract(value, ExpectedT… Security Best Practices Model Context Protocol · in the page docs/2024-11-05/tutorials/security/security_best_practices …:) Client->>Client: Execute JavaScript (XSS) Client->>Client: Extract proxy auth token Client->>Proxy: Malicious stdio command request Note over Client,Proxy: Using stolen authenticati… Build an MCP client Model Context Protocol · in the page docs/2025-03-26/develop/build-client ….call_tool` * Uses `chat` helper method to wrap Anthropic API calls * Extracts tool result content with `result.dig("result", "content")` * Passes tool results back to Claude for a final response ###… Client Best Practices Model Context Protocol · in the page docs/2025-03-26/develop/clients/client-best-practices …`any` or `string` and handle the unstructured output downstream. * **Extract a typed result using a fast model**, for single-shot calls outside loops. Expose a host-brokered `extract(value, ExpectedT… Security Best Practices Model Context Protocol · in the page docs/2025-03-26/tutorials/security/security_best_practices …:) Client->>Client: Execute JavaScript (XSS) Client->>Client: Extract proxy auth token Client->>Proxy: Malicious stdio command request Note over Client,Proxy: Using stolen authenticati… Build an MCP client Model Context Protocol · in the page docs/2025-06-18/develop/build-client ….call_tool` * Uses `chat` helper method to wrap Anthropic API calls * Extracts tool result content with `result.dig("result", "content")` * Passes tool results back to Claude for a final response ###… Client Best Practices Model Context Protocol · in the page docs/2025-06-18/develop/clients/client-best-practices …am. The real fix is for server authors to provide `outputSchema`. * **Extract a typed result using a fast model**, for single-shot calls outside loops. Expose a host-brokered `extract(value, ExpectedT… Security Best Practices Model Context Protocol · in the page docs/2025-06-18/tutorials/security/security_best_practices …:) Client->>Client: Execute JavaScript (XSS) Client->>Client: Extract proxy auth token Client->>Proxy: Malicious stdio command request Note over Client,Proxy: Using stolen authenticati…