757 pages for task.

compaction-threshold Claude Developer Platform · in the page build-with-claude/compaction-threshold …tends the effective context length for long-running conversations and tasks by automatically summarizing older context when approaching the context window limit. It also keeps the active context small… context-editing Claude Developer Platform · in the page build-with-claude/context-editing …that summary. This allows Claude to continue working on long-running tasks that would otherwise exceed the [context window](https://platform.claude.com/docs/en/build-with-claude/context-windows). ##… context-windows Claude Developer Platform · in the page build-with-claude/context-windows …") throughout a conversation. This lets the model manage long-running tasks against the space that remains rather than guess how many tokens are left. Context awareness is automatic: there is nothing… effort Claude Developer Platform · in the page build-with-claude/effort …nnet 5.5, Claude Sonnet 5, Claude Sonnet 4.6, and Claude Haiku 5.5. | Tasks requiring the deepest possible reasoning and most thorough analysis | | `xhigh` | Extended capability for… This will automatically use the environment variable VOYAGE_API_KEY. Claude Developer Platform · in the page build-with-claude/embeddings …s embeddings, their applications, and how to use embedding models for tasks such as search, recommendations, and anomaly detection. --- ## Before implementing embeddings When selecting an embeddings… extended-thinking Claude Developer Platform · in the page build-with-claude/extended-thinking …a target rather than a strict cap. Actual token usage varies with the task, and Claude might stop reasoning well before the budget is exhausted; `max_tokens` remains the hard ceiling on total output.… fast-mode Claude Developer Platform · in the page build-with-claude/fast-mode …); ``` ```csharp C# AnthropicClient client = new(); async Task<Message> CreateMessageWithFastFallback( MessageCreateParams parameters, int? maxRetries = null, int maxAtte… files Claude Developer Platform · in the page build-with-claude/files …mage/gif`, `image/webp` | `image` | Image analysis, visual tasks | | Datasets, others (see [Upload and analyze your own files](https://platform.claude.com/docs/en/agents-and-tools/too… handling-stop-reasons Claude Developer Platform · in the page build-with-claude/handling-stop-reasons …return response; } ``` ```csharp C# static async Task<Message> HandleEmptyResponse(AnthropicClient client, List<MessageParam> messages) { var response = await client.M… mid-conversation-effort-example Claude Developer Platform · in the page build-with-claude/mid-conversation-effort-example …s maximum thoroughness behind every substantive request, scouting the task itself and then fanning work out to parallel subagents by default. When it is off, the same orchestration tool goes back to p… mid-conversation-system-messages Claude Developer Platform · in the page build-with-claude/mid-conversation-system-messages …pt-engineering/prompting-claude-sonnet-5-5#mid-turn-user-messages-and-task-budgets) and [Prompting Claude Haiku 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-… multilingual-support Claude Developer Platform · in the page build-with-claude/multilingual-support …/build-with-claude/multilingual-support description: Claude excels at tasks across multiple languages, maintaining strong cross-lingual performance relative to English. --- ## Overview Claude demons… overview Claude Developer Platform · in the page build-with-claude/overview …| Enhanced reasoning capabilities for complex tasks, with an optional summary of Claude's reasoning before its final answer.… pdf-support Claude Developer Platform · in the page build-with-claude/pdf-support …ude.com/docs/en/build-with-claude/vision#limitations) as other vision tasks. ### Supported platforms and models All [active models](https://platform.claude.com/docs/en/models/overview) support PDF p… preserved-thinking Claude Developer Platform · in the page build-with-claude/preserved-thinking …it generates more output tokens. Output quality might also change on tasks where later turns build on earlier reasoning. Use `"drop_block"` as a stopgap while you fix the edit, but not as a long-term… Request 2 caches its request content (not the response) Claude Developer Platform · in the page build-with-claude/prompt-caching …. This significantly reduces processing time and costs for repetitive tasks or prompts with consistent elements. <Note> To learn how zero data retention (ZDR) applies to this feature, see [API and… claude-prompting-best-practices Claude Developer Platform · in the page build-with-claude/prompt-engineering/claude-prompting-best-practices …1) | Differences from Claude Fable 5: effort levels, finishing long tasks, user-facing progress updates, passing thinking blocks back unchanged, tool-call batching in agent loops, search triggering… prompting-claude-fable-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5 …s capability range. It also performs reliably on more straightforward tasks. Claude Fable 5 has several behavioral differences from Claude Opus 4.8 that might require prompt or scaffolding updates. C… Delivering work Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5-1 …tool-call batching, conversation history, writing style, formatting, task completion, compaction summaries, scope and test coverage, search triggering, safeguard false positives, file edits, long out… prompting-claude-haiku-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-haiku-5-5 …g agent prompt, the model stops before the work is done and hands the task back: [Prevent early stopping in long agent prompts](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering… prompting-claude-opus-4-8 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-4-8 …gths in long-horizon agentic work, knowledge work, vision, and memory tasks. It performs well out of the box on existing Claude Opus 4.7 prompts. The following patterns cover the behaviors that most o… prompting-claude-opus-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5 …ns for Claude Opus 5, covering response verbosity, agentic narration, task scoping, subagent delegation, self-correction, and output artifacts when thinking is disabled. --- This guide covers the pro… prompting-claude-opus-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5-5 …PI integrations and chat, progress updates, unattended and multiagent tasks, safeguard refusals, frontend design, complex visual inputs, multiapp workflows, and pasted text in user messages." --- Thi… prompting-claude-sonnet-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5 …ces). Claude Sonnet 5 has particular strengths in coding and agentic tasks. It performs well out of the box on existing Claude Sonnet 4.6 prompts. The patterns in this guide cover the behaviors that… prompting-claude-sonnet-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5 …t-5-5#calibrate-effort) * The model stops to check in before a coding task is done, or does more than you asked: [Steer initiative and scope](https://platform.claude.com/docs/en/build-with-claude/prom… skills-guide Claude Developer Platform · in the page build-with-claude/skills-guide …Best practices ### When to use multiple Skills Combine Skills when tasks involve multiple document types or domains: **Good use cases:** * Data analysis (Excel) + presentation creation (PowerPoin… thinking Claude Developer Platform · in the page build-with-claude/thinking …pproach halfway through. For a proof, a tricky bug, or a long agentic task, the first approach is often not the best one. Thinking removes that constraint. When thinking is active, Claude works throu… thinking-steering-and-cost Claude Developer Platform · in the page build-with-claude/thinking-steering-and-cost …thinking block at all; a multistep math problem or a tricky debugging task triggers deeper reasoning. This determination occurs for each request. The same conversation can contain turns with and with… token-counting Claude Developer Platform · in the page build-with-claude/token-counting …onse); ``` ```csharp C# using System; using System.Threading.Tasks; using Anthropic; using Anthropic.Models.Messages; AnthropicClient client = new(); var parameters = new MessageCou… vision Claude Developer Platform · in the page build-with-claude/vision …lt to read. Confirm your compression settings are appropriate for the task by inspecting the actual images sent to the API. *** ## Coordinates and bounding boxes For bounding boxes, points, and pix… vision-coordinates Claude Developer Platform · in the page build-with-claude/vision-coordinates …pelines, form extraction, chart parsing, UI element location, and any task where you act on a specific region of an image. For sending images, supported formats, and per-model resolution limits, see [… working-with-messages Claude Developer Platform · in the page build-with-claude/working-with-messages …for** | Custom agent loops and fine-grained control | Long-running tasks and asynchronous work | This guide covers common patterns for working with the Messages AP… API usage primer for Claude Claude Developer Platform · in the page claude_api_primer …de-opus-5-5 Step up for the hardest long-running agentic and research tasks, at 2.5x Claude Opus 5.5 pricing: Claude Fable 5.1: claude-fable-5-1 Previous Opus model: Claude Opus 5: claude-opus-5 Smart… scripting Claude Developer Platform · in the page cli-sdks-libraries/cli/scripting …d authenticate curl calls with CLI credentials. --- This page covers task-oriented workflows built on the `ant` CLI. For the underlying flags and output options, see [Using the CLI](https://platform.… apple-foundation-models Claude Developer Platform · in the page cli-sdks-libraries/libraries/apple-foundation-models …fast, private, and available offline, but it is sized for lightweight tasks. Escalate to Claude when you need larger context, frontier reasoning, or server-side tools such as web search and code execu… openai-sdk Claude Developer Platform · in the page cli-sdks-libraries/libraries/openai-sdk …egacy mode. Although thinking improves Claude's reasoning for complex tasks, the OpenAI SDK doesn't return Claude's thinking. For full thinking features, including [summarized thinking](https://platfo… overview Claude Developer Platform · in the page cli-sdks-libraries/overview ….com/docs/en/overview"> Agentic coding tool for delegating coding tasks to Claude </Card> <Card title="Claude Agent SDK" href="https://code.claude.com/docs/en/agent-sdk/overview"> Build a… csharp Claude Developer Platform · in the page cli-sdks-libraries/sdks/csharp …an instance of `MessageCreateParams`, and it returns an instance of `Task<Message>`. ## Advanced usage ### Binary responses The SDK defines methods that return binary responses, which are used for… home Claude Developer Platform · in the page home …and long-horizon agentic work* — Most capable · Research · Multi-day tasks * [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) (`claude-opus-5-5`) — New — *For long-… intro Claude Developer Platform · in the page intro …thy, and intelligent AI platform built by Anthropic. Claude excels at tasks involving language, reasoning, analysis, coding, and more. --- <Note> Looking to chat with Claude? Visit [claude.ai](http… compliance-faq Claude Developer Platform · in the page manage-claude/compliance-faq …endpoints return Cowork sessions only. Each run of a Cowork scheduled task in the cloud is a remote session: the remote session list endpoint returns it as an [agent-owned session](https://platform.cl… compliance-sessions Claude Developer Platform · in the page manage-claude/compliance-sessions …l`. For agent-owned sessions (for example, runs of a Cowork scheduled task in the cloud), `user` is `null`, `agent_id` carries the agent's ID (prefix `cagt_`), and `started_by_user` identifies the hum… inference-hooks Claude Developer Platform · in the page manage-claude/inference-hooks …he content is in a file or an earlier message, the user selects **New task**. * **Claude Tag.** In Slack, the user first edits the denied message, or deletes it if it is a reply. They then send `@Clau… inference-hooks-endpoint Claude Developer Platform · in the page manage-claude/inference-hooks-endpoint …} }); server.setExecutor(Executors.newVirtualThreadPerTaskExecutor()); server.start(); } ``` ```php PHP <?php // Run with: php -S 0.0.0.0:8000 server.php // Drain t… organization-webhooks Claude Developer Platform · in the page manage-claude/organization-webhooks …Manage endpoints With the Admin API, you can make these requests: | Task | Request… plugins-api Claude Developer Platform · in the page manage-claude/plugins-api …---- | | Skill | Instructions and files that Claude loads when a task calls for it. | | Command | A saved prompt a member runs by typing `/` followed by th… aws Claude Developer Platform · in the page manage-claude/wif-providers/aws …ration issuers, and federation rules. * An AWS workload (EKS pod, ECS task, Lambda function, or EC2 instance) with an attached IAM role. * The `aws` CLI or an AWS SDK available in the workload. * Perm… Create the app registration that represents the Claude API audience. Claude Developer Platform · in the page manage-claude/wif-providers/azure …te static readonly HttpClient httpClient = new(); public async Task<string> GetIdentityTokenAsync(CancellationToken ct = default) { // App Service, Functions, and Container Apps… gcp Claude Developer Platform · in the page manage-claude/wif-providers/gcp …s = { { "Metadata-Flavor", "Google" } }, }; public async Task<string> GetIdentityTokenAsync(CancellationToken ct = default) { return await httpClient.GetStringAsync(METADA… kubernetes Claude Developer Platform · in the page manage-claude/wif-providers/kubernetes …through [projected service account tokens](https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/#serviceaccount-token-volume-projection). The cluster's API server acts as…