1,488 pages for read.
Titles and paths first, then pages whose text carries it. Each row opens that page as this site last read it.
kubernetes
Claude Developer Platform · in the page
manage-claude/wif-providers/kubernetes
…espace>:<service-account>`. You can find your cluster's issuer URL by reading its discovery document: ```bash cURL kubectl get --raw /.well-known/openid-configuration | jq -r .issuer ``` <Note> Th…
okta
Claude Developer Platform · in the page
manage-claude/wif-providers/okta
…ur Okta custom authorization server URL and discovery mode. Anthropic reads Okta's `.well-known/openid-configuration` discovery document and fetches the JWKS from the `jwks_uri` it advertises. ```jso…
Replace NODE_UID with the node's UID:
Claude Developer Platform · in the page
manage-claude/wif-providers/spiffe
…s://github.com/spiffe/spire/blob/main/support/oidc-discovery-provider/README.md), a standalone helper that publishes `/.well-known/openid-configuration` and a JWKS endpoint for the trust domain's JWT…
wif-reference
Claude Developer Platform · in the page
manage-claude/wif-reference
…| ## Environment variables The SDK reads these variables to perform a federated token exchange with no constructor arguments. | Variable | Re…
workload-identity-federation
Claude Developer Platform · in the page
manage-claude/workload-identity-federation
…-...` API keys. The tokens come from an identity provider (IdP) you already operate: AWS IAM, Google Cloud, or any standards-compliant OIDC issuer such as GitHub Actions, Kubernetes, SPIFFE, Microsoft…
workspaces
Claude Developer Platform · in the page
manage-claude/workspaces
…he following SDK and CLI examples construct the default client, which reads the Admin API key from the `ANTHROPIC_API_KEY` environment variable; the SDK exposes these endpoints under `client.organizat…
agent-setup
Claude Developer Platform · in the page
managed-agents/agent-setup
…| Required. A human-readable name for the agent.…
budgets
Claude Developer Platform · in the page
managed-agents/budgets
…re whole cents, rounded to the nearest cent, so a reported figure can read up to half a cent either side of the exact amount enforcement uses. ## When a session reaches its budget The cap is enforce…
choosing-an-environment
Claude Developer Platform · in the page
managed-agents/choosing-an-environment
…ged infrastructure, with common languages, databases, and utilities already installed. You choose its network rules and any extra packages to install. * **Self-hosted sandbox:** You run the sandbox on…
DCF Model Rubric
Claude Developer Platform · in the page
managed-agents/define-outcomes
…{rubric.id}") ``` ```typescript TypeScript import { writeFile, readFile } from "node:fs/promises"; import Anthropic from "@anthropic-ai/sdk"; import { toFile } from "@anthropic-ai/sdk";…
dreams
Claude Developer Platform · in the page
managed-agents/dreams
…ons, and stale entries. **Dreams** let Claude clean that up. A dream reads an existing memory store alongside past session transcripts, then produces a new, reorganized memory store: duplicates merge…
environments
Claude Developer Platform · in the page
managed-agents/environments
…ork access, except for a general safety blocklist. Before you use it, read [Risks of unrestricted networking](https://platform.claude.com/docs/en/managed-agents/environments#risks-of-unrestricted-netw…
event-deltas
Claude Developer Platform · in the page
managed-agents/event-deltas
…ection. Add the `event_deltas[]` query parameter to the stream you're reading, and repeat it once for each event type you want previewed. The accepted values are `agent.message` and `agent.thinking`.…
events-and-streaming
Claude Developer Platform · in the page
managed-agents/events-and-streaming
…"content": [{"type": "text", "text": "Summarize the repo README"}], }, ], ) for event in stream: match event.type: case "agent…
files
Claude Developer Platform · in the page
managed-agents/files
…ts/files description: Upload files and mount them in your sandbox for reading and processing. featureMetadata: topic: title: Managed Agents url: https://platform.claude.com/docs/en/managed-a…
github
Claude Developer Platform · in the page
managed-agents/github
…b description: Connect your agent to GitHub repositories for cloning, reading, and creating pull requests. featureMetadata: topic: title: Managed Agents url: https://platform.claude.com/docs…
mcp-connector
Claude Developer Platform · in the page
managed-agents/mcp-connector
…ox. The model receives a truncated preview with the file path and can read the full content from there. ## Provide authentication at session creation When starting a session, pass `vault_ids` (java:…
memory
Claude Developer Platform · in the page
managed-agents/memory
…it is mounted as a directory inside the session's sandbox. The agent reads and writes it with the same file tools it uses for the rest of the filesystem, and a note describing each mount is automatic…
migration
Claude Developer Platform · in the page
managed-agents/migration
…nt SDK](https://code.claude.com/docs/en/agent-sdk/overview), you're already working with agents, tools, and sessions as concepts. The difference is where they run: the SDK runs in a process you operat…
multiagent-orchestration
Claude Developer Platform · in the page
managed-agents/multiagent-orchestration
…agents in two ways. With **subagents**, it delegates tasks itself and reads what each subagent reports. With **dynamic workflows**, it writes a workflow: a program that runs many agents in the backgro…
overview
Claude Developer Platform · in the page
managed-agents/overview
…on, and runtime, you get a fully managed environment where Claude can read files, run commands, browse the web, and run code securely. The harness supports built-in prompt caching, compaction, and oth…
permission-policies
Claude Developer Platform · in the page
managed-agents/permission-policies
…e server to allow a call it would otherwise deny. The server does not read intent from a tool result, a fetched webpage, an MCP server's response, or a message between [session threads](https://platfo…
quickstart
Claude Developer Platform · in the page
managed-agents/quickstart
…placed in `$(go env GOPATH)/bin`. Add it to your `PATH` if it isn't already: ```bash export PATH="$PATH:$(go env GOPATH)/bin" ``` </Tab> </Tabs> Check the installation: ```bash ant --…
reference
Claude Developer Platform · in the page
managed-agents/reference
…| | `agent.thread_context_compacted` | Conversation history was compacted to fit the context window.…
scheduled-deployments
Claude Developer Platform · in the page
managed-agents/scheduled-deployments
…he deployment's budget applies to runs started afterward; a session already running keeps the cap it started with, which you can [change through the session itself](https://platform.claude.com/docs/en…
secure-deployment
Claude Developer Platform · in the page
managed-agents/secure-deployment
…uto` on `bash`, `write`, `edit`, `web_fetch`, and MCP tools that only read data. `always_ask` instead on a tool if you cannot undo its changes outside the sandbox, or if relayed end-user text alone sh…
secure-deployment-monitoring
Claude Developer Platform · in the page
managed-agents/secure-deployment-monitoring
…ed-agents/secure-deployment). ## Optionally have an offline reviewer read every transcript An offline reviewer is a job you run, separate from the sessions it reviews, that reads each session's even…
secure-deployment-risks
Claude Developer Platform · in the page
managed-agents/secure-deployment-risks
…o. ## Why this matters Hidden instructions in content that an agent reads can steer the agent. This is called [prompt injection](https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guar…
spawn.sh: called once per claimed work item
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes
…ronment. Tool execution stays on your host: the filesystem the agent reads and writes, the processes it spawns, and the network it can reach are all under your control. Tool inputs and outputs still…
self-hosted-sandboxes-custom-tools
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-custom-tools
…async with ( streamable_http_client(MCP_SERVER_URL) as (read, write, _), ClientSession(read, write) as mcp_session, AsyncAnthropic() as client, ):…
self-hosted-sandboxes-memory
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-memory
…n self-hosted sandboxes: prepare the host, configure sync, and handle read-only stores and conflicts." featureMetadata: topic: title: Managed Agents url: https://platform.claude.com/docs/en/…
self-hosted-sandboxes-operations
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-operations
…/docs/en/managed-agents/self-hosted-sandboxes-operations description: Read queue depth, stop sessions and workers without losing work, and fix common self-hosted sandbox failures. featureMetadata: t…
self-hosted-sandboxes-reference
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-reference
…---- | | `--environment-id` | The environment to poll for work. Also reads from `ANTHROPIC_ENVIRONMENT_ID`.…
self-hosted-sandboxes-security
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-security
…necessary Linux capabilities, running as a non-root user, and using a read-only root filesystem. * **Network egress controls.** Your sandbox's network access is determined by your VPC and firewall rul…
self-hosted-sandboxes-workers
Claude Developer Platform · in the page
managed-agents/self-hosted-sandboxes-workers
…ndle(w http.ResponseWriter, r *http.Request) { body, err := io.ReadAll(r.Body) if err != nil { http.Error(w, "bad request", http.StatusBadRequest) return }…
session-observability
Claude Developer Platform · in the page
managed-agents/session-observability
…n-observability description: Inspect a session in the Claude Console, read its token usage and list cost, and debug unexpected agent behavior. featureMetadata: topic: title: Managed Agents u…
session-operations
Claude Developer Platform · in the page
managed-agents/session-operations
…agents-2026-04-01 --- Once a session exists, use these operations to read, update, archive, or delete it. See [Start a session](https://platform.claude.com/docs/en/managed-agents/sessions) for creati…
sessions
Claude Developer Platform · in the page
managed-agents/sessions
…], ) # initial_events are not echoed on the create response; read them back # from the session's event list. for event in client.beta.sessions.events.list(seeded_session.id): if eve…
skills
Claude Developer Platform · in the page
managed-agents/skills
…rence when attaching it to an agent. Anthropic pre-built skills are already available in every workspace and don't require this step. To use only pre-built skills, skip to [Attach skills to an agent](…
tools
Claude Developer Platform · in the page
managed-agents/tools
…h` | Run bash commands in a shell session | | Read | `read` | Read a file from the sandbox filesystem | | Write | `write` | Write a file to…
tools-web-restrictions
Claude Developer Platform · in the page
managed-agents/tools-web-restrictions
…ents/multiagent-orchestration), every domain list that applies to a thread is enforced at the same time. An agent listed in the `predefined_agents` (java, php: `predefinedAgents`; csharp, go: `Predefi…
vaults
Claude Developer Platform · in the page
managed-agents/vaults
…"client_id": "1234567890.0987654321", "scope": "channels:read chat:write", "refresh_token": "xoxe-1-...", "token_endpoint_auth": {"type": "client_secret_post", "cl…
webhooks
Claude Developer Platform · in the page
managed-agents/webhooks
…| | `session.thread_created` | New [multiagent thread](https://platform.claude.com/docs/en/managed-agents/session-threads) opened: an a…
workflow-runs
Claude Developer Platform · in the page
managed-agents/workflow-runs
…rver runs a workflow in the background. Its agents work in [session threads](https://platform.claude.com/docs/en/managed-agents/session-threads) that the server creates as the workflow needs them. You…
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
…cceeds Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost. It's available on the Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-…
overview
Claude Developer Platform · in the page
models/fable-5-1/overview
…xtends Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, and brings stronger long-running agentic coding, multistep research, and document, spreadsheet, an…
whats-new-fable-5-1
Claude Developer Platform · in the page
models/fable-5-1/whats-new-fable-5-1
…xtends Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, and brings stronger long-running agentic coding, multistep research, and document, spreadsheet, an…
overview
Claude Developer Platform · in the page
models/fable-5/overview
…ce per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.…
overview
Claude Developer Platform · in the page
models/haiku-4-5/overview
…ce per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.…
migration-guide
Claude Developer Platform · in the page
models/haiku-5-5/migration-guide
…models/haiku-5-5/migration-guide#configure-thinking). 4. If your code reads the first content block as the answer, select blocks by `type` instead. See [Configure thinking](https://platform.claude.com…