What this read moved
26–49 of 49This capture is too large to show at once. Changes 26-49 of 49 are below, significant first; the rest are on the following screens.
managed-agents/github Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Accessing GitHub
33url: https://platform.claude.com/docs/en/managed-agents/github
44description: Connect your agent to GitHub repositories for cloning, reading, and creating pull requests.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113You can mount a GitHub repository to your session sandbox and connect to the GitHub MCP for making pull requests.
1214
managed-agents/mcp-connector Changed · +6 / -4 lines
## Compatibility
from line 2
22title: MCP connector
33url: https://platform.claude.com/docs/en/managed-agents/mcp-connector
44description: Connect MCP servers to your agents for access to external tools and data sources.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113Claude Managed Agents supports connecting [Model Context Protocol (MCP)](https://modelcontextprotocol.io) servers to your agents. This gives the agent access to external tools, data sources, and services through a standardized protocol.
1214
managed-agents/memory Changed · +3 / -4 lines
## Compatibility
from line 2
22title: Using agent memory
33url: https://platform.claude.com/docs/en/managed-agents/memory
44description: Give your agents persistent memory that survives across sessions using memory stores.
5featureMetadata:
6 status: beta
7 betaHeader: agent-memory-2026-07-22
58---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `agent-memory-2026-07-22`
109
1110Each Managed Agents session starts with a fresh context by default. When a session ends, any state the agent built up is gone. Memory stores let the agent carry information across sessions: user preferences, project conventions, prior mistakes, and domain context.
1211
managed-agents/migration Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Migration
33url: https://platform.claude.com/docs/en/managed-agents/migration
44description: Move an existing agent built on the Messages API or the Claude Agent SDK to Claude Managed Agents.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113Claude Managed Agents replaces your hand-written agent loop with managed infrastructure. This page covers what changes when you migrate from a custom loop built on the [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) or from the [Claude Agent SDK](https://code.claude.com/docs/en/agent-sdk/overview).
1214
managed-agents/multiagent-orchestration Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Multiagent orchestration
33url: https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration
44description: Coordinate multiple agents within a single session.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113Multiagent orchestration lets one agent coordinate with others to complete complex work. Agents can act in parallel with their own isolated context, which helps improve output quality and can also improve time to completion.
1214
managed-agents/onboarding Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Build in Console
33url: https://platform.claude.com/docs/en/managed-agents/onboarding
44description: Create, test, and iterate on agents visually in Console, then run them from your code with the API.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113[Console](https://platform.claude.com/workspaces/default/agent-quickstart/) provides a visual interface for creating and configuring agents. It lets you iterate on configuration interactively before writing code.
1214
managed-agents/overview Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Claude Managed Agents overview
33url: https://platform.claude.com/docs/en/managed-agents/overview
44description: Pre-built, configurable agent harness that runs in managed infrastructure. Best for long-running tasks and asynchronous work.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113Anthropic offers two ways to build with Claude, each suited to different use cases:
1214
managed-agents/permission-policies Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Permission policies
33url: https://platform.claude.com/docs/en/managed-agents/permission-policies
44description: Control when agent and MCP tools execute.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113Permission policies control whether server-executed tools (the pre-built agent toolset and MCP toolset) run automatically, wait for your approval, or have each call evaluated by the server. Custom tools are executed by your application and controlled by you, so they are not governed by permission policies.
1214
managed-agents/quickstart Changed · +26 / -8 lines
## Compatibility
from line 2
22title: Get started with Claude Managed Agents
33url: https://platform.claude.com/docs/en/managed-agents/quickstart
44description: Create your first autonomous agent.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
612
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
10
1113This guide walks you through creating an agent, setting up an environment, starting a session, and streaming agent responses.
1214
1315<Tip>
from line 182
180182 </File>
181183 </MultiFileExample>
182184
185 <ForLanguage tab="CLI">
186 [`ant apply`](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/apply) prints the agent's ID and records it in `claude-lock.json`. You'll reference it in every session you create.
187 </ForLanguage>
188
183189 ```python Python
184190 from anthropic import Anthropic
185191
from line 338
332338
333339 puts "Agent ID: #{agent.id}, version: #{agent.version}"
334340 ```
341
342 <ForLanguage not="CLI">
343 Save the returned `agent.id`. You'll reference it in every session you create.
344 </ForLanguage>
335345 </CodeGroup>
336346
337347 The `agent_toolset_20260401` tool type enables the full set of pre-built agent tools (bash, file operations, web search, and more). See [Tools](https://platform.claude.com/docs/en/managed-agents/tools) for the complete list and per-tool configuration options.
338
339 Save the returned `agent.id` (the CLI's [`ant apply`](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/apply) prints it and records it in `claude-lock.json`). You'll reference it in every session you create.
340348 </Step>
341349
342350 <Step title="Create an environment">
from line 390
382390 </File>
383391 </MultiFileExample>
384392
393 <ForLanguage tab="CLI">
394 `ant apply` prints the environment's ID and records it in `claude-lock.json`. You'll reference it in every session you create.
395
396 <Tip>
397 [`ant apply`](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/apply) accepts more than one file, so you can create the agent and the environment with one command instead: `ant apply coding-assistant.md environment.yaml`.
398 </Tip>
399 </ForLanguage>
400
385401 ```python Python
386402 environment = client.beta.environments.create(
387403 name="quickstart-env",
from line 478
462478
463479 puts "Environment ID: #{environment.id}"
464480 ```
465 </CodeGroup>
466481
467 Save the returned `environment.id` (also in `claude-lock.json` if you used `ant apply`). You'll reference it in every session you create.
482 <ForLanguage not="CLI">
483 Save the returned `environment.id`. You'll reference it in every session you create.
484 </ForLanguage>
485 </CodeGroup>
468486
469487 <Tip>
470488 To run the sandbox on your own infrastructure instead of a cloud sandbox, see
managed-agents/reference Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Reference
33url: https://platform.claude.com/docs/en/managed-agents/reference
44description: Event types, self-hosted worker CLI flags, supported MCP server types, rate limits, and branding guidelines for Claude Managed Agents.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113This page collects reference material for Claude Managed Agents. For task-oriented guides, follow the links in each section. For the operations on the session resource, see [Session operations](https://platform.claude.com/docs/en/managed-agents/session-operations).
1214
managed-agents/scheduled-deployments Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Scheduled deployments
33url: https://platform.claude.com/docs/en/managed-agents/scheduled-deployments
44description: "Create and manage deployments with the Claude API: run an agent on a recurring cron schedule and inspect its run history."
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113A **scheduled deployment** allows an [agent](https://platform.claude.com/docs/en/managed-agents/agent-setup) to start [sessions](https://platform.claude.com/docs/en/managed-agents/sessions) autonomously, enabling task completion over a predictable cadence. You create and manage deployments with the Deployments API, part of the Claude API.
1214
managed-agents/self-hosted-sandboxes Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Self-hosted sandboxes
33url: https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes
44description: Run Claude Managed Agents sessions in self-hosted sandboxes, keeping tool execution, files, and network egress in your own infrastructure.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113By default, Managed Agents executes tools and code inside [Anthropic-managed cloud sandboxes](https://platform.claude.com/docs/en/managed-agents/cloud-sandboxes-reference). Self-hosted sandboxes keep the orchestration on Anthropic's side but move tool execution into infrastructure you control, so the agent's code, filesystem, and network egress never leave your environment.
1214
managed-agents/self-hosted-sandboxes-security Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Security model
33url: https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-security
44description: Shared responsibility model for self-hosted sandbox environments.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113Anthropic secures the control plane across all environments: session and work queue integrity, multitenant isolation, and agent-context minimization. When you self-host, the following responsibilities fall to you.
1214
managed-agents/session-operations Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Session operations
33url: https://platform.claude.com/docs/en/managed-agents/session-operations
44description: Retrieve, list, update, archive, and delete Claude Managed Agents sessions.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113Once 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 creating a session and sending it work.
1214
managed-agents/sessions Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Start a session
33url: https://platform.claude.com/docs/en/managed-agents/sessions
44description: Create a session to run your agent and begin executing tasks.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113A session is an agent instance within an environment. Each session references an [agent](https://platform.claude.com/docs/en/managed-agents/agent-setup) and an [environment](https://platform.claude.com/docs/en/managed-agents/environments) (both created separately), and maintains conversation history across multiple interactions. Sessions follow a two-step lifecycle: first [create the session](https://platform.claude.com/docs/en/managed-agents/sessions#creating-a-session), then [send a user event](https://platform.claude.com/docs/en/managed-agents/sessions#starting-the-session) to start work. You can also collapse both steps into one call with [`initial_events`](https://platform.claude.com/docs/en/managed-agents/sessions#seed-the-session-with-initial-events).
1214
managed-agents/skills Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Skills
33url: https://platform.claude.com/docs/en/managed-agents/skills
44description: Attach pre-built or custom skills to an agent in Claude Managed Agents to give it reusable, filesystem-based expertise for domain-specific workflows.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113Skills are reusable, filesystem-based resources that give your agent domain-specific expertise: workflows, context, and best practices that turn a general-purpose agent into a specialist. Each skill you add incurs a modest cost on the session's context window, adding instructions and metadata that help the model use the skill. Learn more in the [Agent Skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) overview.
1214
managed-agents/tools Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Tools
33url: https://platform.claude.com/docs/en/managed-agents/tools
44description: Configure tools available to your agent.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113Claude Managed Agents provides a set of built-in tools that Claude can use autonomously within a [session](https://platform.claude.com/docs/en/managed-agents/sessions). You control which tools are available by specifying them in the agent configuration.
1214
managed-agents/vaults Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Authenticate with vaults
33url: https://platform.claude.com/docs/en/managed-agents/vaults
44description: Register per-user credentials when creating sessions.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113Vaults and credentials are authentication primitives that let you register credentials for third-party services once and reference them by ID at session creation. This means you don't need to run your own secret store, transmit tokens on every call, or lose track of which end user an agent acted on behalf of.
1214
managed-agents/webhooks Changed · +6 / -4 lines
## Compatibility
from line 2
22title: Subscribe to webhooks
33url: https://platform.claude.com/docs/en/managed-agents/webhooks
44description: Get notified when major events happen without polling.
5featureMetadata:
6 topic:
7 title: Managed Agents
8 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
10 betaHeader: managed-agents-2026-04-01
511---
6
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
1012
1113Sessions are long-running interactions. While most real-time interactions happen through the [SSE event stream](https://platform.claude.com/docs/en/managed-agents/events-and-streaming), webhooks notify you of major state changes.
1214
agents-and-tools/tool-use/tool-runner Changed · +1 / -1 lines
from line 1093
10931093
10941094### Automatic context management
10951095
1096For long-running agentic tasks, the TypeScript and Ruby tool runners support automatic [compaction](https://platform.claude.com/docs/en/build-with-claude/context-editing#client-side-compaction-sdk), which generates summaries when token usage exceeds a threshold so the conversation can continue beyond context window limits. Both SDKs have deprecated this client-side option in favor of [server-side compaction](https://platform.claude.com/docs/en/build-with-claude/compaction-threshold), which works with every SDK's tool runner through the `context_management` request parameter. The Python SDK (v1.0 and later) and the Go, Java, C#, and PHP tool runners don't include client-side compaction.
1096For long-running agentic tasks, the TypeScript and Ruby tool runners support automatic [compaction](https://platform.claude.com/docs/en/build-with-claude/context-editing#client-side-compaction-sdk), which generates summaries when token usage exceeds a threshold so the conversation can continue beyond context window limits. Both SDKs have deprecated this client-side option in favor of [server-side compaction](https://platform.claude.com/docs/en/build-with-claude/compaction-threshold), which works with every SDK's tool runner through the `context_management` request parameter. The Python SDK (v1.0 and later) and the Go, Java, C#, and PHP tool runners don't include client-side compaction. The Python, TypeScript, C#, Go, and Java tool runners have a `compact_before_next_turn()` helper for on-demand compaction, spelled in each language's own casing. See [Compact in a loop](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#compact-in-a-loop). Use it or a `context_management` compaction edit on a runner, not both.
10971097
10981098### Debugging tool execution
10991099
build-with-claude/overview Changed · +1 / -1 lines
from line 94
9494
9595| Feature | Description | ZDR | Availability |
9696| ------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------ | ------------------------------------------------------------------------------------------------- |
97| [Compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) | Server-side context summarization for long-running conversations. When context approaches the window limit, the API automatically summarizes earlier parts of the conversation. | ZDR eligible | <PlatformAvailability claudeApiBeta claudePlatformAwsBeta bedrockBeta vertexAiBeta azureAiBeta /> |
97| [Compaction at a token threshold](https://platform.claude.com/docs/en/build-with-claude/compaction-threshold) | Server-side context summarization for long-running conversations. When input tokens reach the trigger threshold, the API automatically summarizes earlier parts of the conversation. | ZDR eligible | <PlatformAvailability claudeApiBeta claudePlatformAwsBeta bedrockBeta vertexAiBeta azureAiBeta /> |
9898| [Context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing) | Automatically manage conversation context with configurable strategies. Supports clearing tool results when approaching token limits and managing thinking blocks in extended thinking conversations. | ZDR eligible | <PlatformAvailability claudeApiBeta claudePlatformAwsBeta bedrockBeta vertexAiBeta azureAiBeta /> |
9999| [Automatic prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#automatic-caching) | Simplify prompt caching to a single API parameter. The system automatically caches the last cacheable block in your request, moving the cache point forward as conversations grow. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |
100100| [Prompt caching (5m)](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) | Provide Claude with more background knowledge and example outputs to reduce costs and latency. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |
manage-claude/compliance-faq Changed · +1 / -1 lines
from line 69
6969 To retrieve message bodies and file contents, use the chat, message, and file endpoints with a Compliance Access Key carrying `read:compliance_user_data`. The same key and scope retrieve transcripts of sessions on users' machines (such as Cowork and Claude Code sessions) through the [local session endpoints](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions), and transcripts of Cowork sessions in the cloud through the [remote session endpoints](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-remote-sessions). These endpoints serve Claude Enterprise content only; Claude Console workloads, and Claude API workloads authenticated with an API key, expose administrative and resource events through the Activity Feed but do not expose prompt text or model responses through the Compliance API.
7070 </Accordion>
7171
72 <Accordion title="Do Cowork, Claude Code, Claude Science, and Claude for Microsoft 365 sessions appear in the Compliance API?">
72 <Accordion title="Do Cowork, Claude Code, Claude Science, Claude for Microsoft 365, and Claude in Chrome sessions appear in the Compliance API?">
7373 Yes. Cowork sessions in Claude Desktop that run on users' machines, Claude Code sessions (in the terminal, in Claude Desktop, or in an IDE extension), sessions in the Claude Science desktop app, Claude for Microsoft 365 sessions (in Excel, PowerPoint, Word, and Outlook), and chats in the Claude in Chrome browser extension are captured while users are signed in with their Claude Enterprise account and are available through the [local session endpoints](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions). Cowork sessions started on claude.ai web or mobile, which run in the cloud in Anthropic-managed environments, are available through the [remote session endpoints](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-remote-sessions). Each family has a list endpoint that returns session metadata and a messages endpoint that returns the session transcript (user prompts, assistant responses, and tool calls and results). The local family adds a third endpoint that retrieves one session's metadata. All of these endpoints use your existing Compliance Access Key with `read:compliance_user_data`; no new key or scope is needed.
7474
7575 Local sessions are captured as their requests reach the Claude API, so nothing is installed on the device, and on-device activity that never reaches the API is not captured. Claude Code sessions authenticated with a Claude Console API key, Claude Code sessions run through a third-party cloud platform (Amazon Bedrock, Google Cloud, or Microsoft Foundry), and [Claude Code cloud sessions](https://code.claude.com/docs/en/claude-code-on-the-web), which run on cloud infrastructure instead of the user's machine, are not captured. These cloud sessions are not remote sessions, even though both run in the cloud; the remote session endpoints return Cowork sessions only. Organizations with [HIPAA readiness](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#hipaa-readiness) enabled get no local session data, and sessions for which [zero data retention (ZDR)](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#zero-data-retention-zdr-scope) is in effect are excluded.
manage-claude/compliance-sessions Changed · +1 / -1 lines
from line 272
272272
273273* `content_unavailable` means the content cannot be returned. The `content` array is empty, and `provenance.reason` states why. `not_captured` means no content is available for the turn. It does not prove that no record was stored: content that Anthropic's data-handling policies withhold from the Compliance API is reported with the same reason, and so are individual turns within an otherwise captured session that are unavailable for such reasons. An unusable customer-managed key is the one exception and returns [503 Service Unavailable](https://platform.claude.com/docs/en/manage-claude/compliance-errors#local-sessions-temporarily-unavailable) instead. `client_aborted` means the client closed the connection or cancelled the request before the response completed, so the turn's response was not captured; any partial output already streamed to the client is not included, and this reason applies to assistant-role turns only. `cmek_key_revoked` is reserved for content encrypted under your organization's customer-managed key when that key is unavailable (for example, revoked). It is not currently returned, because an unusable key produces a 503 instead, but handle it for forward compatibility. `retention_elapsed` means the content aged past retention. `oversize` means a single message exceeded the per-message size bound; the message is still returned, with an empty `content` array.
274274* `client_asserted` marks assistant messages that the client supplied as conversation history and that could not be matched to a captured response; their authorship is not verified.
275* `synthetic_marker` marks records generated by the endpoint itself, such as the marker that stands in for the system prompt. When the client rewrites or compacts its conversation history mid-session (for example, after context compaction), the transcript inserts a marker message at that point and continues with the new content the client sent; when your organization has a finite retention period, the rewritten history itself is withheld (a second marker notes this) and only the latest user turn and what follows are shown.
275* `synthetic_marker` marks records generated by the endpoint itself, such as the marker that stands in for the system prompt. When the client rewrites or compacts its conversation history mid-session (for example, after context compaction), the transcript inserts a marker message at that point and continues with the new content the client sent. When your organization has a finite retention period and that new content includes assistant messages, the transcript withholds the new content up to and including its last assistant message (a second marker notes this) and shows only the user messages after that point, followed by the rest of the session.
276276
277277Marker and client-asserted messages begin with a bracketed explanatory `text` block flagged `truncated: true`, for example `[system prompt content not shown]`. Treat these records as present but unavailable or unverified rather than missing, and tolerate unrecognized `provenance` types and reasons.
278278
manage-claude/inference-hooks Changed · +2 / -0 lines
from line 31
3131
3232Your AI security server sees what the user sees: transcript text, tool calls and their results, and text extracted from attachments. It never receives raw file or image bytes, system prompts, or Anthropic-internal context.
3333
34The Inference hooks system doesn't keep its own copy of prompt or response content. It stores only your hook configuration and metadata about hook activity, such as verdicts, timestamps, and request identifiers. The Claude product you use stores prompts and responses under its own data retention rules, whether or not hooks are on. For example, a message that a hook blocks on claude.ai stays in the conversation.
35
3436If your AI security server is unreachable, returns an error, or doesn't respond within the timeout, your organization's failure handling setting decides the outcome: block the request, or allow it to proceed without inspection. Sustained failures attributable to your server trip a circuit breaker: Anthropic stops contacting it and applies your failure handling setting to every request, then resets the breaker automatically once it detects that your server is returning verdicts again; see [Circuit breaker](https://platform.claude.com/docs/en/manage-claude/inference-hooks-configuration#circuit-breaker).
3537
3638Enforcement can roll out at your pace, so nobody has to be blocked on day one: shadow mode observes verdicts on live traffic without blocking anything, a rollout percentage inspects a chosen fraction of requests, and exclusions exempt members of chosen roles entirely. See [Configure Inference hooks](https://platform.claude.com/docs/en/manage-claude/inference-hooks-configuration).