Follow Discord
Sweep 30 Oct 2026 · 01:02Z Build v2.1.314 532 read Stable v2.1.308 Latest v2.1.314 Next v2.1.314 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Developer Platform
One capture · api

One read of Claude Developer Platformapi-20261028T203725Z

116 pages moved out of 821 read.

Pages moved 116 significant first
Pages read 821 in this capture
Captured 20:37 UTC
Corpus hash 82e28663d5c2 corpus-hash

What this read moved

76-100 of 116, page 4 of 5

This capture is too large to show at once. Changes 76-100 of 116 are below, significant first; the rest are on the following screens.

managed-agents/migration Changed · +25 / -0 lines

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
35 Claude Models on Google Cloud (Anthropic managed): beta
1136---
1237 
1338Claude 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).

managed-agents/multiagent-orchestration Changed · +63 / -1 lines

## Availability ### API support #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) ### Required beta headers ### Data handling

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
35 Claude Models on Google Cloud (Anthropic managed): beta
1136---
1237 
1338Multiagent 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.
from line 1244
12191244 
12201245No `agent.tool_use` events are emitted for a consultation, and no `agent.thread_message_sent` event appears on the session’s event stream, because the consultation input is composed by the platform rather than sent by the agent. If you list the advisor thread’s own events, the advice also appears there as an `agent.thread_message_sent` event. The advice delivery (event 3) is not guaranteed to arrive before the advisor thread’s idle and terminated events, so don’t treat those as a signal that the advice has already been delivered.
12211246 
1222Whether your client can read the advice is the advisor model’s policy. It mirrors the [result variants](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#result-variants) split on the Messages API advisor tool. An advisor model that returns plaintext results there delivers readable text here. One that returns redacted results delivers a `[{"type": "redacted"}]` placeholder on every client surface, while the agent still reads the full advice server-side. The preceding example uses the newest Opus model available to you as the advisor. Claude Opus 5.5 returns redacted results, so your client sees only the placeholder. To read the advice on the event stream, use an advisor that returns plaintext, such as Claude Opus 4.8. A model’s policy can change with no change to the API, so handle both `text` and `redacted` blocks. Some agent models pair only with redacted-result advisors; see the advisor tool’s [compatibility table](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility). Advisor thinking is never surfaced. Clients cannot send `redacted` blocks themselves; an event containing one is rejected with a 400 validation error.
1247Whether your client can read the advice is the advisor model’s policy. It mirrors the [result variants](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#result-variants) split on the Messages API advisor tool. An advisor model that returns plaintext results there delivers readable text here. One that returns redacted results delivers a `[{"type": "redacted"}]` placeholder on every client surface, while the agent still reads the full advice server-side. The preceding example uses the newest Opus model available to you as the advisor. Claude Opus 5.5 returns redacted results, so your client sees only the placeholder. To read the advice on the event stream, use an advisor that returns plaintext, such as Claude Opus 4.8. A model’s policy can change with no change to the API, so handle both `text` and `redacted` blocks. Some agent models pair only with redacted-result advisors; see the advisor tool’s [Model compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/advisor-tool#model-compatibility) section. Advisor thinking is never surfaced. Clients cannot send `redacted` blocks themselves; an event containing one is rejected with a 400 validation error.
12231248 
12241249A failed or interrupted consultation never fails the agent’s turn: the agent continues after a generic notice that the consultation failed. A session-level `user.interrupt` during a consultation terminates the advisor thread with no advice delivered; a `user.interrupt` with the advisor thread’s `session_thread_id` (java: `sessionThreadId`; php: `sessionThreadID`; csharp, go: `SessionThreadID`) abandons only that consultation.
12251250 
from line 1301
12761301Once the agent has the `multiagent_20261001` type, a setting that a later update leaves out keeps its stored value.
12771302 
12781303The update doesn’t change sessions that already exist. To use the new block, create a session after the update.
1304 
1305## Availability
1306 
1307Multiagent orchestration is in beta on every model.
1308 
1309### API support
1310 
1311#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
1312 
1313* Availability: Available
1314 
1315| Status | Cloud platforms |
1316| ------ | ----------------------- |
1317| Beta | All supported platforms |
1318 
1319### Required beta headers
1320 
1321[Beta headers overview](https://platform.claude.com/docs/en/api/beta-headers)
1322 
1323Beta headers allow you to access experimental features and new model capabilities before they become part of the standard API.
1324 
1325* `managed-agents-2026-04-01`
1326 
1327### Data handling
1328 
1329[Data handling overview](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility)
1330 
1331| Item | Zero data retention | HIPAA |
1332| ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
1333| Status | Not eligible | Not eligible |
1334| Details | Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes. | Applies to all Managed Agents sub-features, including Self-hosted sandboxes. |
1335 
1336Applicable endpoints:
1337 
1338* `/v1/agents`
1339* `/v1/sessions`
1340* `/v1/environments`
12791341 

managed-agents/onboarding Changed · +61 / -0 lines

## Availability ### API support #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) ### Required beta headers ### Data handling

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
1135---
1236 
1337The [Claude 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.
from line 143
119143 )
120144 ```
121145</CodeGroup>
146 
147## Availability
148 
149Console agent builder is in beta on every model.
150 
151### API support
152 
153#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
154 
155* Availability: Available
156 
157| Status | Cloud platforms |
158| ------ | ------------------------------------------------------------------------------------------------------------------ |
159| Beta | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) |
160 
161### Required beta headers
162 
163[Beta headers overview](https://platform.claude.com/docs/en/api/beta-headers)
164 
165Beta headers allow you to access experimental features and new model capabilities before they become part of the standard API.
166 
167* `managed-agents-2026-04-01`
168 
169### Data handling
170 
171[Data handling overview](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility)
172 
173| Item | Zero data retention | HIPAA |
174| ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
175| Status | Not eligible | Not eligible |
176| Details | Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes. | Applies to all Managed Agents sub-features, including Self-hosted sandboxes. |
177 
178Applicable endpoints:
179 
180* `/v1/agents`
181* `/v1/sessions`
182* `/v1/environments`
122183 

managed-agents/overview Changed · +58 / -0 lines

## Availability ### API support ### Required beta headers ### Data handling

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
35 Claude Models on Google Cloud (Anthropic managed): beta
1136---
1237 
1338Anthropic offers two ways to build with Claude, each suited to different use cases:
from line 136
111136Claude Managed Agents is stateful by design: sessions are long-running, resume cleanly after pauses, and store conversation history, sandbox state, and outputs server-side. Because of this, Managed Agents is not currently eligible for [Zero Data Retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#zero-data-retention-zdr-scope) or HIPAA Business Associate Agreement (BAA) coverage. You retain control over this data: you can [delete sessions](https://platform.claude.com/docs/en/managed-agents/session-operations#deleting-a-session), and separately delete any [files](https://platform.claude.com/docs/en/build-with-claude/files#delete-a-file) you uploaded, at any time through the API. For eligibility across all features, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility).
112137 
113138See [Rate limits](https://platform.claude.com/docs/en/managed-agents/reference#rate-limits) and [Branding guidelines](https://platform.claude.com/docs/en/managed-agents/reference#branding-guidelines) in the reference.
139 
140## Availability
141 
142Managed Agents are in beta on every model.
143 
144### API support
145 
146| Status | Cloud platforms | Models |
147| ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------- |
148| Beta | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | [All models](https://platform.claude.com/docs/en/models/overview) |
149 
150### Required beta headers
151 
152[Beta headers overview](https://platform.claude.com/docs/en/api/beta-headers)
153 
154Beta headers allow you to access experimental features and new model capabilities before they become part of the standard API.
155 
156* `managed-agents-2026-04-01`
157 
158### Data handling
159 
160[Data handling overview](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility)
161 
162| Item | Zero data retention | HIPAA |
163| ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
164| Status | Not eligible | Not eligible |
165| Details | Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes. | Applies to all Managed Agents sub-features, including Self-hosted sandboxes. |
166 
167Applicable endpoints:
168 
169* `/v1/agents`
170* `/v1/sessions`
171* `/v1/environments`
114172 

managed-agents/permission-policies Changed · +62 / -0 lines

## Availability ### API support #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) ### Required beta headers ### Data handling

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
35 Claude Models on Google Cloud (Anthropic managed): beta
1136---
1237 
1338Permission 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 run by your application and controlled by you, so they are not governed by permission policies.
from line 1322
12971322 Send events, stream responses, and interrupt or redirect your session while it runs.
12981323 </Card>
12991324</CardGroup>
1325 
1326## Availability
1327 
1328Permission policies are in beta on every model.
1329 
1330### API support
1331 
1332#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
1333 
1334* Availability: Always on
1335 
1336| Status | Cloud platforms |
1337| ------ | ----------------------- |
1338| Beta | All supported platforms |
1339 
1340### Required beta headers
1341 
1342[Beta headers overview](https://platform.claude.com/docs/en/api/beta-headers)
1343 
1344Beta headers allow you to access experimental features and new model capabilities before they become part of the standard API.
1345 
1346* `managed-agents-2026-04-01`
1347 
1348### Data handling
1349 
1350[Data handling overview](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility)
1351 
1352| Item | Zero data retention | HIPAA |
1353| ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
1354| Status | Not eligible | Not eligible |
1355| Details | Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes. | Applies to all Managed Agents sub-features, including Self-hosted sandboxes. |
1356 
1357Applicable endpoints:
1358 
1359* `/v1/agents`
1360* `/v1/sessions`
1361* `/v1/environments`
13001362 

managed-agents/quickstart Changed · +25 / -0 lines

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
35 Claude Models on Google Cloud (Anthropic managed): beta
1136---
1237 
1338This guide walks you through creating an agent, setting up an environment, starting a session, and streaming agent responses.

managed-agents/reference Changed · +25 / -0 lines

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
35 Claude Models on Google Cloud (Anthropic managed): beta
1136---
1237 
1338This 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).

managed-agents/scheduled-deployments Changed · +58 / -1 lines

## Availability ### API support #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) ### Required beta headers ### Data handling

from line 6
66 topic:
77 title: Managed Agents
88 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
109 betaHeader: managed-agents-2026-04-01
10 zdr:
11 eligibility: not-eligible
12 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
13 supportedModels:
14 - claude-fable-5-1
15 - claude-mythos-5-1
16 - claude-fable-5
17 - claude-mythos-5
18 - claude-mythos-preview
19 - claude-opus-5-5
20 - claude-opus-5
21 - claude-sonnet-5-5
22 - claude-sonnet-5
23 - claude-haiku-5-5
24 - claude-haiku-4-5-20251001
25 - claude-opus-4-8
26 - claude-opus-4-7
27 - claude-opus-4-6
28 - claude-sonnet-4-6
29 - claude-opus-4-5-20251101
30 - claude-sonnet-4-5-20250929
1131---
1232 
1333A **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, so the agent can complete tasks on a predictable cadence. You create and manage deployments with the Deployments API, part of the Claude API.
from line 804
784804 run = client.beta.deployments.run(deployment.id)
785805 ```
786806</CodeGroup>
807 
808## Availability
809 
810Scheduled deployments are available on every model.
811 
812### API support
813 
814#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
815 
816* Availability: Available
817 
818| Status | Cloud platforms | Models |
819| --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------- |
820| Available | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | [All models](https://platform.claude.com/docs/en/models/overview) |
821 
822### Required beta headers
823 
824[Beta headers overview](https://platform.claude.com/docs/en/api/beta-headers)
825 
826Beta headers allow you to access experimental features and new model capabilities before they become part of the standard API.
827 
828* `managed-agents-2026-04-01`
829 
830### Data handling
831 
832[Data handling overview](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility)
833 
834| Item | Zero data retention | HIPAA |
835| ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
836| Status | Not eligible | Not eligible |
837| Details | Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes. | Applies to all Managed Agents sub-features, including Self-hosted sandboxes. |
838 
839Applicable endpoints:
840 
841* `/v1/agents`
842* `/v1/sessions`
843* `/v1/environments`
787844 

managed-agents/secure-deployment Changed · +25 / -0 lines

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
35 Claude Models on Google Cloud (Anthropic managed): beta
1136---
1237 
1338This guide lists the settings that limit what an agent on Claude Managed Agents can reach and do, most important first. Each section links to the page that covers the setting in full.

managed-agents/secure-deployment-monitoring Changed · +25 / -0 lines

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
35 Claude Models on Google Cloud (Anthropic managed): beta
1136---
1237 
1338Optionally review each session’s events with an offline job. Watch webhooks for sessions that need attention, and delete sessions you no longer need. To limit what an agent can do before it runs, see [Secure your Managed Agents deployment](https://platform.claude.com/docs/en/managed-agents/secure-deployment).

managed-agents/secure-deployment-risks Changed · +25 / -0 lines

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
35 Claude Models on Google Cloud (Anthropic managed): beta
1136---
1237 
1338This page explains why the settings in [Secure your Managed Agents deployment](https://platform.claude.com/docs/en/managed-agents/secure-deployment) matter, and what the sandbox can and cannot do.

managed-agents/self-hosted-sandboxes-custom-tools Changed · +21 / -1 lines

from line 6
66 topic:
77 title: Managed Agents
88 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
109 betaHeader: managed-agents-2026-04-01
10 zdr:
11 eligibility: not-eligible
12 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
13 supportedModels:
14 - claude-fable-5-1
15 - claude-mythos-5-1
16 - claude-fable-5
17 - claude-mythos-5
18 - claude-mythos-preview
19 - claude-opus-5-5
20 - claude-opus-5
21 - claude-sonnet-5-5
22 - claude-sonnet-5
23 - claude-haiku-5-5
24 - claude-haiku-4-5-20251001
25 - claude-opus-4-8
26 - claude-opus-4-7
27 - claude-opus-4-6
28 - claude-sonnet-4-6
29 - claude-opus-4-5-20251101
30 - claude-sonnet-4-5-20250929
1131---
1232 
1333[Custom tools](https://platform.claude.com/docs/en/managed-agents/tools#custom-tools) are tools your own code runs: the agent emits an `agent.custom_tool_use` event and waits for a matching `user.custom_tool_result`. Your worker can be that code. Because it runs inside your sandbox, the tool reaches the internal services, credentials, and network egress you configured for the sandbox, and nothing more.

managed-agents/self-hosted-sandboxes-memory Changed · +21 / -1 lines

from line 6
66 topic:
77 title: Managed Agents
88 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
109 betaHeader: managed-agents-2026-04-01
10 zdr:
11 eligibility: not-eligible
12 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
13 supportedModels:
14 - claude-fable-5-1
15 - claude-mythos-5-1
16 - claude-fable-5
17 - claude-mythos-5
18 - claude-mythos-preview
19 - claude-opus-5-5
20 - claude-opus-5
21 - claude-sonnet-5-5
22 - claude-sonnet-5
23 - claude-haiku-5-5
24 - claude-haiku-4-5-20251001
25 - claude-opus-4-8
26 - claude-opus-4-7
27 - claude-opus-4-6
28 - claude-sonnet-4-6
29 - claude-opus-4-5-20251101
30 - claude-sonnet-4-5-20250929
1131---
1232 
1333Sessions on a self-hosted environment attach [memory stores](https://platform.claude.com/docs/en/managed-agents/memory) exactly as sessions on cloud environments do. List them in `resources` (csharp, go: `Resources`) when you create the session, as shown in [Attach a memory store to a session](https://platform.claude.com/docs/en/managed-agents/memory#attach-a-memory-store-to-a-session). A session accepts up to 8 memory stores.

managed-agents/self-hosted-sandboxes-operations Changed · +21 / -1 lines

from line 6
66 topic:
77 title: Managed Agents
88 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
109 betaHeader: managed-agents-2026-04-01
10 zdr:
11 eligibility: not-eligible
12 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
13 supportedModels:
14 - claude-fable-5-1
15 - claude-mythos-5-1
16 - claude-fable-5
17 - claude-mythos-5
18 - claude-mythos-preview
19 - claude-opus-5-5
20 - claude-opus-5
21 - claude-sonnet-5-5
22 - claude-sonnet-5
23 - claude-haiku-5-5
24 - claude-haiku-4-5-20251001
25 - claude-opus-4-8
26 - claude-opus-4-7
27 - claude-opus-4-6
28 - claude-sonnet-4-6
29 - claude-opus-4-5-20251101
30 - claude-sonnet-4-5-20250929
1131---
1232 
1333The monitoring calls on this page run from your monitoring or operations tooling, authenticated with your Claude API key. The worker helpers handle the claim and keep-alive loop, so you don’t call those endpoints directly.

managed-agents/self-hosted-sandboxes-reference Changed · +21 / -1 lines

from line 6
66 topic:
77 title: Managed Agents
88 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
109 betaHeader: managed-agents-2026-04-01
10 zdr:
11 eligibility: not-eligible
12 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
13 supportedModels:
14 - claude-fable-5-1
15 - claude-mythos-5-1
16 - claude-fable-5
17 - claude-mythos-5
18 - claude-mythos-preview
19 - claude-opus-5-5
20 - claude-opus-5
21 - claude-sonnet-5-5
22 - claude-sonnet-5
23 - claude-haiku-5-5
24 - claude-haiku-4-5-20251001
25 - claude-opus-4-8
26 - claude-opus-4-7
27 - claude-opus-4-6
28 - claude-sonnet-4-6
29 - claude-opus-4-5-20251101
30 - claude-sonnet-4-5-20250929
1131---
1232 
1333This page documents the pre-built workers that serve a `self_hosted` environment. For task-oriented guides, start with [Self-hosted sandboxes](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes) and [Deploy self-hosted workers](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-workers).

managed-agents/self-hosted-sandboxes-security Changed · +21 / -1 lines

from line 6
66 topic:
77 title: Managed Agents
88 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
109 betaHeader: managed-agents-2026-04-01
10 zdr:
11 eligibility: not-eligible
12 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
13 supportedModels:
14 - claude-fable-5-1
15 - claude-mythos-5-1
16 - claude-fable-5
17 - claude-mythos-5
18 - claude-mythos-preview
19 - claude-opus-5-5
20 - claude-opus-5
21 - claude-sonnet-5-5
22 - claude-sonnet-5
23 - claude-haiku-5-5
24 - claude-haiku-4-5-20251001
25 - claude-opus-4-8
26 - claude-opus-4-7
27 - claude-opus-4-6
28 - claude-sonnet-4-6
29 - claude-opus-4-5-20251101
30 - claude-sonnet-4-5-20250929
1131---
1232 
1333Anthropic 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.

managed-agents/self-hosted-sandboxes-workers Changed · +61 / -0 lines

## Availability ### API support #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) ### Required beta headers ### Data handling

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
1135---
1236 
1337The [quickstart](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes#quickstart) runs one `ant` CLI worker that polls continuously and runs every session in one process. This page covers the other ways to run a worker and how to choose among them.
from line 924
900924 Shared responsibility model for self-hosted sandbox environments.
901925 </Card>
902926</CardGroup>
927 
928## Availability
929 
930Self-hosted workers are in beta on every model.
931 
932### API support
933 
934#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
935 
936* Availability: Available
937 
938| Status | Cloud platforms |
939| ------ | ------------------------------------------------------------------------------------------------------------------ |
940| Beta | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) |
941 
942### Required beta headers
943 
944[Beta headers overview](https://platform.claude.com/docs/en/api/beta-headers)
945 
946Beta headers allow you to access experimental features and new model capabilities before they become part of the standard API.
947 
948* `managed-agents-2026-04-01`
949 
950### Data handling
951 
952[Data handling overview](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility)
953 
954| Item | Zero data retention | HIPAA |
955| ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
956| Status | Not eligible | Not eligible |
957| Details | Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes. | Applies to all Managed Agents sub-features, including Self-hosted sandboxes. |
958 
959Applicable endpoints:
960 
961* `/v1/agents`
962* `/v1/sessions`
963* `/v1/environments`
903964 

managed-agents/session-observability Changed · +61 / -0 lines

## Availability ### API support #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) ### Required beta headers ### Data handling

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
1135---
1236 
1337Use the session viewer in the Claude Console to inspect what an agent did in a session, without writing any code. Use the session’s `usage` (csharp, go: `Usage`) totals to see what that work consumed. To see a session’s turns, model requests, and tool uses in your observability platform, set up [OpenTelemetry tracing](https://platform.claude.com/docs/en/manage-claude/opentelemetry).
from line 136
112136 Cap a session’s spend with a hard dollar budget enforced at public list rates.
113137 </Card>
114138</CardGroup>
139 
140## Availability
141 
142Session viewer is in beta on every model.
143 
144### API support
145 
146#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
147 
148* Availability: Always on
149 
150| Status | Cloud platforms |
151| ------ | ------------------------------------------------------------------------------------------------------------------ |
152| Beta | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) |
153 
154### Required beta headers
155 
156[Beta headers overview](https://platform.claude.com/docs/en/api/beta-headers)
157 
158Beta headers allow you to access experimental features and new model capabilities before they become part of the standard API.
159 
160* `managed-agents-2026-04-01`
161 
162### Data handling
163 
164[Data handling overview](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility)
165 
166| Item | Zero data retention | HIPAA |
167| ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
168| Status | Not eligible | Not eligible |
169| Details | Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes. | Applies to all Managed Agents sub-features, including Self-hosted sandboxes. |
170 
171Applicable endpoints:
172 
173* `/v1/agents`
174* `/v1/sessions`
175* `/v1/environments`
115176 

managed-agents/session-operations Changed · +25 / -0 lines

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
35 Claude Models on Google Cloud (Anthropic managed): beta
1136---
1237 
1338Once 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.

managed-agents/session-threads Changed · +58 / -1 lines

## Availability ### API support #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) ### Required beta headers ### Data handling

from line 6
66 topic:
77 title: Managed Agents
88 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
109 betaHeader: managed-agents-2026-04-01
10 zdr:
11 eligibility: not-eligible
12 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
13 supportedModels:
14 - claude-fable-5-1
15 - claude-mythos-5-1
16 - claude-fable-5
17 - claude-mythos-5
18 - claude-mythos-preview
19 - claude-opus-5-5
20 - claude-opus-5
21 - claude-sonnet-5-5
22 - claude-sonnet-5
23 - claude-haiku-5-5
24 - claude-haiku-4-5-20251001
25 - claude-opus-4-8
26 - claude-opus-4-7
27 - claude-opus-4-6
28 - claude-sonnet-4-6
29 - claude-opus-4-5-20251101
30 - claude-sonnet-4-5-20250929
1131---
1232 
1333In a [multiagent session](https://platform.claude.com/docs/en/managed-agents/multiagent-orchestration), each agent works in its own **session thread**. This page covers how to list, interrupt, and archive threads, the events they send, and how tool permissions work across them. A [workflow run](https://platform.claude.com/docs/en/managed-agents/workflow-runs) creates session threads too.
from line 800
780800</CodeGroup>
781801 
782802The previous pattern answers the calls that an idle event lists. On the primary stream, a subagent’s `session.thread_status_idle` event can arrive before the `agent.tool_use` or `agent.mcp_tool_use` events that its `stop_reason.event_ids` lists. A `user.tool_confirmation` for a call whose event hasn’t arrived yet can return 400. To avoid that, answer each call whose [`evaluated_permission` (java, php: `evaluatedPermission`; csharp, go: `EvaluatedPermission`)](https://platform.claude.com/docs/en/managed-agents/permission-policies#see-how-each-call-was-evaluated) is `ask` when its own event arrives on the primary stream.
803 
804## Availability
805 
806Session threads are available on every model.
807 
808### API support
809 
810#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
811 
812* Availability: Always on
813 
814| Status | Cloud platforms |
815| --------- | ----------------------- |
816| Available | All supported platforms |
817 
818### Required beta headers
819 
820[Beta headers overview](https://platform.claude.com/docs/en/api/beta-headers)
821 
822Beta headers allow you to access experimental features and new model capabilities before they become part of the standard API.
823 
824* `managed-agents-2026-04-01`
825 
826### Data handling
827 
828[Data handling overview](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility)
829 
830| Item | Zero data retention | HIPAA |
831| ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
832| Status | Not eligible | Not eligible |
833| Details | Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes. | Applies to all Managed Agents sub-features, including Self-hosted sandboxes. |
834 
835Applicable endpoints:
836 
837* `/v1/agents`
838* `/v1/sessions`
839* `/v1/environments`
783840 

managed-agents/sessions Changed · +25 / -0 lines

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
35 Claude Models on Google Cloud (Anthropic managed): beta
1136---
1237 
1338A 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` (java, php: `initialEvents`; csharp, go: `InitialEvents`)](https://platform.claude.com/docs/en/managed-agents/sessions#seed-the-session-with-initial-events).

managed-agents/skills Changed · +25 / -0 lines

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
35 Claude Models on Google Cloud (Anthropic managed): beta
1136---
1237 
1338Skills 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.

managed-agents/tools Changed · +61 / -0 lines

## Availability ### API support #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) ### Required beta headers ### Data handling

from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 status: beta
1010 betaHeader: managed-agents-2026-04-01
11 zdr:
12 eligibility: not-eligible
13 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
14 supportedModels:
15 - claude-fable-5-1
16 - claude-mythos-5-1
17 - claude-fable-5
18 - claude-mythos-5
19 - claude-mythos-preview
20 - claude-opus-5-5
21 - claude-opus-5
22 - claude-sonnet-5-5
23 - claude-sonnet-5
24 - claude-haiku-5-5
25 - claude-haiku-4-5-20251001
26 - claude-opus-4-8
27 - claude-opus-4-7
28 - claude-opus-4-6
29 - claude-sonnet-4-6
30 - claude-opus-4-5-20251101
31 - claude-sonnet-4-5-20250929
32 supportedPlatforms:
33 Claude API: beta
34 Claude Platform on AWS: beta
1135---
1236 
1337Claude 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.
from line 537
513537 Send events, stream responses, and interrupt or redirect your session while it runs.
514538 </Card>
515539</CardGroup>
540 
541## Availability
542 
543Agent toolset is in beta on every model.
544 
545### API support
546 
547#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
548 
549* Availability: Available
550 
551| Status | Cloud platforms |
552| ------ | ------------------------------------------------------------------------------------------------------------------ |
553| Beta | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) |
554 
555### Required beta headers
556 
557[Beta headers overview](https://platform.claude.com/docs/en/api/beta-headers)
558 
559Beta headers allow you to access experimental features and new model capabilities before they become part of the standard API.
560 
561* `managed-agents-2026-04-01`
562 
563### Data handling
564 
565[Data handling overview](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility)
566 
567| Item | Zero data retention | HIPAA |
568| ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
569| Status | Not eligible | Not eligible |
570| Details | Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes. | Applies to all Managed Agents sub-features, including Self-hosted sandboxes. |
571 
572Applicable endpoints:
573 
574* `/v1/agents`
575* `/v1/sessions`
576* `/v1/environments`
516577 

managed-agents/tools-web-restrictions Changed · +61 / -1 lines

## Availability ### API support #### [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) ### Required beta headers

from line 6
66 topic:
77 title: Managed Agents
88 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
109 betaHeader: managed-agents-2026-04-01
10 supportedModels:
11 - claude-fable-5-1
12 - claude-mythos-5-1
13 - claude-fable-5
14 - claude-mythos-5
15 - claude-mythos-preview
16 - claude-opus-5-5
17 - claude-opus-5
18 - claude-sonnet-5-5
19 - claude-sonnet-5
20 - claude-haiku-5-5
21 - claude-haiku-4-5-20251001
22 - claude-opus-4-8
23 - claude-opus-4-7
24 - claude-opus-4-6
25 - claude-sonnet-4-6
26 - claude-opus-4-5-20251101
27 - claude-sonnet-4-5-20250929
28 supportedPlatforms:
29 Claude API: ga
30 Claude Platform on AWS: beta
31 Claude Models on Google Cloud (Anthropic managed): beta
1132---
1233 
34**API support**: Usage differs by product.
35 
36* **Messages API**: Set `allowed_domains` or `blocked_domains` on the `web_search` or `web_fetch` tool in the request.
37* **Managed Agents**: Set the same fields on the agent toolset; each list holds at most 64 domains.
38 
1339To control which sites the agent’s web tools can reach, set a domain list on the `web_search` and `web_fetch` entries of the [agent toolset](https://platform.claude.com/docs/en/managed-agents/tools#configuring-the-toolset). Each of these `configs` (csharp, go: `Configs`) entries takes one of two lists:
1440 
1541* **`allowed_domains` (java, php: `allowedDomains`; csharp, go: `AllowedDomains`):** The tool can reach only these hosts.
from line 544
518544 Coordinate multiple agents within a single session.
519545 </Card>
520546</CardGroup>
547 
548## Availability
549 
550Web domain restrictions are available or in beta, depending on the API.
551 
552### API support
553 
554#### [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages)
555 
556* Availability: Available
557* Usage: Set `allowed_domains` or `blocked_domains` on the `web_search` or `web_fetch` tool in the request.
558 
559| Status | Cloud platforms |
560| --------- | --------------- |
561| Available | Claude API |
562 
563#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
564 
565* Availability: Available
566* Usage: Set the same fields on the `web_search` and `web_fetch` entries of the agent toolset. Unlike the Messages API, each list holds at most 64 ASCII domains, and `web_fetch` domains cannot include a path.
567 
568| Status | Cloud platforms | Models |
569| ------ | ----------------------- | ----------------------------------------------------------------- |
570| Beta | All supported platforms | [All models](https://platform.claude.com/docs/en/models/overview) |
571 
572### Required beta headers
573 
574[Beta headers overview](https://platform.claude.com/docs/en/api/beta-headers)
575 
576Beta headers allow you to access experimental features and new model capabilities before they become part of the standard API.
577 
578| Header | APIs |
579| --------------------------- | ----------------------------------------------------------------------------- |
580| `managed-agents-2026-04-01` | [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) |
521581 

managed-agents/vaults Changed · +58 / -1 lines

## Availability ### API support #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) ### Required beta headers ### Data handling

from line 6
66 topic:
77 title: Managed Agents
88 url: https://platform.claude.com/docs/en/managed-agents/overview
9 status: beta
109 betaHeader: managed-agents-2026-04-01
10 zdr:
11 eligibility: not-eligible
12 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
13 supportedModels:
14 - claude-fable-5-1
15 - claude-mythos-5-1
16 - claude-fable-5
17 - claude-mythos-5
18 - claude-mythos-preview
19 - claude-opus-5-5
20 - claude-opus-5
21 - claude-sonnet-5-5
22 - claude-sonnet-5
23 - claude-haiku-5-5
24 - claude-haiku-4-5-20251001
25 - claude-opus-4-8
26 - claude-opus-4-7
27 - claude-opus-4-6
28 - claude-sonnet-4-6
29 - claude-opus-4-5-20251101
30 - claude-sonnet-4-5-20250929
1131---
1232 
1333Vaults 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.
from line 1113
10931113* **Archive a vault:** `POST /v1/vaults/{id}/archive`. Cascades to all credentials. Secrets are purged; records are retained for auditing. Future sessions referencing this vault fail; running sessions continue.
10941114* **Archive a credential:** `POST /v1/vaults/{id}/credentials/{cred_id}/archive`. Purges the secret payload; the credential key (`mcp_server_url` or `secret_name`) remains visible and is freed for a replacement credential.
10951115* **Delete a vault or credential:** Hard delete. The record is not retained. Use archive if you need an audit trail.
1116 
1117## Availability
1118 
1119Vaults are available on every model.
1120 
1121### API support
1122 
1123#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
1124 
1125* Availability: Available
1126 
1127| Status | Cloud platforms | Models |
1128| --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------- |
1129| Available | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) | [All models](https://platform.claude.com/docs/en/models/overview) |
1130 
1131### Required beta headers
1132 
1133[Beta headers overview](https://platform.claude.com/docs/en/api/beta-headers)
1134 
1135Beta headers allow you to access experimental features and new model capabilities before they become part of the standard API.
1136 
1137* `managed-agents-2026-04-01`
1138 
1139### Data handling
1140 
1141[Data handling overview](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility)
1142 
1143| Item | Zero data retention | HIPAA |
1144| ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
1145| Status | Not eligible | Not eligible |
1146| Details | Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes. | Applies to all Managed Agents sub-features, including Self-hosted sandboxes. |
1147 
1148Applicable endpoints:
1149 
1150* `/v1/agents`
1151* `/v1/sessions`
1152* `/v1/environments`
10961153 
Feedback