multiagent-orchestration changedmanaged-agents/multiagent-orchestration
Recorded here
Lines+63added
Lines−1removed
From line
8
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits32to this page, all time
## Availability ### API support #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) ### Required beta headers ### Data handling
The whole hunk
from line 8, old and new numbered
/
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
No line in this hunk matches that.