Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
One capture · api

One read of Claude Developer Platform

256 pages moved out of 629 read.

api-20260916T150721Z

Pages moved 256 significant first
Pages read 629 in this capture
Captured 15:07 UTC
Corpus hash e061c4643db4 corpus-hash

What this read moved

76–100 of 256

This capture is too large to show at once. Changes 76-100 of 256 are below, significant first; the rest are on the following screens.

managed-agents/permission-policies Changed · +4 / -4 lines

## Compatibility

from line 4
44description: Control when agent and MCP tools execute.
55---
66 
7Permission 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.
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
810 
9<Note>
10 Managed Agents API requests require the `managed-agents-2026-04-01` beta header, except memory store endpoints, which use `agent-memory-2026-07-22` instead. The SDK sets the correct beta header automatically. See [Beta headers](https://platform.claude.com/docs/en/api/beta-headers#endpoint-specific-headers).
11</Note>
11Permission 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.
1212 
1313## Permission policy types
1414 

managed-agents/quickstart Changed · +5 / -5 lines

## Compatibility

from line 4
44description: Create your first autonomous agent.
55---
66 
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
10 
711This guide walks you through creating an agent, setting up an environment, starting a session, and streaming agent responses.
812 
913<Tip>
from line 41
3741 For Linux environments, download the release binary directly.
3842 
3943 ```bash
40 VERSION=1.30.0
44 VERSION=1.33.0
4145 OS=$(uname -s | tr '[:upper:]' '[:lower:]')
4246 case $(uname -m) in
4347 x86_64) ARCH=amd64 ;;
from line 128
124128```
125129 
126130## Create your first session
127 
128<Note>
129 Managed Agents API requests require the `managed-agents-2026-04-01` beta header, except memory store endpoints, which use `agent-memory-2026-07-22` instead. The SDK sets the correct beta header automatically. See [Beta headers](https://platform.claude.com/docs/en/api/beta-headers#endpoint-specific-headers).
130</Note>
131131 
132132<Steps>
133133 <Step title="Create an agent">

managed-agents/reference Changed · +4 / -4 lines

## Compatibility

from line 4
44description: Event types, self-hosted worker CLI flags, supported MCP server types, rate limits, and branding guidelines for Claude Managed Agents.
55---
66 
7This 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).
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
810 
9<Note>
10 Managed Agents API requests require the `managed-agents-2026-04-01` beta header, except memory store endpoints, which use `agent-memory-2026-07-22` instead. The SDK sets the correct beta header automatically. See [Beta headers](https://platform.claude.com/docs/en/api/beta-headers#endpoint-specific-headers).
11</Note>
11This 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).
1212 
1313## Event types
1414 

managed-agents/scheduled-deployments Changed · +4 / -4 lines

## Compatibility

from line 4
44description: "Create and manage deployments with the Claude API: run an agent on a recurring cron schedule and inspect its run history."
55---
66 
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
10 
711A **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.
812 
913For the launch context and examples of what teams run on schedules, see [scheduled deployments and vaults in Claude Managed Agents](https://claude.com/blog/whats-new-in-claude-managed-agents) on the blog.
10 
11<Note>
12 All Managed Agents API requests require the `managed-agents-2026-04-01` beta header. The SDK sets the beta header automatically.
13</Note>
1414 
1515## Create a scheduled deployment
1616 

managed-agents/self-hosted-sandboxes Changed · +6 / -2 lines

## Compatibility

from line 4
44description: Run Claude Managed Agents sessions in self-hosted sandboxes, keeping tool execution, files, and network egress in your own infrastructure.
55---
66 
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
10 
711By 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.
812 
913Tool execution stays on your host: the filesystem the agent reads and writes, the processes it spawns, and the network it can reach are all under your control. Tool inputs and outputs still flow to Anthropic's control plane (where Claude runs) so the model can see results and determine what to do next. The agent's [skills](https://platform.claude.com/docs/en/managed-agents/skills) and the contents of any [memory stores](https://platform.claude.com/docs/en/managed-agents/memory) attached to the session are stored by Anthropic and copied into your sandbox for the session; changes the agent makes to memory files sync back to the store. See the [security model](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes-security) for the full data-flow boundary.
from line 218
214218 For Linux environments, download the release binary directly.
215219 
216220 ```bash
217 VERSION=1.30.0
221 VERSION=1.33.0
218222 OS=$(uname -s | tr '[:upper:]' '[:lower:]')
219223 case $(uname -m) in
220224 x86_64) ARCH=amd64 ;;
from line 256
252256 
253257 ```text
254258 FROM your-base-image
255 ARG ANT_VERSION=1.30.0
259 ARG ANT_VERSION=1.33.0
256260 ARG TARGETARCH
257261 RUN ARCH=$([ "$TARGETARCH" = "arm64" ] && echo arm64 || echo amd64) && \
258262 curl -fsSL "https://github.com/anthropics/anthropic-cli/releases/download/v${ANT_VERSION}/ant_${ANT_VERSION}_linux_${ARCH}.tar.gz" \

managed-agents/self-hosted-sandboxes-security Changed · +4 / -0 lines

## Compatibility

from line 4
44description: Shared responsibility model for self-hosted sandbox environments.
55---
66 
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
10 
711Anthropic 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.
812 
913## What you own

managed-agents/session-operations Changed · +4 / -4 lines

## Compatibility

from line 4
44description: Retrieve, list, update, archive, and delete Claude Managed Agents sessions.
55---
66 
7Once 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.
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
810 
9<Note>
10 Managed Agents API requests require the `managed-agents-2026-04-01` beta header, except memory store endpoints, which use `agent-memory-2026-07-22` instead. The SDK sets the correct beta header automatically. See [Beta headers](https://platform.claude.com/docs/en/api/beta-headers#endpoint-specific-headers).
11</Note>
11Once 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.
1212 
1313## Session statuses
1414 

managed-agents/sessions Changed · +4 / -4 lines

## Compatibility

from line 4
44description: Create a session to run your agent and begin executing tasks.
55---
66 
7A 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).
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
810 
9<Note>
10 Managed Agents API requests require the `managed-agents-2026-04-01` beta header, except memory store endpoints, which use `agent-memory-2026-07-22` instead. The SDK sets the correct beta header automatically. See [Beta headers](https://platform.claude.com/docs/en/api/beta-headers#endpoint-specific-headers).
11</Note>
11A 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).
1212 
1313## Creating a session
1414 

managed-agents/skills Changed · +4 / -4 lines

## Compatibility

from line 4
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.
55---
66 
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
10 
711Skills 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.
812 
913Skills reach your agent in two ways: attach them through the agent's `skills` array, or [load them from a GitHub repository](https://platform.claude.com/docs/en/managed-agents/skills#load-skills-from-a-github-repository) mounted on the session. Attached skills come in two types. All skills work the same way: your agent invokes them automatically when they are relevant to the task.
from line 16
1216* **Custom skills:** Skills you author and upload to your workspace.
1317 
1418To learn how to author custom skills, see [Agent Skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) and [Skill authoring best practices](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices). To upload a custom skill to your workspace, see [Create a custom skill](https://platform.claude.com/docs/en/managed-agents/skills#create-a-custom-skill).
15 
16<Note>
17 Managed Agents API requests require the `managed-agents-2026-04-01` beta header, except memory store endpoints, which use `agent-memory-2026-07-22` instead. The SDK sets the correct beta header automatically. See [Beta headers](https://platform.claude.com/docs/en/api/beta-headers#endpoint-specific-headers).
18</Note>
1919 
2020## Create a custom skill
2121 

managed-agents/tools Changed · +4 / -4 lines

## Compatibility

from line 4
44description: Configure tools available to your agent.
55---
66 
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
10 
711Claude 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.
812 
913Claude Managed Agents also supports custom, user-defined tools. Your application executes these tools separately and returns the results to Claude, which uses them to continue the task. To give the agent tools from an MCP server, use the [MCP connector](https://platform.claude.com/docs/en/managed-agents/mcp-connector) instead.
10 
11<Note>
12 Managed Agents API requests require the `managed-agents-2026-04-01` beta header, except memory store endpoints, which use `agent-memory-2026-07-22` instead. The SDK sets the correct beta header automatically. See [Beta headers](https://platform.claude.com/docs/en/api/beta-headers#endpoint-specific-headers).
13</Note>
1414 
1515## Available tools
1616 

managed-agents/vaults Changed · +15 / -13 lines

## Compatibility

from line 4
44description: Register per-user credentials when creating sessions.
55---
66 
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
10 
711Vaults 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.
812 
913The vault reference is a per-session parameter, so you can manage your product at the `agent` resource granularity and your users at the `session` resource granularity.
1014 
11<Note>
12 Managed Agents API requests require the `managed-agents-2026-04-01` beta header, except memory store endpoints, which use `agent-memory-2026-07-22` instead. The SDK sets the correct beta header automatically. See [Beta headers](https://platform.claude.com/docs/en/api/beta-headers#endpoint-specific-headers).
13</Note>
14 
1515## Create a vault
1616 
1717<Warning>
from line 168
168168 "access_token": "xoxp-...",
169169 "expires_at": "2099-12-31T23:59:59Z",
170170 "refresh": {
171 "token_endpoint": "https://slack.com/api/oauth.v2.access",
171 "token_endpoint": "https://slack.com/api/oauth.v2.user.access",
172172 "client_id": "1234567890.0987654321",
173173 "scope": "channels:read chat:write",
174174 "refresh_token": "xoxe-1-...",
from line 191
191191 access_token: xoxp-...
192192 expires_at: "2099-12-31T23:59:59Z"
193193 refresh:
194 token_endpoint: https://slack.com/api/oauth.v2.access
194 token_endpoint: https://slack.com/api/oauth.v2.user.access
195195 client_id: "1234567890.0987654321"
196196 scope: channels:read chat:write
197197 refresh_token: xoxe-1-...
from line 212
212212 "access_token": "xoxp-...",
213213 "expires_at": "2099-12-31T23:59:59Z",
214214 "refresh": {
215 "token_endpoint": "https://slack.com/api/oauth.v2.access",
215 "token_endpoint": "https://slack.com/api/oauth.v2.user.access",
216216 "client_id": "1234567890.0987654321",
217217 "scope": "channels:read chat:write",
218218 "refresh_token": "xoxe-1-...",
from line 231
231231 access_token: "xoxp-...",
232232 expires_at: "2099-12-31T23:59:59Z",
233233 refresh: {
234 token_endpoint: "https://slack.com/api/oauth.v2.access",
234 token_endpoint: "https://slack.com/api/oauth.v2.user.access",
235235 client_id: "1234567890.0987654321",
236236 scope: "channels:read chat:write",
237237 refresh_token: "xoxe-1-...",
from line 256
256256 ExpiresAt = DateTimeOffset.Parse("2099-12-31T23:59:59Z"),
257257 Refresh = new()
258258 {
259 TokenEndpoint = "https://slack.com/api/oauth.v2.access",
259 TokenEndpoint = "https://slack.com/api/oauth.v2.user.access",
260260 ClientID = "1234567890.0987654321",
261261 Scope = "channels:read chat:write",
262262 RefreshToken = "xoxe-1-...",
from line 280
280280 AccessToken: "xoxp-...",
281281 ExpiresAt: anthropic.Time(time.Date(2099, time.December, 31, 23, 59, 59, 0, time.UTC)),
282282 Refresh: anthropic.BetaManagedAgentsMCPOAuthRefreshParams{
283 TokenEndpoint: "https://slack.com/api/oauth.v2.access",
283 TokenEndpoint: "https://slack.com/api/oauth.v2.user.access",
284284 ClientID: "1234567890.0987654321",
285285 Scope: anthropic.String("channels:read chat:write"),
286286 RefreshToken: "xoxe-1-...",
from line 309
309309 .accessToken("xoxp-...")
310310 .expiresAt(OffsetDateTime.parse("2099-12-31T23:59:59Z"))
311311 .refresh(BetaManagedAgentsMcpOAuthRefreshParams.builder()
312 .tokenEndpoint("https://slack.com/api/oauth.v2.access")
312 .tokenEndpoint("https://slack.com/api/oauth.v2.user.access")
313313 .clientId("1234567890.0987654321")
314314 .scope("channels:read chat:write")
315315 .refreshToken("xoxe-1-...")
from line 329
329329 accessToken: 'xoxp-...',
330330 expiresAt: new DateTimeImmutable('2099-12-31T23:59:59Z'),
331331 refresh: ManagedAgentsMCPOAuthRefreshParams::with(
332 tokenEndpoint: 'https://slack.com/api/oauth.v2.access',
332 tokenEndpoint: 'https://slack.com/api/oauth.v2.user.access',
333333 clientID: '1234567890.0987654321',
334334 scope: 'channels:read chat:write',
335335 refreshToken: 'xoxe-1-...',
from line 352
352352 access_token: "xoxp-...",
353353 expires_at: "2099-12-31T23:59:59Z",
354354 refresh: {
355 token_endpoint: "https://slack.com/api/oauth.v2.access",
355 token_endpoint: "https://slack.com/api/oauth.v2.user.access",
356356 client_id: "1234567890.0987654321",
357357 scope: "channels:read chat:write",
358358 refresh_token: "xoxe-1-...",
from line 365
365365 )
366366 ```
367367 </CodeGroup>
368 
369 Set `refresh.token_endpoint` to the token endpoint of the OAuth flow that issued the refresh token, because Anthropic sends every refresh request to that URL and the field can't be changed after the credential is created.
368370 </Tab>
369371 
370372 <Tab title="MCP static bearer">

managed-agents/webhooks Changed · +4 / -0 lines

## Compatibility

from line 4
44description: Get notified when major events happen without polling.
55---
66 
7## Compatibility
8- Status: Beta
9- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `managed-agents-2026-04-01`
10 
711Sessions 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.
812 
913Webhook events return the event `type` and `id`, not the full object. When you receive a webhook event, you need to fetch the object directly with a `GET` call. This avoids delivering stale data on retries and keeps every delivery small.

agents-and-tools/agent-skills/quickstart Changed · +1 / -1 lines

from line 499
499499 if fileID != "" {
500500 // Download the file and save it
501501 outputPath := filepath.Join(os.TempDir(), "renewable_energy.pptx")
502 fileContent, err := client.Files.Download(ctx, fileID)
502 fileContent, err := client.Files.Download(ctx, fileID, anthropic.FileDownloadParams{})
503503 if err != nil {
504504 panic(err)
505505 }

agents-and-tools/tool-use/code-execution-tool Changed · +2 / -2 lines

from line 686
686686 fileIDs := extractFileIDs(response)
687687 
688688 for _, fileID := range fileIDs {
689 fileMetadata, err := client.Files.GetMetadata(ctx, fileID)
689 fileMetadata, err := client.Files.GetMetadata(ctx, fileID, anthropic.FileGetMetadataParams{})
690690 if err != nil {
691691 log.Fatal(err)
692692 }
693693 
694 fileContent, err := client.Files.Download(ctx, fileID)
694 fileContent, err := client.Files.Download(ctx, fileID, anthropic.FileDownloadParams{})
695695 if err != nil {
696696 log.Fatal(err)
697697 }

api/beta/agents/archive Changed · +3 / -1 lines

from line 21
2121 
2222 - `string`
2323 
24 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more`
24 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
2525 
2626 - `"message-batches-2024-09-24"`
2727 
from line 112
112112 - `"thinking-binding-controls-2026-08-01"`
113113 
114114 - `"mid-conversation-system-clear-at-2026-08-21"`
115 
116 - `"compact-2026-09-04"`
115117 
116118- `"anthropic-workspace-id": optional string`
117119 

api/beta/agents/create Changed · +3 / -1 lines

from line 17
1717 
1818 - `string`
1919 
20 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more`
20 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
2121 
2222 - `"message-batches-2024-09-24"`
2323 
from line 108
108108 - `"thinking-binding-controls-2026-08-01"`
109109 
110110 - `"mid-conversation-system-clear-at-2026-08-21"`
111 
112 - `"compact-2026-09-04"`
111113 
112114- `"anthropic-workspace-id": optional string`
113115 

api/beta/agents/list Changed · +3 / -1 lines

from line 45
4545 
4646 - `string`
4747 
48 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more`
48 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
4949 
5050 - `"message-batches-2024-09-24"`
5151 
from line 136
136136 - `"thinking-binding-controls-2026-08-01"`
137137 
138138 - `"mid-conversation-system-clear-at-2026-08-21"`
139 
140 - `"compact-2026-09-04"`
139141 
140142- `"anthropic-workspace-id": optional string`
141143 

api/beta/agents/retrieve Changed · +3 / -1 lines

from line 29
2929 
3030 - `string`
3131 
32 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more`
32 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
3333 
3434 - `"message-batches-2024-09-24"`
3535 
from line 120
120120 - `"thinking-binding-controls-2026-08-01"`
121121 
122122 - `"mid-conversation-system-clear-at-2026-08-21"`
123 
124 - `"compact-2026-09-04"`
123125 
124126- `"anthropic-workspace-id": optional string`
125127 

api/beta/agents/update Changed · +3 / -1 lines

from line 21
2121 
2222 - `string`
2323 
24 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more`
24 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
2525 
2626 - `"message-batches-2024-09-24"`
2727 
from line 112
112112 - `"thinking-binding-controls-2026-08-01"`
113113 
114114 - `"mid-conversation-system-clear-at-2026-08-21"`
115 
116 - `"compact-2026-09-04"`
115117 
116118- `"anthropic-workspace-id": optional string`
117119 

api/beta/agents/versions Changed · +3 / -1 lines

from line 35
3535 
3636 - `string`
3737 
38 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more`
38 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
3939 
4040 - `"message-batches-2024-09-24"`
4141 
from line 126
126126 - `"thinking-binding-controls-2026-08-01"`
127127 
128128 - `"mid-conversation-system-clear-at-2026-08-21"`
129 
130 - `"compact-2026-09-04"`
129131 
130132- `"anthropic-workspace-id": optional string`
131133 

api/beta/agents/versions/list Changed · +3 / -1 lines

from line 33
3333 
3434 - `string`
3535 
36 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more`
36 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
3737 
3838 - `"message-batches-2024-09-24"`
3939 
from line 124
124124 - `"thinking-binding-controls-2026-08-01"`
125125 
126126 - `"mid-conversation-system-clear-at-2026-08-21"`
127 
128 - `"compact-2026-09-04"`
127129 
128130- `"anthropic-workspace-id": optional string`
129131 

api/beta/deployment_runs/list Changed · +3 / -1 lines

from line 69
6969 
7070 - `string`
7171 
72 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more`
72 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
7373 
7474 - `"message-batches-2024-09-24"`
7575 
from line 160
160160 - `"thinking-binding-controls-2026-08-01"`
161161 
162162 - `"mid-conversation-system-clear-at-2026-08-21"`
163 
164 - `"compact-2026-09-04"`
163165 
164166- `"anthropic-workspace-id": optional string`
165167 

api/beta/deployment_runs/retrieve Changed · +3 / -1 lines

from line 21
2121 
2222 - `string`
2323 
24 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more`
24 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
2525 
2626 - `"message-batches-2024-09-24"`
2727 
from line 112
112112 - `"thinking-binding-controls-2026-08-01"`
113113 
114114 - `"mid-conversation-system-clear-at-2026-08-21"`
115 
116 - `"compact-2026-09-04"`
115117 
116118- `"anthropic-workspace-id": optional string`
117119 

api/beta/deployments/archive Changed · +3 / -1 lines

from line 21
2121 
2222 - `string`
2323 
24 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more`
24 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
2525 
2626 - `"message-batches-2024-09-24"`
2727 
from line 112
112112 - `"thinking-binding-controls-2026-08-01"`
113113 
114114 - `"mid-conversation-system-clear-at-2026-08-21"`
115 
116 - `"compact-2026-09-04"`
115117 
116118- `"anthropic-workspace-id": optional string`
117119 

api/beta/deployments/create Changed · +3 / -1 lines

from line 17
1717 
1818 - `string`
1919 
20 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 42 more`
20 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`
2121 
2222 - `"message-batches-2024-09-24"`
2323 
from line 108
108108 - `"thinking-binding-controls-2026-08-01"`
109109 
110110 - `"mid-conversation-system-clear-at-2026-08-21"`
111 
112 - `"compact-2026-09-04"`
111113 
112114- `"anthropic-workspace-id": optional string`
113115