One change
Agents
api/beta/agents
Nearest release: v2.1.245, published an hour after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
api/beta/agents Changed · +1020 / -1799 lines
### Headers ### Body parameters #### Response (200) ### Query parameters ### Headers #### Response (200) ### Path parameters ### Query parameters ### Headers #### Response (200) ### Path parameters ### Headers ### Body parameters #### Response (200) ### Path parameters ### Headers #### Response (200) ## Domain types ## Agents › Versions ### List Agent Versions #### Path parameters #### Query parameters #### Headers #### Returns #### Example ##### Response (200) ### Header Parameters ### Body Parameters #### Response ### Query Parameters ### Header Parameters #### Response ### Path Parameters ### Query Parameters ### Header Parameters #### Response ### Path Parameters ### Header Parameters ### Body Parameters #### Response ### Path Parameters ### Header Parameters #### Response ## Domain Types # Versions ## List Agent Versions ### Path Parameters ### Query Parameters ### Header Parameters #### Response
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
The two sides of this change are too far apart to line up, so this is the differ's own diff of it.
from line 1
---- -title: Agents -url: https://platform.claude.com/docs/en/api/beta/agents ---- - # Agents ## Create Agent -**post** `/v1/agents` +**POST** `/v1/agents` Create Agent -### Header Parameters +### Headers - `"anthropic-beta": optional array of AnthropicBeta`
from line 84
- `"mid-conversation-tool-changes-2026-07-01"` -### Body Parameters +### Body parameters - `model: BetaManagedAgentsModel or BetaManagedAgentsModelConfigParams`
from line 156
- `string` - - `BetaManagedAgentsModelConfigParams object { id, effort, inference_geo, speed }` + - `BetaManagedAgentsModelConfigParams object` An object that defines additional configuration control over model use
from line 184
- `"max"` - - `BetaManagedAgentsEffortLow object { type }` + - `BetaManagedAgentsEffortLow object` Low effort. Favors latency over reasoning depth. - `type: "low"` - - `"low"` - - - `BetaManagedAgentsEffortMedium object { type }` + - `BetaManagedAgentsEffortMedium object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - - `"medium"` - - - `BetaManagedAgentsEffortHigh object { type }` + - `BetaManagedAgentsEffortHigh object` High effort. Favors reasoning depth. - `type: "high"` - - `"high"` - - - `BetaManagedAgentsEffortXhigh object { type }` + - `BetaManagedAgentsEffortXhigh object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - - `"xhigh"` - - - `BetaManagedAgentsEffortMax object { type }` + - `BetaManagedAgentsEffortMax object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - - `"max"` - - `inference_geo: optional string or null` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. On update, `model` is whole-object replacement — omitting inference_geo clears it.
from line 230
Human-readable name for the agent. + minLength: 1, maxLength: 256 + - `description: optional string or null` Description of what the agent does. + maxLength: 2048 + - `mcp_servers: optional array of BetaManagedAgentsURLMCPServerParams` MCP servers this agent connects to. Maximum 20. Names must be unique within the array. Every server must be referenced by an `mcp_toolset` in `tools`; unreferenced servers are rejected. See the [MCP connector guide](https://platform.claude.com/docs/en/managed-agents/mcp-connector).
from line 246
Unique name for this server, referenced by mcp_toolset configurations. 1-255 characters. + minLength: 1, maxLength: 255 + - `type: "url"` - - `"url"` - - `url: string` Endpoint URL for the MCP server. + maxLength: 2048 + - `metadata: optional map[string]` Arbitrary key-value metadata. Maximum 16 pairs, keys up to 64 chars, values up to 512 chars.
from line 270
- `string` - - `BetaManagedAgentsAgentParams object { id, type, version }` + - `BetaManagedAgentsAgentParams object` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version
from line 278
The `agent` ID. + minLength: 1, maxLength: 128 + - `type: "agent"` - - `"agent"` - - `version: optional number` The specific `agent` version to use. Omit to use the latest version. Must be at least 1 if specified. - - `BetaManagedAgentsMultiagentSelfParams object { type }` + format: int32 + + - `BetaManagedAgentsMultiagentSelfParams object` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `type: "self"` - - `"self"` - - - `BetaManagedAgentsAdvisorParams object { model, type }` + - `BetaManagedAgentsAdvisorParams object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. At most one per roster; the entry occupies the roster name `anthropic.advisor`.
from line 302
A Claude model id. The model must be permitted as an advisor for this agent's model — see the sessions/threads/advisor spec. + minLength: 1, maxLength: 256 + - `type: "advisor"` - - `"advisor"` - - `type: "coordinator"` - - `"coordinator"` - - `skills: optional array of BetaManagedAgentsSkillParams` Skills available to the agent. - - `BetaManagedAgentsAnthropicSkillParams object { skill_id, type, version }` + - `BetaManagedAgentsAnthropicSkillParams object` An Anthropic-managed skill.
from line 320
Identifier of the Anthropic skill (e.g., "xlsx"). + minLength: 1, maxLength: 64 + - `type: "anthropic"` - - `"anthropic"` - - `version: optional string or null` Version to pin. Defaults to latest if omitted. - - `BetaManagedAgentsCustomSkillParams object { skill_id, type, version }` + minLength: 1, maxLength: 64 + + - `BetaManagedAgentsCustomSkillParams object` A user-created custom skill.
from line 338
Tagged ID of the custom skill (e.g., "skill_01XJ5..."). + minLength: 1, maxLength: 64 + - `type: "custom"` - - `"custom"` - - `version: optional string or null` Version to pin. Defaults to latest if omitted. + minLength: 1, maxLength: 64 + - `system: optional string or null` System prompt for the agent. + maxLength: 100000 + - `tools: optional array of BetaManagedAgentsAgentToolset20260401Params or BetaManagedAgentsMCPToolsetParams or BetaManagedAgentsCustomToolParams` Tool configurations available to the agent. Maximum of 128 tools across all toolsets allowed. - - `BetaManagedAgentsAgentToolset20260401Params object { type, configs, default_config }` + - `BetaManagedAgentsAgentToolset20260401Params object` Configuration for built-in agent tools. Use this to enable or disable groups of tools available to the agent. - `type: "agent_toolset_20260401"` - - `"agent_toolset_20260401"` - - `configs: optional array of BetaManagedAgentsAgentToolConfigParams` Per-tool configuration overrides. - - `BetaManagedAgentsBashToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsBashToolConfigParams object` Configuration override for the bash tool.
from line 376
Must be "bash". - - `"bash"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 384
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: optional "bash"` - - `"bash"` - - - `BetaManagedAgentsEditToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsEditToolConfigParams object` Configuration override for the edit tool.
from line 406
Must be "edit". - - `"edit"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 414
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "edit"` - - `"edit"` - - - `BetaManagedAgentsReadToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsReadToolConfigParams object` Configuration override for the read tool.
from line 432
Must be "read". - - `"read"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 440
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "read"` - - `"read"` - - - `BetaManagedAgentsWriteToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsWriteToolConfigParams object` Configuration override for the write tool.
from line 458
Must be "write". - - `"write"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 466
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "write"` - - `"write"` - - - `BetaManagedAgentsGlobToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsGlobToolConfigParams object` Configuration override for the glob tool.
from line 484
Must be "glob". - - `"glob"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 492
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "glob"` - - `"glob"` - - - `BetaManagedAgentsGrepToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsGrepToolConfigParams object` Configuration override for the grep tool.
from line 510
Must be "grep". - - `"grep"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 518
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "grep"` - - `"grep"` - - - `BetaManagedAgentsWebFetchToolConfigParams object { name, allowed_domains, blocked_domains, 4 more }` + - `BetaManagedAgentsWebFetchToolConfigParams object` Configuration override for the web_fetch tool.
from line 536
Must be "web_fetch". - - `"web_fetch"` - - `allowed_domains: optional array of string` Only fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains.
from line 552
Maximum number of tokens of fetched text content to include in context per call. Does not apply to binary content such as PDFs. + format: int32 + - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or null` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "web_fetch"` - - `"web_fetch"` - - - `BetaManagedAgentsWebSearchToolConfigParams object { name, allowed_domains, blocked_domains, 4 more }` + - `BetaManagedAgentsWebSearchToolConfigParams object` Configuration override for the web_search tool.
from line 576
Must be "web_search". - - `"web_search"` - - `allowed_domains: optional array of string` Only return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains.
from line 592
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "web_search"` - - `"web_search"` - - `user_location: optional BetaManagedAgentsUserLocation or null` Approximate user location for search result localization.
from line 610
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 624
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + - `default_config: optional BetaManagedAgentsAgentToolsetDefaultConfigParams or null` Default configuration for all tools in a toolset.
from line 644
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - - `BetaManagedAgentsMCPToolsetParams object { mcp_server_name, type, configs, default_config }` + - `BetaManagedAgentsMCPToolsetParams object` Configuration for tools from an MCP server defined in `mcp_servers`.
from line 660
Name of the MCP server. Must match a server name from the mcp_servers array. 1-255 characters. + minLength: 1, maxLength: 255 + - `type: "mcp_toolset"` - - `"mcp_toolset"` - - `configs: optional array of BetaManagedAgentsMCPToolConfigParams` Per-tool configuration overrides.
from line 672
Name of the MCP tool to configure. 1-128 characters. + minLength: 1, maxLength: 128 + - `enabled: optional boolean or null` Whether this tool is enabled. Overrides the `default_config` setting.
from line 682
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 702
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - - `BetaManagedAgentsCustomToolParams object { description, input_schema, name, type }` + - `BetaManagedAgentsCustomToolParams object` A custom tool that is executed by the API client rather than the agent. When the agent calls this tool, an `agent.custom_tool_use` event is emitted and the session goes idle, waiting for the client to provide the result via a `user.custom_tool_result` event.
from line 718
Description of what the tool does, shown to the agent to help it decide when to use the tool. + minLength: 1 + - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: "object"` - - `"object"` - - `properties: optional map[unknown] or null` - `required: optional array of string or null`
from line 734
Unique name for the tool. 1-128 characters; letters, digits, underscores, and hyphens. + minLength: 1, maxLength: 128 + - `type: "custom"` - - `"custom"` - ### Returns -- `BetaManagedAgentsAgent object { id, archived_at, created_at, 12 more }` +- `BetaManagedAgentsAgent object` A Managed Agents `agent`.
from line 750
A timestamp in RFC 3339 format + format: date-time + - `created_at: string` A timestamp in RFC 3339 format + format: date-time + - `description: string or null` - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`
from line 766
- `type: "url"` - - `"url"` - - `url: string` - `metadata: map[string]`
from line 844
How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes. - - `BetaManagedAgentsEffortLow object { type }` + - `BetaManagedAgentsEffortLow object` Low effort. Favors latency over reasoning depth. - `type: "low"` - - `"low"` - - - `BetaManagedAgentsEffortMedium object { type }` + - `BetaManagedAgentsEffortMedium object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - - `"medium"` - - - `BetaManagedAgentsEffortHigh object { type }` + - `BetaManagedAgentsEffortHigh object` High effort. Favors reasoning depth. - `type: "high"` - - `"high"` - - - `BetaManagedAgentsEffortXhigh object { type }` + - `BetaManagedAgentsEffortXhigh object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - - `"xhigh"` - - - `BetaManagedAgentsEffortMax object { type }` + - `BetaManagedAgentsEffortMax object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - - `"max"` - - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.
from line 894
Agents the coordinator may spawn as session threads, each resolved to a specific version. - - `BetaManagedAgentsAgentReference object { id, type, version }` + - `BetaManagedAgentsAgentReference object` A resolved agent reference with a concrete version.
from line 902
- `type: "agent"` - - `"agent"` - - `version: number` - - `BetaManagedAgentsAdvisor object { model, type }` + format: int32 + + - `BetaManagedAgentsAdvisor object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
from line 916
- `type: "advisor"` - - `"advisor"` - - `type: "coordinator"` - - `"coordinator"` - - `name: string` - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - - `BetaManagedAgentsAnthropicSkill object { skill_id, type, version }` + - `BetaManagedAgentsAnthropicSkill object` A resolved Anthropic-managed skill.
from line 930
- `type: "anthropic"` - - `"anthropic"` - - `version: string` - - `BetaManagedAgentsCustomSkill object { skill_id, type, version }` + - `BetaManagedAgentsCustomSkill object` A resolved user-created custom skill.
from line 940
- `type: "custom"` - - `"custom"` - - `version: string` - `system: string or null` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - - `BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }` + - `BetaManagedAgentsAgentToolset20260401 object` - `configs: array of BetaManagedAgentsAgentToolConfig` - - `BetaManagedAgentsBashToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsBashToolConfig object` Configuration for the bash tool.
from line 958
- `name: "bash"` - - `"bash"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "bash"` - - `"bash"` - - - `BetaManagedAgentsEditToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsEditToolConfig object` Configuration for the edit tool.
from line 984
- `name: "edit"` - - `"edit"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "edit"` - - `"edit"` - - - `BetaManagedAgentsReadToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsReadToolConfig object` Configuration for the read tool.
from line 1006
- `name: "read"` - - `"read"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "read"` - - `"read"` - - - `BetaManagedAgentsWriteToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsWriteToolConfig object` Configuration for the write tool.
from line 1028
- `name: "write"` - - `"write"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "write"` - - `"write"` - - - `BetaManagedAgentsGlobToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGlobToolConfig object` Configuration for the glob tool.
from line 1050
- `name: "glob"` - - `"glob"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "glob"` - - `"glob"` - - - `BetaManagedAgentsGrepToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGrepToolConfig object` Configuration for the grep tool.
from line 1072
- `name: "grep"` - - `"grep"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "grep"` - - `"grep"` - - - `BetaManagedAgentsWebFetchToolConfig object { enabled, name, permission_policy, 4 more }` + - `BetaManagedAgentsWebFetchToolConfig object` Configuration for the web_fetch tool.
from line 1094
- `name: "web_fetch"` - - `"web_fetch"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_fetch"` - - `"web_fetch"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number or null` - - `BetaManagedAgentsWebSearchToolConfig object { enabled, name, permission_policy, 4 more }` + format: int32 + + - `BetaManagedAgentsWebSearchToolConfig object` Configuration for the web_search tool.
from line 1124
- `name: "web_search"` - - `"web_search"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_search"` - - `"web_search"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string`
from line 1150
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 1164
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools.
from line 1182
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "agent_toolset_20260401"` - - `"agent_toolset_20260401"` - - - `BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }` + - `BetaManagedAgentsMCPToolset object` - `configs: array of BetaManagedAgentsMCPToolConfig`
from line 1204
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 1222
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 1234
- `type: "mcp_toolset"` - - `"mcp_toolset"` - - - `BetaManagedAgentsCustomTool object { description, input_schema, name, type }` + - `BetaManagedAgentsCustomTool object` A custom tool as returned in API responses.
from line 1246
- `type: "object"` - - `"object"` - - `properties: optional map[unknown] or null` - `required: optional array of string or null`
from line 1254
- `type: "custom"` - - `"custom"` - - `type: "agent"` - - `"agent"` - - `updated_at: string` A timestamp in RFC 3339 format + format: date-time + - `version: number` The agent's current version. Starts at 1 and increments when the agent is modified. + format: int32 + ### Example -```http +```bash curl https://api.anthropic.com/v1/agents \ -H 'Content-Type: application/json' \ -H 'anthropic-version: 2023-06-01' \
from line 1292
}' ``` -#### Response +#### Response (200) ```json {
from line 1371
## List Agents -**get** `/v1/agents` +**GET** `/v1/agents` List Agents -### Query Parameters +### Query parameters - `"created_at[gte]": optional string` Return agents created at or after this time (inclusive). + format: date-time + - `"created_at[lte]": optional string` Return agents created at or before this time (inclusive). + format: date-time + - `include_archived: optional boolean` Include archived agents in results. Defaults to false.
from line 1397
Maximum results per page. Default 20, maximum 100. + format: int32 + - `page: optional string` Opaque pagination cursor from a previous response. -### Header Parameters +### Headers - `"anthropic-beta": optional array of AnthropicBeta`
from line 1493
A timestamp in RFC 3339 format + format: date-time + - `created_at: string` A timestamp in RFC 3339 format + format: date-time + - `description: string or null` - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`
from line 1509
- `type: "url"` - - `"url"` - - `url: string` - `metadata: map[string]`
from line 1587
How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes. - - `BetaManagedAgentsEffortLow object { type }` + - `BetaManagedAgentsEffortLow object` Low effort. Favors latency over reasoning depth. - `type: "low"` - - `"low"` - - - `BetaManagedAgentsEffortMedium object { type }` + - `BetaManagedAgentsEffortMedium object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - - `"medium"` - - - `BetaManagedAgentsEffortHigh object { type }` + - `BetaManagedAgentsEffortHigh object` High effort. Favors reasoning depth. - `type: "high"` - - `"high"` - - - `BetaManagedAgentsEffortXhigh object { type }` + - `BetaManagedAgentsEffortXhigh object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - - `"xhigh"` - - - `BetaManagedAgentsEffortMax object { type }` + - `BetaManagedAgentsEffortMax object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - - `"max"` - - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.
from line 1637
Agents the coordinator may spawn as session threads, each resolved to a specific version. - - `BetaManagedAgentsAgentReference object { id, type, version }` + - `BetaManagedAgentsAgentReference object` A resolved agent reference with a concrete version.
from line 1645
- `type: "agent"` - - `"agent"` - - `version: number` - - `BetaManagedAgentsAdvisor object { model, type }` + format: int32 + + - `BetaManagedAgentsAdvisor object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
from line 1659
- `type: "advisor"` - - `"advisor"` - - `type: "coordinator"` - - `"coordinator"` - - `name: string` - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - - `BetaManagedAgentsAnthropicSkill object { skill_id, type, version }` + - `BetaManagedAgentsAnthropicSkill object` A resolved Anthropic-managed skill.
from line 1673
- `type: "anthropic"` - - `"anthropic"` - - `version: string` - - `BetaManagedAgentsCustomSkill object { skill_id, type, version }` + - `BetaManagedAgentsCustomSkill object` A resolved user-created custom skill.
from line 1683
- `type: "custom"` - - `"custom"` - - `version: string` - `system: string or null` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - - `BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }` + - `BetaManagedAgentsAgentToolset20260401 object` - `configs: array of BetaManagedAgentsAgentToolConfig` - - `BetaManagedAgentsBashToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsBashToolConfig object` Configuration for the bash tool.
from line 1701
- `name: "bash"` - - `"bash"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "bash"` - - `"bash"` - - - `BetaManagedAgentsEditToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsEditToolConfig object` Configuration for the edit tool.
from line 1727
- `name: "edit"` - - `"edit"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "edit"` - - `"edit"` - - - `BetaManagedAgentsReadToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsReadToolConfig object` Configuration for the read tool.
from line 1749
- `name: "read"` - - `"read"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "read"` - - `"read"` - - - `BetaManagedAgentsWriteToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsWriteToolConfig object` Configuration for the write tool.
from line 1771
- `name: "write"` - - `"write"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "write"` - - `"write"` - - - `BetaManagedAgentsGlobToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGlobToolConfig object` Configuration for the glob tool.
from line 1793
- `name: "glob"` - - `"glob"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "glob"` - - `"glob"` - - - `BetaManagedAgentsGrepToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGrepToolConfig object` Configuration for the grep tool.
from line 1815
- `name: "grep"` - - `"grep"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "grep"` - - `"grep"` - - - `BetaManagedAgentsWebFetchToolConfig object { enabled, name, permission_policy, 4 more }` + - `BetaManagedAgentsWebFetchToolConfig object` Configuration for the web_fetch tool.
from line 1837
- `name: "web_fetch"` - - `"web_fetch"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_fetch"` - - `"web_fetch"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number or null` - - `BetaManagedAgentsWebSearchToolConfig object { enabled, name, permission_policy, 4 more }` + format: int32 + + - `BetaManagedAgentsWebSearchToolConfig object` Configuration for the web_search tool.
from line 1867
- `name: "web_search"` - - `"web_search"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_search"` - - `"web_search"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string`
from line 1893
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 1907
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools.
from line 1925
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "agent_toolset_20260401"` - - `"agent_toolset_20260401"` - - - `BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }` + - `BetaManagedAgentsMCPToolset object` - `configs: array of BetaManagedAgentsMCPToolConfig`
from line 1947
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 1965
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 1977
- `type: "mcp_toolset"` - - `"mcp_toolset"` - - - `BetaManagedAgentsCustomTool object { description, input_schema, name, type }` + - `BetaManagedAgentsCustomTool object` A custom tool as returned in API responses.
from line 1989
- `type: "object"` - - `"object"` - - `properties: optional map[unknown] or null` - `required: optional array of string or null`
from line 1997
- `type: "custom"` - - `"custom"` - - `type: "agent"` - - `"agent"` - - `updated_at: string` A timestamp in RFC 3339 format + format: date-time + - `version: number` The agent's current version. Starts at 1 and increments when the agent is modified. + format: int32 + - `next_page: optional string or null` Opaque cursor for the next page. Null when no more results. ### Example -```http +```bash curl https://api.anthropic.com/v1/agents \ -H 'anthropic-version: 2023-06-01' \ -H 'anthropic-beta: managed-agents-2026-04-01' \ -H "X-Api-Key: $ANTHROPIC_API_KEY" ``` -#### Response +#### Response (200) ```json {
from line 2108
## Get Agent -**get** `/v1/agents/{agent_id}` +**GET** `/v1/agents/{agent_id}` Get Agent -### Path Parameters +### Path parameters - `agent_id: string` -### Query Parameters +### Query parameters - `version: optional number` Agent version. Omit for the most recent version. Must be at least 1 if specified. -### Header Parameters + format: int32 + +### Headers - `"anthropic-beta": optional array of AnthropicBeta`
from line 2204
### Returns -- `BetaManagedAgentsAgent object { id, archived_at, created_at, 12 more }` +- `BetaManagedAgentsAgent object` A Managed Agents `agent`.
from line 2214
A timestamp in RFC 3339 format + format: date-time + - `created_at: string` A timestamp in RFC 3339 format + format: date-time + - `description: string or null` - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`
from line 2230
- `type: "url"` - - `"url"` - - `url: string` - `metadata: map[string]`
from line 2308
How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes. - - `BetaManagedAgentsEffortLow object { type }` + - `BetaManagedAgentsEffortLow object` Low effort. Favors latency over reasoning depth. - `type: "low"` - - `"low"` - - - `BetaManagedAgentsEffortMedium object { type }` + - `BetaManagedAgentsEffortMedium object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - - `"medium"` - - - `BetaManagedAgentsEffortHigh object { type }` + - `BetaManagedAgentsEffortHigh object` High effort. Favors reasoning depth. - `type: "high"` - - `"high"` - - - `BetaManagedAgentsEffortXhigh object { type }` + - `BetaManagedAgentsEffortXhigh object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - - `"xhigh"` - - - `BetaManagedAgentsEffortMax object { type }` + - `BetaManagedAgentsEffortMax object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - - `"max"` - - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.
from line 2358
Agents the coordinator may spawn as session threads, each resolved to a specific version. - - `BetaManagedAgentsAgentReference object { id, type, version }` + - `BetaManagedAgentsAgentReference object` A resolved agent reference with a concrete version.
from line 2366
- `type: "agent"` - - `"agent"` - - `version: number` - - `BetaManagedAgentsAdvisor object { model, type }` + format: int32 + + - `BetaManagedAgentsAdvisor object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
from line 2380
- `type: "advisor"` - - `"advisor"` - - `type: "coordinator"` - - `"coordinator"` - - `name: string` - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - - `BetaManagedAgentsAnthropicSkill object { skill_id, type, version }` + - `BetaManagedAgentsAnthropicSkill object` A resolved Anthropic-managed skill.
from line 2394
- `type: "anthropic"` - - `"anthropic"` - - `version: string` - - `BetaManagedAgentsCustomSkill object { skill_id, type, version }` + - `BetaManagedAgentsCustomSkill object` A resolved user-created custom skill.
from line 2404
- `type: "custom"` - - `"custom"` - - `version: string` - `system: string or null` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - - `BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }` + - `BetaManagedAgentsAgentToolset20260401 object` - `configs: array of BetaManagedAgentsAgentToolConfig` - - `BetaManagedAgentsBashToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsBashToolConfig object` Configuration for the bash tool.
from line 2422
- `name: "bash"` - - `"bash"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "bash"` - - `"bash"` - - - `BetaManagedAgentsEditToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsEditToolConfig object` Configuration for the edit tool.
from line 2448
- `name: "edit"` - - `"edit"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "edit"` - - `"edit"` - - - `BetaManagedAgentsReadToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsReadToolConfig object` Configuration for the read tool.
from line 2470
- `name: "read"` - - `"read"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "read"` - - `"read"` - - - `BetaManagedAgentsWriteToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsWriteToolConfig object` Configuration for the write tool.
from line 2492
- `name: "write"` - - `"write"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "write"` - - `"write"` - - - `BetaManagedAgentsGlobToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGlobToolConfig object` Configuration for the glob tool.
from line 2514
- `name: "glob"` - - `"glob"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "glob"` - - `"glob"` - - - `BetaManagedAgentsGrepToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGrepToolConfig object` Configuration for the grep tool.
from line 2536
- `name: "grep"` - - `"grep"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "grep"` - - `"grep"` - - - `BetaManagedAgentsWebFetchToolConfig object { enabled, name, permission_policy, 4 more }` + - `BetaManagedAgentsWebFetchToolConfig object` Configuration for the web_fetch tool.
from line 2558
- `name: "web_fetch"` - - `"web_fetch"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_fetch"` - - `"web_fetch"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number or null` - - `BetaManagedAgentsWebSearchToolConfig object { enabled, name, permission_policy, 4 more }` + format: int32 + + - `BetaManagedAgentsWebSearchToolConfig object` Configuration for the web_search tool.
from line 2588
- `name: "web_search"` - - `"web_search"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_search"` - - `"web_search"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string`
from line 2614
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 2628
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools.
from line 2646
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "agent_toolset_20260401"` - - `"agent_toolset_20260401"` - - - `BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }` + - `BetaManagedAgentsMCPToolset object` - `configs: array of BetaManagedAgentsMCPToolConfig`
from line 2668
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 2686
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 2698
- `type: "mcp_toolset"` - - `"mcp_toolset"` - - - `BetaManagedAgentsCustomTool object { description, input_schema, name, type }` + - `BetaManagedAgentsCustomTool object` A custom tool as returned in API responses.
from line 2710
- `type: "object"` - - `"object"` - - `properties: optional map[unknown] or null` - `required: optional array of string or null`
from line 2718
- `type: "custom"` - - `"custom"` - - `type: "agent"` - - `"agent"` - - `updated_at: string` A timestamp in RFC 3339 format + format: date-time + - `version: number` The agent's current version. Starts at 1 and increments when the agent is modified. + format: int32 + ### Example -```http +```bash curl https://api.anthropic.com/v1/agents/$AGENT_ID \ -H 'anthropic-version: 2023-06-01' \ -H 'anthropic-beta: managed-agents-2026-04-01' \ -H "X-Api-Key: $ANTHROPIC_API_KEY" ``` -#### Response +#### Response (200) ```json {
from line 2820
## Update Agent -**post** `/v1/agents/{agent_id}` +**POST** `/v1/agents/{agent_id}` Update Agent -### Path Parameters +### Path parameters - `agent_id: string` -### Header Parameters +### Headers - `"anthropic-beta": optional array of AnthropicBeta`
from line 2906
- `"mid-conversation-tool-changes-2026-07-01"` -### Body Parameters +### Body parameters - `description: optional string or null` Description. Omit to preserve; send empty string or null to clear. + maxLength: 2048 + - `mcp_servers: optional array of BetaManagedAgentsURLMCPServerParams or null` MCP servers. Full replacement. Omit to preserve; send empty array or `null` to clear. Names must be unique. Maximum 20. Every server must be referenced by an `mcp_toolset` in the agent's resulting `tools`; unreferenced servers are rejected. See the [MCP connector guide](https://platform.claude.com/docs/en/managed-agents/mcp-connector).
from line 2922
Unique name for this server, referenced by mcp_toolset configurations. 1-255 characters. + minLength: 1, maxLength: 255 + - `type: "url"` - - `"url"` - - `url: string` Endpoint URL for the MCP server. + maxLength: 2048 + - `metadata: optional map[string] or null` Metadata patch. Set a key to a string to upsert it, or to null to delete it. Omit the field to preserve. The stored bag is limited to 16 keys (up to 64 chars each) with values up to 512 chars.
from line 3006
- `string` - - `BetaManagedAgentsModelConfigParams object { id, effort, inference_geo, speed }` + - `BetaManagedAgentsModelConfigParams object` An object that defines additional configuration control over model use
from line 3034
- `"max"` - - `BetaManagedAgentsEffortLow object { type }` + - `BetaManagedAgentsEffortLow object` Low effort. Favors latency over reasoning depth. - `type: "low"` - - `"low"` - - - `BetaManagedAgentsEffortMedium object { type }` + - `BetaManagedAgentsEffortMedium object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - - `"medium"` - - - `BetaManagedAgentsEffortHigh object { type }` + - `BetaManagedAgentsEffortHigh object` High effort. Favors reasoning depth. - `type: "high"` - - `"high"` - - - `BetaManagedAgentsEffortXhigh object { type }` + - `BetaManagedAgentsEffortXhigh object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - - `"xhigh"` - - - `BetaManagedAgentsEffortMax object { type }` + - `BetaManagedAgentsEffortMax object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - - `"max"` - - `inference_geo: optional string or null` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. On update, `model` is whole-object replacement — omitting inference_geo clears it.
from line 3086
- `string` - - `BetaManagedAgentsAgentParams object { id, type, version }` + - `BetaManagedAgentsAgentParams object` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version
from line 3094
The `agent` ID. + minLength: 1, maxLength: 128 + - `type: "agent"` - - `"agent"` - - `version: optional number` The specific `agent` version to use. Omit to use the latest version. Must be at least 1 if specified. - - `BetaManagedAgentsMultiagentSelfParams object { type }` + format: int32 + + - `BetaManagedAgentsMultiagentSelfParams object` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `type: "self"` - - `"self"` - - - `BetaManagedAgentsAdvisorParams object { model, type }` + - `BetaManagedAgentsAdvisorParams object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. At most one per roster; the entry occupies the roster name `anthropic.advisor`.
from line 3118
A Claude model id. The model must be permitted as an advisor for this agent's model — see the sessions/threads/advisor spec. + minLength: 1, maxLength: 256 + - `type: "advisor"` - - `"advisor"` - - `type: "coordinator"` - - `"coordinator"` - - `name: optional string` Human-readable name. Must be non-empty. Omit to preserve. Cannot be cleared. + maxLength: 256 + - `skills: optional array of BetaManagedAgentsSkillParams or null` Skills. Full replacement. Omit to preserve; send empty array or null to clear. - - `BetaManagedAgentsAnthropicSkillParams object { skill_id, type, version }` + - `BetaManagedAgentsAnthropicSkillParams object` An Anthropic-managed skill.
from line 3142
Identifier of the Anthropic skill (e.g., "xlsx"). + minLength: 1, maxLength: 64 + - `type: "anthropic"` - - `"anthropic"` - - `version: optional string or null` Version to pin. Defaults to latest if omitted. - - `BetaManagedAgentsCustomSkillParams object { skill_id, type, version }` + minLength: 1, maxLength: 64 + + - `BetaManagedAgentsCustomSkillParams object` A user-created custom skill.
from line 3160
Tagged ID of the custom skill (e.g., "skill_01XJ5..."). + minLength: 1, maxLength: 64 + - `type: "custom"` - - `"custom"` - - `version: optional string or null` Version to pin. Defaults to latest if omitted. + minLength: 1, maxLength: 64 + - `system: optional string or null` System prompt. Omit to preserve; send empty string or null to clear. + maxLength: 100000 + - `tools: optional array of BetaManagedAgentsAgentToolset20260401Params or BetaManagedAgentsMCPToolsetParams or BetaManagedAgentsCustomToolParams or null` Tool configurations available to the agent. Full replacement. Omit to preserve; send empty array or null to clear. Maximum of 128 tools across all toolsets allowed. - - `BetaManagedAgentsAgentToolset20260401Params object { type, configs, default_config }` + - `BetaManagedAgentsAgentToolset20260401Params object` Configuration for built-in agent tools. Use this to enable or disable groups of tools available to the agent. - `type: "agent_toolset_20260401"` - - `"agent_toolset_20260401"` - - `configs: optional array of BetaManagedAgentsAgentToolConfigParams` Per-tool configuration overrides. - - `BetaManagedAgentsBashToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsBashToolConfigParams object` Configuration override for the bash tool.
from line 3198
Must be "bash". - - `"bash"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 3206
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: optional "bash"` - - `"bash"` - - - `BetaManagedAgentsEditToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsEditToolConfigParams object` Configuration override for the edit tool.
from line 3228
Must be "edit". - - `"edit"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 3236
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "edit"` - - `"edit"` - - - `BetaManagedAgentsReadToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsReadToolConfigParams object` Configuration override for the read tool.
from line 3254
Must be "read". - - `"read"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 3262
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "read"` - - `"read"` - - - `BetaManagedAgentsWriteToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsWriteToolConfigParams object` Configuration override for the write tool.
from line 3280
Must be "write". - - `"write"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 3288
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "write"` - - `"write"` - - - `BetaManagedAgentsGlobToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsGlobToolConfigParams object` Configuration override for the glob tool.
from line 3306
Must be "glob". - - `"glob"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 3314
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "glob"` - - `"glob"` - - - `BetaManagedAgentsGrepToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsGrepToolConfigParams object` Configuration override for the grep tool.
from line 3332
Must be "grep". - - `"grep"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 3340
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "grep"` - - `"grep"` - - - `BetaManagedAgentsWebFetchToolConfigParams object { name, allowed_domains, blocked_domains, 4 more }` + - `BetaManagedAgentsWebFetchToolConfigParams object` Configuration override for the web_fetch tool.
from line 3358
Must be "web_fetch". - - `"web_fetch"` - - `allowed_domains: optional array of string` Only fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains.
from line 3374
Maximum number of tokens of fetched text content to include in context per call. Does not apply to binary content such as PDFs. + format: int32 + - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or null` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "web_fetch"` - - `"web_fetch"` - - - `BetaManagedAgentsWebSearchToolConfigParams object { name, allowed_domains, blocked_domains, 4 more }` + - `BetaManagedAgentsWebSearchToolConfigParams object` Configuration override for the web_search tool.
from line 3398
Must be "web_search". - - `"web_search"` - - `allowed_domains: optional array of string` Only return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains.
from line 3414
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "web_search"` - - `"web_search"` - - `user_location: optional BetaManagedAgentsUserLocation or null` Approximate user location for search result localization.
from line 3432
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 3446
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + - `default_config: optional BetaManagedAgentsAgentToolsetDefaultConfigParams or null` Default configuration for all tools in a toolset.
from line 3466
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - - `BetaManagedAgentsMCPToolsetParams object { mcp_server_name, type, configs, default_config }` + - `BetaManagedAgentsMCPToolsetParams object` Configuration for tools from an MCP server defined in `mcp_servers`.
from line 3482
Name of the MCP server. Must match a server name from the mcp_servers array. 1-255 characters. + minLength: 1, maxLength: 255 + - `type: "mcp_toolset"` - - `"mcp_toolset"` - - `configs: optional array of BetaManagedAgentsMCPToolConfigParams` Per-tool configuration overrides.
from line 3494
Name of the MCP tool to configure. 1-128 characters. + minLength: 1, maxLength: 128 + - `enabled: optional boolean or null` Whether this tool is enabled. Overrides the `default_config` setting.
from line 3504
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 3524
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - - `BetaManagedAgentsCustomToolParams object { description, input_schema, name, type }` + - `BetaManagedAgentsCustomToolParams object` A custom tool that is executed by the API client rather than the agent. When the agent calls this tool, an `agent.custom_tool_use` event is emitted and the session goes idle, waiting for the client to provide the result via a `user.custom_tool_result` event.
from line 3540
Description of what the tool does, shown to the agent to help it decide when to use the tool. + minLength: 1 + - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: "object"` - - `"object"` - - `properties: optional map[unknown] or null` - `required: optional array of string or null`
from line 3556
Unique name for the tool. 1-128 characters; letters, digits, underscores, and hyphens. + minLength: 1, maxLength: 128 + - `type: "custom"` - - `"custom"` - - `version: optional number` The agent's current version, used to prevent concurrent overwrites. Obtain this value from a create or retrieve response. Must be at least 1 if specified. When supplied, the request fails if it does not match the server's current version; omit to apply the update unconditionally. + format: int32 + ### Returns -- `BetaManagedAgentsAgent object { id, archived_at, created_at, 12 more }` +- `BetaManagedAgentsAgent object` A Managed Agents `agent`.
from line 3578
A timestamp in RFC 3339 format + format: date-time + - `created_at: string` A timestamp in RFC 3339 format + format: date-time + - `description: string or null` - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`
from line 3594
- `type: "url"` - - `"url"` - - `url: string` - `metadata: map[string]`
from line 3672
How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes. - - `BetaManagedAgentsEffortLow object { type }` + - `BetaManagedAgentsEffortLow object` Low effort. Favors latency over reasoning depth. - `type: "low"` - - `"low"` - - - `BetaManagedAgentsEffortMedium object { type }` + - `BetaManagedAgentsEffortMedium object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - - `"medium"` - - - `BetaManagedAgentsEffortHigh object { type }` + - `BetaManagedAgentsEffortHigh object` High effort. Favors reasoning depth. - `type: "high"` - - `"high"` - - - `BetaManagedAgentsEffortXhigh object { type }` + - `BetaManagedAgentsEffortXhigh object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - - `"xhigh"` - - - `BetaManagedAgentsEffortMax object { type }` + - `BetaManagedAgentsEffortMax object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - - `"max"` - - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.
from line 3722
Agents the coordinator may spawn as session threads, each resolved to a specific version. - - `BetaManagedAgentsAgentReference object { id, type, version }` + - `BetaManagedAgentsAgentReference object` A resolved agent reference with a concrete version.
from line 3730
- `type: "agent"` - - `"agent"` - - `version: number` - - `BetaManagedAgentsAdvisor object { model, type }` + format: int32 + + - `BetaManagedAgentsAdvisor object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
from line 3744
- `type: "advisor"` - - `"advisor"` - - `type: "coordinator"` - - `"coordinator"` - - `name: string` - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - - `BetaManagedAgentsAnthropicSkill object { skill_id, type, version }` + - `BetaManagedAgentsAnthropicSkill object` A resolved Anthropic-managed skill.
from line 3758
- `type: "anthropic"` - - `"anthropic"` - - `version: string` - - `BetaManagedAgentsCustomSkill object { skill_id, type, version }` + - `BetaManagedAgentsCustomSkill object` A resolved user-created custom skill.
from line 3768
- `type: "custom"` - - `"custom"` - - `version: string` - `system: string or null` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - - `BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }` + - `BetaManagedAgentsAgentToolset20260401 object` - `configs: array of BetaManagedAgentsAgentToolConfig` - - `BetaManagedAgentsBashToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsBashToolConfig object` Configuration for the bash tool.
from line 3786
- `name: "bash"` - - `"bash"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "bash"` - - `"bash"` - - - `BetaManagedAgentsEditToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsEditToolConfig object` Configuration for the edit tool.
from line 3812
- `name: "edit"` - - `"edit"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "edit"` - - `"edit"` - - - `BetaManagedAgentsReadToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsReadToolConfig object` Configuration for the read tool.
from line 3834
- `name: "read"` - - `"read"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "read"` - - `"read"` - - - `BetaManagedAgentsWriteToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsWriteToolConfig object` Configuration for the write tool.
from line 3856
- `name: "write"` - - `"write"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "write"` - - `"write"` - - - `BetaManagedAgentsGlobToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGlobToolConfig object` Configuration for the glob tool.
from line 3878
- `name: "glob"` - - `"glob"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "glob"` - - `"glob"` - - - `BetaManagedAgentsGrepToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGrepToolConfig object` Configuration for the grep tool.
from line 3900
- `name: "grep"` - - `"grep"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "grep"` - - `"grep"` - - - `BetaManagedAgentsWebFetchToolConfig object { enabled, name, permission_policy, 4 more }` + - `BetaManagedAgentsWebFetchToolConfig object` Configuration for the web_fetch tool.
from line 3922
- `name: "web_fetch"` - - `"web_fetch"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_fetch"` - - `"web_fetch"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number or null` - - `BetaManagedAgentsWebSearchToolConfig object { enabled, name, permission_policy, 4 more }` + format: int32 + + - `BetaManagedAgentsWebSearchToolConfig object` Configuration for the web_search tool.
from line 3952
- `name: "web_search"` - - `"web_search"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_search"` - - `"web_search"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string`
from line 3978
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 3992
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools.
from line 4010
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "agent_toolset_20260401"` - - `"agent_toolset_20260401"` - - - `BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }` + - `BetaManagedAgentsMCPToolset object` - `configs: array of BetaManagedAgentsMCPToolConfig`
from line 4032
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 4050
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 4062
- `type: "mcp_toolset"` - - `"mcp_toolset"` - - - `BetaManagedAgentsCustomTool object { description, input_schema, name, type }` + - `BetaManagedAgentsCustomTool object` A custom tool as returned in API responses.
from line 4074
- `type: "object"` - - `"object"` - - `properties: optional map[unknown] or null` - `required: optional array of string or null`
from line 4082
- `type: "custom"` - - `"custom"` - - `type: "agent"` - - `"agent"` - - `updated_at: string` A timestamp in RFC 3339 format + format: date-time + - `version: number` The agent's current version. Starts at 1 and increments when the agent is modified. + format: int32 + ### Example -```http +```bash curl https://api.anthropic.com/v1/agents/$AGENT_ID \ -H 'Content-Type: application/json' \ -H 'anthropic-version: 2023-06-01' \
from line 4111
}' ``` -#### Response +#### Response (200) ```json {
from line 4190
## Archive Agent -**post** `/v1/agents/{agent_id}/archive` +**POST** `/v1/agents/{agent_id}/archive` Archive Agent -### Path Parameters +### Path parameters - `agent_id: string` -### Header Parameters +### Headers - `"anthropic-beta": optional array of AnthropicBeta`
from line 4278
### Returns -- `BetaManagedAgentsAgent object { id, archived_at, created_at, 12 more }` +- `BetaManagedAgentsAgent object` A Managed Agents `agent`.
from line 4288
A timestamp in RFC 3339 format + format: date-time + - `created_at: string` A timestamp in RFC 3339 format + format: date-time + - `description: string or null` - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`
from line 4304
- `type: "url"` - - `"url"` - - `url: string` - `metadata: map[string]`
from line 4382
How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes. - - `BetaManagedAgentsEffortLow object { type }` + - `BetaManagedAgentsEffortLow object` Low effort. Favors latency over reasoning depth. - `type: "low"` - - `"low"` - - - `BetaManagedAgentsEffortMedium object { type }` + - `BetaManagedAgentsEffortMedium object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - - `"medium"` - - - `BetaManagedAgentsEffortHigh object { type }` + - `BetaManagedAgentsEffortHigh object` High effort. Favors reasoning depth. - `type: "high"` - - `"high"` - - - `BetaManagedAgentsEffortXhigh object { type }` + - `BetaManagedAgentsEffortXhigh object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - - `"xhigh"` - - - `BetaManagedAgentsEffortMax object { type }` + - `BetaManagedAgentsEffortMax object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - - `"max"` - - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.
from line 4432
Agents the coordinator may spawn as session threads, each resolved to a specific version. - - `BetaManagedAgentsAgentReference object { id, type, version }` + - `BetaManagedAgentsAgentReference object` A resolved agent reference with a concrete version.
from line 4440
- `type: "agent"` - - `"agent"` - - `version: number` - - `BetaManagedAgentsAdvisor object { model, type }` + format: int32 + + - `BetaManagedAgentsAdvisor object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
from line 4454
- `type: "advisor"` - - `"advisor"` - - `type: "coordinator"` - - `"coordinator"` - - `name: string` - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - - `BetaManagedAgentsAnthropicSkill object { skill_id, type, version }` + - `BetaManagedAgentsAnthropicSkill object` A resolved Anthropic-managed skill.
from line 4468
- `type: "anthropic"` - - `"anthropic"` - - `version: string` - - `BetaManagedAgentsCustomSkill object { skill_id, type, version }` + - `BetaManagedAgentsCustomSkill object` A resolved user-created custom skill.
from line 4478
- `type: "custom"` - - `"custom"` - - `version: string` - `system: string or null` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - - `BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }` + - `BetaManagedAgentsAgentToolset20260401 object` - `configs: array of BetaManagedAgentsAgentToolConfig` - - `BetaManagedAgentsBashToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsBashToolConfig object` Configuration for the bash tool.
from line 4496
- `name: "bash"` - - `"bash"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "bash"` - - `"bash"` - - - `BetaManagedAgentsEditToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsEditToolConfig object` Configuration for the edit tool.
from line 4522
- `name: "edit"` - - `"edit"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "edit"` - - `"edit"` - - - `BetaManagedAgentsReadToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsReadToolConfig object` Configuration for the read tool.
from line 4544
- `name: "read"` - - `"read"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "read"` - - `"read"` - - - `BetaManagedAgentsWriteToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsWriteToolConfig object` Configuration for the write tool.
from line 4566
- `name: "write"` - - `"write"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "write"` - - `"write"` - - - `BetaManagedAgentsGlobToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGlobToolConfig object` Configuration for the glob tool.
from line 4588
- `name: "glob"` - - `"glob"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "glob"` - - `"glob"` - - - `BetaManagedAgentsGrepToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGrepToolConfig object` Configuration for the grep tool.
from line 4610
- `name: "grep"` - - `"grep"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "grep"` - - `"grep"` - - - `BetaManagedAgentsWebFetchToolConfig object { enabled, name, permission_policy, 4 more }` + - `BetaManagedAgentsWebFetchToolConfig object` Configuration for the web_fetch tool.
from line 4632
- `name: "web_fetch"` - - `"web_fetch"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_fetch"` - - `"web_fetch"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number or null` - - `BetaManagedAgentsWebSearchToolConfig object { enabled, name, permission_policy, 4 more }` + format: int32 + + - `BetaManagedAgentsWebSearchToolConfig object` Configuration for the web_search tool.
from line 4662
- `name: "web_search"` - - `"web_search"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_search"` - - `"web_search"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string`
from line 4688
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 4702
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools.
from line 4720
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "agent_toolset_20260401"` - - `"agent_toolset_20260401"` - - - `BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }` + - `BetaManagedAgentsMCPToolset object` - `configs: array of BetaManagedAgentsMCPToolConfig`
from line 4742
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 4760
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 4772
- `type: "mcp_toolset"` - - `"mcp_toolset"` - - - `BetaManagedAgentsCustomTool object { description, input_schema, name, type }` + - `BetaManagedAgentsCustomTool object` A custom tool as returned in API responses.
from line 4784
- `type: "object"` - - `"object"` - - `properties: optional map[unknown] or null` - `required: optional array of string or null`
from line 4792
- `type: "custom"` - - `"custom"` - - `type: "agent"` - - `"agent"` - - `updated_at: string` A timestamp in RFC 3339 format + format: date-time + - `version: number` The agent's current version. Starts at 1 and increments when the agent is modified. + format: int32 + ### Example -```http +```bash curl https://api.anthropic.com/v1/agents/$AGENT_ID/archive \ -X POST \ -H 'anthropic-version: 2023-06-01' \
from line 4816
-H "X-Api-Key: $ANTHROPIC_API_KEY" ``` -#### Response +#### Response (200) ```json {
from line 4893
} ``` -## Domain Types +## Domain types ### Beta Managed Agents Advisor -- `BetaManagedAgentsAdvisor object { model, type }` +- `BetaManagedAgentsAdvisor object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
from line 4907
- `type: "advisor"` - - `"advisor"` - ### Beta Managed Agents Agent -- `BetaManagedAgentsAgent object { id, archived_at, created_at, 12 more }` +- `BetaManagedAgentsAgent object` A Managed Agents `agent`.
from line 4919
A timestamp in RFC 3339 format + format: date-time + - `created_at: string` A timestamp in RFC 3339 format + format: date-time + - `description: string or null` - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`
from line 4935
- `type: "url"` - - `"url"` - - `url: string` - `metadata: map[string]`
from line 5013
How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes. - - `BetaManagedAgentsEffortLow object { type }` + - `BetaManagedAgentsEffortLow object` Low effort. Favors latency over reasoning depth. - `type: "low"` - - `"low"` - - - `BetaManagedAgentsEffortMedium object { type }` + - `BetaManagedAgentsEffortMedium object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - - `"medium"` - - - `BetaManagedAgentsEffortHigh object { type }` + - `BetaManagedAgentsEffortHigh object` High effort. Favors reasoning depth. - `type: "high"` - - `"high"` - - - `BetaManagedAgentsEffortXhigh object { type }` + - `BetaManagedAgentsEffortXhigh object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - - `"xhigh"` - - - `BetaManagedAgentsEffortMax object { type }` + - `BetaManagedAgentsEffortMax object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - - `"max"` - - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.
from line 5063
Agents the coordinator may spawn as session threads, each resolved to a specific version. - - `BetaManagedAgentsAgentReference object { id, type, version }` + - `BetaManagedAgentsAgentReference object` A resolved agent reference with a concrete version.
from line 5071
- `type: "agent"` - - `"agent"` - - `version: number` - - `BetaManagedAgentsAdvisor object { model, type }` + format: int32 + + - `BetaManagedAgentsAdvisor object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
from line 5085
- `type: "advisor"` - - `"advisor"` - - `type: "coordinator"` - - `"coordinator"` - - `name: string` - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - - `BetaManagedAgentsAnthropicSkill object { skill_id, type, version }` + - `BetaManagedAgentsAnthropicSkill object` A resolved Anthropic-managed skill.
from line 5099
- `type: "anthropic"` - - `"anthropic"` - - `version: string` - - `BetaManagedAgentsCustomSkill object { skill_id, type, version }` + - `BetaManagedAgentsCustomSkill object` A resolved user-created custom skill.
from line 5109
- `type: "custom"` - - `"custom"` - - `version: string` - `system: string or null` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - - `BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }` + - `BetaManagedAgentsAgentToolset20260401 object` - `configs: array of BetaManagedAgentsAgentToolConfig` - - `BetaManagedAgentsBashToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsBashToolConfig object` Configuration for the bash tool.
from line 5127
- `name: "bash"` - - `"bash"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "bash"` - - `"bash"` - - - `BetaManagedAgentsEditToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsEditToolConfig object` Configuration for the edit tool.
from line 5153
- `name: "edit"` - - `"edit"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "edit"` - - `"edit"` - - - `BetaManagedAgentsReadToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsReadToolConfig object` Configuration for the read tool.
from line 5175
- `name: "read"` - - `"read"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "read"` - - `"read"` - - - `BetaManagedAgentsWriteToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsWriteToolConfig object` Configuration for the write tool.
from line 5197
- `name: "write"` - - `"write"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "write"` - - `"write"` - - - `BetaManagedAgentsGlobToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGlobToolConfig object` Configuration for the glob tool.
from line 5219
- `name: "glob"` - - `"glob"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "glob"` - - `"glob"` - - - `BetaManagedAgentsGrepToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGrepToolConfig object` Configuration for the grep tool.
from line 5241
- `name: "grep"` - - `"grep"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "grep"` - - `"grep"` - - - `BetaManagedAgentsWebFetchToolConfig object { enabled, name, permission_policy, 4 more }` + - `BetaManagedAgentsWebFetchToolConfig object` Configuration for the web_fetch tool.
from line 5263
- `name: "web_fetch"` - - `"web_fetch"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_fetch"` - - `"web_fetch"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number or null` - - `BetaManagedAgentsWebSearchToolConfig object { enabled, name, permission_policy, 4 more }` + format: int32 + + - `BetaManagedAgentsWebSearchToolConfig object` Configuration for the web_search tool.
from line 5293
- `name: "web_search"` - - `"web_search"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_search"` - - `"web_search"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string`
from line 5319
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 5333
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools.
from line 5351
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "agent_toolset_20260401"` - - `"agent_toolset_20260401"` - - - `BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }` + - `BetaManagedAgentsMCPToolset object` - `configs: array of BetaManagedAgentsMCPToolConfig`
from line 5373
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 5391
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 5403
- `type: "mcp_toolset"` - - `"mcp_toolset"` - - - `BetaManagedAgentsCustomTool object { description, input_schema, name, type }` + - `BetaManagedAgentsCustomTool object` A custom tool as returned in API responses.
from line 5415
- `type: "object"` - - `"object"` - - `properties: optional map[unknown] or null` - `required: optional array of string or null`
from line 5423
- `type: "custom"` - - `"custom"` - - `type: "agent"` - - `"agent"` - - `updated_at: string` A timestamp in RFC 3339 format + format: date-time + - `version: number` The agent's current version. Starts at 1 and increments when the agent is modified. + format: int32 + ### Beta Managed Agents Agent Reference -- `BetaManagedAgentsAgentReference object { id, type, version }` +- `BetaManagedAgentsAgentReference object` A resolved agent reference with a concrete version.
from line 5447
- `type: "agent"` - - `"agent"` - - `version: number` + format: int32 + ### Beta Managed Agents Agent Tool Config - `BetaManagedAgentsAgentToolConfig = BetaManagedAgentsBashToolConfig or BetaManagedAgentsEditToolConfig or BetaManagedAgentsReadToolConfig or 5 more` Configuration for a specific agent tool. - - `BetaManagedAgentsBashToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsBashToolConfig object` Configuration for the bash tool.
from line 5465
- `name: "bash"` - - `"bash"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "bash"` - - `"bash"` - - - `BetaManagedAgentsEditToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsEditToolConfig object` Configuration for the edit tool.
from line 5491
- `name: "edit"` - - `"edit"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "edit"` - - `"edit"` - - - `BetaManagedAgentsReadToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsReadToolConfig object` Configuration for the read tool.
from line 5513
- `name: "read"` - - `"read"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "read"` - - `"read"` - - - `BetaManagedAgentsWriteToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsWriteToolConfig object` Configuration for the write tool.
from line 5535
- `name: "write"` - - `"write"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "write"` - - `"write"` - - - `BetaManagedAgentsGlobToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGlobToolConfig object` Configuration for the glob tool.
from line 5557
- `name: "glob"` - - `"glob"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "glob"` - - `"glob"` - - - `BetaManagedAgentsGrepToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGrepToolConfig object` Configuration for the grep tool.
from line 5579
- `name: "grep"` - - `"grep"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "grep"` - - `"grep"` - - - `BetaManagedAgentsWebFetchToolConfig object { enabled, name, permission_policy, 4 more }` + - `BetaManagedAgentsWebFetchToolConfig object` Configuration for the web_fetch tool.
from line 5601
- `name: "web_fetch"` - - `"web_fetch"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_fetch"` - - `"web_fetch"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number or null` - - `BetaManagedAgentsWebSearchToolConfig object { enabled, name, permission_policy, 4 more }` + format: int32 + + - `BetaManagedAgentsWebSearchToolConfig object` Configuration for the web_search tool.
from line 5631
- `name: "web_search"` - - `"web_search"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_search"` - - `"web_search"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string`
from line 5657
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 5671
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + ### Beta Managed Agents Agent Tool Config Params - `BetaManagedAgentsAgentToolConfigParams = BetaManagedAgentsBashToolConfigParams or BetaManagedAgentsEditToolConfigParams or BetaManagedAgentsReadToolConfigParams or 5 more` Configuration override for a specific tool within a toolset. - - `BetaManagedAgentsBashToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsBashToolConfigParams object` Configuration override for the bash tool.
from line 5693
Must be "bash". - - `"bash"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 5701
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: optional "bash"` - - `"bash"` - - - `BetaManagedAgentsEditToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsEditToolConfigParams object` Configuration override for the edit tool.
from line 5723
Must be "edit". - - `"edit"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 5731
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "edit"` - - `"edit"` - - - `BetaManagedAgentsReadToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsReadToolConfigParams object` Configuration override for the read tool.
from line 5749
Must be "read". - - `"read"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 5757
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "read"` - - `"read"` - - - `BetaManagedAgentsWriteToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsWriteToolConfigParams object` Configuration override for the write tool.
from line 5775
Must be "write". - - `"write"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 5783
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "write"` - - `"write"` - - - `BetaManagedAgentsGlobToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsGlobToolConfigParams object` Configuration override for the glob tool.
from line 5801
Must be "glob". - - `"glob"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 5809
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "glob"` - - `"glob"` - - - `BetaManagedAgentsGrepToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsGrepToolConfigParams object` Configuration override for the grep tool.
from line 5827
Must be "grep". - - `"grep"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 5835
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "grep"` - - `"grep"` - - - `BetaManagedAgentsWebFetchToolConfigParams object { name, allowed_domains, blocked_domains, 4 more }` + - `BetaManagedAgentsWebFetchToolConfigParams object` Configuration override for the web_fetch tool.
from line 5853
Must be "web_fetch". - - `"web_fetch"` - - `allowed_domains: optional array of string` Only fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains.
from line 5869
Maximum number of tokens of fetched text content to include in context per call. Does not apply to binary content such as PDFs. + format: int32 + - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or null` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "web_fetch"` - - `"web_fetch"` - - - `BetaManagedAgentsWebSearchToolConfigParams object { name, allowed_domains, blocked_domains, 4 more }` + - `BetaManagedAgentsWebSearchToolConfigParams object` Configuration override for the web_search tool.
from line 5893
Must be "web_search". - - `"web_search"` - - `allowed_domains: optional array of string` Only return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains.
from line 5909
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "web_search"` - - `"web_search"` - - `user_location: optional BetaManagedAgentsUserLocation or null` Approximate user location for search result localization.
from line 5927
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 5941
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + ### Beta Managed Agents Agent Toolset Default Config -- `BetaManagedAgentsAgentToolsetDefaultConfig object { enabled, permission_policy }` +- `BetaManagedAgentsAgentToolsetDefaultConfig object` Resolved default configuration for agent tools.
from line 5961
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - ### Beta Managed Agents Agent Toolset Default Config Params -- `BetaManagedAgentsAgentToolsetDefaultConfigParams object { enabled, permission_policy }` +- `BetaManagedAgentsAgentToolsetDefaultConfigParams object` Default configuration for all tools in a toolset.
from line 5987
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - ### Beta Managed Agents Agent Toolset20260401 -- `BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }` +- `BetaManagedAgentsAgentToolset20260401 object` - `configs: array of BetaManagedAgentsAgentToolConfig` - - `BetaManagedAgentsBashToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsBashToolConfig object` Configuration for the bash tool.
from line 6013
- `name: "bash"` - - `"bash"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "bash"` - - `"bash"` - - - `BetaManagedAgentsEditToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsEditToolConfig object` Configuration for the edit tool.
from line 6039
- `name: "edit"` - - `"edit"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "edit"` - - `"edit"` - - - `BetaManagedAgentsReadToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsReadToolConfig object` Configuration for the read tool.
from line 6061
- `name: "read"` - - `"read"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "read"` - - `"read"` - - - `BetaManagedAgentsWriteToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsWriteToolConfig object` Configuration for the write tool.
from line 6083
- `name: "write"` - - `"write"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "write"` - - `"write"` - - - `BetaManagedAgentsGlobToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGlobToolConfig object` Configuration for the glob tool.
from line 6105
- `name: "glob"` - - `"glob"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "glob"` - - `"glob"` - - - `BetaManagedAgentsGrepToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGrepToolConfig object` Configuration for the grep tool.
from line 6127
- `name: "grep"` - - `"grep"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "grep"` - - `"grep"` - - - `BetaManagedAgentsWebFetchToolConfig object { enabled, name, permission_policy, 4 more }` + - `BetaManagedAgentsWebFetchToolConfig object` Configuration for the web_fetch tool.
from line 6149
- `name: "web_fetch"` - - `"web_fetch"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_fetch"` - - `"web_fetch"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number or null` - - `BetaManagedAgentsWebSearchToolConfig object { enabled, name, permission_policy, 4 more }` + format: int32 + + - `BetaManagedAgentsWebSearchToolConfig object` Configuration for the web_search tool.
from line 6179
- `name: "web_search"` - - `"web_search"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_search"` - - `"web_search"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string`
from line 6205
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 6219
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools.
from line 6237
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "agent_toolset_20260401"` - - `"agent_toolset_20260401"` - ### Beta Managed Agents Agent Toolset20260401 Bash Input -- `BetaManagedAgentsAgentToolset20260401BashInput object { command, restart, timeout_ms }` +- `BetaManagedAgentsAgentToolset20260401BashInput object` Input payload for the `bash` tool of the `agent_toolset_20260401` toolset. All fields are optional;
from line 6271
Per-call timeout in milliseconds. Defaults to the runner-wide tool timeout when omitted or zero. + minimum: 0 + ### Beta Managed Agents Agent Toolset20260401 Edit Input -- `BetaManagedAgentsAgentToolset20260401EditInput object { file_path, new_string, old_string, replace_all }` +- `BetaManagedAgentsAgentToolset20260401EditInput object` Input payload for the `edit` tool. Performs a string replacement in the named file; by default `old_string` must
from line 6300
### Beta Managed Agents Agent Toolset20260401 Glob Input -- `BetaManagedAgentsAgentToolset20260401GlobInput object { pattern, path }` +- `BetaManagedAgentsAgentToolset20260401GlobInput object` Input payload for the `glob` tool. Returns paths matching a doublestar glob pattern, newest first.
from line 6318
### Beta Managed Agents Agent Toolset20260401 Grep Input -- `BetaManagedAgentsAgentToolset20260401GrepInput object { pattern, path }` +- `BetaManagedAgentsAgentToolset20260401GrepInput object` Input payload for the `grep` tool. Searches file contents for a regular expression, returning matching lines.
from line 6334
### Beta Managed Agents Agent Toolset20260401 Params -- `BetaManagedAgentsAgentToolset20260401Params object { type, configs, default_config }` +- `BetaManagedAgentsAgentToolset20260401Params object` Configuration for built-in agent tools. Use this to enable or disable groups of tools available to the agent. - `type: "agent_toolset_20260401"` - - `"agent_toolset_20260401"` - - `configs: optional array of BetaManagedAgentsAgentToolConfigParams` Per-tool configuration overrides. - - `BetaManagedAgentsBashToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsBashToolConfigParams object` Configuration override for the bash tool.
from line 6352
Must be "bash". - - `"bash"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 6360
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: optional "bash"` - - `"bash"` - - - `BetaManagedAgentsEditToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsEditToolConfigParams object` Configuration override for the edit tool.
from line 6382
Must be "edit". - - `"edit"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 6390
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "edit"` - - `"edit"` - - - `BetaManagedAgentsReadToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsReadToolConfigParams object` Configuration override for the read tool.
from line 6408
Must be "read". - - `"read"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 6416
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "read"` - - `"read"` - - - `BetaManagedAgentsWriteToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsWriteToolConfigParams object` Configuration override for the write tool.
from line 6434
Must be "write". - - `"write"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 6442
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "write"` - - `"write"` - - - `BetaManagedAgentsGlobToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsGlobToolConfigParams object` Configuration override for the glob tool.
from line 6460
Must be "glob". - - `"glob"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 6468
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "glob"` - - `"glob"` - - - `BetaManagedAgentsGrepToolConfigParams object { name, enabled, permission_policy, type }` + - `BetaManagedAgentsGrepToolConfigParams object` Configuration override for the grep tool.
from line 6486
Must be "grep". - - `"grep"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 6494
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "grep"` - - `"grep"` - - - `BetaManagedAgentsWebFetchToolConfigParams object { name, allowed_domains, blocked_domains, 4 more }` + - `BetaManagedAgentsWebFetchToolConfigParams object` Configuration override for the web_fetch tool.
from line 6512
Must be "web_fetch". - - `"web_fetch"` - - `allowed_domains: optional array of string` Only fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains.
from line 6528
Maximum number of tokens of fetched text content to include in context per call. Does not apply to binary content such as PDFs. + format: int32 + - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or null` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "web_fetch"` - - `"web_fetch"` - - - `BetaManagedAgentsWebSearchToolConfigParams object { name, allowed_domains, blocked_domains, 4 more }` + - `BetaManagedAgentsWebSearchToolConfigParams object` Configuration override for the web_search tool.
from line 6552
Must be "web_search". - - `"web_search"` - - `allowed_domains: optional array of string` Only return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains.
from line 6568
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: optional "web_search"` - - `"web_search"` - - `user_location: optional BetaManagedAgentsUserLocation or null` Approximate user location for search result localization.
from line 6586
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 6600
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + - `default_config: optional BetaManagedAgentsAgentToolsetDefaultConfigParams or null` Default configuration for all tools in a toolset.
from line 6620
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. ### Beta Managed Agents Agent Toolset20260401 Read Input -- `BetaManagedAgentsAgentToolset20260401ReadInput object { file_path, view_range }` +- `BetaManagedAgentsAgentToolset20260401ReadInput object` Input payload for the `read` tool. Reads file contents relative to the runner's working directory (or absolute when
from line 6646
range. When omitted the entire file is returned. `end_line` of 0 or negative means "to end of file". + minItems: 2, maxItems: 2 + ### Beta Managed Agents Agent Toolset20260401 Write Input -- `BetaManagedAgentsAgentToolset20260401WriteInput object { content, file_path }` +- `BetaManagedAgentsAgentToolset20260401WriteInput object` Input payload for the `write` tool. Writes (overwriting) the entire file contents.
from line 6665
### Beta Managed Agents Always Allow Policy -- `BetaManagedAgentsAlwaysAllowPolicy object { type }` +- `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - ### Beta Managed Agents Always Ask Policy -- `BetaManagedAgentsAlwaysAskPolicy object { type }` +- `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - ### Beta Managed Agents Anthropic Skill -- `BetaManagedAgentsAnthropicSkill object { skill_id, type, version }` +- `BetaManagedAgentsAnthropicSkill object` A resolved Anthropic-managed skill.
from line 6689
- `type: "anthropic"` - - `"anthropic"` - - `version: string` ### Beta Managed Agents Anthropic Skill Params -- `BetaManagedAgentsAnthropicSkillParams object { skill_id, type, version }` +- `BetaManagedAgentsAnthropicSkillParams object` An Anthropic-managed skill.
from line 6701
Identifier of the Anthropic skill (e.g., "xlsx"). + minLength: 1, maxLength: 64 + - `type: "anthropic"` - - `"anthropic"` - - `version: optional string or null` Version to pin. Defaults to latest if omitted. + minLength: 1, maxLength: 64 + ### Beta Managed Agents Bash Tool Config -- `BetaManagedAgentsBashToolConfig object { enabled, name, permission_policy, type }` +- `BetaManagedAgentsBashToolConfig object` Configuration for the bash tool.
from line 6721
- `name: "bash"` - - `"bash"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "bash"` - - `"bash"` - ### Beta Managed Agents Bash Tool Config Params -- `BetaManagedAgentsBashToolConfigParams object { name, enabled, permission_policy, type }` +- `BetaManagedAgentsBashToolConfigParams object` Configuration override for the bash tool.
from line 6749
Must be "bash". - - `"bash"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 6757
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: optional "bash"` - - `"bash"` - ### Beta Managed Agents Custom Skill -- `BetaManagedAgentsCustomSkill object { skill_id, type, version }` +- `BetaManagedAgentsCustomSkill object` A resolved user-created custom skill.
from line 6781
- `type: "custom"` - - `"custom"` - - `version: string` ### Beta Managed Agents Custom Skill Params -- `BetaManagedAgentsCustomSkillParams object { skill_id, type, version }` +- `BetaManagedAgentsCustomSkillParams object` A user-created custom skill.
from line 6793
Tagged ID of the custom skill (e.g., "skill_01XJ5..."). + minLength: 1, maxLength: 64 + - `type: "custom"` - - `"custom"` - - `version: optional string or null` Version to pin. Defaults to latest if omitted. + minLength: 1, maxLength: 64 + ### Beta Managed Agents Custom Tool -- `BetaManagedAgentsCustomTool object { description, input_schema, name, type }` +- `BetaManagedAgentsCustomTool object` A custom tool as returned in API responses.
from line 6817
- `type: "object"` - - `"object"` - - `properties: optional map[unknown] or null` - `required: optional array of string or null`
from line 6825
- `type: "custom"` - - `"custom"` - ### Beta Managed Agents Custom Tool Input Schema -- `BetaManagedAgentsCustomToolInputSchema object { type, properties, required }` +- `BetaManagedAgentsCustomToolInputSchema object` JSON Schema for custom tool input parameters. - `type: "object"` - - `"object"` - - `properties: optional map[unknown] or null` - `required: optional array of string or null` ### Beta Managed Agents Custom Tool Params -- `BetaManagedAgentsCustomToolParams object { description, input_schema, name, type }` +- `BetaManagedAgentsCustomToolParams object` A custom tool that is executed by the API client rather than the agent. When the agent calls this tool, an `agent.custom_tool_use` event is emitted and the session goes idle, waiting for the client to provide the result via a `user.custom_tool_result` event.
from line 6847
Description of what the tool does, shown to the agent to help it decide when to use the tool. + minLength: 1 + - `input_schema: BetaManagedAgentsCustomToolInputSchema` JSON Schema for custom tool input parameters. - `type: "object"` - - `"object"` - - `properties: optional map[unknown] or null` - `required: optional array of string or null`
from line 6863
Unique name for the tool. 1-128 characters; letters, digits, underscores, and hyphens. + minLength: 1, maxLength: 128 + - `type: "custom"` - - `"custom"` - ### Beta Managed Agents Edit Tool Config -- `BetaManagedAgentsEditToolConfig object { enabled, name, permission_policy, type }` +- `BetaManagedAgentsEditToolConfig object` Configuration for the edit tool.
from line 6877
- `name: "edit"` - - `"edit"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "edit"` - - `"edit"` - ### Beta Managed Agents Edit Tool Config Params -- `BetaManagedAgentsEditToolConfigParams object { name, enabled, permission_policy, type }` +- `BetaManagedAgentsEditToolConfigParams object` Configuration override for the edit tool.
from line 6905
Must be "edit". - - `"edit"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 6913
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: optional "edit"` - - `"edit"` - ### Beta Managed Agents Effort High -- `BetaManagedAgentsEffortHigh object { type }` +- `BetaManagedAgentsEffortHigh object` High effort. Favors reasoning depth. - `type: "high"` - - `"high"` - ### Beta Managed Agents Effort Low -- `BetaManagedAgentsEffortLow object { type }` +- `BetaManagedAgentsEffortLow object` Low effort. Favors latency over reasoning depth. - `type: "low"` - - `"low"` - ### Beta Managed Agents Effort Max -- `BetaManagedAgentsEffortMax object { type }` +- `BetaManagedAgentsEffortMax object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - - `"max"` - ### Beta Managed Agents Effort Medium -- `BetaManagedAgentsEffortMedium object { type }` +- `BetaManagedAgentsEffortMedium object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - - `"medium"` - ### Beta Managed Agents Effort Xhigh -- `BetaManagedAgentsEffortXhigh object { type }` +- `BetaManagedAgentsEffortXhigh object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - - `"xhigh"` - ### Beta Managed Agents Glob Tool Config -- `BetaManagedAgentsGlobToolConfig object { enabled, name, permission_policy, type }` +- `BetaManagedAgentsGlobToolConfig object` Configuration for the glob tool.
from line 6977
- `name: "glob"` - - `"glob"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "glob"` - - `"glob"` - ### Beta Managed Agents Glob Tool Config Params -- `BetaManagedAgentsGlobToolConfigParams object { name, enabled, permission_policy, type }` +- `BetaManagedAgentsGlobToolConfigParams object` Configuration override for the glob tool.
from line 7005
Must be "glob". - - `"glob"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 7013
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: optional "glob"` - - `"glob"` - ### Beta Managed Agents Grep Tool Config -- `BetaManagedAgentsGrepToolConfig object { enabled, name, permission_policy, type }` +- `BetaManagedAgentsGrepToolConfig object` Configuration for the grep tool.
from line 7037
- `name: "grep"` - - `"grep"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "grep"` - - `"grep"` - ### Beta Managed Agents Grep Tool Config Params -- `BetaManagedAgentsGrepToolConfigParams object { name, enabled, permission_policy, type }` +- `BetaManagedAgentsGrepToolConfigParams object` Configuration override for the grep tool.
from line 7065
Must be "grep". - - `"grep"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 7073
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: optional "grep"` - - `"grep"` - ### Beta Managed Agents MCP Server URL Definition -- `BetaManagedAgentsMCPServerURLDefinition object { name, type, url }` +- `BetaManagedAgentsMCPServerURLDefinition object` URL-based MCP server connection as returned in API responses.
from line 7097
- `type: "url"` - - `"url"` - - `url: string` ### Beta Managed Agents MCP Tool Config -- `BetaManagedAgentsMCPToolConfig object { enabled, name, permission_policy }` +- `BetaManagedAgentsMCPToolConfig object` Resolved configuration for a specific MCP tool.
from line 7113
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - ### Beta Managed Agents MCP Tool Config Params -- `BetaManagedAgentsMCPToolConfigParams object { name, enabled, permission_policy }` +- `BetaManagedAgentsMCPToolConfigParams object` Configuration override for a specific MCP tool.
from line 7135
Name of the MCP tool to configure. 1-128 characters. + minLength: 1, maxLength: 128 + - `enabled: optional boolean or null` Whether this tool is enabled. Overrides the `default_config` setting.
from line 7145
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - ### Beta Managed Agents MCP Toolset -- `BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }` +- `BetaManagedAgentsMCPToolset object` - `configs: array of BetaManagedAgentsMCPToolConfig`
from line 7171
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig` Resolved default configuration for all tools from an MCP server.
from line 7193
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 7205
- `type: "mcp_toolset"` - - `"mcp_toolset"` - ### Beta Managed Agents MCP Toolset Default Config -- `BetaManagedAgentsMCPToolsetDefaultConfig object { enabled, permission_policy }` +- `BetaManagedAgentsMCPToolsetDefaultConfig object` Resolved default configuration for all tools from an MCP server.
from line 7217
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - ### Beta Managed Agents MCP Toolset Default Config Params -- `BetaManagedAgentsMCPToolsetDefaultConfigParams object { enabled, permission_policy }` +- `BetaManagedAgentsMCPToolsetDefaultConfigParams object` Default configuration for all tools from an MCP server.
from line 7243
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - ### Beta Managed Agents MCP Toolset Params -- `BetaManagedAgentsMCPToolsetParams object { mcp_server_name, type, configs, default_config }` +- `BetaManagedAgentsMCPToolsetParams object` Configuration for tools from an MCP server defined in `mcp_servers`.
from line 7265
Name of the MCP server. Must match a server name from the mcp_servers array. 1-255 characters. + minLength: 1, maxLength: 255 + - `type: "mcp_toolset"` - - `"mcp_toolset"` - - `configs: optional array of BetaManagedAgentsMCPToolConfigParams` Per-tool configuration overrides.
from line 7277
Name of the MCP tool to configure. 1-128 characters. + minLength: 1, maxLength: 128 + - `enabled: optional boolean or null` Whether this tool is enabled. Overrides the `default_config` setting.
from line 7287
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `default_config: optional BetaManagedAgentsMCPToolsetDefaultConfigParams or null` Default configuration for all tools from an MCP server.
from line 7311
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 7389
### Beta Managed Agents Model Config -- `BetaManagedAgentsModelConfig object { id, effort, inference_geo, speed }` +- `BetaManagedAgentsModelConfig object` Model identifier and configuration.
from line 7463
How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes. - - `BetaManagedAgentsEffortLow object { type }` + - `BetaManagedAgentsEffortLow object` Low effort. Favors latency over reasoning depth. - `type: "low"` - - `"low"` - - - `BetaManagedAgentsEffortMedium object { type }` + - `BetaManagedAgentsEffortMedium object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - - `"medium"` - - - `BetaManagedAgentsEffortHigh object { type }` + - `BetaManagedAgentsEffortHigh object` High effort. Favors reasoning depth. - `type: "high"` - - `"high"` - - - `BetaManagedAgentsEffortXhigh object { type }` + - `BetaManagedAgentsEffortXhigh object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - - `"xhigh"` - - - `BetaManagedAgentsEffortMax object { type }` + - `BetaManagedAgentsEffortMax object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - - `"max"` - - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.
from line 7507
### Beta Managed Agents Model Config Params -- `BetaManagedAgentsModelConfigParams object { id, effort, inference_geo, speed }` +- `BetaManagedAgentsModelConfigParams object` An object that defines additional configuration control over model use
from line 7595
- `"max"` - - `BetaManagedAgentsEffortLow object { type }` + - `BetaManagedAgentsEffortLow object` Low effort. Favors latency over reasoning depth. - `type: "low"` - - `"low"` - - - `BetaManagedAgentsEffortMedium object { type }` + - `BetaManagedAgentsEffortMedium object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - - `"medium"` - - - `BetaManagedAgentsEffortHigh object { type }` + - `BetaManagedAgentsEffortHigh object` High effort. Favors reasoning depth. - `type: "high"` - - `"high"` - - - `BetaManagedAgentsEffortXhigh object { type }` + - `BetaManagedAgentsEffortXhigh object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - - `"xhigh"` - - - `BetaManagedAgentsEffortMax object { type }` + - `BetaManagedAgentsEffortMax object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - - `"max"` - - `inference_geo: optional string or null` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo. On update, `model` is whole-object replacement — omitting inference_geo clears it.
from line 7639
### Beta Managed Agents Multiagent Coordinator -- `BetaManagedAgentsMultiagentCoordinator object { agents, type }` +- `BetaManagedAgentsMultiagentCoordinator object` Resolved coordinator topology with a concrete agent roster.
from line 7647
Agents the coordinator may spawn as session threads, each resolved to a specific version. - - `BetaManagedAgentsAgentReference object { id, type, version }` + - `BetaManagedAgentsAgentReference object` A resolved agent reference with a concrete version.
from line 7655
- `type: "agent"` - - `"agent"` - - `version: number` - - `BetaManagedAgentsAdvisor object { model, type }` + format: int32 + + - `BetaManagedAgentsAdvisor object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
from line 7669
- `type: "advisor"` - - `"advisor"` - - `type: "coordinator"` - - `"coordinator"` - ### Beta Managed Agents Multiagent Coordinator Params -- `BetaManagedAgentsMultiagentCoordinatorParams object { agents, type }` +- `BetaManagedAgentsMultiagentCoordinatorParams object` A coordinator topology: the session's primary thread orchestrates work by spawning session threads, each running an agent drawn from the `agents` roster.
from line 7683
- `string` - - `BetaManagedAgentsAgentParams object { id, type, version }` + - `BetaManagedAgentsAgentParams object` Specification for an Agent. Provide a specific `version` or use the short-form `agent="agent_id"` for the most recent version
from line 7691
The `agent` ID. + minLength: 1, maxLength: 128 + - `type: "agent"` - - `"agent"` - - `version: optional number` The specific `agent` version to use. Omit to use the latest version. Must be at least 1 if specified. - - `BetaManagedAgentsMultiagentSelfParams object { type }` + format: int32 + + - `BetaManagedAgentsMultiagentSelfParams object` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `type: "self"` - - `"self"` - - - `BetaManagedAgentsAdvisorParams object { model, type }` + - `BetaManagedAgentsAdvisorParams object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn. At most one per roster; the entry occupies the roster name `anthropic.advisor`.
from line 7715
A Claude model id. The model must be permitted as an advisor for this agent's model — see the sessions/threads/advisor spec. + minLength: 1, maxLength: 256 + - `type: "advisor"` - - `"advisor"` - - `type: "coordinator"` - - `"coordinator"` - ### Beta Managed Agents Multiagent Self Params -- `BetaManagedAgentsMultiagentSelfParams object { type }` +- `BetaManagedAgentsMultiagentSelfParams object` Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference. - `type: "self"` - - `"self"` - ### Beta Managed Agents Read Tool Config -- `BetaManagedAgentsReadToolConfig object { enabled, name, permission_policy, type }` +- `BetaManagedAgentsReadToolConfig object` Configuration for the read tool.
from line 7739
- `name: "read"` - - `"read"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "read"` - - `"read"` - ### Beta Managed Agents Read Tool Config Params -- `BetaManagedAgentsReadToolConfigParams object { name, enabled, permission_policy, type }` +- `BetaManagedAgentsReadToolConfigParams object` Configuration override for the read tool.
from line 7767
Must be "read". - - `"read"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 7775
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: optional "read"` - - `"read"` - ### Beta Managed Agents Session Thread Agent -- `BetaManagedAgentsSessionThreadAgent object { id, description, mcp_servers, 7 more }` +- `BetaManagedAgentsSessionThreadAgent object` Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`.
from line 7805
- `type: "url"` - - `"url"` - - `url: string` - `model: BetaManagedAgentsModelConfig`
from line 7881
How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes. - - `BetaManagedAgentsEffortLow object { type }` + - `BetaManagedAgentsEffortLow object` Low effort. Favors latency over reasoning depth. - `type: "low"` - - `"low"` - - - `BetaManagedAgentsEffortMedium object { type }` + - `BetaManagedAgentsEffortMedium object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - - `"medium"` - - - `BetaManagedAgentsEffortHigh object { type }` + - `BetaManagedAgentsEffortHigh object` High effort. Favors reasoning depth. - `type: "high"` - - `"high"` - - - `BetaManagedAgentsEffortXhigh object { type }` + - `BetaManagedAgentsEffortXhigh object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - - `"xhigh"` - - - `BetaManagedAgentsEffortMax object { type }` + - `BetaManagedAgentsEffortMax object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - - `"max"` - - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.
from line 7927
- `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - - `BetaManagedAgentsAnthropicSkill object { skill_id, type, version }` + - `BetaManagedAgentsAnthropicSkill object` A resolved Anthropic-managed skill.
from line 7935
- `type: "anthropic"` - - `"anthropic"` - - `version: string` - - `BetaManagedAgentsCustomSkill object { skill_id, type, version }` + - `BetaManagedAgentsCustomSkill object` A resolved user-created custom skill.
from line 7945
- `type: "custom"` - - `"custom"` - - `version: string` - `system: string or null` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - - `BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }` + - `BetaManagedAgentsAgentToolset20260401 object` - `configs: array of BetaManagedAgentsAgentToolConfig` - - `BetaManagedAgentsBashToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsBashToolConfig object` Configuration for the bash tool.
from line 7963
- `name: "bash"` - - `"bash"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "bash"` - - `"bash"` - - - `BetaManagedAgentsEditToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsEditToolConfig object` Configuration for the edit tool.
from line 7989
- `name: "edit"` - - `"edit"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "edit"` - - `"edit"` - - - `BetaManagedAgentsReadToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsReadToolConfig object` Configuration for the read tool.
from line 8011
- `name: "read"` - - `"read"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "read"` - - `"read"` - - - `BetaManagedAgentsWriteToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsWriteToolConfig object` Configuration for the write tool.
from line 8033
- `name: "write"` - - `"write"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "write"` - - `"write"` - - - `BetaManagedAgentsGlobToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGlobToolConfig object` Configuration for the glob tool.
from line 8055
- `name: "glob"` - - `"glob"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "glob"` - - `"glob"` - - - `BetaManagedAgentsGrepToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGrepToolConfig object` Configuration for the grep tool.
from line 8077
- `name: "grep"` - - `"grep"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "grep"` - - `"grep"` - - - `BetaManagedAgentsWebFetchToolConfig object { enabled, name, permission_policy, 4 more }` + - `BetaManagedAgentsWebFetchToolConfig object` Configuration for the web_fetch tool.
from line 8099
- `name: "web_fetch"` - - `"web_fetch"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_fetch"` - - `"web_fetch"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number or null` - - `BetaManagedAgentsWebSearchToolConfig object { enabled, name, permission_policy, 4 more }` + format: int32 + + - `BetaManagedAgentsWebSearchToolConfig object` Configuration for the web_search tool.
from line 8129
- `name: "web_search"` - - `"web_search"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_search"` - - `"web_search"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string`
from line 8155
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 8169
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools.
from line 8187
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "agent_toolset_20260401"` - - `"agent_toolset_20260401"` - - - `BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }` + - `BetaManagedAgentsMCPToolset object` - `configs: array of BetaManagedAgentsMCPToolConfig`
from line 8209
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 8227
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 8239
- `type: "mcp_toolset"` - - `"mcp_toolset"` - - - `BetaManagedAgentsCustomTool object { description, input_schema, name, type }` + - `BetaManagedAgentsCustomTool object` A custom tool as returned in API responses.
from line 8251
- `type: "object"` - - `"object"` - - `properties: optional map[unknown] or null` - `required: optional array of string or null`
from line 8259
- `type: "custom"` - - `"custom"` - - `type: "agent"` - - `"agent"` - - `version: number` + format: int32 + ### Beta Managed Agents Skill Params - `BetaManagedAgentsSkillParams = BetaManagedAgentsAnthropicSkillParams or BetaManagedAgentsCustomSkillParams` Skill to load in the session container. - - `BetaManagedAgentsAnthropicSkillParams object { skill_id, type, version }` + - `BetaManagedAgentsAnthropicSkillParams object` An Anthropic-managed skill.
from line 8279
Identifier of the Anthropic skill (e.g., "xlsx"). + minLength: 1, maxLength: 64 + - `type: "anthropic"` - - `"anthropic"` - - `version: optional string or null` Version to pin. Defaults to latest if omitted. - - `BetaManagedAgentsCustomSkillParams object { skill_id, type, version }` + minLength: 1, maxLength: 64 + + - `BetaManagedAgentsCustomSkillParams object` A user-created custom skill.
from line 8297
Tagged ID of the custom skill (e.g., "skill_01XJ5..."). + minLength: 1, maxLength: 64 + - `type: "custom"` - - `"custom"` - - `version: optional string or null` Version to pin. Defaults to latest if omitted. + minLength: 1, maxLength: 64 + ### Beta Managed Agents URL MCP Server Params -- `BetaManagedAgentsURLMCPServerParams object { name, type, url }` +- `BetaManagedAgentsURLMCPServerParams object` URL-based MCP server connection.
from line 8317
Unique name for this server, referenced by mcp_toolset configurations. 1-255 characters. + minLength: 1, maxLength: 255 + - `type: "url"` - - `"url"` - - `url: string` Endpoint URL for the MCP server. + maxLength: 2048 + ### Beta Managed Agents User Location -- `BetaManagedAgentsUserLocation object { type, city, country, 2 more }` +- `BetaManagedAgentsUserLocation object` Approximate user location for search result localization.
from line 8337
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 8351
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + ### Beta Managed Agents Web Fetch Tool Config -- `BetaManagedAgentsWebFetchToolConfig object { enabled, name, permission_policy, 4 more }` +- `BetaManagedAgentsWebFetchToolConfig object` Configuration for the web_fetch tool.
from line 8369
- `name: "web_fetch"` - - `"web_fetch"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "web_fetch"` - - `"web_fetch"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number or null` + format: int32 + ### Beta Managed Agents Web Fetch Tool Config Params -- `BetaManagedAgentsWebFetchToolConfigParams object { name, allowed_domains, blocked_domains, 4 more }` +- `BetaManagedAgentsWebFetchToolConfigParams object` Configuration override for the web_fetch tool.
from line 8405
Must be "web_fetch". - - `"web_fetch"` - - `allowed_domains: optional array of string` Only fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains.
from line 8421
Maximum number of tokens of fetched text content to include in context per call. Does not apply to binary content such as PDFs. + format: int32 + - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or null` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: optional "web_fetch"` - - `"web_fetch"` - ### Beta Managed Agents Web Search Tool Config -- `BetaManagedAgentsWebSearchToolConfig object { enabled, name, permission_policy, 4 more }` +- `BetaManagedAgentsWebSearchToolConfig object` Configuration for the web_search tool.
from line 8451
- `name: "web_search"` - - `"web_search"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "web_search"` - - `"web_search"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string`
from line 8481
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 8495
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + ### Beta Managed Agents Web Search Tool Config Params -- `BetaManagedAgentsWebSearchToolConfigParams object { name, allowed_domains, blocked_domains, 4 more }` +- `BetaManagedAgentsWebSearchToolConfigParams object` Configuration override for the web_search tool.
from line 8513
Must be "web_search". - - `"web_search"` - - `allowed_domains: optional array of string` Only return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "docs.example.com" (no scheme or port; an optional path suffix is accepted). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with blocked_domains.
from line 8529
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: optional "web_search"` - - `"web_search"` - - `user_location: optional BetaManagedAgentsUserLocation or null` Approximate user location for search result localization.
from line 8551
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 8565
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + ### Beta Managed Agents Write Tool Config -- `BetaManagedAgentsWriteToolConfig object { enabled, name, permission_policy, type }` +- `BetaManagedAgentsWriteToolConfig object` Configuration for the write tool.
from line 8583
- `name: "write"` - - `"write"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "write"` - - `"write"` - ### Beta Managed Agents Write Tool Config Params -- `BetaManagedAgentsWriteToolConfigParams object { name, enabled, permission_policy, type }` +- `BetaManagedAgentsWriteToolConfigParams object` Configuration override for the write tool.
from line 8611
Must be "write". - - `"write"` - - `enabled: optional boolean or null` Whether this tool is enabled and available to Claude. Overrides the default_config setting.
from line 8619
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: optional "write"` - - `"write"` - -# Versions - -## List Agent Versions - -**get** `/v1/agents/{agent_id}/versions` +## Agents › Versions + +### List Agent Versions + +**GET** `/v1/agents/{agent_id}/versions` List Agent Versions -### Path Parameters +#### Path parameters - `agent_id: string` -### Query Parameters +#### Query parameters - `limit: optional number` Maximum results per page. Default 20, maximum 100. + format: int32 + - `page: optional string` Opaque pagination cursor. -### Header Parameters +#### Headers - `"anthropic-beta": optional array of AnthropicBeta`
from line 8735
- `"mid-conversation-tool-changes-2026-07-01"` -### Returns +#### Returns - `data: array of BetaManagedAgentsAgent`
from line 8747
A timestamp in RFC 3339 format + format: date-time + - `created_at: string` A timestamp in RFC 3339 format + format: date-time + - `description: string or null` - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`
from line 8763
- `type: "url"` - - `"url"` - - `url: string` - `metadata: map[string]`
from line 8841
How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes. - - `BetaManagedAgentsEffortLow object { type }` + - `BetaManagedAgentsEffortLow object` Low effort. Favors latency over reasoning depth. - `type: "low"` - - `"low"` - - - `BetaManagedAgentsEffortMedium object { type }` + - `BetaManagedAgentsEffortMedium object` Medium effort. Balances latency and reasoning depth. - `type: "medium"` - - `"medium"` - - - `BetaManagedAgentsEffortHigh object { type }` + - `BetaManagedAgentsEffortHigh object` High effort. Favors reasoning depth. - `type: "high"` - - `"high"` - - - `BetaManagedAgentsEffortXhigh object { type }` + - `BetaManagedAgentsEffortXhigh object` Extra-high effort. Not all models accept this level. - `type: "xhigh"` - - `"xhigh"` - - - `BetaManagedAgentsEffortMax object { type }` + - `BetaManagedAgentsEffortMax object` Maximum effort. Favors reasoning depth over latency. - `type: "max"` - - `"max"` - - `inference_geo: optional string` Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.
from line 8891
Agents the coordinator may spawn as session threads, each resolved to a specific version. - - `BetaManagedAgentsAgentReference object { id, type, version }` + - `BetaManagedAgentsAgentReference object` A resolved agent reference with a concrete version.
from line 8899
- `type: "agent"` - - `"agent"` - - `version: number` - - `BetaManagedAgentsAdvisor object { model, type }` + format: int32 + + - `BetaManagedAgentsAdvisor object` Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
from line 8913
- `type: "advisor"` - - `"advisor"` - - `type: "coordinator"` - - `"coordinator"` - - `name: string` - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill` - - `BetaManagedAgentsAnthropicSkill object { skill_id, type, version }` + - `BetaManagedAgentsAnthropicSkill object` A resolved Anthropic-managed skill.
from line 8927
- `type: "anthropic"` - - `"anthropic"` - - `version: string` - - `BetaManagedAgentsCustomSkill object { skill_id, type, version }` + - `BetaManagedAgentsCustomSkill object` A resolved user-created custom skill.
from line 8937
- `type: "custom"` - - `"custom"` - - `version: string` - `system: string or null` - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool` - - `BetaManagedAgentsAgentToolset20260401 object { configs, default_config, type }` + - `BetaManagedAgentsAgentToolset20260401 object` - `configs: array of BetaManagedAgentsAgentToolConfig` - - `BetaManagedAgentsBashToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsBashToolConfig object` Configuration for the bash tool.
from line 8955
- `name: "bash"` - - `"bash"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - `type: "always_allow"` - - `"always_allow"` - - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "always_ask"` - - `"always_ask"` - - `type: "bash"` - - `"bash"` - - - `BetaManagedAgentsEditToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsEditToolConfig object` Configuration for the edit tool.
from line 8981
- `name: "edit"` - - `"edit"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "edit"` - - `"edit"` - - - `BetaManagedAgentsReadToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsReadToolConfig object` Configuration for the read tool.
from line 9003
- `name: "read"` - - `"read"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "read"` - - `"read"` - - - `BetaManagedAgentsWriteToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsWriteToolConfig object` Configuration for the write tool.
from line 9025
- `name: "write"` - - `"write"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "write"` - - `"write"` - - - `BetaManagedAgentsGlobToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGlobToolConfig object` Configuration for the glob tool.
from line 9047
- `name: "glob"` - - `"glob"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "glob"` - - `"glob"` - - - `BetaManagedAgentsGrepToolConfig object { enabled, name, permission_policy, type }` + - `BetaManagedAgentsGrepToolConfig object` Configuration for the grep tool.
from line 9069
- `name: "grep"` - - `"grep"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "grep"` - - `"grep"` - - - `BetaManagedAgentsWebFetchToolConfig object { enabled, name, permission_policy, 4 more }` + - `BetaManagedAgentsWebFetchToolConfig object` Configuration for the web_fetch tool.
from line 9091
- `name: "web_fetch"` - - `"web_fetch"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_fetch"` - - `"web_fetch"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string` - `max_content_tokens: optional number or null` - - `BetaManagedAgentsWebSearchToolConfig object { enabled, name, permission_policy, 4 more }` + format: int32 + + - `BetaManagedAgentsWebSearchToolConfig object` Configuration for the web_search tool.
from line 9121
- `name: "web_search"` - - `"web_search"` - - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy` Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "web_search"` - - `"web_search"` - - `allowed_domains: optional array of string` - `blocked_domains: optional array of string`
from line 9147
Location precision. Only "approximate" is supported. - - `"approximate"` - - `city: optional string or null` City name. + minLength: 1, maxLength: 255 + - `country: optional string or null` Two-letter ISO 3166-1 country code, uppercase.
from line 9161
Region or state name. + minLength: 1, maxLength: 255 + - `timezone: optional string or null` IANA timezone identifier, e.g. "America/Los_Angeles". + minLength: 1, maxLength: 255 + - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig` Resolved default configuration for agent tools.
from line 9179
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution. - `type: "agent_toolset_20260401"` - - `"agent_toolset_20260401"` - - - `BetaManagedAgentsMCPToolset object { configs, default_config, mcp_server_name, type }` + - `BetaManagedAgentsMCPToolset object` - `configs: array of BetaManagedAgentsMCPToolConfig`
from line 9201
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 9219
Permission policy for tool execution. - - `BetaManagedAgentsAlwaysAllowPolicy object { type }` + - `BetaManagedAgentsAlwaysAllowPolicy object` Tool calls are automatically approved without user confirmation. - - `BetaManagedAgentsAlwaysAskPolicy object { type }` + - `BetaManagedAgentsAlwaysAskPolicy object` Tool calls require user confirmation before execution.
from line 9231
- `type: "mcp_toolset"` - - `"mcp_toolset"` - - - `BetaManagedAgentsCustomTool object { description, input_schema, name, type }` + - `BetaManagedAgentsCustomTool object` A custom tool as returned in API responses.
from line 9243
- `type: "object"` - - `"object"` - - `properties: optional map[unknown] or null` - `required: optional array of string or null`
from line 9251
- `type: "custom"` - - `"custom"` - - `type: "agent"` - - `"agent"` - - `updated_at: string` A timestamp in RFC 3339 format + format: date-time + - `version: number` The agent's current version. Starts at 1 and increments when the agent is modified. + format: int32 + - `next_page: optional string or null` Opaque cursor for the next page. Null when no more results. -### Example - -```http +#### Example + +```bash curl https://api.anthropic.com/v1/agents/$AGENT_ID/versions \ -H 'anthropic-version: 2023-06-01' \ -H 'anthropic-beta: managed-agents-2026-04-01' \ -H "X-Api-Key: $ANTHROPIC_API_KEY" ``` -#### Response +##### Response (200) ```json {