Agenti
Elenca gli agenti
client.Beta.Agents.List(ctx, params) (*PageCursor[BetaManagedAgentsAgent], error)Ottieni agente
client.Beta.Agents.Get(ctx, agentID, params) (*BetaManagedAgentsAgent, error)Aggiorna agente
client.Beta.Agents.Update(ctx, agentID, params) (*BetaManagedAgentsAgent, error)Archivia agente
client.Beta.Agents.Archive(ctx, agentID, body) (*BetaManagedAgentsAgent, error)Models
type BetaManagedAgentsAdvisor struct { Type: "advisor"; Model }Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
The advisor model id.
type BetaManagedAgentsAgent struct { Type: "agent"; ID; ArchivedAt; /* 13 more */ }A Managed Agents agent.
A Managed Agents agent.
type BetaManagedAgentsAgentReference struct { Type: "agent"; ID; Version }A resolved agent reference with a concrete version.
A resolved agent reference with a concrete version.
Version int64
type BetaManagedAgentsAgentToolConfigUnion interface{…}Configuration for a specific agent tool.
Configuration for a specific agent tool.
type BetaManagedAgentsAgentToolConfigParamsUnion interface{…}Configuration override for a specific tool within a toolset.
Configuration override for a specific tool within a toolset.
type BetaManagedAgentsAgentToolsetDefaultConfig struct { Enabled; PermissionPolicy }Resolved default configuration for agent tools.
Resolved default configuration for agent tools.
PermissionPolicy BetaManagedAgentsAgentToolsetDefaultConfigPermissionPolicyUnionPermission policy for tool execution.
Permission policy for tool execution.
type BetaManagedAgentsAlwaysAllowPolicy struct { Type: "always_allow" }Tool calls are automatically approved without user confirmation.
Tool calls are automatically approved without user confirmation.
type BetaManagedAgentsAlwaysAskPolicy struct { Type: "always_ask" }Tool calls require user confirmation before execution.
Tool calls require user confirmation before execution.
type BetaManagedAgentsAutoPolicy struct { Type: "auto" }The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
type BetaManagedAgentsAgentToolsetDefaultConfigParams struct { Enabled; PermissionPolicy }Default configuration for all tools in a toolset.
Default configuration for all tools in a toolset.
Whether tools are enabled and available to Claude by default. Defaults to true if not specified.
PermissionPolicy BetaManagedAgentsAgentToolsetDefaultConfigParamsPermissionPolicyUnion OptionalDefault permission policy for tools. Controls whether tool calls are auto-approved or require confirmation.
Default permission policy for tools. Controls whether tool calls are auto-approved or require confirmation.
type BetaManagedAgentsAlwaysAllowPolicy struct { Type: "always_allow" }Tool calls are automatically approved without user confirmation.
Tool calls are automatically approved without user confirmation.
type BetaManagedAgentsAlwaysAskPolicy struct { Type: "always_ask" }Tool calls require user confirmation before execution.
Tool calls require user confirmation before execution.
type BetaManagedAgentsAutoPolicy struct { Type: "auto" }The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
type BetaManagedAgentsAgentToolset20260401 struct { Type: "agent_toolset_20260401"; Configs; DefaultConfig }
type BetaManagedAgentsAgentToolset20260401BashInput struct { Command; Restart; TimeoutMs }Input payload for the bash tool of the
agent_toolset_20260401 toolset. All fields are optional;
a normal invocation supplies command, while restart=true
(with no command) reboots the runner-side bash session.
Input payload for the bash tool of the
agent_toolset_20260401 toolset. All fields are optional;
a normal invocation supplies command, while restart=true
(with no command) reboots the runner-side bash session.
Shell command to execute. Omit only when restart is true.
When true, restart the persistent bash session instead of
running a command. Subsequent calls without restart will
run against the fresh session.
TimeoutMs int64 OptionalPer-call timeout in milliseconds. Defaults to the
runner-wide tool timeout when omitted or zero.
Per-call timeout in milliseconds. Defaults to the runner-wide tool timeout when omitted or zero.
type BetaManagedAgentsAgentToolset20260401EditInput struct { FilePath; NewString; OldString; ReplaceAll }Input payload for the edit tool. Performs a string
replacement in the named file; by default old_string must
occur exactly once.
Input payload for the edit tool. Performs a string
replacement in the named file; by default old_string must
occur exactly once.
Path of the file to edit.
Replacement text.
Substring to find and replace.
When true, replace every occurrence of old_string
instead of requiring a unique match.
type BetaManagedAgentsAgentToolset20260401GlobInput struct { Pattern; Path }Input payload for the glob tool. Returns paths matching a
doublestar glob pattern, newest first.
Input payload for the glob tool. Returns paths matching a
doublestar glob pattern, newest first.
Doublestar glob pattern (e.g. **/*.go). Absolute patterns
are only permitted when the runner is configured to allow
them.
Optional directory root to search under. Defaults to the runner's working directory.
type BetaManagedAgentsAgentToolset20260401GrepInput struct { Pattern; Path }Input payload for the grep tool. Searches file contents for
a regular expression, returning matching lines.
Input payload for the grep tool. Searches file contents for
a regular expression, returning matching lines.
Regular expression to search for.
Optional directory root to search under. Defaults to the runner's working directory.
type BetaManagedAgentsAgentToolset20260401Params struct { Type: "agent_toolset_20260401"; Configs; DefaultConfig }Configuration for built-in agent tools. Use this to enable or disable groups of tools available to the agent.
Configuration for built-in agent tools. Use this to enable or disable groups of tools available to the agent.
type BetaManagedAgentsAgentToolset20260401ReadInput struct { FilePath; ViewRange }Input payload for the read tool. Reads file contents
relative to the runner's working directory (or absolute when
the runner permits).
Input payload for the read tool. Reads file contents
relative to the runner's working directory (or absolute when
the runner permits).
Path of the file to read.
ViewRange []int64 OptionalOptional [start_line, end_line] 1-indexed inclusive
range. When omitted the entire file is returned.
end_line of 0 or negative means "to end of file".
Optional [start_line, end_line] 1-indexed inclusive
range. When omitted the entire file is returned.
end_line of 0 or negative means "to end of file".
type BetaManagedAgentsAgentToolset20260401WriteInput struct { Content; FilePath }Input payload for the write tool. Writes (overwriting) the
entire file contents.
Input payload for the write tool. Writes (overwriting) the
entire file contents.
Full file contents to write.
Path of the file to write.
type BetaManagedAgentsAlwaysAllowPolicy struct { Type: "always_allow" }Tool calls are automatically approved without user confirmation.
Tool calls are automatically approved without user confirmation.
type BetaManagedAgentsAlwaysAskPolicy struct { Type: "always_ask" }Tool calls require user confirmation before execution.
Tool calls require user confirmation before execution.
type BetaManagedAgentsAnthropicSkill struct { Type: "anthropic"; SkillID; Version }A resolved Anthropic-managed skill.
A resolved Anthropic-managed skill.
type BetaManagedAgentsAnthropicSkillParams struct { Type: "anthropic"; SkillID; Version }An Anthropic-managed skill.
An Anthropic-managed skill.
SkillID stringIdentifier of the Anthropic skill (e.g., "xlsx").
Identifier of the Anthropic skill (e.g., "xlsx").
Version string OptionalVersion to pin. Defaults to latest if omitted.
Version to pin. Defaults to latest if omitted.
type BetaManagedAgentsAutoPolicy struct { Type: "auto" }The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
type BetaManagedAgentsAWSRoleExecutionIdentity struct { Type: "aws_role"; RoleARN }An AWS IAM role principal as returned in API responses.
An AWS IAM role principal as returned in API responses.
The IAM role's ARN.
type BetaManagedAgentsAWSRoleExecutionIdentityParams struct { Type: "aws_role"; RoleARN }An AWS IAM role principal.
An AWS IAM role principal.
RoleARN stringThe IAM role's ARN, e.g. "arn:aws:iam::123456789012:role/my-agent-runner". Maximum 2048 characters.
The IAM role's ARN, e.g. "arn:aws:iam::123456789012:role/my-agent-runner". Maximum 2048 characters.
type BetaManagedAgentsBashToolConfig struct { Type: "bash"; Enabled; Name; PermissionPolicy }Configuration for the bash tool.
Configuration for the bash tool.
PermissionPolicy BetaManagedAgentsBashToolConfigPermissionPolicyUnionPermission policy for tool execution.
Permission policy for tool execution.
type BetaManagedAgentsAlwaysAllowPolicy struct { Type: "always_allow" }Tool calls are automatically approved without user confirmation.
Tool calls are automatically approved without user confirmation.
type BetaManagedAgentsAlwaysAskPolicy struct { Type: "always_ask" }Tool calls require user confirmation before execution.
Tool calls require user confirmation before execution.
type BetaManagedAgentsAutoPolicy struct { Type: "auto" }The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
type BetaManagedAgentsBashToolConfigParams struct { Type: "bash"; Name; Enabled; PermissionPolicy }Configuration override for the bash tool.
Configuration override for the bash tool.
type BetaManagedAgentsCustomSkill struct { Type: "custom"; SkillID; Version }A resolved user-created custom skill.
A resolved user-created custom skill.
type BetaManagedAgentsCustomSkillParams struct { Type: "custom"; SkillID; Version }A user-created custom skill.
A user-created custom skill.
SkillID stringTagged ID of the custom skill (e.g., "skill_01XJ5...").
Tagged ID of the custom skill (e.g., "skill_01XJ5...").
Version string OptionalVersion to pin. Defaults to latest if omitted.
Version to pin. Defaults to latest if omitted.
type BetaManagedAgentsCustomTool struct { Type: "custom"; Description; InputSchema; Name }A custom tool as returned in API responses.
A custom tool as returned in API responses.
InputSchema BetaManagedAgentsCustomToolInputSchemaJSON Schema for custom tool input parameters.
JSON Schema for custom tool input parameters.
type BetaManagedAgentsCustomToolInputSchema struct { Type: "object"; Properties; Required }JSON Schema for custom tool input parameters.
JSON Schema for custom tool input parameters.
type BetaManagedAgentsCustomToolParams struct { Type: "custom"; Description; InputSchema; Name }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.
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.
Description stringDescription of what the tool does, shown to the agent to help it decide when to use the tool.
Description of what the tool does, shown to the agent to help it decide when to use the tool.
InputSchema BetaManagedAgentsCustomToolInputSchemaParamJSON Schema defining the expected input parameters for the tool.
JSON Schema defining the expected input parameters for the tool.
Name stringUnique name for the tool. 1-128 characters; letters, digits, underscores, and hyphens.
Unique name for the tool. 1-128 characters; letters, digits, underscores, and hyphens.
type BetaManagedAgentsEditToolConfig struct { Type: "edit"; Enabled; Name; PermissionPolicy }Configuration for the edit tool.
Configuration for the edit tool.
PermissionPolicy BetaManagedAgentsEditToolConfigPermissionPolicyUnionPermission policy for tool execution.
Permission policy for tool execution.
type BetaManagedAgentsAlwaysAllowPolicy struct { Type: "always_allow" }Tool calls are automatically approved without user confirmation.
Tool calls are automatically approved without user confirmation.
type BetaManagedAgentsAlwaysAskPolicy struct { Type: "always_ask" }Tool calls require user confirmation before execution.
Tool calls require user confirmation before execution.
type BetaManagedAgentsAutoPolicy struct { Type: "auto" }The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
type BetaManagedAgentsEditToolConfigParams struct { Type: "edit"; Name; Enabled; PermissionPolicy }Configuration override for the edit tool.
Configuration override for the edit tool.
type BetaManagedAgentsEffortHigh struct { Type: "high" }High effort. Favors reasoning depth.
High effort. Favors reasoning depth.
type BetaManagedAgentsEffortLow struct { Type: "low" }Low effort. Favors latency over reasoning depth.
Low effort. Favors latency over reasoning depth.
type BetaManagedAgentsEffortMax struct { Type: "max" }Maximum effort. Favors reasoning depth over latency.
Maximum effort. Favors reasoning depth over latency.
type BetaManagedAgentsEffortMedium struct { Type: "medium" }Medium effort. Balances latency and reasoning depth.
Medium effort. Balances latency and reasoning depth.
type BetaManagedAgentsEffortXhigh struct { Type: "xhigh" }Extra-high effort. Not all models accept this level.
Extra-high effort. Not all models accept this level.
type BetaManagedAgentsExecutionIdentityUnion interface{…}Execution principal for runs of this agent as returned in API responses.
Execution principal for runs of this agent as returned in API responses.
type BetaManagedAgentsAWSRoleExecutionIdentity struct { Type: "aws_role"; RoleARN }An AWS IAM role principal as returned in API responses.
An AWS IAM role principal as returned in API responses.
The IAM role's ARN.
type BetaManagedAgentsServiceAccountExecutionIdentity struct { Type: "service_account" }The Anthropic-managed service account as returned in API responses.
The Anthropic-managed service account as returned in API responses.
type BetaManagedAgentsExecutionIdentityParamsUnion interface{…}Execution principal for runs of this agent: service_account (the default) or aws_role.
Execution principal for runs of this agent: service_account (the default) or aws_role.
type BetaManagedAgentsAWSRoleExecutionIdentityParams struct { Type: "aws_role"; RoleARN }An AWS IAM role principal.
An AWS IAM role principal.
RoleARN stringThe IAM role's ARN, e.g. "arn:aws:iam::123456789012:role/my-agent-runner". Maximum 2048 characters.
The IAM role's ARN, e.g. "arn:aws:iam::123456789012:role/my-agent-runner". Maximum 2048 characters.
type BetaManagedAgentsServiceAccountExecutionIdentityParams struct { Type: "service_account" }The Anthropic-managed service account — the default execution principal. Carries no identifier.
The Anthropic-managed service account — the default execution principal. Carries no identifier.
type BetaManagedAgentsGlobToolConfig struct { Type: "glob"; Enabled; Name; PermissionPolicy }Configuration for the glob tool.
Configuration for the glob tool.
PermissionPolicy BetaManagedAgentsGlobToolConfigPermissionPolicyUnionPermission policy for tool execution.
Permission policy for tool execution.
type BetaManagedAgentsAlwaysAllowPolicy struct { Type: "always_allow" }Tool calls are automatically approved without user confirmation.
Tool calls are automatically approved without user confirmation.
type BetaManagedAgentsAlwaysAskPolicy struct { Type: "always_ask" }Tool calls require user confirmation before execution.
Tool calls require user confirmation before execution.
type BetaManagedAgentsAutoPolicy struct { Type: "auto" }The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
type BetaManagedAgentsGlobToolConfigParams struct { Type: "glob"; Name; Enabled; PermissionPolicy }Configuration override for the glob tool.
Configuration override for the glob tool.
type BetaManagedAgentsGrepToolConfig struct { Type: "grep"; Enabled; Name; PermissionPolicy }Configuration for the grep tool.
Configuration for the grep tool.
PermissionPolicy BetaManagedAgentsGrepToolConfigPermissionPolicyUnionPermission policy for tool execution.
Permission policy for tool execution.
type BetaManagedAgentsAlwaysAllowPolicy struct { Type: "always_allow" }Tool calls are automatically approved without user confirmation.
Tool calls are automatically approved without user confirmation.
type BetaManagedAgentsAlwaysAskPolicy struct { Type: "always_ask" }Tool calls require user confirmation before execution.
Tool calls require user confirmation before execution.
type BetaManagedAgentsAutoPolicy struct { Type: "auto" }The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
type BetaManagedAgentsGrepToolConfigParams struct { Type: "grep"; Name; Enabled; PermissionPolicy }Configuration override for the grep tool.
Configuration override for the grep tool.
type BetaManagedAgentsMCPServerURLDefinition struct { Type: "url"; Name; URL }URL-based MCP server connection as returned in API responses.
URL-based MCP server connection as returned in API responses.
type BetaManagedAgentsMCPToolConfig struct { Enabled; Name; PermissionPolicy }Resolved configuration for a specific MCP tool.
Resolved configuration for a specific MCP tool.
PermissionPolicy BetaManagedAgentsMCPToolConfigPermissionPolicyUnionPermission policy for tool execution.
Permission policy for tool execution.
type BetaManagedAgentsAlwaysAllowPolicy struct { Type: "always_allow" }Tool calls are automatically approved without user confirmation.
Tool calls are automatically approved without user confirmation.
type BetaManagedAgentsAlwaysAskPolicy struct { Type: "always_ask" }Tool calls require user confirmation before execution.
Tool calls require user confirmation before execution.
type BetaManagedAgentsAutoPolicy struct { Type: "auto" }The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
type BetaManagedAgentsMCPToolConfigParams struct { Name; Enabled; PermissionPolicy }Configuration override for a specific MCP tool.
Configuration override for a specific MCP tool.
Name stringName of the MCP tool to configure. 1-128 characters.
Name of the MCP tool to configure. 1-128 characters.
Whether this tool is enabled. Overrides the default_config setting.
PermissionPolicy BetaManagedAgentsMCPToolConfigParamsPermissionPolicyUnion OptionalPermission policy for this tool. Overrides the default_config setting.
Permission policy for this tool. Overrides the default_config setting.
type BetaManagedAgentsAlwaysAllowPolicy struct { Type: "always_allow" }Tool calls are automatically approved without user confirmation.
Tool calls are automatically approved without user confirmation.
type BetaManagedAgentsAlwaysAskPolicy struct { Type: "always_ask" }Tool calls require user confirmation before execution.
Tool calls require user confirmation before execution.
type BetaManagedAgentsAutoPolicy struct { Type: "auto" }The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
type BetaManagedAgentsMCPToolset struct { Type: "mcp_toolset"; Configs; DefaultConfig; MCPServerName }
type BetaManagedAgentsMCPToolsetDefaultConfig struct { Enabled; PermissionPolicy }Resolved default configuration for all tools from an MCP server.
Resolved default configuration for all tools from an MCP server.
PermissionPolicy BetaManagedAgentsMCPToolsetDefaultConfigPermissionPolicyUnionPermission policy for tool execution.
Permission policy for tool execution.
type BetaManagedAgentsAlwaysAllowPolicy struct { Type: "always_allow" }Tool calls are automatically approved without user confirmation.
Tool calls are automatically approved without user confirmation.
type BetaManagedAgentsAlwaysAskPolicy struct { Type: "always_ask" }Tool calls require user confirmation before execution.
Tool calls require user confirmation before execution.
type BetaManagedAgentsAutoPolicy struct { Type: "auto" }The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
type BetaManagedAgentsMCPToolsetDefaultConfigParams struct { Enabled; PermissionPolicy }Default configuration for all tools from an MCP server.
Default configuration for all tools from an MCP server.
Whether tools are enabled by default. Defaults to true if not specified.
PermissionPolicy BetaManagedAgentsMCPToolsetDefaultConfigParamsPermissionPolicyUnion OptionalDefault permission policy for tools from this server.
Default permission policy for tools from this server.
type BetaManagedAgentsAlwaysAllowPolicy struct { Type: "always_allow" }Tool calls are automatically approved without user confirmation.
Tool calls are automatically approved without user confirmation.
type BetaManagedAgentsAlwaysAskPolicy struct { Type: "always_ask" }Tool calls require user confirmation before execution.
Tool calls require user confirmation before execution.
type BetaManagedAgentsAutoPolicy struct { Type: "auto" }The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
type BetaManagedAgentsMCPToolsetParams struct { Type: "mcp_toolset"; MCPServerName; Configs; DefaultConfig }Configuration for tools from an MCP server defined in mcp_servers.
Configuration for tools from an MCP server defined in mcp_servers.
type BetaManagedAgentsModel stringThe model that will power your agent.
The model that will power your agent.
See models for additional details and options.
type BetaManagedAgentsModelConfig struct { ID; Effort; InferenceGeo; Speed }Model identifier and configuration.
Model identifier and configuration.
type BetaManagedAgentsModelConfigParams struct { ID; Effort; InferenceGeo; Speed }An object that defines additional configuration control over model use
An object that defines additional configuration control over model use
type BetaManagedAgentsMultiagentAdvisorUnion interface{…}Whether the session's primary thread can consult an advisor model.
Whether the session's primary thread can consult an advisor model.
type BetaManagedAgentsMultiagentAdvisorEnabled struct { Type: "enabled"; Model }The session's primary thread can consult model mid-turn.
The session's primary thread can consult model mid-turn.
The advisor model id.
type BetaManagedAgentsMultiagentAdvisorDisabled struct { Type: "disabled" }The agent has no advisor.
The agent has no advisor.
type BetaManagedAgentsMultiagentAdvisorDisabled struct { Type: "disabled" }The agent has no advisor.
The agent has no advisor.
type BetaManagedAgentsMultiagentAdvisorDisabledParams struct { Type: "disabled" }The agent has no advisor.
The agent has no advisor.
type BetaManagedAgentsMultiagentAdvisorEnabled struct { Type: "enabled"; Model }The session's primary thread can consult model mid-turn.
The session's primary thread can consult model mid-turn.
The advisor model id.
type BetaManagedAgentsMultiagentAdvisorEnabledParams struct { Type: "enabled"; Model }The session's primary thread can consult model mid-turn.
The session's primary thread can consult model mid-turn.
Model stringA Claude model id. The model must be permitted as an advisor for this agent's model.
A Claude model id. The model must be permitted as an advisor for this agent's model.
type BetaManagedAgentsMultiagentAdvisorParamsUnion interface{…}Whether the session's primary thread can consult an advisor model.
Whether the session's primary thread can consult an advisor model.
type BetaManagedAgentsMultiagentAdvisorEnabledParams struct { Type: "enabled"; Model }The session's primary thread can consult model mid-turn.
The session's primary thread can consult model mid-turn.
Model stringA Claude model id. The model must be permitted as an advisor for this agent's model.
A Claude model id. The model must be permitted as an advisor for this agent's model.
type BetaManagedAgentsMultiagentAdvisorDisabledParams struct { Type: "disabled" }The agent has no advisor.
The agent has no advisor.
type BetaManagedAgentsMultiagentCoordinator struct { Type: "coordinator"; Agents }Resolved coordinator topology with a concrete agent roster.
Resolved coordinator topology with a concrete agent roster.
Agents []BetaManagedAgentsMultiagentCoordinatorAgentUnionAgents the coordinator may spawn as session threads, each resolved to a specific version.
Agents the coordinator may spawn as session threads, each resolved to a specific version.
type BetaManagedAgentsAgentReference struct { Type: "agent"; ID; Version }A resolved agent reference with a concrete version.
A resolved agent reference with a concrete version.
Version int64
type BetaManagedAgentsAdvisor struct { Type: "advisor"; Model }Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
The advisor model id.
type BetaManagedAgentsMultiagentCoordinatorParams struct { Type: "coordinator"; Agents }A coordinator topology: the session's primary thread orchestrates work by spawning session threads, each running an agent drawn from the agents roster.
A coordinator topology: the session's primary thread orchestrates work by spawning session threads, each running an agent drawn from the agents roster.
type BetaManagedAgentsMultiagentInlineAgentsUnion interface{…}Whether the agent can define inline agents. The agent defines an inline agent itself, in a workflow run's plan or when it spawns a session thread, and the inline agent is not saved.
Whether the agent can define inline agents. The agent defines an inline agent itself, in a workflow run's plan or when it spawns a session thread, and the inline agent is not saved.
type BetaManagedAgentsMultiagentInlineAgentsEnabled struct { Type: "enabled" }The agent can define inline agents.
The agent can define inline agents.
type BetaManagedAgentsMultiagentInlineAgentsDisabled struct { Type: "disabled" }The agent cannot define inline agents.
The agent cannot define inline agents.
type BetaManagedAgentsMultiagentInlineAgentsDisabled struct { Type: "disabled" }The agent cannot define inline agents.
The agent cannot define inline agents.
type BetaManagedAgentsMultiagentInlineAgentsDisabledParams struct { Type: "disabled" }The agent cannot define inline agents.
The agent cannot define inline agents.
type BetaManagedAgentsMultiagentInlineAgentsEnabled struct { Type: "enabled" }The agent can define inline agents.
The agent can define inline agents.
type BetaManagedAgentsMultiagentInlineAgentsEnabledParams struct { Type: "enabled" }The agent can define inline agents.
The agent can define inline agents.
type BetaManagedAgentsMultiagentInlineAgentsParamsUnion interface{…}Whether the agent can define inline agents. The agent defines an inline agent itself, in a workflow run's plan or when it spawns a session thread, and the inline agent is not saved.
Whether the agent can define inline agents. The agent defines an inline agent itself, in a workflow run's plan or when it spawns a session thread, and the inline agent is not saved.
type BetaManagedAgentsMultiagentInlineAgentsEnabledParams struct { Type: "enabled" }The agent can define inline agents.
The agent can define inline agents.
type BetaManagedAgentsMultiagentInlineAgentsDisabledParams struct { Type: "disabled" }The agent cannot define inline agents.
The agent cannot define inline agents.
type BetaManagedAgentsMultiagentPredefinedAgentParamsUnion interface{…}One agent in a predefined_agents list. It is an agent ID string, an agent reference with an optional version, or self for the agent that owns this configuration.
One agent in a predefined_agents list. It is an agent ID string, an agent reference with an optional version, or self for the agent that owns this configuration.
type BetaManagedAgentsAgentParams struct { Type: "agent"; ID; Version }Specification for an Agent. Provide a specific version or use the short-form agent="agent_id" for the most recent version
Specification for an Agent. Provide a specific version or use the short-form agent="agent_id" for the most recent version
ID stringThe agent ID.
The agent ID.
Version int64 OptionalThe specific agent version to use. Omit to use the latest version. Must be at least 1 if specified.
The specific agent version to use. Omit to use the latest version. Must be at least 1 if specified.
type BetaManagedAgentsMultiagentSelfParams struct { Type: "self" }Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference.
Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference.
type BetaManagedAgentsMultiagentSelfParams struct { Type: "self" }Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference.
Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference.
type BetaManagedAgentsMultiagentSubagentsUnion interface{…}Whether the agent can spawn session threads.
Whether the agent can spawn session threads.
type BetaManagedAgentsMultiagentSubagentsDisabled struct { Type: "disabled" }The agent cannot spawn session threads.
The agent cannot spawn session threads.
type BetaManagedAgentsMultiagentSubagentsDisabledParams struct { Type: "disabled" }The agent cannot spawn session threads.
The agent cannot spawn session threads.
type BetaManagedAgentsMultiagentSubagentsEnabled struct { Type: "enabled"; InlineAgents; PredefinedAgents }The agent can spawn session threads.
The agent can spawn session threads.
InlineAgents BetaManagedAgentsMultiagentInlineAgentsUnionWhether the agent can define inline agents, which are not saved, when it spawns session threads.
Whether the agent can define inline agents, which are not saved, when it spawns session threads.
type BetaManagedAgentsMultiagentInlineAgentsEnabled struct { Type: "enabled" }The agent can define inline agents.
The agent can define inline agents.
type BetaManagedAgentsMultiagentInlineAgentsDisabled struct { Type: "disabled" }The agent cannot define inline agents.
The agent cannot define inline agents.
PredefinedAgents []BetaManagedAgentsAgentReferencePredefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version.
Predefined agents, which are saved agents that this agent can spawn as session threads, each resolved to a specific version.
Version int64
type BetaManagedAgentsMultiagentSubagentsEnabledParams struct { Type: "enabled"; InlineAgents; PredefinedAgents }The agent can spawn session threads. Each thread runs a predefined agent, which is a saved agent in predefined_agents, or an inline agent, which the agent defines when it spawns the thread and which is not saved. If inline_agents is disabled, predefined_agents must name at least one agent.
The agent can spawn session threads. Each thread runs a predefined agent, which is a saved agent in predefined_agents, or an inline agent, which the agent defines when it spawns the thread and which is not saved. If inline_agents is disabled, predefined_agents must name at least one agent.
type BetaManagedAgentsMultiagentSubagentsParamsUnion interface{…}Whether the agent can spawn session threads.
Whether the agent can spawn session threads.
type BetaManagedAgentsMultiagentSubagentsEnabledParams struct { Type: "enabled"; InlineAgents; PredefinedAgents }The agent can spawn session threads. Each thread runs a predefined agent, which is a saved agent in predefined_agents, or an inline agent, which the agent defines when it spawns the thread and which is not saved. If inline_agents is disabled, predefined_agents must name at least one agent.
The agent can spawn session threads. Each thread runs a predefined agent, which is a saved agent in predefined_agents, or an inline agent, which the agent defines when it spawns the thread and which is not saved. If inline_agents is disabled, predefined_agents must name at least one agent.
type BetaManagedAgentsMultiagentSubagentsDisabledParams struct { Type: "disabled" }The agent cannot spawn session threads.
The agent cannot spawn session threads.
type BetaManagedAgentsMultiagentWorkflowsUnion interface{…}Whether the agent can start workflow runs.
Whether the agent can start workflow runs.
type BetaManagedAgentsMultiagentWorkflowsDisabled struct { Type: "disabled" }The agent cannot start workflow runs.
The agent cannot start workflow runs.
type BetaManagedAgentsMultiagentWorkflowsDisabledParams struct { Type: "disabled" }The agent cannot start workflow runs.
The agent cannot start workflow runs.
type BetaManagedAgentsMultiagentWorkflowsEnabled struct { Type: "enabled"; InlineAgents; PredefinedAgents }The agent can start workflow runs.
The agent can start workflow runs.
InlineAgents BetaManagedAgentsMultiagentInlineAgentsUnionWhether a run's plan can define inline agents, which are not saved.
Whether a run's plan can define inline agents, which are not saved.
type BetaManagedAgentsMultiagentInlineAgentsEnabled struct { Type: "enabled" }The agent can define inline agents.
The agent can define inline agents.
type BetaManagedAgentsMultiagentInlineAgentsDisabled struct { Type: "disabled" }The agent cannot define inline agents.
The agent cannot define inline agents.
PredefinedAgents []BetaManagedAgentsAgentReferencePredefined agents, which are saved agents that a run's plan can use, each resolved to a specific version.
Predefined agents, which are saved agents that a run's plan can use, each resolved to a specific version.
Version int64
type BetaManagedAgentsMultiagentWorkflowsEnabledParams struct { Type: "enabled"; InlineAgents; PredefinedAgents }The agent can start workflow runs. Each run follows a plan, a program that the agent writes. A plan can use predefined agents, which are the saved agents in predefined_agents, and inline agents, which it defines itself and which are not saved. If inline_agents is disabled, predefined_agents must name at least one agent.
The agent can start workflow runs. Each run follows a plan, a program that the agent writes. A plan can use predefined agents, which are the saved agents in predefined_agents, and inline agents, which it defines itself and which are not saved. If inline_agents is disabled, predefined_agents must name at least one agent.
type BetaManagedAgentsMultiagentWorkflowsParamsUnion interface{…}Whether the agent can start workflow runs.
Whether the agent can start workflow runs.
type BetaManagedAgentsMultiagentWorkflowsEnabledParams struct { Type: "enabled"; InlineAgents; PredefinedAgents }The agent can start workflow runs. Each run follows a plan, a program that the agent writes. A plan can use predefined agents, which are the saved agents in predefined_agents, and inline agents, which it defines itself and which are not saved. If inline_agents is disabled, predefined_agents must name at least one agent.
The agent can start workflow runs. Each run follows a plan, a program that the agent writes. A plan can use predefined agents, which are the saved agents in predefined_agents, and inline agents, which it defines itself and which are not saved. If inline_agents is disabled, predefined_agents must name at least one agent.
type BetaManagedAgentsMultiagentWorkflowsDisabledParams struct { Type: "disabled" }The agent cannot start workflow runs.
The agent cannot start workflow runs.
type BetaManagedAgentsMultiagent20261001 struct { Type: "multiagent_20261001"; Advisor; Subagents; Workflows }Resolved multiagent configuration with three members, each enabled or disabled on its own.
Resolved multiagent configuration with three members, each enabled or disabled on its own.
Whether the session's primary thread can consult an advisor model.
Whether the session's primary thread can consult an advisor model.
type BetaManagedAgentsMultiagentAdvisorEnabled struct { Type: "enabled"; Model }The session's primary thread can consult model mid-turn.
The session's primary thread can consult model mid-turn.
The advisor model id.
type BetaManagedAgentsMultiagentAdvisorDisabled struct { Type: "disabled" }The agent has no advisor.
The agent has no advisor.
Whether the agent can spawn session threads.
Whether the agent can spawn session threads.
Whether the agent can start workflow runs.
Whether the agent can start workflow runs.
type BetaManagedAgentsMultiagent20261001Params struct { Type: "multiagent_20261001"; Advisor; Subagents; Workflows }Multiagent configuration with three members, each enabled or disabled on its own. On an update, if the agent's stored multiagent also has type multiagent_20261001, this configuration is merged into the stored one, level by level, instead of replacing it. A key that the update omits keeps its stored value. A key sent as null takes its default, on create as well, so "workflows": null enables workflows. An object sent with a type other than the stored one replaces the stored object, and the keys that it omits take their defaults. A predefined_agents list that is sent replaces the stored list. Every object that is sent needs its type, and an enabled advisor needs its model. Other validation applies to the merged result.
Multiagent configuration with three members, each enabled or disabled on its own. On an update, if the agent's stored multiagent also has type multiagent_20261001, this configuration is merged into the stored one, level by level, instead of replacing it. A key that the update omits keeps its stored value. A key sent as null takes its default, on create as well, so "workflows": null enables workflows. An object sent with a type other than the stored one replaces the stored object, and the keys that it omits take their defaults. A predefined_agents list that is sent replaces the stored list. Every object that is sent needs its type, and an enabled advisor needs its model. Other validation applies to the merged result.
type BetaManagedAgentsReadToolConfig struct { Type: "read"; Enabled; Name; PermissionPolicy }Configuration for the read tool.
Configuration for the read tool.
PermissionPolicy BetaManagedAgentsReadToolConfigPermissionPolicyUnionPermission policy for tool execution.
Permission policy for tool execution.
type BetaManagedAgentsAlwaysAllowPolicy struct { Type: "always_allow" }Tool calls are automatically approved without user confirmation.
Tool calls are automatically approved without user confirmation.
type BetaManagedAgentsAlwaysAskPolicy struct { Type: "always_ask" }Tool calls require user confirmation before execution.
Tool calls require user confirmation before execution.
type BetaManagedAgentsAutoPolicy struct { Type: "auto" }The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
type BetaManagedAgentsReadToolConfigParams struct { Type: "read"; Name; Enabled; PermissionPolicy }Configuration override for the read tool.
Configuration override for the read tool.
type BetaManagedAgentsServiceAccountExecutionIdentity struct { Type: "service_account" }The Anthropic-managed service account as returned in API responses.
The Anthropic-managed service account as returned in API responses.
type BetaManagedAgentsServiceAccountExecutionIdentityParams struct { Type: "service_account" }The Anthropic-managed service account — the default execution principal. Carries no identifier.
The Anthropic-managed service account — the default execution principal. Carries no identifier.
type BetaManagedAgentsSessionThreadAgent struct { Type: "agent"; ID; Description; /* 8 more */ }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.
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.
type BetaManagedAgentsSkillParamsUnion interface{…}Skill to load in the session container.
Skill to load in the session container.
type BetaManagedAgentsAnthropicSkillParams struct { Type: "anthropic"; SkillID; Version }An Anthropic-managed skill.
An Anthropic-managed skill.
SkillID stringIdentifier of the Anthropic skill (e.g., "xlsx").
Identifier of the Anthropic skill (e.g., "xlsx").
Version string OptionalVersion to pin. Defaults to latest if omitted.
Version to pin. Defaults to latest if omitted.
type BetaManagedAgentsCustomSkillParams struct { Type: "custom"; SkillID; Version }A user-created custom skill.
A user-created custom skill.
SkillID stringTagged ID of the custom skill (e.g., "skill_01XJ5...").
Tagged ID of the custom skill (e.g., "skill_01XJ5...").
Version string OptionalVersion to pin. Defaults to latest if omitted.
Version to pin. Defaults to latest if omitted.
type BetaManagedAgentsURLMCPServerParams struct { Type: "url"; Name; URL }URL-based MCP server connection.
URL-based MCP server connection.
Name stringUnique name for this server, referenced by mcp_toolset configurations. 1-255 characters.
Unique name for this server, referenced by mcp_toolset configurations. 1-255 characters.
URL stringEndpoint URL for the MCP server.
Endpoint URL for the MCP server.
type BetaManagedAgentsUserLocation struct { Type: "approximate"; City; Country; /* 2 more */ }Approximate user location for search result localization.
Approximate user location for search result localization.
Location precision. Only "approximate" is supported.
City string OptionalCity name.
City name.
Two-letter ISO 3166-1 country code, uppercase.
Region string OptionalRegion or state name.
Region or state name.
Timezone string OptionalIANA timezone identifier, e.g. "America/Los_Angeles".
IANA timezone identifier, e.g. "America/Los_Angeles".
type BetaManagedAgentsWebFetchToolConfig struct { Type: "web_fetch"; Enabled; Name; /* 5 more */ }Configuration for the web_fetch tool.
Configuration for the web_fetch tool.
type BetaManagedAgentsWebFetchToolConfigParams struct { Type: "web_fetch"; Name; AllowedDomains; /* 5 more */ }Configuration override for the web_fetch tool.
Configuration override for the web_fetch tool.
type BetaManagedAgentsWebFetchURLSourceAll struct { Type: "all" }Every URL from this source may be fetched. This is the default.
Every URL from this source may be fetched. This is the default.
type BetaManagedAgentsWebFetchURLSourceExcept struct { Type: "except"; Tools }Every tool's results contribute URLs that may be fetched, except the named tools' results.
Every tool's results contribute URLs that may be fetched, except the named tools' results.
The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results.
The tools whose results do not contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "all" to leave out no tool's results.
Must be "tool_reference".
Name stringName of the tool. Compared exactly, so upper and lower case letters are different.
Name of the tool. Compared exactly, so upper and lower case letters are different.
type BetaManagedAgentsWebFetchURLSourceNone struct { Type: "none" }This source contributes no URLs that may be fetched.
This source contributes no URLs that may be fetched.
type BetaManagedAgentsWebFetchURLSourceOnly struct { Type: "only"; Tools }Only the named tools' results contribute URLs that may be fetched.
Only the named tools' results contribute URLs that may be fetched.
The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results.
The tools whose results contribute. Between 1 and 128 entries, each with a different name. An empty list is rejected; use "none" to allow no tool's results.
Must be "tool_reference".
Name stringName of the tool. Compared exactly, so upper and lower case letters are different.
Name of the tool. Compared exactly, so upper and lower case letters are different.
type BetaManagedAgentsWebFetchURLSourceShorthand stringString form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}.
String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}.
type BetaManagedAgentsWebFetchURLSourceToolFilterUnion interface{…}Which tools' results contribute URLs that may be fetched.
Which tools' results contribute URLs that may be fetched.
type BetaManagedAgentsWebFetchURLSourceToolFilterParamsUnion interface{…}Which tools' results contribute URLs that may be fetched. Accepts the string "all" or "none", or an object whose type is "all", "none", "only" or "except". Responses use the object form.
Which tools' results contribute URLs that may be fetched. Accepts the string "all" or "none", or an object whose type is "all", "none", "only" or "except". Responses use the object form.
type BetaManagedAgentsWebFetchURLSourceShorthand stringString form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}.
String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}.
type BetaManagedAgentsWebFetchURLSourceToolFilterUnion interface{…}Which tools' results contribute URLs that may be fetched.
Which tools' results contribute URLs that may be fetched.
type BetaManagedAgentsWebFetchURLSourceToolReference struct { Type: "tool_reference"; Name }Names one tool in an only or except list.
Names one tool in an only or except list.
Must be "tool_reference".
Name stringName of the tool. Compared exactly, so upper and lower case letters are different.
Name of the tool. Compared exactly, so upper and lower case letters are different.
type BetaManagedAgentsWebFetchURLSourceUserInputUnion interface{…}Whether URLs in the text of user messages may be fetched.
Whether URLs in the text of user messages may be fetched.
type BetaManagedAgentsWebFetchURLSourceAll struct { Type: "all" }Every URL from this source may be fetched. This is the default.
Every URL from this source may be fetched. This is the default.
type BetaManagedAgentsWebFetchURLSourceNone struct { Type: "none" }This source contributes no URLs that may be fetched.
This source contributes no URLs that may be fetched.
type BetaManagedAgentsWebFetchURLSourceUserInputParamsUnion interface{…}Whether URLs in the text of user messages may be fetched. Accepts the string "all" or "none", or the object {"type": "all"} or {"type": "none"}. Responses use the object form.
Whether URLs in the text of user messages may be fetched. Accepts the string "all" or "none", or the object {"type": "all"} or {"type": "none"}. Responses use the object form.
type BetaManagedAgentsWebFetchURLSourceShorthand stringString form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}.
String form of a url_sources value that has no field other than its type: "all" means {"type": "all"} and "none" means {"type": "none"}.
type BetaManagedAgentsWebFetchURLSourceUserInputUnion interface{…}Whether URLs in the text of user messages may be fetched.
Whether URLs in the text of user messages may be fetched.
type BetaManagedAgentsWebFetchURLSourceAll struct { Type: "all" }Every URL from this source may be fetched. This is the default.
Every URL from this source may be fetched. This is the default.
type BetaManagedAgentsWebFetchURLSourceNone struct { Type: "none" }This source contributes no URLs that may be fetched.
This source contributes no URLs that may be fetched.
type BetaManagedAgentsWebFetchURLSources struct { ClientToolResults; ServerToolResults; UserInput }Which sources contribute URLs the web_fetch tool may fetch. A key that is null was not set and allows every URL from that source.
Which sources contribute URLs the web_fetch tool may fetch. A key that is null was not set and allows every URL from that source.
ClientToolResults BetaManagedAgentsWebFetchURLSourceToolFilterUnionWhich custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results.
Which custom tools' results contribute URLs that may be fetched. Null when not set, which allows every custom tool's results.
ServerToolResults BetaManagedAgentsWebFetchURLSourceToolFilterUnionWhich of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both.
Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both.
Whether URLs in the text of user messages may be fetched. Null when not set, which allows them.
Whether URLs in the text of user messages may be fetched. Null when not set, which allows them.
type BetaManagedAgentsWebFetchURLSourceAll struct { Type: "all" }Every URL from this source may be fetched. This is the default.
Every URL from this source may be fetched. This is the default.
type BetaManagedAgentsWebFetchURLSourceNone struct { Type: "none" }This source contributes no URLs that may be fetched.
This source contributes no URLs that may be fetched.
type BetaManagedAgentsWebFetchURLSourcesParams struct { ClientToolResults; ServerToolResults; UserInput }Which sources contribute URLs the web_fetch tool may fetch. When web_fetch is limited to URLs the conversation has already shown the model (in a user message, a custom tool's result, or an earlier web_search or web_fetch result), each key narrows one of those sources and defaults to "all". Setting all three keys to "none" is rejected.
Which sources contribute URLs the web_fetch tool may fetch. When web_fetch is limited to URLs the conversation has already shown the model (in a user message, a custom tool's result, or an earlier web_search or web_fetch result), each key narrows one of those sources and defaults to "all". Setting all three keys to "none" is rejected.
type BetaManagedAgentsWebSearchToolConfig struct { Type: "web_search"; Enabled; Name; /* 4 more */ }Configuration for the web_search tool.
Configuration for the web_search tool.
type BetaManagedAgentsWebSearchToolConfigParams struct { Type: "web_search"; Name; AllowedDomains; /* 4 more */ }Configuration override for the web_search tool.
Configuration override for the web_search tool.
type BetaManagedAgentsWriteToolConfig struct { Type: "write"; Enabled; Name; PermissionPolicy }Configuration for the write tool.
Configuration for the write tool.
PermissionPolicy BetaManagedAgentsWriteToolConfigPermissionPolicyUnionPermission policy for tool execution.
Permission policy for tool execution.
type BetaManagedAgentsAlwaysAllowPolicy struct { Type: "always_allow" }Tool calls are automatically approved without user confirmation.
Tool calls are automatically approved without user confirmation.
type BetaManagedAgentsAlwaysAskPolicy struct { Type: "always_ask" }Tool calls require user confirmation before execution.
Tool calls require user confirmation before execution.
type BetaManagedAgentsAutoPolicy struct { Type: "auto" }The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
type BetaManagedAgentsWriteToolConfigParams struct { Type: "write"; Name; Enabled; PermissionPolicy }Configuration override for the write tool.
Configuration override for the write tool.