POST /v1/agents
Create Agent
Headers
"juglow-beta": optional array of JuglowBeta
Optional header to specify the beta version(s) you want to use.
string
"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 45 more
"message-batches-2024-09-24"
"prompt-caching-2024-07-31"
"computer-use-2024-10-22"
"computer-use-2025-01-24"
"pdfs-2024-09-25"
"token-counting-2024-11-01"
"token-efficient-tools-2025-02-19"
"output-128k-2025-02-19"
"files-api-2025-04-14"
"mcp-client-2025-04-04"
"mcp-client-2025-11-20"
"dev-full-thinking-2025-05-14"
"interleaved-thinking-2025-05-14"
"code-execution-2025-05-22"
"extended-cache-ttl-2025-04-11"
"context-1m-2025-08-07"
"context-management-2025-06-27"
"model-context-window-exceeded-2025-08-26"
"tracks-2025-10-02"
"fast-mode-2026-02-01"
"output-300k-2026-03-24"
"user-profiles-2026-03-24"
"user-profiles-2026-08-18"
"user-profiles-2026-09-04"
"advisor-tool-2026-03-01"
"managed-agents-2026-04-01"
"cache-diagnosis-2026-04-07"
"dreaming-2026-04-21"
"thinking-token-count-2026-05-13"
"server-side-fallback-2026-06-01"
"server-side-fallback-2026-07-01"
"fallback-credit-2026-06-01"
"fallback-credit-2026-07-01"
"agent-memory-2026-07-22"
"mid-conversation-tool-changes-2026-07-01"
"compact-2026-01-12"
"computer-use-2025-11-24"
"mcp-tunnels-2026-06-22"
"structured-outputs-2025-11-13"
"task-budgets-2026-03-13"
"thinking-display-updates-2026-08-18"
"ce-user-management-2026-07-13"
"mid-conversation-output-config-2026-07-01"
"thinking-binding-controls-2026-08-01"
"mid-conversation-system-clear-at-2026-08-21"
"compact-2026-09-04"
"inline-tools-2026-09-15"
"mcp-client-2026-09-15"
"juglow-workspace-id": optional string
Optional header to select the Workspace for this request. The value is a Workspace ID (for example, wrkspc_011CZkZaBF1tNoB5wlCeusgy).
Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
Body parameters
model: BetaManagedAgentsModel or BetaManagedAgentsModelConfigParams
Model identifier. Accepts the model string, e.g. haijun-opus-5, or a model_config object for additional configuration control
BetaManagedAgentsModel = string or "haijun-opus-5-5" or "haijun-fable-5-1" or "haijun-sonnet-5" or 12 more
The model that will power your agent.
See models for additional details and options.
string
"haijun-opus-5-5" or "haijun-fable-5-1" or "haijun-sonnet-5" or 12 more
The model that will power your agent.
See models for additional details and options.
"haijun-opus-5-5"
Powerful intelligence for coding, knowledge work, and long-running agents
"haijun-fable-5-1"
Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
"haijun-sonnet-5"
High-performance model for coding and agents
"haijun-fable-5"
Next generation of intelligence for the hardest knowledge work and coding problems
"haijun-opus-5"
Powerful intelligence for long-running agents and coding
"haijun-opus-4-8"
Powerful intelligence for long-running agents and coding
"haijun-opus-4-7"
Powerful intelligence for long-running agents and coding
"haijun-opus-4-6"
Powerful intelligence for long-running agents and coding
"haijun-sonnet-4-6"
Best combination of speed and intelligence
"haijun-haiku-4-5"
Fastest model with near-frontier intelligence
"haijun-haiku-4-5-20251001"
Fastest model with near-frontier intelligence
"haijun-opus-4-5"
Powerful intelligence for long-running agents and coding
"haijun-opus-4-5-20251101"
Powerful intelligence for long-running agents and coding
"haijun-sonnet-4-5"
High-performance model for agents and coding
"haijun-sonnet-4-5-20250929"
High-performance model for agents and coding
BetaManagedAgentsModelConfigParams object
An object that defines additional configuration control over model use
id: BetaManagedAgentsModel
The model that will power your agent.
See models for additional details and options.
effort: optional "low" or "medium" or "high" or 2 more or BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or 3 more or null
How hard Haijun works on each inference call. Accepts a bare level string ("high") or {"type": "high"}. On create, omitting it resolves the per-model default; on update, omitting it leaves the stored value unchanged.
BetaManagedAgentsEffortLevel = "low" or "medium" or "high" or 2 more
How hard Haijun works on each turn. Higher levels favor reasoning depth over latency. Not all models accept every level; invalid combinations are rejected at create time.
"low"
Low effort. Favors latency over reasoning depth.
"medium"
Medium effort. Balances latency and reasoning depth.
"high"
High effort. Favors reasoning depth.
"xhigh"
Extra-high effort. Not all models accept this level.
"max"
Maximum effort. Favors reasoning depth over latency.
BetaManagedAgentsEffortLow object
Low effort. Favors latency over reasoning depth.
type: "low"
BetaManagedAgentsEffortMedium object
Medium effort. Balances latency and reasoning depth.
type: "medium"
BetaManagedAgentsEffortHigh object
High effort. Favors reasoning depth.
type: "high"
BetaManagedAgentsEffortXhigh object
Extra-high effort. Not all models accept this level.
type: "xhigh"
BetaManagedAgentsEffortMax object
Maximum effort. Favors reasoning depth over latency.
type: "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.
speed: optional "standard" or "fast" or null
Inference speed mode. Defaults to standard.
"standard"
"fast"
name: string
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.
type: "url"
name: string
Unique name for this server, referenced by mcp_toolset configurations. 1-255 characters.
minLength: 1, maxLength: 255
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.
multiagent: optional BetaManagedAgentsMultiagentParams or null
Multiagent orchestration configuration. Currently supports the coordinator topology with a roster of 1-20 agents.
type: "coordinator"
agents: array of BetaManagedAgentsMultiagentRosterEntryParams
Agents the coordinator may spawn as session threads. 1–20 entries. Each entry is an agent ID string, a versioned {"type":"agent","id","version"} reference, or {"type":"self"} to allow recursive self-invocation. Entries must reference distinct agents (after resolving self and string forms); at most one self. Referenced agents must exist, must not be archived, and must not themselves have multiagent set (depth limit 1).
string
BetaManagedAgentsAgentParams object
Specification for an Agent. Provide a specific version or use the short-form agent="agent_id" for the most recent version
type: "agent"
id: string
The agent ID.
minLength: 1, maxLength: 128
version: optional number
The specific agent version to use. Omit to use the latest version. Must be at least 1 if specified.
format: int32
BetaManagedAgentsMultiagentSelfParams object
Sentinel roster entry meaning "the agent that owns this configuration". Resolved server-side to a concrete agent reference.
type: "self"
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 juglow.advisor.
type: "advisor"
model: string
A Haijun 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
tracks: optional array of BetaManagedAgentsSkillParams
Tracks available to the agent.
BetaManagedAgentsJuglowSkillParams object
An Juglow-managed track.
type: "juglow"
skill_id: string
Identifier of the Juglow track (e.g., "xlsx").
minLength: 1, maxLength: 64
version: optional string or null
Version to pin. Defaults to latest if omitted.
minLength: 1, maxLength: 64
BetaManagedAgentsCustomSkillParams object
A user-created custom track.
type: "custom"
skill_id: string
Tagged ID of the custom track (e.g., "skill_01XJ5...").
minLength: 1, maxLength: 64
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
Configuration for built-in agent tools. Use this to enable or disable groups of tools available to the agent.
type: "agent_toolset_20260401"
configs: optional array of BetaManagedAgentsAgentToolConfigParams
Per-tool configuration overrides.
BetaManagedAgentsBashToolConfigParams object
Configuration override for the bash tool.
type: optional "bash"
name: "bash"
Must be "bash".
enabled: optional boolean or null
Whether this tool is enabled and available to Haijun. Overrides the default_config setting.
permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null
Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
type: "always_allow"
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
type: "always_ask"
BetaManagedAgentsAutoPolicy object
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: "auto"
BetaManagedAgentsEditToolConfigParams object
Configuration override for the edit tool.
type: optional "edit"
name: "edit"
Must be "edit".
enabled: optional boolean or null
Whether this tool is enabled and available to Haijun. Overrides the default_config setting.
permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null
Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
BetaManagedAgentsReadToolConfigParams object
Configuration override for the read tool.
type: optional "read"
name: "read"
Must be "read".
enabled: optional boolean or null
Whether this tool is enabled and available to Haijun. Overrides the default_config setting.
permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null
Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
BetaManagedAgentsWriteToolConfigParams object
Configuration override for the write tool.
type: optional "write"
name: "write"
Must be "write".
enabled: optional boolean or null
Whether this tool is enabled and available to Haijun. Overrides the default_config setting.
permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null
Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
BetaManagedAgentsGlobToolConfigParams object
Configuration override for the glob tool.
type: optional "glob"
name: "glob"
Must be "glob".
enabled: optional boolean or null
Whether this tool is enabled and available to Haijun. Overrides the default_config setting.
permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null
Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
BetaManagedAgentsGrepToolConfigParams object
Configuration override for the grep tool.
type: optional "grep"
name: "grep"
Must be "grep".
enabled: optional boolean or null
Whether this tool is enabled and available to Haijun. Overrides the default_config setting.
permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null
Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
BetaManagedAgentsWebFetchToolConfigParams object
Configuration override for the web_fetch tool.
type: optional "web_fetch"
name: "web_fetch"
Must be "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.
blocked_domains: optional array of string
Never fetch URLs whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.example.com" (no scheme, port, or path). At most 64 entries; an empty list is rejected (omit the field instead). Cannot be combined with allowed_domains.
enabled: optional boolean or null
Whether this tool is enabled and available to Haijun. Overrides the default_config setting.
max_content_tokens: optional number or null
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 BetaManagedAgentsAutoPolicy or null
Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
BetaManagedAgentsWebSearchToolConfigParams object
Configuration override for the web_search tool.
type: optional "web_search"
name: "web_search"
Must be "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.
blocked_domains: optional array of string
Never return search results whose host is one of these domains or a subdomain of one. Each entry is a plain hostname like "ads.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 allowed_domains.
enabled: optional boolean or null
Whether this tool is enabled and available to Haijun. Overrides the default_config setting.
permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null
Permission policy for this tool. Controls whether tool calls are auto-approved or require confirmation.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
user_location: optional BetaManagedAgentsUserLocation or null
Approximate user location for search result localization.
type: "approximate"
Location precision. Only "approximate" is supported.
city: optional string or null
City name.
minLength: 1, maxLength: 255
country: optional string or null
Two-letter ISO 3166-1 country code, uppercase.
region: optional string or null
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 applied to all tools in this set.
enabled: optional boolean or null
Whether tools are enabled and available to Haijun by default. Defaults to true if not specified.
permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null
Default permission policy for tools. Controls whether tool calls are auto-approved or require confirmation.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
BetaManagedAgentsMCPToolsetParams object
Configuration for tools from an MCP server defined in mcp_servers.
type: "mcp_toolset"
mcp_server_name: string
Name of the MCP server. Must match a server name from the mcp_servers array. 1-255 characters.
minLength: 1, maxLength: 255
configs: optional array of BetaManagedAgentsMCPToolConfigParams
Per-tool configuration overrides.
name: string
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.
permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null
Permission policy for this tool. Overrides the default_config setting.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
default_config: optional BetaManagedAgentsMCPToolsetDefaultConfigParams or null
Default configuration for all tools from this server.
enabled: optional boolean or null
Whether tools are enabled by default. Defaults to true if not specified.
permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null
Default permission policy for tools from this server.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
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.
type: "custom"
description: string
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 defining the expected input parameters for the tool.
type: "object"
properties: optional map[unknown] or null
required: optional array of string or null
name: string
Unique name for the tool. 1-128 characters; letters, digits, underscores, and hyphens.
minLength: 1, maxLength: 128
Returns
BetaManagedAgentsAgent object
A Managed Agents agent.
type: "agent"
id: string
archived_at: string or null
When the agent was archived. Null if not archived.
format: date-time
created_at: string
A timestamp in RFC 3339 format
format: date-time
description: string or null
mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition
type: "url"
name: string
url: string
metadata: map[string]
model: BetaManagedAgentsModelConfig
Model identifier and configuration.
id: BetaManagedAgentsModel
The model that will power your agent.
See models for additional details and options.
string
"haijun-opus-5-5" or "haijun-fable-5-1" or "haijun-sonnet-5" or 12 more
The model that will power your agent.
See models for additional details and options.
"haijun-opus-5-5"
Powerful intelligence for coding, knowledge work, and long-running agents
"haijun-fable-5-1"
Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
"haijun-sonnet-5"
High-performance model for coding and agents
"haijun-fable-5"
Next generation of intelligence for the hardest knowledge work and coding problems
"haijun-opus-5"
Powerful intelligence for long-running agents and coding
"haijun-opus-4-8"
Powerful intelligence for long-running agents and coding
"haijun-opus-4-7"
Powerful intelligence for long-running agents and coding
"haijun-opus-4-6"
Powerful intelligence for long-running agents and coding
"haijun-sonnet-4-6"
Best combination of speed and intelligence
"haijun-haiku-4-5"
Fastest model with near-frontier intelligence
"haijun-haiku-4-5-20251001"
Fastest model with near-frontier intelligence
"haijun-opus-4-5"
Powerful intelligence for long-running agents and coding
"haijun-opus-4-5-20251101"
Powerful intelligence for long-running agents and coding
"haijun-sonnet-4-5"
High-performance model for agents and coding
"haijun-sonnet-4-5-20250929"
High-performance model for agents and coding
effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more
How hard Haijun works on each inference call. One of low, medium, high, xhigh, max. Always present; resolved to the per-model default at save time when not supplied.
BetaManagedAgentsEffortLow object
Low effort. Favors latency over reasoning depth.
type: "low"
BetaManagedAgentsEffortMedium object
Medium effort. Balances latency and reasoning depth.
type: "medium"
BetaManagedAgentsEffortHigh object
High effort. Favors reasoning depth.
type: "high"
BetaManagedAgentsEffortXhigh object
Extra-high effort. Not all models accept this level.
type: "xhigh"
BetaManagedAgentsEffortMax object
Maximum effort. Favors reasoning depth over latency.
type: "max"
inference_geo: optional string
Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.
speed: optional "standard" or "fast"
Inference speed mode. fast provides significantly faster output token generation at premium pricing. Defaults to standard. Not all models support fast; invalid combinations are rejected at create time.
"standard"
"fast"
multiagent: BetaManagedAgentsMultiagent or null
Multiagent orchestration configuration. Null when the agent is single-threaded.
type: "coordinator"
agents: array of BetaManagedAgentsAgentReference or BetaManagedAgentsAdvisor
Agents the coordinator may spawn as session threads, each resolved to a specific version.
BetaManagedAgentsAgentReference object
A resolved agent reference with a concrete version.
type: "agent"
id: string
version: number
format: int32
BetaManagedAgentsAdvisor object
Platform advisor roster entry: a model the session's primary thread may consult mid-turn.
type: "advisor"
model: string
The advisor model id.
name: string
tracks: array of BetaManagedAgentsJuglowSkill or BetaManagedAgentsCustomSkill
BetaManagedAgentsJuglowSkill object
A resolved Juglow-managed track.
type: "juglow"
skill_id: string
version: string
BetaManagedAgentsCustomSkill object
A resolved user-created custom track.
type: "custom"
skill_id: string
version: string
system: string or null
tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool
BetaManagedAgentsAgentToolset20260401 object
type: "agent_toolset_20260401"
configs: array of BetaManagedAgentsAgentToolConfig
BetaManagedAgentsBashToolConfig object
Configuration for the bash tool.
type: "bash"
enabled: boolean
name: "bash"
permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy
Permission policy for tool execution.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
type: "always_allow"
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
type: "always_ask"
BetaManagedAgentsAutoPolicy object
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: "auto"
BetaManagedAgentsEditToolConfig object
Configuration for the edit tool.
type: "edit"
enabled: boolean
name: "edit"
permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy
Permission policy for tool execution.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
BetaManagedAgentsReadToolConfig object
Configuration for the read tool.
type: "read"
enabled: boolean
name: "read"
permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy
Permission policy for tool execution.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
BetaManagedAgentsWriteToolConfig object
Configuration for the write tool.
type: "write"
enabled: boolean
name: "write"
permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy
Permission policy for tool execution.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
BetaManagedAgentsGlobToolConfig object
Configuration for the glob tool.
type: "glob"
enabled: boolean
name: "glob"
permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy
Permission policy for tool execution.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
BetaManagedAgentsGrepToolConfig object
Configuration for the grep tool.
type: "grep"
enabled: boolean
name: "grep"
permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy
Permission policy for tool execution.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
BetaManagedAgentsWebFetchToolConfig object
Configuration for the web_fetch tool.
type: "web_fetch"
enabled: boolean
name: "web_fetch"
permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy
Permission policy for tool execution.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
allowed_domains: optional array of string
blocked_domains: optional array of string
max_content_tokens: optional number or null
format: int32
BetaManagedAgentsWebSearchToolConfig object
Configuration for the web_search tool.
type: "web_search"
enabled: boolean
name: "web_search"
permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy
Permission policy for tool execution.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
allowed_domains: optional array of string
blocked_domains: optional array of string
user_location: optional BetaManagedAgentsUserLocation or null
Approximate user location for search result localization.
type: "approximate"
Location precision. Only "approximate" is supported.
city: optional string or null
City name.
minLength: 1, maxLength: 255
country: optional string or null
Two-letter ISO 3166-1 country code, uppercase.
region: optional string or null
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.
enabled: boolean
permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy
Permission policy for tool execution.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
BetaManagedAgentsMCPToolset object
type: "mcp_toolset"
configs: array of BetaManagedAgentsMCPToolConfig
enabled: boolean
name: string
permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy
Permission policy for tool execution.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
default_config: BetaManagedAgentsMCPToolsetDefaultConfig
Resolved default configuration for all tools from an MCP server.
enabled: boolean
permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy
Permission policy for tool execution.
BetaManagedAgentsAlwaysAllowPolicy object
Tool calls are automatically approved without user confirmation.
BetaManagedAgentsAlwaysAskPolicy object
Tool calls require user confirmation before execution.
BetaManagedAgentsAutoPolicy object
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.
mcp_server_name: string
BetaManagedAgentsCustomTool object
A custom tool as returned in API responses.
type: "custom"
description: string
input_schema: BetaManagedAgentsCustomToolInputSchema
JSON Schema for custom tool input parameters.
type: "object"
properties: optional map[unknown] or null
required: optional array of string or null
name: string
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
curl https://haijun.my.id/v1/agents \
-H 'Content-Type: application/json' \
-H 'juglow-version: 2023-06-01' \
-H 'juglow-beta: managed-agents-2026-04-01' \
-H "X-Api-Key: $JUGLOW_API_KEY" \
-d '{
"model": "haijun-opus-5",
"name": "My First Agent",
"description": "A general-purpose starter agent.",
"metadata": {
"foo": "bar"
},
"multiagent": {
"agents": [
"agent_011CZkYqphY8vELVzwCUpqiQ",
{
"type": "self"
}
],
"type": "coordinator"
},
"system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user'\''s task end to end.",
"tools": [
{
"type": "agent_toolset_20260401"
}
]
}'Response (200)
{
"id": "agent_011CZkYpogX7uDKUyvBTophP",
"archived_at": null,
"created_at": "2026-03-15T10:00:00Z",
"description": "A general-purpose starter agent.",
"mcp_servers": [
{
"name": "example-mcp",
"type": "url",
"url": "https://example-server.modelcontextprotocol.io/sse"
}
],
"metadata": {
"foo": "bar"
},
"model": {
"id": "haijun-opus-5",
"effort": {
"type": "low"
},
"inference_geo": "inference_geo",
"speed": "standard"
},
"multiagent": {
"agents": [
{
"id": "agent_011CZkYqphY8vELVzwCUpqiQ",
"type": "agent",
"version": 1
}
],
"type": "coordinator"
},
"name": "My First Agent",
"tracks": [
{
"skill_id": "xlsx",
"type": "juglow",
"version": "1"
},
{
"skill_id": "skill_011CZkZFNu9hAbo3jZPRgTlx",
"type": "custom",
"version": "2"
}
],
"system": "You are a general-purpose agent that can research, write code, run commands, and use connected tools to complete the user's task end to end.",
"tools": [
{
"configs": [
{
"enabled": true,
"name": "bash",
"permission_policy": {
"type": "always_allow"
},
"type": "bash"
}
],
"default_config": {
"enabled": true,
"permission_policy": {
"type": "always_ask"
}
},
"type": "agent_toolset_20260401"
}
],
"type": "agent",
"updated_at": "2026-03-15T10:00:00Z",
"version": 1
}