Skip to main content
PATCH
Update Agent Config

Authorizations

x-api-key
string
header
required

Headers

x-selected-account-id
string | null

Path Parameters

agent_config_id
string
required

Query Parameters

task_id
string | null

If set, after persisting the patch we shallow-merge the changed fields into this task's params column on Agentex so the worker picks up the new values on its next turn. Caller-provided context — Agentex enforces task ownership via its own auth, so the side-effect no-ops if the caller doesn't own the task.

Body

application/json
name
string
Required string length: 1 - 255
description
string
Maximum string length: 2000
system_prompt
string
Required string length: 1 - 100000
harness
enum<string>

Supported agent harness strategies.

Mirrors PROVIDERS in golden-agent's project/harness/activity.py.

Available options:
claude-code,
codex,
litellm
allowed_tools
enum<string>[]

Tools an agent config may be granted.

Granting an MCP server name (Slack, Linear, etc.) authorizes every tool exposed by that server, scoped via the agent's credentials.

Available options:
Read,
Write,
Edit,
Bash,
Glob,
Grep,
List,
WebFetch,
WebSearch,
Task,
TodoWrite,
NotebookEdit,
ExitPlanMode,
Slack,
Linear,
GitHub,
Confluence,
Notion,
Datadog,
PagerDuty,
Salesforce,
Figma,
Granola
model
string
Required string length: 1 - 255

Response

Successful Response

id
string
required
name
string
required
system_prompt
string
required
harness
string
required
allowed_tools
string[]
required
model
string
required
created_at
string<date-time>
required
updated_at
string<date-time>
required
object
string
default:agent_config
Allowed value: "agent_config"
description
string