Create Agent Config

agent_configs.create() -> AgentConfigCreateResponse

POST/v5/agent_configs

Create a reusable agent configuration (system prompt, harness, model, allowed tools) under the caller’s account.

The config is a template that a chat session or a non-chat trigger later turns into task params; creating one does not start any task. persistent_workspace opts tasks made from this config into a durable /workspace that survives sandbox death (off by default, and fixed once a task starts), and repos overrides which repositories provisioning clones into that workspace — omit it (null) to use the deployment default, or pass an empty list to clone nothing. A repos override is rejected with a 422 on the model-agnostic (litellm) harness unless persistent_workspace is also true, because non-persistent litellm tasks run in a pre-cloned warm-pool sandbox where the override would be ignored. allowed_tools may name MCP servers (Slack, Linear, GitHub, …) alongside harness tools, and granting an MCP server name authorizes every tool it exposes.

ParametersExpand Collapse

harness: Literal["claude-code", "codex", "litellm"]

Harness strategy. See Harness enum for supported values.

One of the following:

"claude-code"

"codex"

"litellm"

model: str

maxLength255

minLength1

name: str

maxLength255

minLength1

system_prompt: str

maxLength100000

minLength1

allowed_tools: Optional[List[Literal["Read", "Write", "Edit", 34 more]]]

Tools enabled for this config. See AllowedTool enum for the catalogue.

One of the following:

"Read"

"Write"

"Edit"

"Bash"

"Glob"

"Grep"

"List"

"WebFetch"

"WebSearch"

"Task"

"TodoWrite"

"NotebookEdit"

"ExitPlanMode"

"Slack"

"Linear"

"GitHub"

"Confluence"

"Notion"

"Datadog"

"PagerDuty"

"Salesforce"

"Figma"

"Granola"

"Jira"

"Gmail"

"GoogleCalendar"

"GoogleDrive"

"GoogleDocs"

"GoogleSheets"

"GoogleSlides"

"Snowflake"

"Redash"

"Tableau"

"Metabase"

"Gong"

"ZoomInfo"

"Clay"

description: Optional[str]

maxLength2000

persistent_workspace: Optional[bool]

Give tasks a persistent /workspace that survives sandbox death. Fixed for a task’s life; defaults off.

repos: Optional[Iterable[RepoSpecParam]]

Per-config repo override. None uses the deployment default; an empty list clones nothing.

url: str

maxLength2048

minLength1

depth: Optional[int]

minimum1

path: Optional[str]

maxLength1024

ReturnsExpand Collapse

class AgentConfigCreateResponse: …

id: str

allowed_tools: List[str]

created_at: datetime

formatdate-time

harness: str

model: str

name: str

system_prompt: str

updated_at: datetime

formatdate-time

description: Optional[str]

object: Optional[Literal["agent_config"]]

persistent_workspace: Optional[bool]

repos: Optional[List[RepoSpec]]

url: str

maxLength2048

minLength1

depth: Optional[int]

minimum1

path: Optional[str]

maxLength1024

Create Agent Config

import os
from scale_gp_beta import SGPClient

client = SGPClient(
    api_key=os.environ.get("SGP_API_KEY"),  # This is the default and can be omitted
)
agent_config = client.agent_configs.create(
    harness="claude-code",
    model="x",
    name="x",
    system_prompt="x",
)
print(agent_config.id)

{
  "id": "id",
  "allowed_tools": [
    "string"
  ],
  "created_at": "2019-12-27T18:11:19.117Z",
  "harness": "harness",
  "model": "model",
  "name": "name",
  "system_prompt": "system_prompt",
  "updated_at": "2019-12-27T18:11:19.117Z",
  "description": "description",
  "object": "agent_config",
  "persistent_workspace": true,
  "repos": [
    {
      "url": "x",
      "depth": 1,
      "path": "path"
    }
  ]
}

Returns Examples

{
  "id": "id",
  "allowed_tools": [
    "string"
  ],
  "created_at": "2019-12-27T18:11:19.117Z",
  "harness": "harness",
  "model": "model",
  "name": "name",
  "system_prompt": "system_prompt",
  "updated_at": "2019-12-27T18:11:19.117Z",
  "description": "description",
  "object": "agent_config",
  "persistent_workspace": true,
  "repos": [
    {
      "url": "x",
      "depth": 1,
      "path": "path"
    }
  ]
}