HighLevel: Execute Agent (Deprecated)

← Agent studio operations · Get started

Operation gohighlevel.executeagent_deprecated

Provider route: POST /agent-studio/public-api/agents/{agentId}/execute. Alter supplies the connection’s credentials and routing.

Call through Alter

Install @alter-ai/sdk @alter-ai/gohighlevel with npm, or alter-sdk-gohighlevel with pip. Supply your connected customer’s grant ID and the arguments described below.

import { App } from "@alter-ai/sdk";
import { HighLevelIntegration } from "@alter-ai/gohighlevel";

async function execute(input: Parameters<HighLevelIntegration["agentStudio"]["executeAgentDeprecated"]>[0]) {
  const app = new App({ apiKey: process.env.ALTER_API_KEY! });
  try {
    const provider = new HighLevelIntegration(app, { grantId: process.env.PROVIDER_GRANT_ID! });
    const call = await provider.agentStudio.executeAgentDeprecated(input);
    const result = await call.wait();
    return result.bodyJson();
  } finally {
    await app.close();
  }
}

import os
from alter_sdk import App
from alter_sdk_gohighlevel import HighLevelIntegration

async def execute(arguments):
    async with App(api_key=os.environ["ALTER_API_KEY"]) as app:
        provider = HighLevelIntegration(app, {"grant_id": os.environ["PROVIDER_GRANT_ID"]})
        call = await provider.agent_studio.execute_agent_deprecated(arguments)
        result = await call.wait()
        return result.body_json()

Input

Field	Type	Presence	Description and constraints
$	object	Root	Additional keys: not allowed
path	object	Required within parent	Additional keys: not allowed
path.agentId	string	Required within parent
query	object	Optional	Additional keys: not allowed
query.source	string	Optional
body	Model	Required within parent	Expand Execute Agent — request body — body

Referenced models: Execute Agent — request body — body

Response

Response media type: application/json. The table describes the pinned successful response. Referenced models link to their complete fields.

Field	Type	Presence	Description and constraints
$	Model	Root	Expand Execute Agent — response body

Referenced models: Execute Agent — response body

Schemas

Execute Agent — request body — body

Field	Type	Presence	Description and constraints
$	object	Root
attachments	array	Optional	Attachments for the message
attachments[]	Model	Each item	Expand Execute Agent — request body — body attachments item
contactId	string	Optional	Contact ID to associate with this execution. When provided, contact data will be hydrated and made available to the agent.
executionId	string	Optional	Unique session identifier that maintains conversational context across multiple interactions within the same agent session. Omit this field for the first message in a new session. Include the executionId returned from the previous response to maintain context in subsequent messages.
inputVariables	object	Optional	Input variables to pass to the agent. These should match the input variables defined in the agent configuration.
locationId	string	Required within parent	Location ID
message	string	Required within parent	Message to send to the agent
versionId	string	Optional	Published version ID to execute. If not provided, the latest published production version will be used.

Referenced models: Execute Agent — request body — body attachments item

Execute Agent — response body

Field	Type	Presence	Description and constraints
$	object	Root
attachments	array	Required within parent	Response attachments
executionId	string	Required within parent	Unique session identifier that maintains conversational context across multiple interactions within the same agent session. Use this ID in subsequent requests to continue the conversation.
executionStatus	string	Required within parent	Execution status
flowSwitch	boolean	Required within parent	Whether flow was switched
generativeOutputs	array	Required within parent	Generated outputs
goalCompletion	boolean	Required within parent	When end node is added in the graph, this will be true if the agent reached the end node in the graph
interactionId	string	Required within parent	Unique identifier for a single interaction cycle, consisting of one user input and the corresponding agent response. Each message exchange generates a new interactionId.
nextExpectedInput	string	Required within parent	Expected input type for next interaction
response	string	Required within parent	Agent response text
success	boolean	Required within parent	Success status
type	string	Required within parent	Response type

Execute Agent — request body — body attachments item

Field	Type	Presence	Description and constraints
$	object	Root
imageUrl	string	Required within parent	URL of the image attachment
type	string	Required within parent	Type of attachment

Policy, approvals and errors

SDK function policy ID: gohighlevel.executeagent_deprecated. Catalog operation: executeAgent-deprecated. Rules can name either ID; function rules distinguish managed calls and conservatively cover raw calls sharing the route. Existing grant permissions and policy rules apply. wait() returns an immediate result or waits for a required approval; it never approves the request itself. Persist the approval ID to resume after a restart.

Provider errors retain their response; JSON decoding raises ProviderAPIError for provider failures. ManagedOperationError identifies contract/input/retention errors. See error handling and provider-specific behavior. Sensitive input may be refused before approval storage. A decoding error never resubmits a write.

Required provider scopes: ["agent-studio.write"]

Pinned headers: {"Version": "v3"}

Official provider source