run-agent

Resume an agent that ALREADY EXISTS in this project, with a natural-language goal, and return its execution_id. This does NOT run a one-off prompt: 'agentflow_id' is required and there is no project default. If you have no flow yet, provision one first with create-process-flow (POST /v1/docs {"topic":"orchestrate"} has a manifest example that is accepted as written), then pass the id it returns here. Provide 'agentflow_id' (the agent to run — its agentflowId) and 'goal' (what you want it to do). The run is asynchronous: poll the execution by its execution_id for status and the conclusion. For a MULTI-TURN conversation, pass a stable 'session_id' across calls — the agent then recalls prior turns and the runs are grouped as one conversation.

What it is called on each surface

The wire name is run-agent everywhere: it is what the Wexa MCP server advertises, the REST path is POST /v1/run-agent, and each SDK exposes it under its own language's naming convention.

Surface	Name
Wexa MCP server	`run-agent`
REST API	`POST /v1/run-agent`
TypeScript SDK	`fabric.runAgent()`
Python SDK	`fabric.run_agent()`

Arguments

2 of the 6 arguments are required. Omitting a required one is refused before the tool runs, at the validation stage, so it costs nothing and changes nothing.

Argument	Type	Required	Notes
`agentflow_id`	string	Required	Id of the agent to run.
`files`	array	Optional	Optional file ids to add to the execution context.
`goal`	string	Required	Natural-language goal / message for this run (this turn).
`input_variables`	object	Optional	Optional input variables consumed by the agent.
`session_id`	string	Optional	Optional conversation id. Reuse the same value across turns for multi-turn memory + grouping. Omit for a one-shot run.
`start_from_agent_id`	string	Optional	Optional agent id to start the flow from.

project_id, projectID, organization_id and executed_by are not arguments you pass: the platform binds all four from the credential you authenticated with, and both SDKs refuse them before the request leaves your process — see server-bound arguments.

What it returns

The three surfaces wrap this differently, and code written against one will not read another correctly — see return shape.

A real response, captured from a live call to run-agent:

agentflow came back populated and is shown as … here, because the real value runs to thousands of characters. Read it from your own call rather than from this page.

{
  "content": [
    {
      "type": "text",
      "text": "{\"lifecycle_id\":\"qlc_000184\",\"result\":{\"_id\":\"6ab196817566f41b5c28e31a\",\"agent_type\":\"Task\",\"agent_version\":null,\"agentflow\":\"\\u2026\",\"agentflow_id\":\"6ab1945e7566f41b5c28e303\",\"agentflow_name\":\"docs-fixture-agent\",\"agents_output\":[],\"anomaly_detected\":null,\"application_user_id\":\"6a79a770b6c128ccc24bfca7\",\"conclusion\":null,\"created_at\":1790023297.263668,\"duration_ms\":null,\"end_time\":null,\"executed_by\":{\"_id\":\"6a79a770b6c128ccc24bfca7\",\"application_user_id\":\"6a79a770b6c128ccc24bfca7\",\"is_external_application\":true,\"metadata\":null,\"name\":\"6a79a770b6c128ccc24bfca7\",\"type\":\"api\"},\"execution_context\":{},\"execution_id\":\"8ba80297-9dfe-4ff6-9134-a1d9803355dd\",\"files\":[],\"goal\":\"Reply with READY.\",\"goal_template\":null,\"input_variables\":{},\"interop_ask\":null,\"interop_resume\":null,\"is_external_application\":true,\"kb_tags\":[],\"parent_execution_id\":null,\"previews\":{},\"projectID\":\"6aa9beb7ec8121a43b6c791b\",\"runtime_inputs\":{},\"schedule\":null,\"session_id\":null,\"simulation\":false,\"start_from_agent_id\":null,\"status\":\"running\",\"task_id\":\"6ab196817566f41b5c28e31b\",\"total_price\":null,\"total_tokens\":null,\"trigger_source\":\"api\"}}"
    }
  ],
  "isError": false
}

{
  "lifecycle_id": "qlc_000184",
  "result": {
    "_id": "6ab196817566f41b5c28e31a",
    "agent_type": "Task",
    "agent_version": null,
    "agentflow": "\u2026",
    "agentflow_id": "6ab1945e7566f41b5c28e303",
    "agentflow_name": "docs-fixture-agent",
    "agents_output": [],
    "anomaly_detected": null,
    "application_user_id": "6a79a770b6c128ccc24bfca7",
    "conclusion": null,
    "created_at": 1790023297.263668,
    "duration_ms": null,
    "end_time": null,
    "executed_by": {
      "_id": "6a79a770b6c128ccc24bfca7",
      "application_user_id": "6a79a770b6c128ccc24bfca7",
      "is_external_application": true,
      "metadata": null,
      "name": "6a79a770b6c128ccc24bfca7",
      "type": "api"
    },
    "execution_context": {},
    "execution_id": "8ba80297-9dfe-4ff6-9134-a1d9803355dd",
    "files": [],
    "goal": "Reply with READY.",
    "goal_template": null,
    "input_variables": {},
    "interop_ask": null,
    "interop_resume": null,
    "is_external_application": true,
    "kb_tags": [],
    "parent_execution_id": null,
    "previews": {},
    "projectID": "6aa9beb7ec8121a43b6c791b",
    "runtime_inputs": {},
    "schedule": null,
    "session_id": null,
    "simulation": false,
    "start_from_agent_id": null,
    "status": "running",
    "task_id": "6ab196817566f41b5c28e31b",
    "total_price": null,
    "total_tokens": null,
    "trigger_source": "api"
  }
}

// the object you get back IS the result — there is no `.result` to read
{
  _id: '6ab196817566f41b5c28e31a',
  agent_type: 'Task',
  agent_version: null,
  agentflow: '…',
  agentflow_id: '6ab1945e7566f41b5c28e303',
  agentflow_name: 'docs-fixture-agent',
  agents_output: [],
  anomaly_detected: null,
  application_user_id: '6a79a770b6c128ccc24bfca7',
  conclusion: null,
  created_at: 1790023297.263668,
  duration_ms: null,
  end_time: null,
  executed_by: {
    _id: '6a79a770b6c128ccc24bfca7',
    application_user_id: '6a79a770b6c128ccc24bfca7',
    is_external_application: true,
    metadata: null,
    name: '6a79a770b6c128ccc24bfca7',
    type: 'api'
  },
  execution_context: {},
  execution_id: '8ba80297-9dfe-4ff6-9134-a1d9803355dd',
  files: [],
  goal: 'Reply with READY.',
  goal_template: null,
  input_variables: {},
  interop_ask: null,
  interop_resume: null,
  is_external_application: true,
  kb_tags: [],
  parent_execution_id: null,
  previews: {},
  projectID: '6aa9beb7ec8121a43b6c791b',
  runtime_inputs: {},
  schedule: null,
  session_id: null,
  simulation: false,
  start_from_agent_id: null,
  status: 'running',
  task_id: '6ab196817566f41b5c28e31b',
  total_price: null,
  total_tokens: null,
  trigger_source: 'api'
}

// The TS SDK names these camelCase — lifecycleId, traceId — where Python uses
// lifecycle_id and trace_id. Both are non-enumerable: readable, but omitted by
// Object.keys() and JSON.stringify(). `result.lifecycleId` here is undefined.
result.lifecycleId // 'qlc_000184'

# a dict subclass; `result` is already unwrapped
{
 "_id": "6ab196817566f41b5c28e31a",
 "agent_type": "Task",
 "agent_version": None,
 "agentflow": "\u2026",
 "agentflow_id": "6ab1945e7566f41b5c28e303",
 "agentflow_name": "docs-fixture-agent",
 "agents_output": [],
 "anomaly_detected": None,
 "application_user_id": "6a79a770b6c128ccc24bfca7",
 "conclusion": None,
 "created_at": 1790023297.263668,
 "duration_ms": None,
 "end_time": None,
 "executed_by": {
  "_id": "6a79a770b6c128ccc24bfca7",
  "application_user_id": "6a79a770b6c128ccc24bfca7",
  "is_external_application": True,
  "metadata": None,
  "name": "6a79a770b6c128ccc24bfca7",
  "type": "api"
 },
 "execution_context": {},
 "execution_id": "8ba80297-9dfe-4ff6-9134-a1d9803355dd",
 "files": [],
 "goal": "Reply with READY.",
 "goal_template": None,
 "input_variables": {},
 "interop_ask": None,
 "interop_resume": None,
 "is_external_application": True,
 "kb_tags": [],
 "parent_execution_id": None,
 "previews": {},
 "projectID": "6aa9beb7ec8121a43b6c791b",
 "runtime_inputs": {},
 "schedule": None,
 "session_id": None,
 "simulation": False,
 "start_from_agent_id": None,
 "status": "running",
 "task_id": "6ab196817566f41b5c28e31b",
 "total_price": None,
 "total_tokens": None,
 "trigger_source": "api"
}

out.lifecycle_id  # 'qlc_000184' — an attribute, not a key

Keeping the lifecycle_id is what lets you ask later why a call was allowed, refused or held.

Calling it

The same call on all four surfaces. Pick a tab once and every code block in the documentation follows it.

The ids in this example are real, and resolve against the project the documentation is written against. Swap them for your own. A value in angle brackets is one only you can supply, and the platform refuses a literal <...>.

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run-agent",
    "arguments": {
      "agentflow_id": "6ab1945e7566f41b5c28e303",
      "goal": "<goal>"
    }
  }
}

curl -sS https://fabric.wexa.ai/v1/run-agent \
  -H "authorization: Bearer $FABRIC_API_KEY" \
  -H "content-type: application/json" \
  -d '{"agentflow_id":"6ab1945e7566f41b5c28e303","goal":"<goal>"}'

import { Fabric } from '@wexa-fabric/sdk'

const fabric = new Fabric()
const { result } = await fabric.runAgent({
  agentflow_id: "6ab1945e7566f41b5c28e303",
  goal: "<goal>"
})

from wexa import Fabric

fabric = Fabric()
out = fabric.run_agent(agentflow_id="6ab1945e7566f41b5c28e303", goal="<goal>")

Errors

Both SDKs raise the same typed errors, chosen from the gateway's own error string first and its HTTP status second. run-agent checks the fabric:agent.run grant, and reaches the seven classes every tool reaches — listed under the common set. These are the ones specific to it:

Error	Status	Raised when
`NotFound`	404	`agentflow_id` matches no agent or process flow in this project.
`ApprovalRequired`	202	A policy held this call for a person to approve. The error carries the approval id; see below.
`ConfigurationError`	5xx	`run-agent` is not available to you. Retrying will not help.

Governance

Every call to run-agent runs through the same ten-stage lifecycle as every other Wexa tool: the credential is resolved to a scope, the fabric:agent.run grant is checked, quota is drawn down, the arguments are validated, policy rules are evaluated, the call is executed, the result is shaped and redacted, and an audit record is written. The lifecycle_id in the response is the handle to that record.

run-agent is marked consequential, which means it changes something rather than only reading. Two things follow. It is audited in full rather than lightly, and a policy rule may hold it for human approval — in which case the call returns 202 and an ApprovalRequired error carrying the approval id, and the SDKs can wait for the decision and resume rather than making you call again.