FruxonDocs
AgentsExecution

Executes an agent using its currently deployed revision.

Runs the agent synchronously and returns the complete result.

API-Only Endpoint

This endpoint is available via API only and requires a Fruxon bearer token: Authorization: Bearer YOUR_TOKEN. Fill in your parameters below and the code samples will update automatically. To generate a token, see the Settings guide.

Python SDK Available

You can also call this endpoint using the Fruxon Python SDK. Install with pip install fruxon — FruxonClient.execute(), .execute_revision(), and .stream() cover this surface, and the fruxon run CLI wraps them with --stream / --no-stream / --revision.

POST
/v1/tenants/{tenant}/agents/{agent}:execute

Authorization

Token
AuthorizationBearer <token>

Fruxon token presented as a Bearer token: Authorization: Bearer fx_pat_… (personal) or fx_sat_… (service account). Generate one from Settings → API Access.

In: header

Path Parameters

agent*string

The unique identifier of the agent.

tenant*string

The tenant identifier

Request Body

The execution parameters and inputs.

parameters?

Key-value parameters to pass to the agent

attachments?

File attachments for the execution. Each entry references a file already uploaded through POST /storage; they are attached to the run's user turn, so a vision-capable model receives the images directly and every file stays addressable by its <fileType:fileId/> link. Maximum 20.

sessionId?string|null

Optional session ID for conversation continuity

mode?string

Integration-config variant this execution resolves against. Honoured on the draft-test endpoints; :execute / :stream run a deployed revision and always resolve Production configs, so the value is ignored there.

Value in"UNSPECIFIED" | "PRODUCTION" | "SANDBOX"
environmentSlug?string|null

Optional environment slug for per-end-customer cost tracking and analytics. Auto-creates the environment on first use (subject to the per-tenant environment cap).

Lengthlength <= 64
sandboxRouting?|null

How to route a connection the agent uses during this test, by connection id: SIMULATED, READ_THROUGH, or NONE — shown as Live, which reaches the connection with its production credentials. Honoured on the draft-test endpoints only, and it makes the test a sandbox run. A sandbox test simulates every connection left out that has no sandbox saved; nothing is saved on the connection.

replyStyle?

The reply style to test with instead of the agent's active one: {"version": 3} for a particular version (a draft under review, say), or {"off": true} for none — send the same message both ways to compare. Honoured on the draft-test endpoints only; a deployed run always gets the active reply style.

[key: string]?never

Response Body

curl -X POST "https://api.fruxon.com/v1/tenants/string/agents/string:execute" \  -H "Content-Type: application/json" \  -d '{}'
{
  "response": "string",
  "trace": {
    "agentId": "string",
    "agentRevision": 0,
    "createdAt": 0,
    "parameters": {},
    "startTime": 0,
    "endTime": 0,
    "duration": 0,
    "traces": [
      {
        "id": "string",
        "displayName": "string",
        "type": "UNSPECIFIED",
        "llmStepTrace": null,
        "toolTrace": null,
        "hitlTrace": null,
        "steps": [],
        "result": null,
        "status": "UNSPECIFIED",
        "error": "string",
        "startTime": 0,
        "endTime": 0,
        "duration": 0,
        "creditsCharged": null
      }
    ],
    "result": {
      "strValue": "string",
      "jsonValue": null,
      "fileLink": "string",
      "flowControl": null
    },
    "inputCost": 0,
    "outputCost": 0,
    "cachedCost": 0,
    "cacheWriteCost": 0,
    "thinkingCost": 0,
    "webSearchCost": 0,
    "toolCost": 0,
    "totalCost": 0,
    "inputTokens": 0,
    "outputTokens": 0,
    "cachedTokens": 0,
    "cacheWriteTokens": 0,
    "thinkingTokens": 0,
    "webSearchCalls": 0,
    "providerReportedCost": null
  },
  "sessionId": "string",
  "links": [
    {
      "fileId": "string",
      "fileType": "string",
      "displayName": "string",
      "promptLink": "<string:string/>"
    }
  ],
  "executionRecordId": "00000000-0000-0000-0000-000000000000",
  "status": "COMPLETED",
  "humanApprovalRequestId": "00000000-0000-0000-0000-000000000000",
  "suppressOutbound": false,
  "messageBlocks": []
}
{
  "type": "string",
  "title": "string",
  "status": 0,
  "detail": "string",
  "instance": "string",
  "property1": null,
  "property2": null
}
Empty
Empty
{
  "type": "string",
  "title": "string",
  "status": 0,
  "detail": "string",
  "instance": "string",
  "property1": null,
  "property2": null
}
{
  "type": "string",
  "title": "string",
  "status": 0,
  "detail": "string",
  "instance": "string",
  "property1": null,
  "property2": null
}

Previews the system blocks a published revision of the agent receives.

The author's prompt plus every block the platform adds around it, in the order the model receives them, for the given kind of run. Same shape as `draft:previewSystemBlocks`.

Executes an agent using its currently deployed revision with streaming output.

Returns results as Server-Sent Events (SSE) for real-time progress updates.