FruxonDocs
AgentsExecution Records

Gets per-environment execution summaries for an agent.

Returns aggregated execution count, total cost, and last activity time for each environment that has execution records for this agent, ordered by environment slug. Pass `?include=trends` to also populate week-over-week deltas (current 7-day window vs. prior 7-day window).

GET
/v1/tenants/{tenant}/agents/{agent}/environmentsSummary

Authorization

Bearer
AuthorizationBearer <token>

JWT Authorization header using the Bearer scheme. Enter 'Bearer' [space] and then your token.

In: header

Path Parameters

agent*string

The unique identifier of the agent.

tenant*string

The tenant identifier

Query Parameters

PageSize?integer

The maximum number of items to return per page

Formatint32
PageToken.Skip?integer
Formatint32
PageToken.Cursor?string

Opaque pagination token returned by an external service. Pass it back unchanged rather than interpreting it as an offset.

query?string

Optional case-insensitive substring matched against the environment slug and display name.

include?string

Comma-separated list of expansion options. Currently recognized: trends. Unknown values are ignored.

from?integer

Optional window start as Unix milliseconds (inclusive). When neither bound is supplied, the summary is all-time. If either bound is supplied, this defaults to 30 days before to (or now), mirroring the environmentCostTimeseries windowing convention.

Formatint64
to?integer

Optional window end as Unix milliseconds (exclusive). Defaults to now when a window is requested.

Formatint64
orderBy?string

Sort order, AIP-132 style ("cost desc"). Sortable fields: slug, name, group, executions, errorRate, latency (p95), cost, trend (size of the week-over-week cost move) and lastActive. Defaults to slug ascending; ties break on slug so pages are stable.

Response Body

curl -X GET "https://api.fruxon.com/v1/tenants/string/agents/string/environmentsSummary"
{
  "items": [
    {
      "environmentSlug": "string",
      "name": "string",
      "group": "string",
      "executionCount": 0,
      "totalCost": 0,
      "relevanceCheckCount": 0,
      "lastActiveAt": 0,
      "errorCount": 0,
      "avgDurationMs": 0,
      "p95DurationMs": 0,
      "trends": {
        "costWowDelta": null,
        "executionsWowDelta": null,
        "errorRateWowDeltaPp": null,
        "currentExecutions": 0,
        "priorExecutions": 0
      }
    }
  ],
  "nextPageToken": "string",
  "totalCount": 0
}
Empty
Empty
{
  "type": "string",
  "title": "string",
  "status": 0,
  "detail": "string",
  "instance": "string",
  "property1": null,
  "property2": null
}

Gets the agent's conversations and escalations bucketed over time.

A conversation is a customer visit, counted the way the Application's support KPIs count it: the customer's messages in one conversation, split wherever they went quiet for four hours. It is escalated when the agent handed it to a person, or tried to and reached nobody (`deadEnded`). Production traffic only. Each conversation is counted in the bucket it started in; buckets with none are omitted. Counting is live over the workspace's run history, so a window reaching further back is counted from `countedFromMs`.

Lists execution records for an agent.

Returns a paginated list of all executions, ordered by most recent first. Optionally filter by time range using the `startTime` and `endTime` query parameters. `query` narrows to the runs whose subject, input or output contains a text; it needs `startTime` and a window of at most 31 days.