lumen.metrics.answer

Use for normal agent answers: compact metric summary with grounded evidence.

Return a compact, grounded answer over a Lumen metric aggregate.

Overview

Property	Value
Workflow type	Atomic
Library	App-lumen
Version	1.0

Input Schema

Field	Type	Required	Default	Description
organization_uuid	uuid	Yes	—	Organization UUID to scope the query.
metric_name	string	Yes	—	Metric name or wildcard pattern.
project	string	No	—	Project filter; supports Lumen wildcards.
service_name	string	No	—	Exact service_name filter.
from	string	No	—	ISO 8601 lower time bound.
to	string	No	—	ISO 8601 upper time bound.
filters	list	No	—	Dimension filters as strings like attrs.env:prod or resource_attrs.namespace:default.
question	string	No	—	Natural-language question to echo in the answer.
interval	string	No	—	Bucket interval: 5m, 1h, or 1d.
agg	string	No	—	Aggregation: avg, sum, min, max, count.
group_by	string	No	—	Optional group dimension.
max_groups	integer	No	—	Grouped series cap.
recent_buckets	integer	No	—	Latest buckets to consider in the answer; default 6, capped at 100.
include_evidence	boolean	No	—	Whether to include compact evidence; default true.
include_aggregate	boolean	No	—	Whether to include the trimmed aggregate payload; default false.

Output Schema

Field	Type	Required	Default	Description
answer	string	Yes	—	—
metric_name	string	Yes	—	—
query	json	Yes	—	—
evidence	json	No	—	—
aggregate	json	No	—	—
error	string	No	—	—
error_type	string	No	—	—

States

State	Initial	Terminal	Success	Auto-advance	Description
done	Yes	Yes	Yes	—	—

API Usage

POST /api/workflows/start
Content-Type: application/json

{
  "workflow_type": "lumen.metrics.answer",
  "initial_data": {
    "organization_uuid": "value",
    "metric_name": "value"
  }
}