Skip to content

Scoring Run Event

Viewing v2— current version

POST

Sent when a batch of output scoring settles, however it was triggered.

Media typeapplication/json
ScoringRunWebhookEvent

Delivered when a scoring run settles.

Also raised for the automatic scoring that follows a generation, in which case data carries the inference_id of the generation whose outputs were judged.

object
id
required
Id

Unique event id, repeated in the webhook-id header.

string
type
required
WebhookEventType

Scoring_run.completed or scoring_run.failed.

string
Allowed values: inference.completed inference.failed inference.cancelled training.succeeded training.failed scoring_run.completed scoring_run.failed workflow_run.succeeded workflow_run.failed workflow_run.cancelled
created_at
required
Created At

When the event was raised (RFC 3339).

string
data
required
GetScoringRunOutput

Identical to the body of GET on the scoring run.

object
scoring_run_id
required
Scoring Run Id

Unique identifier for this scoring run.

string format: uuid
status
required
ScoringRunStatus

Current status: pending, complete, or failed.

string
Allowed values: pending complete failed
inference_id
Inference Id

The generation whose outputs this run judged, when it was started automatically.

string format: uuid
nullable
poll_interval_seconds
Poll Interval Seconds

Suggested polling interval in seconds. Present while pending.

integer
nullable
requested_pair_count
required
Requested Pair Count

How many (file, rule) pairs the run set out to judge.

integer
completed_pair_count
required
Completed Pair Count

How many produced a verdict. Lower than requested means some pairs went unjudged.

integer
file_ids
File Ids

The files the run was asked to judge.

Array<string>
default:
rule_ids
Rule Ids

The rules the run judged against.

Array<string>
default:
scores
Scores

The verdicts recorded. Present once the run is complete.

Array<object>
nullable
ScoringRunFileScore
object
file_id
required
File Id

The file this verdict is about.

string format: uuid
rule_id
required
Rule Id

The scoring rule that produced it.

string format: uuid
rule_name
required
Rule Name

The rule’s name as it stood when the verdict was recorded.

string
score
required
Score

Score in [0, 100] against that rule.

integer
rationale
Rationale

The judge’s reasoning, in its own words.

string
""
finished_at
Finished At

When the run settled. Present once terminal.

string format: date-time
nullable
error
Error

Error message. Present only on failed.

string
nullable
error_code
Error Code

Machine-readable error code. Present only on failed.

string
nullable
webhook
Any of:
WebhookStatusView

What a job’s GET reports about the callback attached to it.

The URL is echoed so a caller can tell which of its endpoints a run was aimed at; the rest is how the delivery went, which is the only place a failed delivery is visible.

object
url
required
Url

The callback URL this run was submitted with.

string
status
required
WebhookDeliveryStatus

Pending until a delivery settles, then delivered or failed.

string
Allowed values: pending delivered failed
attempts
required
Attempts

How many delivery attempts have been made.

integer
last_attempt_at
Last Attempt At

When the last attempt was made.

string format: date-time
nullable
last_response_status
Last Response Status

HTTP status the receiver returned on the last attempt, if it responded.

integer
nullable
last_error
Last Error

Why the last attempt did not succeed. Null once delivered.

string
nullable
metadata
Metadata

Whatever you sent as webhook.metadata.

object
key
additional properties
string

Successful Response

Media typeapplication/json
Examplegenerated
example

Validation Error

Media typeapplication/json
HTTPValidationError
object
detail
Detail
Array<object>
ValidationError
object
loc
required
Location
Array
msg
required
Message
string
type
required
Error Type
string
input
Input
ctx
Context
object
Examplegenerated
{
"detail": [
{
"loc": [
"example"
],
"msg": "example",
"type": "example",
"input": "example",
"ctx": {}
}
]
}