Agent Insight Monitors

createRun

POST /agent_insight_monitors/{monitor_id}/runs

Start an Agent Insights run for a monitor.

Paramètres d’en-tête

Foundry-Features enum obligatoire

A feature flag opt-in required when using preview operations or modifying persisted preview resources.

AgentInsights=V1Preview

Operation-Id string

Client-generated unique ID for idempotent retries. When absent, the server creates the job unconditionally.

Paramètres de chemin d’accès

monitor_id string obligatoire

The identifier of the monitor.

Paramètres de la requête

api-version string obligatoire

The API version to use for this operation.

Corps de la demande

Run inputs. Send an empty object to use the default 168-hour lookback window.

Content-Type: application/json

lookback_hours number

Optional finite positive number of hours of trace history to analyze, up to 2,160. Defaults to 168.

Réponses

The request has succeeded and a new resource has been created as a result.

En-têtes

Operation-Location string obligatoire

URL to poll for the job status.

Location string obligatoire

URL of the created job resource.

Corps

Content-Type: application/json

id string obligatoire

Server-assigned unique identifier.

inputs AgentInsightRunCreate

Inputs used when creating an agent insight run.

lookback_hours number

Optional finite positive number of hours of trace history to analyze, up to 2,160. Defaults to 168.

result AgentInsightRunResult

Result statistics produced when an agent insight run succeeds.

traces_in_window integer obligatoire

The number of traces in the analyzed time window.

traces_analyzed integer obligatoire

The number of traces analyzed by the run.

insights_created integer obligatoire

The number of insights created by the run.

insights_updated integer obligatoire

The number of insights updated by the run.

insights_reopened integer obligatoire

The number of insights reopened by the run.

token_usage AgentInsightTokenUsage obligatoire

Token usage for an Agent Insights run.

input_tokens integer obligatoire

The number of input tokens used by the run.

output_tokens integer obligatoire

The number of output tokens used by the run.

cached_tokens integer

The number of input tokens served from cache.

total_tokens integer obligatoire

The total number of tokens used by the run.

status string | enum obligatoire

Extensible status values shared by Foundry jobs.

Un des éléments suivants :

string

enum

queuedin_progresssucceededfailedcancelled

error OpenAI.Error

code string | null obligatoire

message string obligatoire

param string | null

type string

misalignment OpenAI.MisalignmentErrorDetailsResource

review_target string | null

error_type string | enum

Un des éléments suivants :

string

enum

potentially_unintended_data_transferpotentially_unintended_data_accesspotentially_unintended_destructive_activityother

detailed_explanation string

The public explanation for this block.

steer OpenAI._MisalignmentSteer

message string obligatoire

The public continuation instruction.

details OpenAI.Error[]

Additional errors that contributed to this failure.

additionalInfo object

Additional structured information about the failure.

debugInfo object

Diagnostic information supplied by the service for troubleshooting.

monitor_id string obligatoire

The Agent Insights monitor this run belongs to.

agent_name string obligatoire

The agent whose traces are analyzed by this run.

trigger string | enum obligatoire

The trigger that started an agent insight run.

Un des éléments suivants :

string

enum

on_demandscheduled

created_at integer obligatoire

updated_at integer obligatoire

window_start integer obligatoire

window_end integer obligatoire

started_at integer

completed_at integer

model_deployment_name string obligatoire

The model deployment used to analyze traces for this run.

Requête

POST /agent_insight_monitors/{monitor_id}/runs HTTP/1.1

Response

Status: 201
Content-Type: application/json

Status: 4XX
Content-Type: application/json

Status: 5XX
Content-Type: application/json