Skip to main content
PUT
/
chef-runs
/
{id}
/
label
Attach an evaluator label to a Chef compose-run
curl --request PUT \
  --url https://api.interchange.io/api/v2/storefront/chef-runs/{id}/label \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "label": {}
}'
{
  "id": "<string>",
  "storefrontId": "<string>",
  "operatingInstructionsVersion": 0,
  "buyerScope": {
    "operatorDomain": "<string>",
    "brandDomain": "<string>",
    "country": "<string>"
  },
  "buyerInstructions": {
    "matchedRowIds": [
      "<string>"
    ],
    "effectiveDiscountPercent": 123,
    "notes": [
      "<string>"
    ]
  },
  "brief": "<string>",
  "buyingMode": "<string>",
  "ingredientsSnapshot": "<unknown>",
  "prompt": "<string>",
  "rawLlmOutput": "<unknown>",
  "parsedOutput": "<unknown>",
  "runRationale": "<string>",
  "composedProductIds": [
    "<string>"
  ],
  "result": {
    "code": "<string>",
    "message": "<string>"
  },
  "modelName": "<string>",
  "durationMs": 0,
  "evalLabel": "<unknown>",
  "createdAt": "2023-11-07T05:31:56Z"
}

Documentation Index

Fetch the complete documentation index at: https://docs.interchange.io/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

API key or access token

Path Parameters

​
id
integer
required

Surrogate id of the chef-run row.

Required range: x <= 9007199254740991
Example:

42

Body

application/json

Attach (or replace) an evaluator label on a chef-run row. The label is freeform JSON the eval workflow defines.

​
label
object
required

Response

Attach an evaluator label to a Chef compose-run

A single chef-compose run record: inputs, prompt, raw + parsed LLM output, persisted product ids, and result envelope.

​
id
string
required
​
storefrontId
string
required
​
operatingInstructionsVersion
integer
required
Required range: -9007199254740991 <= x <= 9007199254740991
​
buyerScope
object
required

Buyer scope extracted from the AdCP get_products request that drove this run.

​
buyerInstructions
object
required

Resolver output: which buyer-instructions rows matched and the effective discount + notes applied.

​
brief
string | null
required
​
buyingMode
string
required
​
ingredientsSnapshot
any
required
​
prompt
string
required
​
rawLlmOutput
any
required
​
parsedOutput
any
required
​
runRationale
string | null
required
​
composedProductIds
string[]
required
​
result
object
required

Outcome envelope: ok on success, error with code/message on failure, skipped when the pipeline short-circuited.

​
modelName
string
required
​
durationMs
integer | null
required
Required range: -9007199254740991 <= x <= 9007199254740991
​
evalLabel
any
required
​
createdAt
string<date-time>
required
Pattern: ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d(?::[0-5]\d(?:\.\d+)?)?(?:Z))$