Update product

Update an existing product. See Products.

PATCH /products/{id}

Update product

cURL

curl --request PATCH \
  --url https://api.galtea.ai/products/{id} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "id": "prod_123",
  "organizationId": "org_123",
  "userId": "user_123",
  "name": "Sample Product",
  "description": "Sample product description",
  "riskLevel": "HIGH",
  "operatorType": "PROVIDER",
  "capabilities": "Can process and analyze data",
  "inabilities": "Cannot process sensitive financial data",
  "policies": "Must comply with data protection regulations",
  "otelOutputSourceRule": {
    "spanName": "ExecuteActivity:save_reply",
    "attribute": "app.arguments",
    "path": "$[0].message.content",
    "predicate": {
      "path": "$[0].message.role",
      "equals": "assistant"
    }
  },
  "autoCloseScope": "PRODUCTION",
  "autoCloseInactivityMinutes": 30,
  "closedSessionInferenceCreationPolicy": "REOPEN_AND_REEVALUATE",
  "tags": [
    "internal",
    "beta"
  ],
  "createdAt": "2023-11-07T05:31:56Z",
  "deletedAt": "2023-11-07T05:31:56Z"
}
'

200

{
  "id": "prod_123",
  "organizationId": "org_123",
  "userId": "user_123",
  "name": "Sample Product",
  "description": "Sample product description",
  "riskLevel": "HIGH",
  "operatorType": "PROVIDER",
  "capabilities": "Can process and analyze data",
  "inabilities": "Cannot process sensitive financial data",
  "policies": "Must comply with data protection regulations",
  "otelOutputSourceRule": {
    "spanName": "ExecuteActivity:save_reply",
    "attribute": "app.arguments",
    "path": "$[0].message.content",
    "predicate": {
      "path": "$[0].message.role",
      "equals": "assistant"
    }
  },
  "autoCloseScope": "PRODUCTION",
  "autoCloseInactivityMinutes": 30,
  "closedSessionInferenceCreationPolicy": "REOPEN_AND_REEVALUATE",
  "tags": [
    "internal",
    "beta"
  ],
  "source": "banking",
  "createdAt": "2023-11-07T05:31:56Z",
  "deletedAt": "2023-11-07T05:31:56Z"
}

Authorizations

Authorization · string · header · required

API key authorization. Pass your API key in the Authorization header as a Bearer token. Both new (gsk_*) and legacy (gsk-) API keys are accepted, e.g. Authorization: Bearer gsk_... or Authorization: Bearer gsk-....

Path Parameters

id · string · required

Product ID

Body

application/json

Updated product data

id · string

Example:

"prod_123"

organizationId · string

Example:

"org_123"

userId · string | null

Example:

"user_123"

name · string

Example:

"Sample Product"

description · string

Example:

"Sample product description"

riskLevel · enum<string> | null

EU AI Act risk classification. PROHIBITED: banned AI use cases. GPAI: general-purpose AI. GPAI_SYSTEMIC: GPAI with systemic risk. HIGH: high-risk AI system. SPECIAL_SYSTEM: special-category system.

Available options: PROHIBITED, GPAI, GPAI_SYSTEMIC, HIGH, SPECIAL_SYSTEM

Example:

"HIGH"

operatorType · enum<string> | null

EU AI Act operator role classification.

Available options: AUTHORISED_REPRESENTATIVE, DEPLOYER, DISTRIBUTER, IMPORTER, PRODUCT_MANUFACTURER, PROVIDER

Example:

"PROVIDER"

capabilities · string | null

Example:

"Can process and analyze data"

inabilities · string | null

Example:

"Cannot process sensitive financial data"

policies · string | null

Example:

"Must comply with data protection regulations"

otelOutputSourceRule · object | null

Recover a turn's user-visible output for templated or non-LLM replies whose final answer lives on a non-LLM span. Set per product or version (version wins). Applied only when no LLM output is present.

Show child attributes

Example:

{
  "spanName": "ExecuteActivity:save_reply",
  "attribute": "app.arguments",
  "path": "$[0].message.content",
  "predicate": {
    "path": "$[0].message.role",
    "equals": "assistant"
  }
}

autoCloseScope · enum<string> · default: PRODUCTION

Which sessions the product-level auto-close sweep considers. PRODUCTION (default) closes only production sessions; DEVELOPMENT only test sessions; ALL both; NONE disables auto-close.

Available options: NONE, DEVELOPMENT, PRODUCTION, ALL

Example:

"PRODUCTION"

autoCloseInactivityMinutes · integer · default: 30

Minutes of inactivity after which an eligible session is auto-closed.

Required range: x >= 1

Example:

30

closedSessionInferenceCreationPolicy · enum<string> · default: REOPEN_AND_REEVALUATE

What happens when a new trace is created for an already-closed session. REOPEN_AND_REEVALUATE (the default) stores the trace, returns the session to PENDING and marks its existing monitor evaluations OUTDATED so a monitor scores the session again once it closes for good (production sessions only; a development session is dropped like IGNORE). IGNORE drops the trace silently. REJECT returns an error.

Available options: REJECT, IGNORE, REOPEN_AND_REEVALUATE

Example:

"REOPEN_AND_REEVALUATE"

tags · string[]

Free-form labels for organizing products. Normalized to lowercase and trimmed on save.

Example:

["internal", "beta"]

createdAt · string<date-time>

deletedAt · string<date-time> | null

Response

200

application/json

Product updated successfully

id · string

Example:

"prod_123"

organizationId · string

Example:

"org_123"

userId · string | null

Example:

"user_123"

name · string

Example:

"Sample Product"

description · string

Example:

"Sample product description"

riskLevel · enum<string> | null

EU AI Act risk classification. PROHIBITED: banned AI use cases. GPAI: general-purpose AI. GPAI_SYSTEMIC: GPAI with systemic risk. HIGH: high-risk AI system. SPECIAL_SYSTEM: special-category system.

Available options: PROHIBITED, GPAI, GPAI_SYSTEMIC, HIGH, SPECIAL_SYSTEM

Example:

"HIGH"

operatorType · enum<string> | null

EU AI Act operator role classification.

Available options: AUTHORISED_REPRESENTATIVE, DEPLOYER, DISTRIBUTER, IMPORTER, PRODUCT_MANUFACTURER, PROVIDER

Example:

"PROVIDER"

capabilities · string | null

Example:

"Can process and analyze data"

inabilities · string | null

Example:

"Cannot process sensitive financial data"

policies · string | null

Example:

"Must comply with data protection regulations"

otelOutputSourceRule · object | null

Recover a turn's user-visible output for templated or non-LLM replies whose final answer lives on a non-LLM span. Set per product or version (version wins). Applied only when no LLM output is present.

Show child attributes

Example:

{
  "spanName": "ExecuteActivity:save_reply",
  "attribute": "app.arguments",
  "path": "$[0].message.content",
  "predicate": {
    "path": "$[0].message.role",
    "equals": "assistant"
  }
}

autoCloseScope · enum<string> · default: PRODUCTION

Which sessions the product-level auto-close sweep considers. PRODUCTION (default) closes only production sessions; DEVELOPMENT only test sessions; ALL both; NONE disables auto-close.

Available options: NONE, DEVELOPMENT, PRODUCTION, ALL

Example:

"PRODUCTION"

autoCloseInactivityMinutes · integer · default: 30

Minutes of inactivity after which an eligible session is auto-closed.

Required range: x >= 1

Example:

30

closedSessionInferenceCreationPolicy · enum<string> · default: REOPEN_AND_REEVALUATE

What happens when a new trace is created for an already-closed session. REOPEN_AND_REEVALUATE (the default) stores the trace, returns the session to PENDING and marks its existing monitor evaluations OUTDATED so a monitor scores the session again once it closes for good (production sessions only; a development session is dropped like IGNORE). IGNORE drops the trace silently. REJECT returns an error.

Available options: REJECT, IGNORE, REOPEN_AND_REEVALUATE

Example:

"REOPEN_AND_REEVALUATE"

tags · string[]

Free-form labels for organizing products. Normalized to lowercase and trimmed on save.

Example:

["internal", "beta"]

source · string | null · read-only

Demo key the product was cloned from (e.g. "banking"); null for user-created products. Server-stamped on demo-clone; not client-writable.

Example:

"banking"

createdAt · string<date-time>

deletedAt · string<date-time> | null