COconstructor
Agent insights

Retrieve conversational agent replies

Hold one turn of a conversation with the full shopping agent. The agent interprets the shopper's message, decides what it needs, and answers from whichever sources the domain has configured: product discovery across search, browse and recommendations, and a knowledge base of articles for questions the catalog cannot answer. A single turn can produce several kinds of content, so a reply may combine prose with product sets, cited articles, images or recipes, and it usually ends with refinements the shopper can pick from to continue. parameters.domain chooses which configured domain answers, and with it the agent's instructions, tools and models. Pass thread_id from a previous turn to continue that conversation with its history intact; omit it to start a new one. Results stream back as server-sent events (text/event-stream) so the agent's reply can be rendered as it is produced. To receive the finished reply as a single JSON document instead, send Accept: application/json.

post/v1/agent_insights/chat

Request

  • Base URL
    https://agent.cnstrc.com
  • URL
    https://agent.cnstrc.com/v1/agent_insights/chat
  • Auth
    none required

Query parameters

keystring required

The key of the index to use.

thread_idstring uuid

A unique identifier for the conversation thread. This ID links multiple requests to the same conversation. When omitted, a new thread is created.

guardboolean

Turn the content moderation check on or off. When on, shopper input is screened before the agent processes it.

num_result_eventsinteger

The maximum number of result events to return.

num_results_per_eventinteger

The maximum number of results to return per item_results event.

fieldsstring[]

A list of specific item fields to return in the response. Allows the request to control which fields are returned.

show_hidden_fieldsboolean

A flag to return all hidden fields in the response.

hidden_fieldsstring[]

A list of specific hidden fields to return in the response. Unlike show_hidden_fields this parameter allows the request to control which hidden fields are returned. Used to return item fields for a particular store or user segment.

variations_return_type'default' | 'all' | 'matched'
groups_max_depthinteger

The maximum depth of the group hierarchy in the response.

groups_startstring

A flag to specify the start of the group hierarchy returned in the response. current returns groups starting from the currently selected one. top returns groups starting from the root category in the hierarchy. group_id:{id}, returns the whole tree starting from group with the provided id.

groups_pathstring[]

Specifies the path from the root group to the current group you are browsing. It is used to construct the parents path in the response.groups for the current browsed group. Max depth allowed for the path is 10. This option is only accepted when groups_start is 'current'.

groups_sort_by'relevance' | 'value' | 'num_matches'
groups_sort_order'ascending' | 'descending'
show_hidden_facetsboolean

A flag to return all facets configured as hidden in response.facets.

hidden_facetsstring[]

A list of specific hidden facets to return in the response. Unlike show_hidden_facets this parameter allows the request to control which hidden facets are returned. Used to return facets for a particular store or user segment.

show_hidden_facet_optionsboolean

A flag to return all hidden facets options in the response.

show_protected_facetsboolean

A flag to return all protected facets in the response. Requires authentication.

facet_optionsobject

A list of specific facet options per facet to return in the response. This parameter accepts up to 5 facets and works only with facets of type multiple. Invalid facet options will be ignored. Used to return facet options for a particular facet like store or user segment.

facet_groups_limitinteger

The maximum limit of the facet groups returned in the response.

show_hidden_sort_optionsboolean

A flag to return all sort options configured as hidden in response.sort_options.

hidden_sort_optionsstring[]

A list of sort_by fields whose hidden sort options should be included in the response. Unlike show_hidden_sort_options this parameter allows you to specify exactly which hidden sort options are returned.

An object containing options to format different aspects of the response.

qsstring json

Additional query parameters to forward to the underlying Constructor search, browse and recommendations API calls, as a JSON-encoded string: for example qs={"sort_by":"price","sort_order":"ascending"}. Each mode forwards only the keys that apply to the calls it makes, and any key managed by page_context.filters must not be overridden here.

cstring

The ID of the client and version that the request is coming from, such as cio-js-2.90.

usstring[]

A customer defined context (such as vip-club-member) used to evaluate redirect or refined tag rules. Pass multiple segments by passing multiple us arguments.

uistring

A customer generated anonymized identifier for a user on a customer website. It should only be sent for logged in customers and helps constructor to tie multiple client and session ID's together to form a behavioral data profile across devices.

feature_variantsobject

Feature variants keyed by feature name. Accepts flattened feature_variants[<feature_name>] query parameters.

featuresobject

Feature toggles keyed by feature name. Accepts flattened features[<feature_name>] query parameters.

sinteger

An integer representing the user's session number (starting with 1), incremented after a 30 minute period of inactivity.

istring

A globally unique identifier for the user browser (or mobile application instance) making the request.

Request body

shopper_inputstring required

The shopper's message to the agent.

Response

AI-powered agent insights, streamed as server-sent events or aggregated into a single JSON document.

result_idstring required

Agent insight result ID.

thread_idstring uuid

A unique identifier for the conversation thread. Pass it back on the next request to continue the same conversation. Only populated for conversational modes.

status'complete' | 'partial' required

Whether the collected stream represents the agent's full answer.

  • complete: the underlying stream finished normally.
  • partial: the stream was truncated or emitted a server_error, so the answer may be incomplete.
messagestring

The agent's text output. When the agent produced several message events they are joined in the order they were emitted.

route'customer_support'

Where the client should send the shopper next. customer_support marks a customer support answer.

Example response

{
  "follow_up_refinement": {
    "options": [
      "Yes, sub-zero",
      "No, mild weather"
    ],
    "question": "Do you need it for winter conditions?"
  },
  "item_results": [
    {
      "request": {
        "ids": [
          "item_id_1"
        ],
        "params": {
          "num_results_per_page": 20
        },
        "type": "browse"
      },
      "response": {
        "results": [
          {
            "value": "Waterproof Hiking Boot",
            "matched_terms": [
              "waterproof",
              "hiking"
            ],
            "is_slotted": false,
            "labels": {},
            "data": {
              "id": "item_id_1",
              "url": "https://example.com/product/item_id_1",
              "image_url": "https://cdn.example.com/item_id_1.jpg"
            }
          }
        ]
      },
      "result_id": "973e152a-ee03-47d2-a01b-1214da90a02b"
    }
  ],
  "message": "Based on your interest in hiking gear, here are some waterproof options...",
  "result_id": "550e8400-e29b-41d4-a716-446655440000",
  "status": "complete",
  "thread_id": "662e8400-e29b-41d4-a716-446655440001"
}

Changes

No recorded changes to this operation across all 1 revision of this API.