@coval/sdk 0.4.4 → 0.4.6

package/src/generated/models/CovalAgentsAPICreateAgentRequest.ts

@@ -137,10 +137,8 @@ export interface CovalAgentsAPICreateAgentRequest {
      * *Optional:*
      * - `generate_token_headers` - Token-request headers as a JSON object or encoded object string
      * - `token_request_payload` - Fields merged into the token request as a JSON object or encoded object string
-     * - `sandbox_id` - Convenience value for an `X-Sandbox-ID` token-request header
      * - `content_type` - Convenience value for the token-request `Content-Type` header
      * - `livekit_agent_name` - Agent dispatch name
-     * - `livekit_agent_metadata` - Agent dispatch metadata
      * 
      * **For DAILY (Pipecat Cloud) agents:**
      * 
@@ -159,7 +157,7 @@ export interface CovalAgentsAPICreateAgentRequest {
      * *Connection mode:*
      * - `connection_mode` - `direct` (default), `http_first`, or `twiml_webhook`.
      * - `http_url`, `http_method`, `http_request_body`, `http_headers`, `websocket_url_response_path` - HTTP-first setup fields when `connection_mode=http_first`.
-     * - `voice_url`, `voice_http_method`, `voice_http_headers`, `voice_form_fields`, `twilio_account_sid`, `twilio_from_number`, `twilio_to_number` - TwiML voice-webhook fields when `connection_mode=twiml_webhook`. This mode is currently API-configured; it is not a connection-mode option in the agent editor.
+     * - `voice_url`, `voice_http_method`, `voice_http_headers`, `voice_form_fields`, `twilio_account_sid`, `twilio_from_number`, `twilio_to_number` - TwiML voice-webhook fields when `connection_mode=twiml_webhook`.
      * 
      * *Authentication (optional):*
      * - `authorization_header` - Auth header sent during the WebSocket handshake. Supports:
@@ -188,9 +186,10 @@ export interface CovalAgentsAPICreateAgentRequest {
      * - `send_media_template` - Outbound template for image attachments. Must contain `{{media_data}}`; may also include `{{media_name}}` and `{{mime_type}}`. Set exactly to `{{media_data}}` to send raw bytes, otherwise Coval base64-encodes the image into the JSON template.
      * - `send_dtmf_template` - Outbound template for keypad digits. Must contain `{{digit}}`.
      * 
-     * *WebSocket placeholders:*
-     * - `{{simulation_output_id}}` (legacy alias `{{simulation_id}}`) resolves only in `initialization_json`.
-     * - `{{stream_sid}}` and `{{call_sid}}` resolve in `initialization_json` and the audio, media, and DTMF send templates. They are generated per simulation in Twilio SID format and are not Coval simulation output IDs.
+     * *Per-simulation placeholders:*
+     * - Connection setup fields support `{{run_id}}`, `{{simulation_output_id}}` (legacy alias `{{simulation_id}}`), `{{stream_sid}}`, `{{call_sid}}`, `{{agent.*}}`, `{{test_case.*}}`, `{{sim_wrapper.*}}`, and `{{run_metadata.*}}`.
+     * - Connection setup fields are `initialization_json` in direct and HTTP-first modes; `custom_headers` in every mode; `http_request_body` and `http_headers` in HTTP-first mode; and `voice_form_fields` and `voice_http_headers` in TwiML webhook mode.
+     * - `{{stream_sid}}` and `{{call_sid}}` also resolve in `send_audio_template`, `send_media_template`, and `send_dtmf_template`. Coval generates fresh Twilio-shaped values for every simulation.
      * 
      * *Non-audio event capture (optional):*
      * - `non_audio_event_message_types` - List of message-type values to emit as `WebsocketEventFrame`s instead of dropping. Each match carries the message type, optional `event` name, and original payload. Useful for cart updates, transcript fragments, or session telemetry.

package/src/generated/models/CovalMetricsAPICreateMetricRequest.ts

@@ -131,11 +131,52 @@ export interface CovalMetricsAPICreateMetricRequest {
      * @memberof CovalMetricsAPICreateMetricRequest
      */
     sql_query?: string;
+    /**
+     * Where the metric reads its criteria from. Required for METRIC_COMPOSITE_EVALUATION.
+     * `test_case` reads a field off each test case (most commonly its expected behaviors),
+     * `test_case_attribute` reads from the test case's attributes, and `metric_metadata`
+     * uses the fixed list in `criteria`.
+     * 
+     * @type {CovalMetricsAPICreateMetricRequestCriteriaSourceEnum}
+     * @memberof CovalMetricsAPICreateMetricRequest
+     */
+    criteria_source?: CovalMetricsAPICreateMetricRequestCriteriaSourceEnum;
+    /**
+     * Path to the criteria on the source. Required when `criteria_source` is `test_case`
+     * or `test_case_attribute`.
+     * 
+     * @type {string}
+     * @memberof CovalMetricsAPICreateMetricRequest
+     */
+    criteria_path?: string;
+    /**
+     * Literal list of criteria. Required when `criteria_source` is `metric_metadata`.
+     * @type {Array<string>}
+     * @memberof CovalMetricsAPICreateMetricRequest
+     */
+    criteria?: Array<string>;
+    /**
+     * How per-criterion verdicts aggregate into the metric's value. Each criterion is judged
+     * independently as met or not met; `percentage_of_criteria_met` scores the fraction met
+     * among the criteria the judge could evaluate.
+     * 
+     * @type {CovalMetricsAPICreateMetricRequestReportingMethodEnum}
+     * @memberof CovalMetricsAPICreateMetricRequest
+     */
+    reporting_method?: CovalMetricsAPICreateMetricRequestReportingMethodEnum;
+    /**
+     * Custom prompt template used to evaluate each criterion. Include a `{criterion}`
+     * placeholder; if it is omitted the criterion is appended to the prompt.
+     * 
+     * @type {string}
+     * @memberof CovalMetricsAPICreateMetricRequest
+     */
+    base_prompt_template?: string;
     /**
      * Inject OTel trace context into the LLM judge prompt during evaluation.
-     * Supported for LLM judge metric types only (`METRIC_LLM_BINARY`, `METRIC_CATEGORICAL`,
-     * `METRIC_NUMERICAL_LLM_JUDGE`, `METRIC_AUDIO_LLM_BINARY`, `METRIC_AUDIO_LLM_CATEGORICAL`,
-     * `METRIC_AUDIO_LLM_NUMERICAL`).
+     * Supported for LLM judge metric types and `METRIC_COMPOSITE_EVALUATION` (`METRIC_LLM_BINARY`,
+     * `METRIC_CATEGORICAL`, `METRIC_NUMERICAL_LLM_JUDGE`, `METRIC_AUDIO_LLM_BINARY`,
+     * `METRIC_AUDIO_LLM_CATEGORICAL`, `METRIC_AUDIO_LLM_NUMERICAL`, `METRIC_COMPOSITE_EVALUATION`).
      * 
      * @type {boolean}
      * @memberof CovalMetricsAPICreateMetricRequest
@@ -176,6 +217,26 @@ export const CovalMetricsAPICreateMetricRequestRoleEnum = {
 } as const;
 export type CovalMetricsAPICreateMetricRequestRoleEnum = typeof CovalMetricsAPICreateMetricRequestRoleEnum[keyof typeof CovalMetricsAPICreateMetricRequestRoleEnum];
 
+/**
+ * @export
+ */
+export const CovalMetricsAPICreateMetricRequestCriteriaSourceEnum = {
+    TestCase: 'test_case',
+    TestCaseAttribute: 'test_case_attribute',
+    MetricMetadata: 'metric_metadata'
+} as const;
+export type CovalMetricsAPICreateMetricRequestCriteriaSourceEnum = typeof CovalMetricsAPICreateMetricRequestCriteriaSourceEnum[keyof typeof CovalMetricsAPICreateMetricRequestCriteriaSourceEnum];
+
+/**
+ * @export
+ */
+export const CovalMetricsAPICreateMetricRequestReportingMethodEnum = {
+    PercentageOfCriteriaMet: 'percentage_of_criteria_met',
+    CountOfCriteriaMet: 'count_of_criteria_met',
+    AllCriteriaMet: 'all_criteria_met'
+} as const;
+export type CovalMetricsAPICreateMetricRequestReportingMethodEnum = typeof CovalMetricsAPICreateMetricRequestReportingMethodEnum[keyof typeof CovalMetricsAPICreateMetricRequestReportingMethodEnum];
+
 
 /**
  * Check if a given object implements the CovalMetricsAPICreateMetricRequest interface.
@@ -210,6 +271,11 @@ export function CovalMetricsAPICreateMetricRequestFromJSONTyped(json: any, ignor
         'role': json['role'] == null ? undefined : json['role'],
         'min_pause_duration_seconds': json['min_pause_duration_seconds'] == null ? undefined : json['min_pause_duration_seconds'],
         'sql_query': json['sql_query'] == null ? undefined : json['sql_query'],
+        'criteria_source': json['criteria_source'] == null ? undefined : json['criteria_source'],
+        'criteria_path': json['criteria_path'] == null ? undefined : json['criteria_path'],
+        'criteria': json['criteria'] == null ? undefined : json['criteria'],
+        'reporting_method': json['reporting_method'] == null ? undefined : json['reporting_method'],
+        'base_prompt_template': json['base_prompt_template'] == null ? undefined : json['base_prompt_template'],
         'include_traces': json['include_traces'] == null ? undefined : json['include_traces'],
         'runtime_config': json['runtime_config'] == null ? undefined : CovalMetricsAPIMetricRuntimeConfigFromJSON(json['runtime_config']),
         'target_condition': json['target_condition'] == null ? undefined : CovalMetricsAPITargetConditionFromJSON(json['target_condition']),
@@ -241,6 +307,11 @@ export function CovalMetricsAPICreateMetricRequestToJSONTyped(value?: CovalMetri
         'role': value['role'],
         'min_pause_duration_seconds': value['min_pause_duration_seconds'],
         'sql_query': value['sql_query'],
+        'criteria_source': value['criteria_source'],
+        'criteria_path': value['criteria_path'],
+        'criteria': value['criteria'],
+        'reporting_method': value['reporting_method'],
+        'base_prompt_template': value['base_prompt_template'],
         'include_traces': value['include_traces'],
         'runtime_config': CovalMetricsAPIMetricRuntimeConfigToJSON(value['runtime_config']),
         'target_condition': CovalMetricsAPITargetConditionToJSON(value['target_condition']),

package/src/generated/models/CovalMetricsAPIMetricResource.ts

@@ -145,11 +145,41 @@ export interface CovalMetricsAPIMetricResource {
      * @memberof CovalMetricsAPIMetricResource
      */
     sql_query?: string | null;
+    /**
+     * Where a METRIC_COMPOSITE_EVALUATION metric reads its criteria from.
+     * @type {CovalMetricsAPIMetricResourceCriteriaSourceEnum}
+     * @memberof CovalMetricsAPIMetricResource
+     */
+    criteria_source?: CovalMetricsAPIMetricResourceCriteriaSourceEnum | null;
+    /**
+     * Path to the criteria on the source, when `criteria_source` is `test_case` or `test_case_attribute`.
+     * @type {string}
+     * @memberof CovalMetricsAPIMetricResource
+     */
+    criteria_path?: string | null;
+    /**
+     * Literal criteria, when `criteria_source` is `metric_metadata`.
+     * @type {Array<string>}
+     * @memberof CovalMetricsAPIMetricResource
+     */
+    criteria?: Array<string> | null;
+    /**
+     * How the per-criterion verdicts are aggregated into the metric's value.
+     * @type {CovalMetricsAPIMetricResourceReportingMethodEnum}
+     * @memberof CovalMetricsAPIMetricResource
+     */
+    reporting_method?: CovalMetricsAPIMetricResourceReportingMethodEnum | null;
+    /**
+     * Custom prompt template used to evaluate each criterion.
+     * @type {string}
+     * @memberof CovalMetricsAPIMetricResource
+     */
+    base_prompt_template?: string | null;
     /**
      * Whether OTel trace context is injected into the LLM judge prompt during evaluation.
-     * Supported for LLM judge metric types only (`METRIC_LLM_BINARY`, `METRIC_CATEGORICAL`,
-     * `METRIC_NUMERICAL_LLM_JUDGE`, `METRIC_AUDIO_LLM_BINARY`, `METRIC_AUDIO_LLM_CATEGORICAL`,
-     * `METRIC_AUDIO_LLM_NUMERICAL`).
+     * Supported for LLM judge metric types and `METRIC_COMPOSITE_EVALUATION` (`METRIC_LLM_BINARY`,
+     * `METRIC_CATEGORICAL`, `METRIC_NUMERICAL_LLM_JUDGE`, `METRIC_AUDIO_LLM_BINARY`,
+     * `METRIC_AUDIO_LLM_CATEGORICAL`, `METRIC_AUDIO_LLM_NUMERICAL`, `METRIC_COMPOSITE_EVALUATION`).
      * 
      * @type {boolean}
      * @memberof CovalMetricsAPIMetricResource
@@ -213,6 +243,26 @@ export const CovalMetricsAPIMetricResourceRoleEnum = {
 } as const;
 export type CovalMetricsAPIMetricResourceRoleEnum = typeof CovalMetricsAPIMetricResourceRoleEnum[keyof typeof CovalMetricsAPIMetricResourceRoleEnum];
 
+/**
+ * @export
+ */
+export const CovalMetricsAPIMetricResourceCriteriaSourceEnum = {
+    TestCase: 'test_case',
+    TestCaseAttribute: 'test_case_attribute',
+    MetricMetadata: 'metric_metadata'
+} as const;
+export type CovalMetricsAPIMetricResourceCriteriaSourceEnum = typeof CovalMetricsAPIMetricResourceCriteriaSourceEnum[keyof typeof CovalMetricsAPIMetricResourceCriteriaSourceEnum];
+
+/**
+ * @export
+ */
+export const CovalMetricsAPIMetricResourceReportingMethodEnum = {
+    PercentageOfCriteriaMet: 'percentage_of_criteria_met',
+    CountOfCriteriaMet: 'count_of_criteria_met',
+    AllCriteriaMet: 'all_criteria_met'
+} as const;
+export type CovalMetricsAPIMetricResourceReportingMethodEnum = typeof CovalMetricsAPIMetricResourceReportingMethodEnum[keyof typeof CovalMetricsAPIMetricResourceReportingMethodEnum];
+
 
 /**
  * Check if a given object implements the CovalMetricsAPIMetricResource interface.
@@ -246,6 +296,11 @@ export function CovalMetricsAPIMetricResourceFromJSONTyped(json: any, ignoreDisc
         'role': json['role'] == null ? undefined : json['role'],
         'min_pause_duration_seconds': json['min_pause_duration_seconds'] == null ? undefined : json['min_pause_duration_seconds'],
         'sql_query': json['sql_query'] == null ? undefined : json['sql_query'],
+        'criteria_source': json['criteria_source'] == null ? undefined : json['criteria_source'],
+        'criteria_path': json['criteria_path'] == null ? undefined : json['criteria_path'],
+        'criteria': json['criteria'] == null ? undefined : json['criteria'],
+        'reporting_method': json['reporting_method'] == null ? undefined : json['reporting_method'],
+        'base_prompt_template': json['base_prompt_template'] == null ? undefined : json['base_prompt_template'],
         'include_traces': json['include_traces'] == null ? undefined : json['include_traces'],
         'runtime_config': json['runtime_config'] == null ? undefined : CovalMetricsAPIMetricRuntimeConfigFromJSON(json['runtime_config']),
         'target_condition': json['target_condition'] == null ? undefined : CovalMetricsAPITargetConditionFromJSON(json['target_condition']),
@@ -283,6 +338,11 @@ export function CovalMetricsAPIMetricResourceToJSONTyped(value?: CovalMetricsAPI
         'role': value['role'],
         'min_pause_duration_seconds': value['min_pause_duration_seconds'],
         'sql_query': value['sql_query'],
+        'criteria_source': value['criteria_source'],
+        'criteria_path': value['criteria_path'],
+        'criteria': value['criteria'],
+        'reporting_method': value['reporting_method'],
+        'base_prompt_template': value['base_prompt_template'],
         'include_traces': value['include_traces'],
         'runtime_config': CovalMetricsAPIMetricRuntimeConfigToJSON(value['runtime_config']),
         'target_condition': CovalMetricsAPITargetConditionToJSON(value['target_condition']),

package/src/generated/models/CovalMetricsAPIMetricType.ts

@@ -27,6 +27,8 @@
  * - `METRIC_TRANSCRIPT_REGEX` - Regex pattern matching
  * - `METRIC_PAUSE_ANALYSIS` - Speech pause detection
  * - `METRIC_SQL_FLOAT` - Custom SQL query over the simulation's data (set `sql_query`)
+ * - `METRIC_COMPOSITE_EVALUATION` - Judges a list of criteria independently and reports how
+ *   many were met (set `criteria_source`, and `criteria_path` or `criteria` to match)
  * 
  * @export
  */
@@ -41,7 +43,8 @@ export const CovalMetricsAPIMetricType = {
     MetricMetadataField: 'METRIC_METADATA_FIELD',
     MetricTranscriptRegex: 'METRIC_TRANSCRIPT_REGEX',
     MetricPauseAnalysis: 'METRIC_PAUSE_ANALYSIS',
-    MetricSqlFloat: 'METRIC_SQL_FLOAT'
+    MetricSqlFloat: 'METRIC_SQL_FLOAT',
+    MetricCompositeEvaluation: 'METRIC_COMPOSITE_EVALUATION'
 } as const;
 export type CovalMetricsAPIMetricType = typeof CovalMetricsAPIMetricType[keyof typeof CovalMetricsAPIMetricType];
 

package/src/generated/models/CovalMetricsAPITestMetricBatchItemResult.ts

@@ -0,0 +1,101 @@
+/* tslint:disable */
+/* eslint-disable */
+/**
+ * Coval Agents API
+ *  Manage configurations for simulations and evaluations. 
+ *
+ * The version of the OpenAPI document: 1.0.0
+ * Contact: support@coval.dev
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+
+import { mapValues } from '../runtime.js';
+import type { CovalMetricsAPITestMetricItemStatus } from './CovalMetricsAPITestMetricItemStatus.js';
+import {
+    CovalMetricsAPITestMetricItemStatusFromJSON,
+    CovalMetricsAPITestMetricItemStatusFromJSONTyped,
+    CovalMetricsAPITestMetricItemStatusToJSON,
+    CovalMetricsAPITestMetricItemStatusToJSONTyped,
+} from './CovalMetricsAPITestMetricItemStatus.js';
+
+/**
+ * Result for one simulation output in a test-metric request.
+ * @export
+ * @interface CovalMetricsAPITestMetricBatchItemResult
+ */
+export interface CovalMetricsAPITestMetricBatchItemResult {
+    /**
+     * The simulation output ID this result applies to.
+     * @type {string}
+     * @memberof CovalMetricsAPITestMetricBatchItemResult
+     */
+    simulation_output_id: string;
+    /**
+     * 
+     * @type {CovalMetricsAPITestMetricItemStatus}
+     * @memberof CovalMetricsAPITestMetricBatchItemResult
+     */
+    status: CovalMetricsAPITestMetricItemStatus;
+    /**
+     * ULID of the created metric output, used to poll for the result. Null unless `status` is `QUEUED`.
+     * @type {string}
+     * @memberof CovalMetricsAPITestMetricBatchItemResult
+     */
+    metric_output_ulid?: string | null;
+    /**
+     * Human-readable error detail when the item was not queued.
+     * @type {string}
+     * @memberof CovalMetricsAPITestMetricBatchItemResult
+     */
+    error?: string | null;
+}
+
+
+
+/**
+ * Check if a given object implements the CovalMetricsAPITestMetricBatchItemResult interface.
+ */
+export function instanceOfCovalMetricsAPITestMetricBatchItemResult(value: object): value is CovalMetricsAPITestMetricBatchItemResult {
+    if (!('simulation_output_id' in value) || value['simulation_output_id'] === undefined) return false;
+    if (!('status' in value) || value['status'] === undefined) return false;
+    return true;
+}
+
+export function CovalMetricsAPITestMetricBatchItemResultFromJSON(json: any): CovalMetricsAPITestMetricBatchItemResult {
+    return CovalMetricsAPITestMetricBatchItemResultFromJSONTyped(json, false);
+}
+
+export function CovalMetricsAPITestMetricBatchItemResultFromJSONTyped(json: any, ignoreDiscriminator: boolean): CovalMetricsAPITestMetricBatchItemResult {
+    if (json == null) {
+        return json;
+    }
+    return {
+        
+        'simulation_output_id': json['simulation_output_id'],
+        'status': CovalMetricsAPITestMetricItemStatusFromJSON(json['status']),
+        'metric_output_ulid': json['metric_output_ulid'] == null ? undefined : json['metric_output_ulid'],
+        'error': json['error'] == null ? undefined : json['error'],
+    };
+}
+
+export function CovalMetricsAPITestMetricBatchItemResultToJSON(json: any): CovalMetricsAPITestMetricBatchItemResult {
+    return CovalMetricsAPITestMetricBatchItemResultToJSONTyped(json, false);
+}
+
+export function CovalMetricsAPITestMetricBatchItemResultToJSONTyped(value?: CovalMetricsAPITestMetricBatchItemResult | null, ignoreDiscriminator: boolean = false): any {
+    if (value == null) {
+        return value;
+    }
+
+    return {
+        
+        'simulation_output_id': value['simulation_output_id'],
+        'status': CovalMetricsAPITestMetricItemStatusToJSON(value['status']),
+        'metric_output_ulid': value['metric_output_ulid'],
+        'error': value['error'],
+    };
+}
+

package/src/generated/models/CovalMetricsAPITestMetricItemStatus.ts

@@ -0,0 +1,61 @@
+/* tslint:disable */
+/* eslint-disable */
+/**
+ * Coval Agents API
+ *  Manage configurations for simulations and evaluations. 
+ *
+ * The version of the OpenAPI document: 1.0.0
+ * Contact: support@coval.dev
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+
+
+/**
+ * Per-simulation-output outcome of a test-metric request.
+ * 
+ * - `QUEUED` - Metric execution queued successfully
+ * - `NOT_FOUND` - Simulation output not found
+ * - `FORBIDDEN` - Access to the simulation output denied
+ * - `ENQUEUE_FAILED` - Failed to enqueue the metric execution
+ * 
+ * @export
+ */
+export const CovalMetricsAPITestMetricItemStatus = {
+    Queued: 'QUEUED',
+    NotFound: 'NOT_FOUND',
+    Forbidden: 'FORBIDDEN',
+    EnqueueFailed: 'ENQUEUE_FAILED'
+} as const;
+export type CovalMetricsAPITestMetricItemStatus = typeof CovalMetricsAPITestMetricItemStatus[keyof typeof CovalMetricsAPITestMetricItemStatus];
+
+
+export function instanceOfCovalMetricsAPITestMetricItemStatus(value: any): boolean {
+    for (const key in CovalMetricsAPITestMetricItemStatus) {
+        if (Object.prototype.hasOwnProperty.call(CovalMetricsAPITestMetricItemStatus, key)) {
+            if (CovalMetricsAPITestMetricItemStatus[key as keyof typeof CovalMetricsAPITestMetricItemStatus] === value) {
+                return true;
+            }
+        }
+    }
+    return false;
+}
+
+export function CovalMetricsAPITestMetricItemStatusFromJSON(json: any): CovalMetricsAPITestMetricItemStatus {
+    return CovalMetricsAPITestMetricItemStatusFromJSONTyped(json, false);
+}
+
+export function CovalMetricsAPITestMetricItemStatusFromJSONTyped(json: any, ignoreDiscriminator: boolean): CovalMetricsAPITestMetricItemStatus {
+    return json as CovalMetricsAPITestMetricItemStatus;
+}
+
+export function CovalMetricsAPITestMetricItemStatusToJSON(value?: CovalMetricsAPITestMetricItemStatus | null): any {
+    return value as any;
+}
+
+export function CovalMetricsAPITestMetricItemStatusToJSONTyped(value: any, ignoreDiscriminator: boolean): CovalMetricsAPITestMetricItemStatus {
+    return value as CovalMetricsAPITestMetricItemStatus;
+}
+

package/src/generated/models/CovalMetricsAPITestMetricRequest.ts

@@ -14,17 +14,24 @@
 
 import { mapValues } from '../runtime.js';
 /**
- * 
+ * Provide exactly one of `simulation_output_id` or `simulation_output_ids`.
  * @export
  * @interface CovalMetricsAPITestMetricRequest
  */
 export interface CovalMetricsAPITestMetricRequest {
     /**
-     * The simulation output ID (22-character ShortUUID) to run the metric against
+     * Deprecated: a single simulation output ID (22-character ShortUUID) to run the metric against. Prefer `simulation_output_ids`.
      * @type {string}
      * @memberof CovalMetricsAPITestMetricRequest
+     * @deprecated
      */
-    simulation_output_id: string;
+    simulation_output_id?: string;
+    /**
+     * Simulation output IDs (22-character ShortUUIDs) to run the metric against; 1–100 per call.
+     * @type {Array<string>}
+     * @memberof CovalMetricsAPITestMetricRequest
+     */
+    simulation_output_ids?: Array<string>;
     /**
      * Optional developer identifier for debugging
      * @type {string}
@@ -37,7 +44,6 @@ export interface CovalMetricsAPITestMetricRequest {
  * Check if a given object implements the CovalMetricsAPITestMetricRequest interface.
  */
 export function instanceOfCovalMetricsAPITestMetricRequest(value: object): value is CovalMetricsAPITestMetricRequest {
-    if (!('simulation_output_id' in value) || value['simulation_output_id'] === undefined) return false;
     return true;
 }
 
@@ -51,7 +57,8 @@ export function CovalMetricsAPITestMetricRequestFromJSONTyped(json: any, ignoreD
     }
     return {
         
-        'simulation_output_id': json['simulation_output_id'],
+        'simulation_output_id': json['simulation_output_id'] == null ? undefined : json['simulation_output_id'],
+        'simulation_output_ids': json['simulation_output_ids'] == null ? undefined : json['simulation_output_ids'],
         'dev_id': json['dev_id'] == null ? undefined : json['dev_id'],
     };
 }
@@ -68,6 +75,7 @@ export function CovalMetricsAPITestMetricRequestToJSONTyped(value?: CovalMetrics
     return {
         
         'simulation_output_id': value['simulation_output_id'],
+        'simulation_output_ids': value['simulation_output_ids'],
         'dev_id': value['dev_id'],
     };
 }

package/src/generated/models/CovalMetricsAPITestMetricResponse.ts

@@ -13,6 +13,14 @@
  */
 
 import { mapValues } from '../runtime.js';
+import type { CovalMetricsAPITestMetricBatchItemResult } from './CovalMetricsAPITestMetricBatchItemResult.js';
+import {
+    CovalMetricsAPITestMetricBatchItemResultFromJSON,
+    CovalMetricsAPITestMetricBatchItemResultFromJSONTyped,
+    CovalMetricsAPITestMetricBatchItemResultToJSON,
+    CovalMetricsAPITestMetricBatchItemResultToJSONTyped,
+} from './CovalMetricsAPITestMetricBatchItemResult.js';
+
 /**
  * 
  * @export
@@ -20,17 +28,25 @@ import { mapValues } from '../runtime.js';
  */
 export interface CovalMetricsAPITestMetricResponse {
     /**
-     * The ULID of the created metric output, used to track result
+     * One entry per requested simulation output.
+     * @type {Array<CovalMetricsAPITestMetricBatchItemResult>}
+     * @memberof CovalMetricsAPITestMetricResponse
+     */
+    results: Array<CovalMetricsAPITestMetricBatchItemResult>;
+    /**
+     * Deprecated: the ULID of the created metric output, used to track the result. Only set for single `simulation_output_id` requests; null for batch (`simulation_output_ids`) requests, which should read `results` instead.
      * @type {string}
      * @memberof CovalMetricsAPITestMetricResponse
+     * @deprecated
      */
-    metric_output_ulid?: string;
+    metric_output_ulid?: string | null;
 }
 
 /**
  * Check if a given object implements the CovalMetricsAPITestMetricResponse interface.
  */
 export function instanceOfCovalMetricsAPITestMetricResponse(value: object): value is CovalMetricsAPITestMetricResponse {
+    if (!('results' in value) || value['results'] === undefined) return false;
     return true;
 }
 
@@ -44,6 +60,7 @@ export function CovalMetricsAPITestMetricResponseFromJSONTyped(json: any, ignore
     }
     return {
         
+        'results': ((json['results'] as Array<any>).map(CovalMetricsAPITestMetricBatchItemResultFromJSON)),
         'metric_output_ulid': json['metric_output_ulid'] == null ? undefined : json['metric_output_ulid'],
     };
 }
@@ -59,6 +76,7 @@ export function CovalMetricsAPITestMetricResponseToJSONTyped(value?: CovalMetric
 
     return {
         
+        'results': ((value['results'] as Array<any>).map(CovalMetricsAPITestMetricBatchItemResultToJSON)),
         'metric_output_ulid': value['metric_output_ulid'],
     };
 }

package/src/generated/models/CovalMetricsAPIUpdateMetricRequest.ts

@@ -126,9 +126,41 @@ export interface CovalMetricsAPIUpdateMetricRequest {
      * @memberof CovalMetricsAPIUpdateMetricRequest
      */
     sql_query?: string;
+    /**
+     * Where a METRIC_COMPOSITE_EVALUATION metric reads its criteria from.
+     * @type {CovalMetricsAPIUpdateMetricRequestCriteriaSourceEnum}
+     * @memberof CovalMetricsAPIUpdateMetricRequest
+     */
+    criteria_source?: CovalMetricsAPIUpdateMetricRequestCriteriaSourceEnum;
+    /**
+     * Path to the criteria on the source, when `criteria_source` is `test_case`
+     * or `test_case_attribute`.
+     * 
+     * @type {string}
+     * @memberof CovalMetricsAPIUpdateMetricRequest
+     */
+    criteria_path?: string;
+    /**
+     * Literal list of criteria, when `criteria_source` is `metric_metadata`.
+     * @type {Array<string>}
+     * @memberof CovalMetricsAPIUpdateMetricRequest
+     */
+    criteria?: Array<string>;
+    /**
+     * How per-criterion verdicts aggregate into the metric's value.
+     * @type {CovalMetricsAPIUpdateMetricRequestReportingMethodEnum}
+     * @memberof CovalMetricsAPIUpdateMetricRequest
+     */
+    reporting_method?: CovalMetricsAPIUpdateMetricRequestReportingMethodEnum;
+    /**
+     * Custom prompt template used to evaluate each criterion.
+     * @type {string}
+     * @memberof CovalMetricsAPIUpdateMetricRequest
+     */
+    base_prompt_template?: string;
     /**
      * Inject OTel trace context into the LLM judge prompt during evaluation.
-     * Supported for LLM judge metric types only.
+     * Supported for LLM judge metric types and `METRIC_COMPOSITE_EVALUATION`.
      * 
      * @type {boolean}
      * @memberof CovalMetricsAPIUpdateMetricRequest
@@ -169,6 +201,26 @@ export const CovalMetricsAPIUpdateMetricRequestRoleEnum = {
 } as const;
 export type CovalMetricsAPIUpdateMetricRequestRoleEnum = typeof CovalMetricsAPIUpdateMetricRequestRoleEnum[keyof typeof CovalMetricsAPIUpdateMetricRequestRoleEnum];
 
+/**
+ * @export
+ */
+export const CovalMetricsAPIUpdateMetricRequestCriteriaSourceEnum = {
+    TestCase: 'test_case',
+    TestCaseAttribute: 'test_case_attribute',
+    MetricMetadata: 'metric_metadata'
+} as const;
+export type CovalMetricsAPIUpdateMetricRequestCriteriaSourceEnum = typeof CovalMetricsAPIUpdateMetricRequestCriteriaSourceEnum[keyof typeof CovalMetricsAPIUpdateMetricRequestCriteriaSourceEnum];
+
+/**
+ * @export
+ */
+export const CovalMetricsAPIUpdateMetricRequestReportingMethodEnum = {
+    PercentageOfCriteriaMet: 'percentage_of_criteria_met',
+    CountOfCriteriaMet: 'count_of_criteria_met',
+    AllCriteriaMet: 'all_criteria_met'
+} as const;
+export type CovalMetricsAPIUpdateMetricRequestReportingMethodEnum = typeof CovalMetricsAPIUpdateMetricRequestReportingMethodEnum[keyof typeof CovalMetricsAPIUpdateMetricRequestReportingMethodEnum];
+
 
 /**
  * Check if a given object implements the CovalMetricsAPIUpdateMetricRequest interface.
@@ -200,6 +252,11 @@ export function CovalMetricsAPIUpdateMetricRequestFromJSONTyped(json: any, ignor
         'role': json['role'] == null ? undefined : json['role'],
         'min_pause_duration_seconds': json['min_pause_duration_seconds'] == null ? undefined : json['min_pause_duration_seconds'],
         'sql_query': json['sql_query'] == null ? undefined : json['sql_query'],
+        'criteria_source': json['criteria_source'] == null ? undefined : json['criteria_source'],
+        'criteria_path': json['criteria_path'] == null ? undefined : json['criteria_path'],
+        'criteria': json['criteria'] == null ? undefined : json['criteria'],
+        'reporting_method': json['reporting_method'] == null ? undefined : json['reporting_method'],
+        'base_prompt_template': json['base_prompt_template'] == null ? undefined : json['base_prompt_template'],
         'include_traces': json['include_traces'] == null ? undefined : json['include_traces'],
         'runtime_config': json['runtime_config'] == null ? undefined : CovalMetricsAPIMetricRuntimeConfigFromJSON(json['runtime_config']),
         'target_condition': json['target_condition'] == null ? undefined : CovalMetricsAPITargetConditionFromJSON(json['target_condition']),
@@ -231,6 +288,11 @@ export function CovalMetricsAPIUpdateMetricRequestToJSONTyped(value?: CovalMetri
         'role': value['role'],
         'min_pause_duration_seconds': value['min_pause_duration_seconds'],
         'sql_query': value['sql_query'],
+        'criteria_source': value['criteria_source'],
+        'criteria_path': value['criteria_path'],
+        'criteria': value['criteria'],
+        'reporting_method': value['reporting_method'],
+        'base_prompt_template': value['base_prompt_template'],
         'include_traces': value['include_traces'],
         'runtime_config': CovalMetricsAPIMetricRuntimeConfigToJSON(value['runtime_config']),
         'target_condition': CovalMetricsAPITargetConditionToJSON(value['target_condition']),

package/src/generated/models/CovalReviewsAPICreateReviewProjectRequest.ts

@@ -88,6 +88,12 @@ export interface CovalReviewsAPICreateReviewProjectRequest {
      * @memberof CovalReviewsAPICreateReviewProjectRequest
      */
     blind_labeling_shown_metric_ids?: Array<string> | null;
+    /**
+     * Enforce claims and explicit single-author completion for collaborative projects
+     * @type {boolean}
+     * @memberof CovalReviewsAPICreateReviewProjectRequest
+     */
+    enforced_collaboration?: boolean;
 }
 
 
@@ -122,6 +128,7 @@ export function CovalReviewsAPICreateReviewProjectRequestFromJSONTyped(json: any
         'notifications': json['notifications'] == null ? undefined : json['notifications'],
         'project_rules': json['project_rules'] == null ? undefined : ((json['project_rules'] as Array<any>).map(CovalReviewsAPIProjectRuleFromJSON)),
         'blind_labeling_shown_metric_ids': json['blind_labeling_shown_metric_ids'] == null ? undefined : json['blind_labeling_shown_metric_ids'],
+        'enforced_collaboration': json['enforced_collaboration'] == null ? undefined : json['enforced_collaboration'],
     };
 }
 
@@ -145,6 +152,7 @@ export function CovalReviewsAPICreateReviewProjectRequestToJSONTyped(value?: Cov
         'notifications': value['notifications'],
         'project_rules': value['project_rules'] == null ? undefined : ((value['project_rules'] as Array<any>).map(CovalReviewsAPIProjectRuleToJSON)),
         'blind_labeling_shown_metric_ids': value['blind_labeling_shown_metric_ids'],
+        'enforced_collaboration': value['enforced_collaboration'],
     };
 }