@meetkai/mka1 0.54.23 → 0.54.24

package/src/models/operations/listevalruns.ts

@@ -125,6 +125,22 @@ export type ListEvalRunsData = {
   error: { [k: string]: any } | null;
   artifactFileIds: Array<string>;
   metadata: { [k: string]: string };
+  /**
+   * Coding-agent harness that produced this run (e.g. `omp`, `claude-code`). Null for every non-harness eval kind — a null here is not a missing value, it means the run is not an agent run.
+   */
+  agentName: string | null;
+  /**
+   * Version of `agent_name`, as the harness reported it. Null when `agent_name` is.
+   */
+  agentVersion: string | null;
+  /**
+   * Reasoning-effort setting the agent ran at (e.g. `medium`, `xhigh`). Part of the leaderboard's row identity: the same agent and model at two efforts are two rows, not one. Null when `agent_name` is.
+   */
+  agentEffort: string | null;
+  /**
+   * Total spend for the run in USD. Null when the harness did not report cost.
+   */
+  costUsd: number | null;
   createdAt: number;
   startedAt: number | null;
   completedAt: number | null;
@@ -545,6 +561,10 @@ export const ListEvalRunsData$inboundSchema: z.ZodType<
   error: z.nullable(z.record(z.any())),
   artifact_file_ids: z.array(z.string()),
   metadata: z.record(z.string()),
+  agent_name: z.nullable(z.string()),
+  agent_version: z.nullable(z.string()),
+  agent_effort: z.nullable(z.string()),
+  cost_usd: z.nullable(z.number()),
   created_at: z.number().int(),
   started_at: z.nullable(z.number().int()),
   completed_at: z.nullable(z.number().int()),
@@ -562,6 +582,10 @@ export const ListEvalRunsData$inboundSchema: z.ZodType<
     "embedding_model": "embeddingModel",
     "request_counts": "requestCounts",
     "artifact_file_ids": "artifactFileIds",
+    "agent_name": "agentName",
+    "agent_version": "agentVersion",
+    "agent_effort": "agentEffort",
+    "cost_usd": "costUsd",
     "created_at": "createdAt",
     "started_at": "startedAt",
     "completed_at": "completedAt",
@@ -589,6 +613,10 @@ export type ListEvalRunsData$Outbound = {
   error: { [k: string]: any } | null;
   artifact_file_ids: Array<string>;
   metadata: { [k: string]: string };
+  agent_name: string | null;
+  agent_version: string | null;
+  agent_effort: string | null;
+  cost_usd: number | null;
   created_at: number;
   started_at: number | null;
   completed_at: number | null;
@@ -620,6 +648,10 @@ export const ListEvalRunsData$outboundSchema: z.ZodType<
   error: z.nullable(z.record(z.any())),
   artifactFileIds: z.array(z.string()),
   metadata: z.record(z.string()),
+  agentName: z.nullable(z.string()),
+  agentVersion: z.nullable(z.string()),
+  agentEffort: z.nullable(z.string()),
+  costUsd: z.nullable(z.number()),
   createdAt: z.number().int(),
   startedAt: z.nullable(z.number().int()),
   completedAt: z.nullable(z.number().int()),
@@ -637,6 +669,10 @@ export const ListEvalRunsData$outboundSchema: z.ZodType<
     embeddingModel: "embedding_model",
     requestCounts: "request_counts",
     artifactFileIds: "artifact_file_ids",
+    agentName: "agent_name",
+    agentVersion: "agent_version",
+    agentEffort: "agent_effort",
+    costUsd: "cost_usd",
     createdAt: "created_at",
     startedAt: "started_at",
     completedAt: "completed_at",

package/src/models/operations/listevalscheduleruns.ts

@@ -130,6 +130,22 @@ export type ListEvalScheduleRunsData = {
   error: { [k: string]: any } | null;
   artifactFileIds: Array<string>;
   metadata: { [k: string]: string };
+  /**
+   * Coding-agent harness that produced this run (e.g. `omp`, `claude-code`). Null for every non-harness eval kind — a null here is not a missing value, it means the run is not an agent run.
+   */
+  agentName: string | null;
+  /**
+   * Version of `agent_name`, as the harness reported it. Null when `agent_name` is.
+   */
+  agentVersion: string | null;
+  /**
+   * Reasoning-effort setting the agent ran at (e.g. `medium`, `xhigh`). Part of the leaderboard's row identity: the same agent and model at two efforts are two rows, not one. Null when `agent_name` is.
+   */
+  agentEffort: string | null;
+  /**
+   * Total spend for the run in USD. Null when the harness did not report cost.
+   */
+  costUsd: number | null;
   createdAt: number;
   startedAt: number | null;
   completedAt: number | null;
@@ -566,6 +582,10 @@ export const ListEvalScheduleRunsData$inboundSchema: z.ZodType<
   error: z.nullable(z.record(z.any())),
   artifact_file_ids: z.array(z.string()),
   metadata: z.record(z.string()),
+  agent_name: z.nullable(z.string()),
+  agent_version: z.nullable(z.string()),
+  agent_effort: z.nullable(z.string()),
+  cost_usd: z.nullable(z.number()),
   created_at: z.number().int(),
   started_at: z.nullable(z.number().int()),
   completed_at: z.nullable(z.number().int()),
@@ -583,6 +603,10 @@ export const ListEvalScheduleRunsData$inboundSchema: z.ZodType<
     "embedding_model": "embeddingModel",
     "request_counts": "requestCounts",
     "artifact_file_ids": "artifactFileIds",
+    "agent_name": "agentName",
+    "agent_version": "agentVersion",
+    "agent_effort": "agentEffort",
+    "cost_usd": "costUsd",
     "created_at": "createdAt",
     "started_at": "startedAt",
     "completed_at": "completedAt",
@@ -610,6 +634,10 @@ export type ListEvalScheduleRunsData$Outbound = {
   error: { [k: string]: any } | null;
   artifact_file_ids: Array<string>;
   metadata: { [k: string]: string };
+  agent_name: string | null;
+  agent_version: string | null;
+  agent_effort: string | null;
+  cost_usd: number | null;
   created_at: number;
   started_at: number | null;
   completed_at: number | null;
@@ -641,6 +669,10 @@ export const ListEvalScheduleRunsData$outboundSchema: z.ZodType<
   error: z.nullable(z.record(z.any())),
   artifactFileIds: z.array(z.string()),
   metadata: z.record(z.string()),
+  agentName: z.nullable(z.string()),
+  agentVersion: z.nullable(z.string()),
+  agentEffort: z.nullable(z.string()),
+  costUsd: z.nullable(z.number()),
   createdAt: z.number().int(),
   startedAt: z.nullable(z.number().int()),
   completedAt: z.nullable(z.number().int()),
@@ -658,6 +690,10 @@ export const ListEvalScheduleRunsData$outboundSchema: z.ZodType<
     embeddingModel: "embedding_model",
     requestCounts: "request_counts",
     artifactFileIds: "artifact_file_ids",
+    agentName: "agent_name",
+    agentVersion: "agent_version",
+    agentEffort: "agent_effort",
+    costUsd: "cost_usd",
     createdAt: "created_at",
     startedAt: "started_at",
     completedAt: "completed_at",

package/src/models/operations/listevalsuiteleaderboardruns.ts

@@ -116,6 +116,22 @@ export type ListEvalSuiteLeaderboardRunsData = {
   error: { [k: string]: any } | null;
   artifactFileIds: Array<string>;
   metadata: { [k: string]: string };
+  /**
+   * Coding-agent harness that produced this run (e.g. `omp`, `claude-code`). Null for every non-harness eval kind — a null here is not a missing value, it means the run is not an agent run.
+   */
+  agentName: string | null;
+  /**
+   * Version of `agent_name`, as the harness reported it. Null when `agent_name` is.
+   */
+  agentVersion: string | null;
+  /**
+   * Reasoning-effort setting the agent ran at (e.g. `medium`, `xhigh`). Part of the leaderboard's row identity: the same agent and model at two efforts are two rows, not one. Null when `agent_name` is.
+   */
+  agentEffort: string | null;
+  /**
+   * Total spend for the run in USD. Null when the harness did not report cost.
+   */
+  costUsd: number | null;
   createdAt: number;
   startedAt: number | null;
   completedAt: number | null;
@@ -580,6 +596,10 @@ export const ListEvalSuiteLeaderboardRunsData$inboundSchema: z.ZodType<
   error: z.nullable(z.record(z.any())),
   artifact_file_ids: z.array(z.string()),
   metadata: z.record(z.string()),
+  agent_name: z.nullable(z.string()),
+  agent_version: z.nullable(z.string()),
+  agent_effort: z.nullable(z.string()),
+  cost_usd: z.nullable(z.number()),
   created_at: z.number().int(),
   started_at: z.nullable(z.number().int()),
   completed_at: z.nullable(z.number().int()),
@@ -597,6 +617,10 @@ export const ListEvalSuiteLeaderboardRunsData$inboundSchema: z.ZodType<
     "embedding_model": "embeddingModel",
     "request_counts": "requestCounts",
     "artifact_file_ids": "artifactFileIds",
+    "agent_name": "agentName",
+    "agent_version": "agentVersion",
+    "agent_effort": "agentEffort",
+    "cost_usd": "costUsd",
     "created_at": "createdAt",
     "started_at": "startedAt",
     "completed_at": "completedAt",
@@ -624,6 +648,10 @@ export type ListEvalSuiteLeaderboardRunsData$Outbound = {
   error: { [k: string]: any } | null;
   artifact_file_ids: Array<string>;
   metadata: { [k: string]: string };
+  agent_name: string | null;
+  agent_version: string | null;
+  agent_effort: string | null;
+  cost_usd: number | null;
   created_at: number;
   started_at: number | null;
   completed_at: number | null;
@@ -659,6 +687,10 @@ export const ListEvalSuiteLeaderboardRunsData$outboundSchema: z.ZodType<
   error: z.nullable(z.record(z.any())),
   artifactFileIds: z.array(z.string()),
   metadata: z.record(z.string()),
+  agentName: z.nullable(z.string()),
+  agentVersion: z.nullable(z.string()),
+  agentEffort: z.nullable(z.string()),
+  costUsd: z.nullable(z.number()),
   createdAt: z.number().int(),
   startedAt: z.nullable(z.number().int()),
   completedAt: z.nullable(z.number().int()),
@@ -676,6 +708,10 @@ export const ListEvalSuiteLeaderboardRunsData$outboundSchema: z.ZodType<
     embeddingModel: "embedding_model",
     requestCounts: "request_counts",
     artifactFileIds: "artifact_file_ids",
+    agentName: "agent_name",
+    agentVersion: "agent_version",
+    agentEffort: "agent_effort",
+    costUsd: "cost_usd",
     createdAt: "created_at",
     startedAt: "started_at",
     completedAt: "completed_at",

package/src/models/operations/rerunfailedevalsamples.ts

@@ -115,6 +115,22 @@ export type RerunFailedEvalSamplesResponseBody = {
   error: { [k: string]: any } | null;
   artifactFileIds: Array<string>;
   metadata: { [k: string]: string };
+  /**
+   * Coding-agent harness that produced this run (e.g. `omp`, `claude-code`). Null for every non-harness eval kind — a null here is not a missing value, it means the run is not an agent run.
+   */
+  agentName: string | null;
+  /**
+   * Version of `agent_name`, as the harness reported it. Null when `agent_name` is.
+   */
+  agentVersion: string | null;
+  /**
+   * Reasoning-effort setting the agent ran at (e.g. `medium`, `xhigh`). Part of the leaderboard's row identity: the same agent and model at two efforts are two rows, not one. Null when `agent_name` is.
+   */
+  agentEffort: string | null;
+  /**
+   * Total spend for the run in USD. Null when the harness did not report cost.
+   */
+  costUsd: number | null;
   createdAt: number;
   startedAt: number | null;
   completedAt: number | null;
@@ -515,6 +531,10 @@ export const RerunFailedEvalSamplesResponseBody$inboundSchema: z.ZodType<
   error: z.nullable(z.record(z.any())),
   artifact_file_ids: z.array(z.string()),
   metadata: z.record(z.string()),
+  agent_name: z.nullable(z.string()),
+  agent_version: z.nullable(z.string()),
+  agent_effort: z.nullable(z.string()),
+  cost_usd: z.nullable(z.number()),
   created_at: z.number().int(),
   started_at: z.nullable(z.number().int()),
   completed_at: z.nullable(z.number().int()),
@@ -532,6 +552,10 @@ export const RerunFailedEvalSamplesResponseBody$inboundSchema: z.ZodType<
     "embedding_model": "embeddingModel",
     "request_counts": "requestCounts",
     "artifact_file_ids": "artifactFileIds",
+    "agent_name": "agentName",
+    "agent_version": "agentVersion",
+    "agent_effort": "agentEffort",
+    "cost_usd": "costUsd",
     "created_at": "createdAt",
     "started_at": "startedAt",
     "completed_at": "completedAt",
@@ -559,6 +583,10 @@ export type RerunFailedEvalSamplesResponseBody$Outbound = {
   error: { [k: string]: any } | null;
   artifact_file_ids: Array<string>;
   metadata: { [k: string]: string };
+  agent_name: string | null;
+  agent_version: string | null;
+  agent_effort: string | null;
+  cost_usd: number | null;
   created_at: number;
   started_at: number | null;
   completed_at: number | null;
@@ -592,6 +620,10 @@ export const RerunFailedEvalSamplesResponseBody$outboundSchema: z.ZodType<
   error: z.nullable(z.record(z.any())),
   artifactFileIds: z.array(z.string()),
   metadata: z.record(z.string()),
+  agentName: z.nullable(z.string()),
+  agentVersion: z.nullable(z.string()),
+  agentEffort: z.nullable(z.string()),
+  costUsd: z.nullable(z.number()),
   createdAt: z.number().int(),
   startedAt: z.nullable(z.number().int()),
   completedAt: z.nullable(z.number().int()),
@@ -609,6 +641,10 @@ export const RerunFailedEvalSamplesResponseBody$outboundSchema: z.ZodType<
     embeddingModel: "embedding_model",
     requestCounts: "request_counts",
     artifactFileIds: "artifact_file_ids",
+    agentName: "agent_name",
+    agentVersion: "agent_version",
+    agentEffort: "agent_effort",
+    costUsd: "cost_usd",
     createdAt: "created_at",
     startedAt: "started_at",
     completedAt: "completed_at",

package/src/models/operations/retryfailedevalrun.ts

@@ -115,6 +115,22 @@ export type RetryFailedEvalRunResponseBody = {
   error: { [k: string]: any } | null;
   artifactFileIds: Array<string>;
   metadata: { [k: string]: string };
+  /**
+   * Coding-agent harness that produced this run (e.g. `omp`, `claude-code`). Null for every non-harness eval kind — a null here is not a missing value, it means the run is not an agent run.
+   */
+  agentName: string | null;
+  /**
+   * Version of `agent_name`, as the harness reported it. Null when `agent_name` is.
+   */
+  agentVersion: string | null;
+  /**
+   * Reasoning-effort setting the agent ran at (e.g. `medium`, `xhigh`). Part of the leaderboard's row identity: the same agent and model at two efforts are two rows, not one. Null when `agent_name` is.
+   */
+  agentEffort: string | null;
+  /**
+   * Total spend for the run in USD. Null when the harness did not report cost.
+   */
+  costUsd: number | null;
   createdAt: number;
   startedAt: number | null;
   completedAt: number | null;
@@ -509,6 +525,10 @@ export const RetryFailedEvalRunResponseBody$inboundSchema: z.ZodType<
   error: z.nullable(z.record(z.any())),
   artifact_file_ids: z.array(z.string()),
   metadata: z.record(z.string()),
+  agent_name: z.nullable(z.string()),
+  agent_version: z.nullable(z.string()),
+  agent_effort: z.nullable(z.string()),
+  cost_usd: z.nullable(z.number()),
   created_at: z.number().int(),
   started_at: z.nullable(z.number().int()),
   completed_at: z.nullable(z.number().int()),
@@ -526,6 +546,10 @@ export const RetryFailedEvalRunResponseBody$inboundSchema: z.ZodType<
     "embedding_model": "embeddingModel",
     "request_counts": "requestCounts",
     "artifact_file_ids": "artifactFileIds",
+    "agent_name": "agentName",
+    "agent_version": "agentVersion",
+    "agent_effort": "agentEffort",
+    "cost_usd": "costUsd",
     "created_at": "createdAt",
     "started_at": "startedAt",
     "completed_at": "completedAt",
@@ -553,6 +577,10 @@ export type RetryFailedEvalRunResponseBody$Outbound = {
   error: { [k: string]: any } | null;
   artifact_file_ids: Array<string>;
   metadata: { [k: string]: string };
+  agent_name: string | null;
+  agent_version: string | null;
+  agent_effort: string | null;
+  cost_usd: number | null;
   created_at: number;
   started_at: number | null;
   completed_at: number | null;
@@ -584,6 +612,10 @@ export const RetryFailedEvalRunResponseBody$outboundSchema: z.ZodType<
   error: z.nullable(z.record(z.any())),
   artifactFileIds: z.array(z.string()),
   metadata: z.record(z.string()),
+  agentName: z.nullable(z.string()),
+  agentVersion: z.nullable(z.string()),
+  agentEffort: z.nullable(z.string()),
+  costUsd: z.nullable(z.number()),
   createdAt: z.number().int(),
   startedAt: z.nullable(z.number().int()),
   completedAt: z.nullable(z.number().int()),
@@ -601,6 +633,10 @@ export const RetryFailedEvalRunResponseBody$outboundSchema: z.ZodType<
     embeddingModel: "embedding_model",
     requestCounts: "request_counts",
     artifactFileIds: "artifact_file_ids",
+    agentName: "agent_name",
+    agentVersion: "agent_version",
+    agentEffort: "agent_effort",
+    costUsd: "cost_usd",
     createdAt: "created_at",
     startedAt: "started_at",
     completedAt: "completed_at",

package/src/models/operations/uploadevalsampletrajectory.ts

@@ -0,0 +1,98 @@
+/*
+ * Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT.
+ */
+
+import * as z from "zod/v3";
+import { remap as remap$ } from "../../lib/primitives.js";
+import { safeParse } from "../../lib/schemas.js";
+import { Result as SafeParseResult } from "../../types/fp.js";
+import * as components from "../components/index.js";
+import { SDKValidationError } from "../errors/sdkvalidationerror.js";
+
+export type UploadEvalSampleTrajectoryRequest = {
+  runId: string;
+  sampleIndex: number;
+  taskId?: string | undefined;
+  model?: string | undefined;
+  /**
+   * Optional external end-user identifier forwarded by the API gateway.
+   */
+  xOnBehalfOf?: string | undefined;
+  uploadEvalSampleTrajectoryRequest:
+    components.UploadEvalSampleTrajectoryRequest;
+};
+
+/** @internal */
+export const UploadEvalSampleTrajectoryRequest$inboundSchema: z.ZodType<
+  UploadEvalSampleTrajectoryRequest,
+  z.ZodTypeDef,
+  unknown
+> = z.object({
+  run_id: z.string(),
+  sample_index: z.number().int(),
+  task_id: z.string().optional(),
+  model: z.string().optional(),
+  "X-On-Behalf-Of": z.string().optional(),
+  UploadEvalSampleTrajectoryRequest:
+    components.UploadEvalSampleTrajectoryRequest$inboundSchema,
+}).transform((v) => {
+  return remap$(v, {
+    "run_id": "runId",
+    "sample_index": "sampleIndex",
+    "task_id": "taskId",
+    "X-On-Behalf-Of": "xOnBehalfOf",
+    "UploadEvalSampleTrajectoryRequest": "uploadEvalSampleTrajectoryRequest",
+  });
+});
+/** @internal */
+export type UploadEvalSampleTrajectoryRequest$Outbound = {
+  run_id: string;
+  sample_index: number;
+  task_id?: string | undefined;
+  model?: string | undefined;
+  "X-On-Behalf-Of"?: string | undefined;
+  UploadEvalSampleTrajectoryRequest:
+    components.UploadEvalSampleTrajectoryRequest$Outbound;
+};
+
+/** @internal */
+export const UploadEvalSampleTrajectoryRequest$outboundSchema: z.ZodType<
+  UploadEvalSampleTrajectoryRequest$Outbound,
+  z.ZodTypeDef,
+  UploadEvalSampleTrajectoryRequest
+> = z.object({
+  runId: z.string(),
+  sampleIndex: z.number().int(),
+  taskId: z.string().optional(),
+  model: z.string().optional(),
+  xOnBehalfOf: z.string().optional(),
+  uploadEvalSampleTrajectoryRequest:
+    components.UploadEvalSampleTrajectoryRequest$outboundSchema,
+}).transform((v) => {
+  return remap$(v, {
+    runId: "run_id",
+    sampleIndex: "sample_index",
+    taskId: "task_id",
+    xOnBehalfOf: "X-On-Behalf-Of",
+    uploadEvalSampleTrajectoryRequest: "UploadEvalSampleTrajectoryRequest",
+  });
+});
+
+export function uploadEvalSampleTrajectoryRequestToJSON(
+  uploadEvalSampleTrajectoryRequest: UploadEvalSampleTrajectoryRequest,
+): string {
+  return JSON.stringify(
+    UploadEvalSampleTrajectoryRequest$outboundSchema.parse(
+      uploadEvalSampleTrajectoryRequest,
+    ),
+  );
+}
+export function uploadEvalSampleTrajectoryRequestFromJSON(
+  jsonString: string,
+): SafeParseResult<UploadEvalSampleTrajectoryRequest, SDKValidationError> {
+  return safeParse(
+    jsonString,
+    (x) => UploadEvalSampleTrajectoryRequest$inboundSchema.parse(JSON.parse(x)),
+    `Failed to parse 'UploadEvalSampleTrajectoryRequest' from JSON`,
+  );
+}

package/src/react-query/index.ts

@@ -163,6 +163,7 @@ export * from "./llmConversationsListItems.js";
 export * from "./llmConversationsUpdate.js";
 export * from "./llmEmbeddingsEmbed.js";
 export * from "./llmEmbeddingsListModels.js";
+export * from "./llmEvalsAppendAgentTrials.js";
 export * from "./llmEvalsCancelRun.js";
 export * from "./llmEvalsCreateRun.js";
 export * from "./llmEvalsCreateSchedule.js";
@@ -173,10 +174,14 @@ export * from "./llmEvalsDeleteSchedule.js";
 export * from "./llmEvalsDeleteSuite.js";
 export * from "./llmEvalsGetArtifacts.js";
 export * from "./llmEvalsGetRun.js";
+export * from "./llmEvalsGetRunOverview.js";
 export * from "./llmEvalsGetSampleAudio.js";
+export * from "./llmEvalsGetSampleTrajectory.js";
 export * from "./llmEvalsGetSchedule.js";
 export * from "./llmEvalsGetSuite.js";
+export * from "./llmEvalsGetSuiteLeaderboard.js";
 export * from "./llmEvalsGetSuiteVersion.js";
+export * from "./llmEvalsImportAgentRun.js";
 export * from "./llmEvalsImportHistoricalResults.js";
 export * from "./llmEvalsListRuns.js";
 export * from "./llmEvalsListSamples.js";
@@ -189,6 +194,7 @@ export * from "./llmEvalsRerunFailedSamples.js";
 export * from "./llmEvalsRetryFailedRun.js";
 export * from "./llmEvalsTriggerSchedule.js";
 export * from "./llmEvalsUpdateSchedule.js";
+export * from "./llmEvalsUploadSampleTrajectory.js";
 export * from "./llmExtractCreateSchema.js";
 export * from "./llmExtractDeleteSchema.js";
 export * from "./llmExtractExtract.js";

package/src/react-query/llmEvalsAppendAgentTrials.ts

@@ -0,0 +1,109 @@
+/*
+ * Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT.
+ */
+
+import {
+  MutationKey,
+  useMutation,
+  UseMutationResult,
+} from "@tanstack/react-query";
+import { SDKCore } from "../core.js";
+import { llmEvalsAppendAgentTrials } from "../funcs/llmEvalsAppendAgentTrials.js";
+import { combineSignals } from "../lib/primitives.js";
+import { RequestOptions } from "../lib/sdks.js";
+import {
+  ConnectionError,
+  InvalidRequestError,
+  RequestAbortedError,
+  RequestTimeoutError,
+  UnexpectedClientError,
+} from "../models/errors/httpclienterrors.js";
+import { ResponseValidationError } from "../models/errors/responsevalidationerror.js";
+import { SDKError } from "../models/errors/sdkerror.js";
+import { SDKValidationError } from "../models/errors/sdkvalidationerror.js";
+import * as operations from "../models/operations/index.js";
+import { unwrapAsync } from "../types/fp.js";
+import { useSDKContext } from "./_context.js";
+import { MutationHookOptions } from "./_types.js";
+
+export type LlmEvalsAppendAgentTrialsMutationVariables = {
+  request: operations.AppendAgentEvalTrialsRequest;
+  options?: RequestOptions;
+};
+
+export type LlmEvalsAppendAgentTrialsMutationData =
+  operations.AppendAgentEvalTrialsResponseBody;
+
+export type LlmEvalsAppendAgentTrialsMutationError =
+  | SDKError
+  | ResponseValidationError
+  | ConnectionError
+  | RequestAbortedError
+  | RequestTimeoutError
+  | InvalidRequestError
+  | UnexpectedClientError
+  | SDKValidationError;
+
+/**
+ * Append trials to an open coding-agent run
+ *
+ * @remarks
+ * Adds finished trials to a run opened with `finalize: false`, so a job started from MKA1 can be watched while it runs instead of appearing complete out of nowhere at the end. Each trial pins its own `sample_index` and upserts on (task, model, sample_index): a harness cannot tell a timeout from a lost response, so re-sending a batch is safe and replaces rather than duplicates. The whole batch and its aggregate recompute land in one transaction, serialized per run. Counts, metrics and cost are recomputed from the stored rows on every call, never accumulated from the request, so a replayed batch cannot double them. Send `finalize: true` (usually with an empty `trials`) to close the run — until then it stays `in_progress` and off the leaderboards, which only count completed runs. Appending to an already-completed or cancelled run is rejected: that record is finished, and rewriting it would silently move a number someone may have already read.
+ */
+export function useLlmEvalsAppendAgentTrialsMutation(
+  options?: MutationHookOptions<
+    LlmEvalsAppendAgentTrialsMutationData,
+    LlmEvalsAppendAgentTrialsMutationError,
+    LlmEvalsAppendAgentTrialsMutationVariables
+  >,
+): UseMutationResult<
+  LlmEvalsAppendAgentTrialsMutationData,
+  LlmEvalsAppendAgentTrialsMutationError,
+  LlmEvalsAppendAgentTrialsMutationVariables
+> {
+  const client = useSDKContext();
+  return useMutation({
+    ...buildLlmEvalsAppendAgentTrialsMutation(client, options),
+    ...options,
+  });
+}
+
+export function mutationKeyLlmEvalsAppendAgentTrials(): MutationKey {
+  return ["@meetkai/mka1", "evals", "appendAgentTrials"];
+}
+
+export function buildLlmEvalsAppendAgentTrialsMutation(
+  client$: SDKCore,
+  hookOptions?: RequestOptions,
+): {
+  mutationKey: MutationKey;
+  mutationFn: (
+    variables: LlmEvalsAppendAgentTrialsMutationVariables,
+  ) => Promise<LlmEvalsAppendAgentTrialsMutationData>;
+} {
+  return {
+    mutationKey: mutationKeyLlmEvalsAppendAgentTrials(),
+    mutationFn: function llmEvalsAppendAgentTrialsMutationFn({
+      request,
+      options,
+    }): Promise<LlmEvalsAppendAgentTrialsMutationData> {
+      const mergedOptions = {
+        ...hookOptions,
+        ...options,
+        fetchOptions: {
+          ...hookOptions?.fetchOptions,
+          ...options?.fetchOptions,
+          signal: combineSignals(
+            hookOptions?.fetchOptions?.signal,
+            options?.fetchOptions?.signal,
+          ),
+        },
+      };
+      return unwrapAsync(llmEvalsAppendAgentTrials(
+        client$,
+        request,
+        mergedOptions,
+      ));
+    },
+  };
+}