runEvalSet (runner.ts)

Executes evaluation test cases against targets with configurable concurrency, scoring, progress tracking, and cost/token metrics collection.

// Source: https://github.com/open-multi-agent/open-multi-agent | License: MIT | Copyright Shenzhen YuanASI Technology Co., Ltd. and open-multi-agent contributors
// Provided via justclaw.it.com; keep this notice with the code.
import { classifyRunFailure } from '../observability/status.js'
import type { RunCostSummary, StoredRun, TraceStore } from '../observability/store.js'
import type {
  AgentRunResult,
  ConsensusResult,
  RunIdentity,
  TeamRunResult,
  TokenUsage,
  TraceAttributeValue,
} from '../types.js'
import { redactSensitiveText } from '../utils/redaction.js'
import type { EvalCase } from './evalcase.js'
import type { EvalSet } from './evalset.js'
import { aggregateEvalRecords } from './report.js'
import type { EvalRunReport } from './report.js'
import type { EvalRecord } fro

... (truncated -- full source via MCP)