/**
 * V3 CLI Performance Capability Benchmark
 *
 * Runs a small verifiable-answer corpus through the Anthropic API and reports
 * pass-rate, latency, and cost. Closes the capability-evaluation gap that
 * `performance benchmark --suite agent` does NOT cover — that suite measures
 * the agent control plane (router, memory, hooks) without LLM calls; this
 * subcommand measures the actual model's ability to solve agent-style tasks.
 *
 * Features:
 *   - Parallel execution with configurable concurrency
 *   - Multi-model comparison in a single run (`--models a,b,c`)
 *   - Per-task max-tokens overrides (declared in the fixture)
 *   - Configurable corpus via `--questions <path>`
 *
 * Inspired by GAIA / SWE-bench / GSM8K but text-only and scoreable via
 * substring / exact match — no web browsing, no file attachments, no
 * Hugging Face dataset download.
 *
 * API key resolution (in order):
 *   1. $ANTHROPIC_API_KEY env var
 *   2. `gcloud secrets versions access latest --secret=ANTHROPIC_API_KEY`
 *   3. Fail with a clear error
 *
 * Refs: #2156 (Dream Cycle 2026-05-27 capabilities scan)
 */
import type { Command } from '../types.js';
declare const capabilityCommand: Command;
export default capabilityCommand;
//# sourceMappingURL=performance-capability.d.ts.map