import type { ServerStats } from "./llama-server";

export interface SimplebenchOptions { model?: string; allModels: boolean; writeArtifact: boolean; thinkingMax?: boolean; codingLite?: boolean; testAll?: boolean; researchLive?: boolean; llamaServer?: boolean; llamagputop?: boolean; tag?: string; threePTest?: boolean; sequence?: boolean | string; }
export interface RequestMetrics { requestCount: number; retryCount: number; wallTimeMs: number; timeToAnswerMs: number; timeToFirstTokenMs: number | null; startedAt: string | null; finishedAt: string | null; inputTokens: number | null; outputTokens: number | null; totalTokens: number | null; outputTokensPerSecond: number | null; toolCalls: Array<{ name: string; arguments?: unknown }>; }
export interface TestRecord { id: string; kind: "reasoning" | "instructions" | "tools" | "coding" | "research-grounded" | "research-live"; category?: string; prompt: string; response: string | null; expectedAnswer?: string | string[]; extractedAnswer?: string; score: string; passed: boolean; error: string | null; metrics: RequestMetrics; coding?: { publicPassed: boolean; hiddenPassed: boolean; verifiedAfterEdit: boolean; unrelatedFiles: string[]; toolCalls: number; turns: number; efficiency?: "STRONG" | "MODERATE" | "WEAK" | "FAIL"; }; research?: { toolCalls: string[]; files: string[]; }; }
export interface RunArtifact { schemaVersion: 1; benchmark: { name: "opl-simplebench"; suite?: "baseline" | "coding-lite" | "test-all"; tag?: string; model: string; provider: string; providerKind: string; thinking: { requested: "default" | "max"; effective: "provider-default" | "openai-reasoning-effort" | "pi-bedrock-reasoning"; level: "max" | null; modelMetadataSource: "active-context" | "scoped-model" | null; }; startedAt: string; finishedAt: string; wallTimeMs: number; artifactEnabled: boolean; }; tests: TestRecord[]; summary: Record<string, unknown> & { serverStats?: ServerStats }; }