* feat(eval): add resolveEvalModel helper with fail-fast Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(eval): add createRunDir helper with path sanitization Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(eval): add markdown report helpers * refactor(eval): move language test cases under eval/outline-language * feat(eval): add outline-language types * feat(eval): add outline-language LLM judge * feat(eval): add outline-language reporter * feat(eval): add outline-language runner entry * chore(eval): add eval:outline-language pnpm script * refactor(eval): adopt shared createRunDir and drop gpt-4o fallbacks in whiteboard runner * refactor(eval): drop redundant non-null assertions after narrowing Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor(eval): remove SCORER_MODEL_DEFAULT hardcoded gpt-4o fallback * chore(eval): delete tests/generation and clean up vitest/gitignore config * docs(eval): explain why outline-language runner pre-validates env vars Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(eval): escape pipe chars in markdown summary table cells LLM judge output may contain | which breaks GFM table rendering. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: 杨慎 <117187635+cosarah@users.noreply.github.com>
19 lines
660 B
TypeScript
19 lines
660 B
TypeScript
import { resolveModel } from '@/lib/server/resolve-model';
|
|
|
|
/**
|
|
* Resolve a model for an eval runner. Reads `process.env[envVar]`, falls back
|
|
* to `fallback` if provided, and throws a clear error if neither is set.
|
|
*
|
|
* Never introduces a hardcoded default model string — evals must be explicit
|
|
* about what they measure.
|
|
*/
|
|
export async function resolveEvalModel(envVar: string, fallback?: string) {
|
|
const modelString = process.env[envVar] || fallback;
|
|
if (!modelString) {
|
|
throw new Error(
|
|
`Eval model not configured: set ${envVar} in the environment (or pass an explicit fallback).`,
|
|
);
|
|
}
|
|
return resolveModel({ modelString });
|
|
}
|