* 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>
52 lines
2.2 KiB
TypeScript
52 lines
2.2 KiB
TypeScript
import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest';
|
|
|
|
describe('resolveEvalModel', () => {
|
|
const ORIG_ENV = process.env;
|
|
|
|
beforeEach(() => {
|
|
process.env = { ...ORIG_ENV };
|
|
vi.resetModules();
|
|
});
|
|
|
|
afterEach(() => {
|
|
process.env = ORIG_ENV;
|
|
vi.restoreAllMocks();
|
|
});
|
|
|
|
it('throws a helpful error when env var is unset and no fallback is given', async () => {
|
|
delete process.env.EVAL_FOO_MODEL;
|
|
vi.doMock('@/lib/server/resolve-model', () => ({
|
|
resolveModel: vi.fn(),
|
|
}));
|
|
const { resolveEvalModel } = await import('@/eval/shared/resolve-model');
|
|
await expect(resolveEvalModel('EVAL_FOO_MODEL')).rejects.toThrow(/EVAL_FOO_MODEL/);
|
|
});
|
|
|
|
it('uses the env var when set', async () => {
|
|
process.env.EVAL_FOO_MODEL = 'openai:gpt-4.1';
|
|
const resolveModel = vi.fn().mockResolvedValue({ model: 'resolved', modelInfo: {} });
|
|
vi.doMock('@/lib/server/resolve-model', () => ({ resolveModel }));
|
|
const { resolveEvalModel } = await import('@/eval/shared/resolve-model');
|
|
await resolveEvalModel('EVAL_FOO_MODEL');
|
|
expect(resolveModel).toHaveBeenCalledWith({ modelString: 'openai:gpt-4.1' });
|
|
});
|
|
|
|
it('uses the explicit fallback when env var is unset', async () => {
|
|
delete process.env.EVAL_FOO_MODEL;
|
|
const resolveModel = vi.fn().mockResolvedValue({ model: 'resolved', modelInfo: {} });
|
|
vi.doMock('@/lib/server/resolve-model', () => ({ resolveModel }));
|
|
const { resolveEvalModel } = await import('@/eval/shared/resolve-model');
|
|
await resolveEvalModel('EVAL_FOO_MODEL', 'google:gemini-2.5-flash');
|
|
expect(resolveModel).toHaveBeenCalledWith({ modelString: 'google:gemini-2.5-flash' });
|
|
});
|
|
|
|
it('env var takes precedence over fallback', async () => {
|
|
process.env.EVAL_FOO_MODEL = 'anthropic:claude-haiku-4-5';
|
|
const resolveModel = vi.fn().mockResolvedValue({ model: 'resolved', modelInfo: {} });
|
|
vi.doMock('@/lib/server/resolve-model', () => ({ resolveModel }));
|
|
const { resolveEvalModel } = await import('@/eval/shared/resolve-model');
|
|
await resolveEvalModel('EVAL_FOO_MODEL', 'google:gemini-2.5-flash');
|
|
expect(resolveModel).toHaveBeenCalledWith({ modelString: 'anthropic:claude-haiku-4-5' });
|
|
});
|
|
});
|