Files
gstack/lib/model-benchmark/providers/gemini.ts
T
SinabinaandClaude Opus 4.8 7f4574e1d5 refactor: capture plain-text CLI output, drop hardcoded provider schemas
The adapters parsed each vendor's proprietary JSON stream (Claude json,
Codex JSONL, Gemini stream-json) to extract tokens/tool-calls, and a
per-model pricing table turned tokens into cost. That coupling was the
brittle hardcoding GStack 2 exists to avoid — it broke every time a vendor
reshuffled its output, and it duplicated what any tool that instruments the
real model call already does. Braintrust owns scoring; it can't see a CLI
subprocess's tokens anyway, so computing cost ourselves meant maintaining
both a parser and a price table forever.

Now each adapter runs the CLI in plain-text mode and returns stdout. Scoring
is unchanged (Braintrust reads the text). RunResult drops tokens/toolCalls;
the comparison table drops the Tokens/Cost columns. Deletes pricing.ts, all
three JSON parsers, and the Gemini stream-schema parser + its test. Gemini
auth detection (env/OAuth/.env) is kept — that's not schema parsing.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-21 14:34:57 -07:00

75 lines
3.3 KiB
TypeScript

import type { ProviderAdapter, RunOpts, RunResult, AvailabilityCheck, RunError } from './types';
import { execFileSync, spawnSync } from 'child_process';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
/**
* Gemini adapter — wraps the `gemini` CLI in plain-text mode.
*
* Auth comes from its OAuth files, ~/.gemini/.env, or GOOGLE_API_KEY/GEMINI_API_KEY.
* We capture stdout as the answer and do not parse Gemini's stream-json schema —
* that coupling broke every time Gemini reshuffled its event shape.
*/
export class GeminiAdapter implements ProviderAdapter {
readonly name = 'gemini';
readonly family = 'gemini' as const;
async available(): Promise<AvailabilityCheck> {
const res = spawnSync('sh', ['-c', 'command -v gemini'], { timeout: 2000 });
if (res.status !== 0) {
return { ok: false, reason: 'gemini CLI not found on PATH. Install per https://github.com/google-gemini/gemini-cli' };
}
const legacyCfgDir = path.join(os.homedir(), '.config', 'gemini');
const newCfgDir = path.join(os.homedir(), '.gemini');
const newOauth = path.join(newCfgDir, 'oauth_creds.json');
const geminiEnv = path.join(newCfgDir, '.env');
const hasCfg = fs.existsSync(legacyCfgDir) || fs.existsSync(newOauth);
const hasEnvFileKey = fs.existsSync(geminiEnv)
&& /^(?:GOOGLE_API_KEY|GEMINI_API_KEY)\s*=/m.test(fs.readFileSync(geminiEnv, 'utf-8'));
const hasKey = !!process.env.GOOGLE_API_KEY || !!process.env.GEMINI_API_KEY || hasEnvFileKey;
if (!hasCfg && !hasKey) {
return { ok: false, reason: 'No Gemini auth found. Log in via `gemini login` or export GOOGLE_API_KEY/GEMINI_API_KEY.' };
}
return { ok: true };
}
async run(opts: RunOpts): Promise<RunResult> {
const start = Date.now();
// --skip-trust lets the CLI run in disposable/non-git benchmark workdirs.
// Plain -p is non-interactive; benchmark prompts are reasoning tasks, not file
// ops, and the workdir is a throwaway temp dir.
const args = ['-p', opts.prompt, '--skip-trust'];
if (opts.model) args.push('--model', opts.model);
if (opts.extraArgs) args.push(...opts.extraArgs);
try {
const out = execFileSync('gemini', args, {
cwd: opts.workdir,
timeout: opts.timeoutMs,
encoding: 'utf-8',
maxBuffer: 32 * 1024 * 1024,
});
return {
output: out.trim(),
durationMs: Date.now() - start,
modelUsed: opts.model ?? 'gemini',
};
} catch (err: unknown) {
return this.errorResult(Date.now() - start, err, opts.model);
}
}
private errorResult(durationMs: number, err: unknown, model?: string): RunResult {
const e = err as { code?: string; stderr?: Buffer; signal?: string; message?: string };
const stderr = e.stderr?.toString() ?? '';
let code: RunError;
if (e.signal === 'SIGTERM' || e.code === 'ETIMEDOUT') code = 'timeout';
else if (/unauthorized|auth|login|api key/i.test(stderr)) code = 'auth';
else if (/rate[- ]?limit|429|quota/i.test(stderr)) code = 'rate_limit';
else code = 'unknown';
const reason = code === 'timeout' ? 'exceeded timeout' : (e.message ?? stderr ?? 'unknown').slice(0, 400);
return { output: '', durationMs, modelUsed: model ?? 'gemini', error: { code, reason } };
}
}