CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-15 09:25:28 +02:00
Code Issues Packages Projects Releases Wiki Activity

v1.84.1.0 fix: default Codex and Claude to frontier models (#2835)

Browse Source 
* 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>
This commit is contained in:
Garry Tan
2026-09-09 08:57:21 -07:00
committed by GitHub
co-authored by OpenAI Codex
parent c8f0c4e368
commit 71f6048e8a
141 changed files with 2678 additions and 1750 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/helpers/providers/claude.ts
+10 -8
View File
@@ -5,6 +5,7 @@ import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
import { resolveClaudeCommand } from '../../../lib/claude-bin';
import { resolveEvalModel } from '../../../lib/eval-model';
/**
* Claude adapter — wraps the `claude` CLI via claude -p.
@@ -60,8 +61,9 @@ export class ClaudeAdapter implements ProviderAdapter {
if (!resolved) {
throw new Error('claude CLI not resolvable (set GSTACK_CLAUDE_BIN or install)');
}
const model = opts.model ?? process.env.EVALS_MODEL ?? resolveEvalModel('capture');
const args = [...resolved.argsPrefix, '-p', '--output-format', 'json'];
if (opts.model) args.push('--model', opts.model);
args.push('--model', model);
if (opts.extraArgs) args.push(...opts.extraArgs);
try {
@@ -81,27 +83,27 @@ export class ClaudeAdapter implements ProviderAdapter {
tokens: parsed.tokens,
durationMs: Date.now() - start,
toolCalls: parsed.toolCalls,
modelUsed: parsed.modelUsed || opts.model || 'claude-opus-4-7',
modelUsed: parsed.modelUsed || model,
};
} catch (err: unknown) {
const durationMs = Date.now() - start;
const e = err as { code?: string; stderr?: Buffer; signal?: string; message?: string };
const stderr = e.stderr?.toString() ?? '';
if (e.signal === 'SIGTERM' || e.code === 'ETIMEDOUT') {
return this.emptyResult(durationMs, { code: 'timeout', reason: `exceeded ${opts.timeoutMs}ms` }, opts.model);
return this.emptyResult(durationMs, { code: 'timeout', reason: `exceeded ${opts.timeoutMs}ms` }, model);
}
if (/unauthorized|auth|login/i.test(stderr)) {
return this.emptyResult(durationMs, { code: 'auth', reason: stderr.slice(0, 400) }, opts.model);
return this.emptyResult(durationMs, { code: 'auth', reason: stderr.slice(0, 400) }, model);
}
if (/rate[- ]?limit|429/i.test(stderr)) {
return this.emptyResult(durationMs, { code: 'rate_limit', reason: stderr.slice(0, 400) }, opts.model);
return this.emptyResult(durationMs, { code: 'rate_limit', reason: stderr.slice(0, 400) }, model);
}
return this.emptyResult(durationMs, { code: 'unknown', reason: (e.message ?? stderr ?? 'unknown').slice(0, 400) }, opts.model);
return this.emptyResult(durationMs, { code: 'unknown', reason: (e.message ?? stderr ?? 'unknown').slice(0, 400) }, model);
}
}
estimateCost(tokens: { input: number; output: number; cached?: number }, model?: string): number {
return estimateCostUsd(tokens, model ?? 'claude-opus-4-7');
return estimateCostUsd(tokens, model ?? resolveEvalModel('capture'));
}
/**
@@ -137,7 +139,7 @@ export class ClaudeAdapter implements ProviderAdapter {
tokens: { input: 0, output: 0 },
durationMs,
toolCalls: 0,
modelUsed: model ?? 'claude-opus-4-7',
modelUsed: model ?? resolveEvalModel('capture'),
error,
};
}
test/helpers/providers/gpt.ts
+10 -9
View File
@@ -4,6 +4,7 @@ import { execFileSync, spawnSync } from 'child_process';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
import { CODEX_FRONTIER_MODEL } from '../../../scripts/resolvers/constants';
/**
* GPT adapter — wraps the OpenAI `codex` CLI (codex exec with --json output).
@@ -36,8 +37,8 @@ export class GptAdapter implements ProviderAdapter {
// often run in temp dirs / non-git paths), so the read-only sandbox is now
// the only boundary preventing codex from mutating the workdir. If you ever
// remove `-s read-only`, drop `--skip-git-repo-check` too.
const args = ['exec', opts.prompt, '-C', opts.workdir, '-s', 'read-only', '--skip-git-repo-check', '--json'];
if (opts.model) args.push('-m', opts.model);
const model = opts.model ?? process.env.GSTACK_CODEX_MODEL ?? CODEX_FRONTIER_MODEL;
const args = ['exec', opts.prompt, '-C', opts.workdir, '-s', 'read-only', '--skip-git-repo-check', '--json', '-m', model];
if (opts.extraArgs) args.push(...opts.extraArgs);
try {
@@ -53,27 +54,27 @@ export class GptAdapter implements ProviderAdapter {
tokens: parsed.tokens,
durationMs: Date.now() - start,
toolCalls: parsed.toolCalls,
modelUsed: parsed.modelUsed || opts.model || 'gpt-5.4',
modelUsed: parsed.modelUsed || model,
};
} catch (err: unknown) {
const durationMs = Date.now() - start;
const e = err as { code?: string; stderr?: Buffer; signal?: string; message?: string };
const stderr = e.stderr?.toString() ?? '';
if (e.signal === 'SIGTERM' || e.code === 'ETIMEDOUT') {
return this.emptyResult(durationMs, { code: 'timeout', reason: `exceeded ${opts.timeoutMs}ms` }, opts.model);
return this.emptyResult(durationMs, { code: 'timeout', reason: `exceeded ${opts.timeoutMs}ms` }, model);
}
if (/unauthorized|auth|login/i.test(stderr)) {
return this.emptyResult(durationMs, { code: 'auth', reason: stderr.slice(0, 400) }, opts.model);
return this.emptyResult(durationMs, { code: 'auth', reason: stderr.slice(0, 400) }, model);
}
if (/rate[- ]?limit|429/i.test(stderr)) {
return this.emptyResult(durationMs, { code: 'rate_limit', reason: stderr.slice(0, 400) }, opts.model);
return this.emptyResult(durationMs, { code: 'rate_limit', reason: stderr.slice(0, 400) }, model);
}
return this.emptyResult(durationMs, { code: 'unknown', reason: (e.message ?? stderr ?? 'unknown').slice(0, 400) }, opts.model);
return this.emptyResult(durationMs, { code: 'unknown', reason: (e.message ?? stderr ?? 'unknown').slice(0, 400) }, model);
}
}
estimateCost(tokens: { input: number; output: number; cached?: number }, model?: string): number {
return estimateCostUsd(tokens, model ?? 'gpt-5.4');
return estimateCostUsd(tokens, model ?? CODEX_FRONTIER_MODEL);
}
/**
@@ -120,7 +121,7 @@ export class GptAdapter implements ProviderAdapter {
tokens: { input: 0, output: 0 },
durationMs,
toolCalls: 0,
modelUsed: model ?? 'gpt-5.4',
modelUsed: model ?? CODEX_FRONTIER_MODEL,
error,
};
}