CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-07-05 23:57:53 +02:00
Code Issues Packages Projects Releases Wiki Activity

test(auq): default GSTACK_HEADLESS=1 in eval/E2E runners

Browse Source 
Headless harness runs classify as headless (BLOCK on AUQ failure rather than
emit a prose question no one reads). SDK runner uses ambient mutation, not the
Options.env object, to avoid breaking the SDK auth pipeline. Interactive-path
suites opt out by overriding the env per-run.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-06-07 17:51:22 -07:00
parent c475d73b34
commit a4c39380bc
3 changed files with 16 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/helpers/agent-sdk-runner.ts
+8
View File
@@ -300,6 +300,14 @@ export async function runAgentSdkTest(
const queryImpl: QueryProvider = opts.queryProvider ?? query;
const model = opts.model ?? 'claude-opus-4-7';
// Default GSTACK_HEADLESS=1 so SDK-driven eval/E2E runs classify as headless: an
// AskUserQuestion failure BLOCKs instead of emitting a prose question no human can
// answer. Set ambiently (the SDK child inherits process.env) rather than via
// sdkOpts.env — passing an env object to the SDK breaks its auth pipeline (see
// CLAUDE.md). A suite testing the interactive prose-fallback path sets
// process.env.GSTACK_HEADLESS='' before calling.
if (process.env.GSTACK_HEADLESS === undefined) process.env.GSTACK_HEADLESS = '1';
let attempt = 0;
let lastErr: unknown = null;