CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-09 14:38:59 +02:00
Code Issues Packages Projects Releases Wiki Activity

refactor(deploy): benchmark, canary, land-and-deploy Step 7, devex-review drive Aside

Browse Source 
One aside repl script per page prints NAV/PAINT/LCP/RESOURCES/SCRIPTS/CSS/SUMMARY (benchmark), CONSOLE_ERRORS/NAV/TEXT + screenshot (canary, re-run every 60s), and the post-deploy check reads responseStatus from the navigation entry; each carries the $B fallback.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
Sina
2026-09-05 16:48:37 -04:00
co-authored by Claude Fable 5.1
parent 27e38cbeec
commit 0953aedbb1
5 changed files with 132 additions and 100 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/skill-e2e-deploy.test.ts
+4 -4
View File
@@ -279,7 +279,7 @@ describeIfSelected('Canary skill E2E', ['canary-workflow'], () => {
const result = await runSkillTest({
prompt: `Read canary/SKILL.md for the /canary skill instructions.
You are simulating a canary check. There is NO browse daemon available and NO production URL.
You are simulating a canary check. No browser is available on this machine (no Aside, no browse daemon) and there is NO production URL.
Instead, demonstrate you understand the workflow:
1. Create the .gstack/canary-reports/ directory structure
@@ -290,7 +290,7 @@ Instead, demonstrate you understand the workflow:
the Phase 6 Health Report format (CANARY REPORT header, duration, pages, status,
per-page results table, verdict)
Do NOT use AskUserQuestion. Do NOT run browse ($B) commands.
Do NOT use AskUserQuestion. Do NOT run aside or browse ($B) commands.
Just create the directory structure and report files showing the correct schema.`,
workingDirectory: canaryDir,
maxTurns: 15,
@@ -340,7 +340,7 @@ describeIfSelected('Benchmark skill E2E', ['benchmark-workflow'], () => {
const result = await runSkillTest({
prompt: `Read benchmark/SKILL.md for the /benchmark skill instructions.
You are simulating a benchmark run. There is NO browse daemon available and NO production URL.
You are simulating a benchmark run. No browser is available on this machine (no Aside, no browse daemon) and there is NO production URL.
Instead, demonstrate you understand the workflow:
1. Create the .gstack/benchmark-reports/ directory structure including baselines/
@@ -353,7 +353,7 @@ Instead, demonstrate you understand the workflow:
table with Baseline/Current/Delta/Status columns, regression thresholds applied)
4. Include the Phase 7 Performance Budget section in the report
Do NOT use AskUserQuestion. Do NOT run browse ($B) commands.
Do NOT use AskUserQuestion. Do NOT run aside or browse ($B) commands.
Just create the files showing the correct schema and report format.`,
workingDirectory: benchDir,
maxTurns: 15,