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>
This commit is contained in:
Garry Tan
2026-09-09 05:08:30 +00:00
co-authored by OpenAI Codex
parent eb4fd65ed3
commit 2e624adf20
9 changed files with 182 additions and 176 deletions
+1 -1
View File
@@ -177,7 +177,7 @@ describe('gstack-retro-metrics contract', () => {
expect(tmpl).toContain('".claude/skills/gstack/bin/gstack-retro-metrics"');
expect(tmpl).toContain('--base "<default>" --since "<since>"');
expect(tmpl).toContain(
'RETRO_METRICS: unavailable — stale install (compute metrics manually from the steps below)',
'RETRO_METRICS: unavailable — stale install (read the helper source for manual computation)',
);
// Degraded-mode prose keys off the proto handshake.
expect(tmpl).toContain('RETRO_METRICS_PROTO: 1');