RomanNum3ral
/
gstack
mirror of https://github.com/garrytan/gstack.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

evals: demote 4 expensive posture tests to periodic (D2a) 

design-consultation-research ($0.91/304s) and -preview ($0.89/481s) —
the two most expensive gate tests — plus office-hours-forcing-energy
(LLM-judge posture score; its sibling was already demoted) and
cso-full-audit (250s/$0.57; the targeted cso tests stay gate). Saves
~$8-12 and 10-15 min per gate run. The plan-*-finding-floor tests stay
gate deliberately: cheap insurance on the most-edited skill surface.
Housing files have no whole-file self-gates, so the runtime E2E_TIERS
filter handles both tiers; tier-alignment tripwire green.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan 2026-08-15 09:14:12 -07:00
parent c9df02877c
commit 2ac8aac89c
No known key found for this signature in database
GPG Key ID: C1F69E85C74EFE1D
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
test/helpers/touchfiles-data.ts
View File

@ -499,7 +499,7 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
// GBrain CLI round-trip — periodic per Voyage embedding cost (~$0.001/run)
// and external-API-dependency (skips cleanly if VOYAGE_API_KEY unset).
'gbrain-roundtrip-local': 'periodic',
'office-hours-forcing-energy': 'gate', // V1.1 mode-posture regression gate (Sonnet generator)
'office-hours-forcing-energy': 'periodic', // D2a demotion 2026-08: posture score, periodic-grade signal (sibling precedent at office-hours-tone)
// 'office-hours-builder-wildness' retiered to periodic in v1.32 contributor
// wave: this is an LLM-judge creativity score (axis_a ≥4 on a "wildness"
// posture). Per CLAUDE.md tier-classification rules, non-deterministic
@ -658,7 +658,7 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
'global-discover': 'gate',
// CSO — gate for security guardrails, periodic for quality
'cso-full-audit': 'gate', // Hardcoded secrets detection
'cso-full-audit': 'periodic', // D2a demotion 2026-08: 250s/$0.57 full audit; cso targeted tests stay gate
'cso-diff-mode': 'gate',
'cso-infra-scope': 'periodic',
@ -679,8 +679,8 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
// Design — gate for cheap functional, periodic for Opus/quality
'design-consultation-core': 'periodic',
'design-consultation-existing': 'periodic',
'design-consultation-research': 'gate',
'design-consultation-preview': 'gate',
'design-consultation-research': 'periodic', // D2a demotion 2026-08: the two most expensive gate tests ($0.91/304s)
'design-consultation-preview': 'periodic', // D2a demotion 2026-08 ($0.89/481s)
'plan-design-review-no-ui-scope': 'gate',
'design-review-fix': 'periodic',
'design-shotgun-path': 'gate',