mirror of
https://github.com/garrytan/gstack.git
synced 2026-05-05 13:15:24 +02:00
test: E2E test for /plan-tune plain-English inspection flow (gate tier)
test/skill-e2e-plan-tune.test.ts — verifies /plan-tune correctly routes
plain-English intent ("review the questions I've been asked") to the
Review question log section without requiring CLI subcommand syntax.
Seeds a synthetic question-log.jsonl with 3 entries exercising:
- override behavior (user chose expand over recommended selective)
- one-way door respect (user followed ship-test-failure-triage recommendation)
- two-way override (user skipped recommended changelog polish)
Invokes the skill via `claude -p` and asserts:
- Agent surfaces >= 2 of 3 logged question_ids in output
- Agent notices override/skip behavior from the log
- Exit reason is success or error_max_turns (not agent-crash)
Gate-tier because the core v1 DX promise is plain-English intent routing.
If it requires memorized subcommands or breaks on natural language, that's
a regression of the defining feature.
Registered in test/helpers/touchfiles.ts with dependencies:
- plan-tune/** (skill template + generated md)
- scripts/question-registry.ts (required for log lookup)
- scripts/psychographic-signals.ts, scripts/one-way-doors.ts (derive path)
- bin/gstack-question-log, gstack-question-preference, gstack-developer-profile
Skipped when EVALS_ENABLED is not set; runs on `bun run test:evals`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -79,6 +79,9 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
'plan-eng-review-artifact': ['plan-eng-review/**'],
|
||||
'plan-review-report': ['plan-eng-review/**', 'scripts/gen-skill-docs.ts'],
|
||||
|
||||
// /plan-tune (v1 observational)
|
||||
'plan-tune-inspect': ['plan-tune/**', 'scripts/question-registry.ts', 'scripts/psychographic-signals.ts', 'scripts/one-way-doors.ts', 'bin/gstack-question-log', 'bin/gstack-question-preference', 'bin/gstack-developer-profile'],
|
||||
|
||||
// Codex offering verification
|
||||
'codex-offered-office-hours': ['office-hours/**', 'scripts/gen-skill-docs.ts'],
|
||||
'codex-offered-ceo-review': ['plan-ceo-review/**', 'scripts/gen-skill-docs.ts'],
|
||||
@@ -239,6 +242,9 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
|
||||
'plan-eng-coverage-audit': 'gate',
|
||||
'plan-review-report': 'gate',
|
||||
|
||||
// /plan-tune — gate (core v1 DX promise: plain-English intent routing)
|
||||
'plan-tune-inspect': 'gate',
|
||||
|
||||
// Codex offering verification
|
||||
'codex-offered-office-hours': 'gate',
|
||||
'codex-offered-ceo-review': 'gate',
|
||||
|
||||
Reference in New Issue
Block a user