mirror of
https://github.com/garrytan/gstack.git
synced 2026-06-26 03:30:05 +02:00
test(plan-tune): 5 cathedral E2E scenarios + touchfile registration
Plan-tune cathedral T16 (per D12 — all 5 in gate tier). One consolidated
file with five describeIfSelected scenarios, each selectable by its own
touchfile entry so they only run when the relevant code changes (or
EVALS_ALL=1 forces all):
plan-tune-hook-capture — PostToolUse hook fires → question-log fills
plan-tune-enforcement — never-ask + marker + 2-way → deny+reason
+ auto-decided event logged
plan-tune-annotation — declared profile + memory nugget
→ additionalContext surfaced on defer
plan-tune-codex-import — synthetic JSONL → import bin → log with
source=codex-import-marker
plan-tune-dream-cycle — apply proposal → re-fire question
→ memory injected via additionalContext
Each scenario fixtures an isolated git repo + bins + scripts + hooks
under tmp, then exercises the cathedral chain end-to-end against real
on-disk binaries (no mocks at the bin layer). GSTACK_STATE_ROOT keeps
the user's real ~/.gstack untouched.
These five complement the existing unit tests by proving the full
sub-process chain works (not just individual functions in isolation).
They DON'T spawn claude -p because the cathedral's substrate behavior is
deterministic — agent compliance is no longer the variable. The existing
test/skill-e2e-plan-tune.test.ts (plan-tune-inspect) still covers the
LLM-driven intent-routing behavior.
Cost: each scenario runs in ~1s with $0 because no claude -p invocations.
Touchfile-gated, so they only run on PRs that touch cathedral code.
Also fixes a bug found by the E2E: question-log-hook didn't pass the
incoming tool call's cwd to spawnSync when invoking gstack-question-log,
so the bin used the hook process's cwd (the repo root) instead of the
session's cwd. Result: log writes landed in the wrong project bucket.
Fix mirrors the same cwd-passing pattern from question-preference-hook.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -191,6 +191,13 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
// /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'],
|
||||
|
||||
// /plan-tune cathedral (T16 — 5 E2E scenarios, all gate per D12)
|
||||
'plan-tune-hook-capture': ['hosts/claude/hooks/**', 'bin/gstack-question-log', 'bin/gstack-developer-profile', 'plan-tune/**'],
|
||||
'plan-tune-enforcement': ['hosts/claude/hooks/**', 'bin/gstack-question-preference', 'scripts/question-registry.ts'],
|
||||
'plan-tune-annotation': ['hosts/claude/hooks/**', 'scripts/declared-annotation.ts', 'scripts/psychographic-signals.ts', 'scripts/question-registry.ts'],
|
||||
'plan-tune-codex-import': ['bin/gstack-codex-session-import', 'bin/gstack-question-log', 'docs/spikes/codex-session-format.md'],
|
||||
'plan-tune-dream-cycle': ['bin/gstack-distill-free-text', 'bin/gstack-distill-apply', 'hosts/claude/hooks/**', 'plan-tune/**'],
|
||||
|
||||
// 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'],
|
||||
@@ -528,6 +535,13 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
|
||||
// /plan-tune — gate (core v1 DX promise: plain-English intent routing)
|
||||
'plan-tune-inspect': 'gate',
|
||||
|
||||
// /plan-tune cathedral (T16 per D12 — all gate)
|
||||
'plan-tune-hook-capture': 'gate',
|
||||
'plan-tune-enforcement': 'gate',
|
||||
'plan-tune-annotation': 'gate',
|
||||
'plan-tune-codex-import': 'gate',
|
||||
'plan-tune-dream-cycle': 'gate',
|
||||
|
||||
// Codex offering verification
|
||||
'codex-offered-office-hours': 'gate',
|
||||
'codex-offered-ceo-review': 'gate',
|
||||
|
||||
Reference in New Issue
Block a user