mirror of
https://github.com/garrytan/gstack.git
synced 2026-07-06 08:07:53 +02:00
test: regression suite + E2E for v1.27.0.0 rename
Three new regression tests guard the rename's blast radius (per codex Findings #1, #8, #9, #12): - test/no-stale-gstack-brain-refs.test.ts: greps bin/, scripts/, *.tmpl, test/ for forbidden identifiers (gstack-brain-init, gbrain_sync_mode); fails CI if any non-allowlisted file references them. - test/post-rename-doc-regen.test.ts: confirms gen-skill-docs output has no stale references in any */SKILL.md (the cross-product blind spot). - test/setup-gbrain-path4-structure.test.ts: structural lint over the Path 4 prose contract — STOP gates after verify failure, never-write- token rules, mode-aware CLAUDE.md block, bearer always via env-var. Two new gate-tier E2E tests (deterministic stub HTTP server, fixed inputs): - test/skill-e2e-setup-gbrain-remote.test.ts: Path 4 happy path. Stubs an HTTP MCP server, drives the skill via Agent SDK with a stubbed bearer, asserts claude.json gets the http MCP entry, CLAUDE.md gets the remote-http block, the secret token NEVER leaks to CLAUDE.md. - test/skill-e2e-setup-gbrain-bad-token.test.ts: stub server returns 401; asserts the AUTH classifier hint surfaces, no MCP registration occurs, CLAUDE.md is unchanged. Regression guard for the "verify failed → STOP" rule. touchfiles.ts: setup-gbrain-remote and setup-gbrain-bad-token added at gate-tier so CI catches Path 4 regressions on every PR. Plus a few comment refs flipped: bin/gstack-jsonl-merge, bin/gstack-timeline-log (legacy gstack-brain-init mentions in headers). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -133,7 +133,14 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
'plan-eng-finding-count': ['plan-eng-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-eng-finding-count.test.ts'],
|
||||
'plan-design-finding-count': ['plan-design-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-finding-count.test.ts'],
|
||||
'plan-devex-finding-count': ['plan-devex-review/**', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-devex-finding-count.test.ts'],
|
||||
'brain-privacy-gate': ['scripts/resolvers/preamble/generate-brain-sync-block.ts', 'scripts/resolvers/preamble.ts', 'bin/gstack-brain-sync', 'bin/gstack-brain-init', 'bin/gstack-config', 'test/helpers/agent-sdk-runner.ts'],
|
||||
'brain-privacy-gate': ['scripts/resolvers/preamble/generate-brain-sync-block.ts', 'scripts/resolvers/preamble.ts', 'bin/gstack-brain-sync', 'bin/gstack-artifacts-init', 'bin/gstack-config', 'test/helpers/agent-sdk-runner.ts'],
|
||||
|
||||
// /setup-gbrain Path 4 (Remote MCP) — happy + bad-token end-to-end via
|
||||
// Agent SDK. Gate-tier (deterministic stub server, fixed inputs); fires
|
||||
// when the skill template, the verify helper, the artifacts-init helper,
|
||||
// or the detect script changes.
|
||||
'setup-gbrain-remote': ['setup-gbrain/SKILL.md.tmpl', 'bin/gstack-gbrain-mcp-verify', 'bin/gstack-artifacts-init', 'bin/gstack-gbrain-detect', 'test/helpers/agent-sdk-runner.ts'],
|
||||
'setup-gbrain-bad-token': ['setup-gbrain/SKILL.md.tmpl', 'bin/gstack-gbrain-mcp-verify', 'test/helpers/agent-sdk-runner.ts'],
|
||||
|
||||
// AskUserQuestion format regression (RECOMMENDATION + Completeness: N/10)
|
||||
// Fires when either template OR the two preamble resolvers change.
|
||||
@@ -427,6 +434,12 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
|
||||
// costs ~$0.30-$0.50 per run, not needed on every commit)
|
||||
'brain-privacy-gate': 'periodic',
|
||||
|
||||
// /setup-gbrain Path 4 (Remote MCP) — gate-tier. Stub HTTP server is
|
||||
// deterministic; Path 4's STOP gates are the failure mode this catches
|
||||
// (token in CLAUDE.md, partial registration on bad bearer).
|
||||
'setup-gbrain-remote': 'gate',
|
||||
'setup-gbrain-bad-token': 'gate',
|
||||
|
||||
// AskUserQuestion format regression — periodic (Opus 4.7 non-deterministic benchmark)
|
||||
'plan-ceo-review-format-mode': 'periodic',
|
||||
'plan-ceo-review-format-approach': 'periodic',
|
||||
|
||||
Reference in New Issue
Block a user