CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-08-31 18:30:39 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(evals): every E2E key's dep list names its own declaring test file

Browse Source 
129-of-177 keys omitted their own test file, so editing only a test's
prompt or assertions selected NOTHING — the changed test never ran on
the change that changed it. 135 keys self-registered (110 E2E + 25
LLM-judge), resolved by strict declaration evidence (testName:/
testIfSelected/judge call sites), with skill-name false positives
excluded.

e2e-tier-alignment's warn-only branch for unregistered files is now a
hard failure with a 4-entry KNOWN_UNREGISTERED ratchet (template-
literal testNames, fail-open-safe) + a burn-down test so the set only
shrinks. Selection sanity: a one-file diff on skill-e2e-qa-workflow now
selects its 4 tests (was 0); skill-llm-eval 0 → 25.

Known follow-ups (filed): 15 E2E + 2 judge PHANTOM keys select tests
that exist nowhere; codex-e2e-plan-format's testIfSelected names have
no map keys (run-all only).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-08-29 05:06:57 +00:00
co-authored by Claude Fable 5
parent 95b779f7cd
commit 2ec4dcf105
2 changed files with 203 additions and 139 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/helpers/touchfiles-data.ts
+135 -130
View File
@@ -22,8 +22,8 @@
*/
export const E2E_TOUCHFILES: Record<string, string[]> = {
// Browse core (+ test-server dependency)
'browse-basic': ['browse/src/**', 'browse/test/test-server.ts'],
'browse-snapshot': ['browse/src/**', 'browse/test/test-server.ts'],
'browse-basic': ['browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-bws.test.ts'],
'browse-snapshot': ['browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-bws.test.ts'],
// Hermetic isolation canaries (hermetic-env.ts is also a GLOBAL touchfile;
// these entries exist so the canaries themselves stay tier-classified)
@@ -37,21 +37,21 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'first-task-scaffold': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'bin/gstack-first-task-detect', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'test/skill-e2e-first-task-scaffold.test.ts', 'test/helpers/session-runner.ts'],
// SKILL.md setup + preamble (depend on ROOT SKILL.md + gen-skill-docs)
'skillmd-setup-discovery': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'skillmd-no-local-binary': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'skillmd-outside-git': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'skillmd-setup-discovery': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-bws.test.ts'],
'skillmd-no-local-binary': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-bws.test.ts'],
'skillmd-outside-git': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-bws.test.ts'],
'session-awareness': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'operational-learning': ['scripts/resolvers/preamble.ts', 'bin/gstack-learnings-log'],
'session-awareness': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-bws.test.ts'],
'operational-learning': ['scripts/resolvers/preamble.ts', 'bin/gstack-learnings-log', 'test/skill-e2e-bws.test.ts'],
// QA (+ test-server dependency)
'qa-quick': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts'],
'qa-b6-static': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval.html', 'test/fixtures/qa-eval-ground-truth.json'],
'qa-b7-spa': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-spa.html', 'test/fixtures/qa-eval-spa-ground-truth.json'],
'qa-b8-checkout': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-checkout.html', 'test/fixtures/qa-eval-checkout-ground-truth.json'],
'qa-only-no-fix': ['qa-only/**', 'qa/templates/**'],
'qa-fix-loop': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts'],
'qa-bootstrap': ['qa/**', 'ship/**'],
'qa-quick': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-qa-workflow.test.ts'],
'qa-b6-static': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval.html', 'test/fixtures/qa-eval-ground-truth.json', 'test/skill-e2e-qa-bugs.test.ts'],
'qa-b7-spa': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-spa.html', 'test/fixtures/qa-eval-spa-ground-truth.json', 'test/skill-e2e-qa-bugs.test.ts'],
'qa-b8-checkout': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-checkout.html', 'test/fixtures/qa-eval-checkout-ground-truth.json', 'test/skill-e2e-qa-bugs.test.ts'],
'qa-only-no-fix': ['qa-only/**', 'qa/templates/**', 'test/skill-e2e-qa-workflow.test.ts'],
'qa-fix-loop': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-qa-workflow.test.ts'],
'qa-bootstrap': ['qa/**', 'ship/**', 'test/skill-e2e-qa-workflow.test.ts'],
// Review
'review-sql-injection': ['review/**', 'test/fixtures/review-eval-vuln.rb', 'test/skill-e2e-review.test.ts'],
@@ -60,27 +60,27 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'review-design-lite': ['review/**', 'test/fixtures/review-eval-design-slop.*', 'test/skill-e2e-review.test.ts'],
// Review Army (specialist dispatch)
'review-army-migration-safety': ['review/**', 'scripts/resolvers/review-army.ts', 'bin/gstack-diff-scope'],
'review-army-perf-n-plus-one': ['review/**', 'scripts/resolvers/review-army.ts', 'bin/gstack-diff-scope'],
'review-army-delivery-audit': ['review/**', 'scripts/resolvers/review.ts', 'scripts/resolvers/review-army.ts'],
'review-army-quality-score': ['review/**', 'scripts/resolvers/review-army.ts'],
'review-army-json-findings': ['review/**', 'scripts/resolvers/review-army.ts'],
'review-army-red-team': ['review/**', 'scripts/resolvers/review-army.ts'],
'review-army-consensus': ['review/**', 'scripts/resolvers/review-army.ts'],
'review-army-migration-safety': ['review/**', 'scripts/resolvers/review-army.ts', 'bin/gstack-diff-scope', 'test/skill-e2e-review-army.test.ts'],
'review-army-perf-n-plus-one': ['review/**', 'scripts/resolvers/review-army.ts', 'bin/gstack-diff-scope', 'test/skill-e2e-review-army.test.ts'],
'review-army-delivery-audit': ['review/**', 'scripts/resolvers/review.ts', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review-army.test.ts'],
'review-army-quality-score': ['review/**', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review-army.test.ts'],
'review-army-json-findings': ['review/**', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review-army.test.ts'],
'review-army-red-team': ['review/**', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review-army.test.ts'],
'review-army-consensus': ['review/**', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review-army.test.ts'],
// Office Hours
'office-hours-spec-review': ['office-hours/**', 'scripts/gen-skill-docs.ts'],
'office-hours-forcing-energy': ['office-hours/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts'],
'office-hours-builder-wildness': ['office-hours/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts'],
'office-hours-spec-review': ['office-hours/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
'office-hours-forcing-energy': ['office-hours/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts', 'test/skill-e2e-office-hours.test.ts'],
'office-hours-builder-wildness': ['office-hours/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts', 'test/skill-e2e-office-hours.test.ts'],
// Plan reviews
'plan-ceo-review': ['plan-ceo-review/**'],
'plan-ceo-review-selective': ['plan-ceo-review/**'],
'plan-ceo-review-benefits': ['plan-ceo-review/**', 'scripts/gen-skill-docs.ts'],
'plan-ceo-review-expansion-energy': ['plan-ceo-review/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts'],
'plan-eng-review': ['plan-eng-review/**'],
'plan-eng-review-artifact': ['plan-eng-review/**'],
'plan-review-report': ['plan-eng-review/**', 'scripts/gen-skill-docs.ts'],
'plan-ceo-review': ['plan-ceo-review/**', 'test/skill-e2e-plan.test.ts'],
'plan-ceo-review-selective': ['plan-ceo-review/**', 'test/skill-e2e-plan.test.ts'],
'plan-ceo-review-benefits': ['plan-ceo-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
'plan-ceo-review-expansion-energy': ['plan-ceo-review/**', 'scripts/resolvers/preamble.ts', 'test/fixtures/mode-posture/**', 'test/helpers/llm-judge.ts', 'test/skill-e2e-plan.test.ts'],
'plan-eng-review': ['plan-eng-review/**', 'test/skill-e2e-plan.test.ts'],
'plan-eng-review-artifact': ['plan-eng-review/**', 'test/skill-e2e-plan.test.ts'],
'plan-review-report': ['plan-eng-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
// Plan-mode smoke tests — gate-tier safety regression tests. Each test file
// contains TWO test cases as of v1.21: the baseline plan-mode case and the
@@ -91,7 +91,7 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
// regression test outcome between 'asked' and 'auto_decided'.
'plan-ceo-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-ceo-plan-mode.test.ts'],
'plan-eng-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-eng-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-eng-plan-mode.test.ts'],
'plan-design-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-design-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-plan-mode.test.ts'],
'plan-design-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-design-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-plan-mode.test.ts', 'test/skill-e2e-design.test.ts'],
'plan-devex-review-plan-mode': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/review.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-devex-plan-mode.test.ts'],
// Covers ceo (preamble misfire) + eng/design (scope-gate bypass must not
// fire outside plan mode) + the named-target exception case. 4 PTY runs;
@@ -117,7 +117,7 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
// written a never-ask preference, AUQ should still auto-decide rather than
// surfacing the question. Touches the question-tuning + preference
// infrastructure plus the resolvers that own the AUTO_DECIDE preamble.
'auto-decide-preserved': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'plan-ceo-review/**', 'bin/gstack-question-preference', 'bin/gstack-config', 'bin/gstack-slug', 'hosts/claude/hooks/question-preference-hook.ts', 'lib/is-conductor.ts', 'test/helpers/claude-pty-runner.ts'],
'auto-decide-preserved': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'scripts/resolvers/question-tuning.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'plan-ceo-review/**', 'bin/gstack-question-preference', 'bin/gstack-config', 'bin/gstack-slug', 'hosts/claude/hooks/question-preference-hook.ts', 'lib/is-conductor.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-auto-decide-preserved.test.ts'],
// Conductor → prose decision brief (Conductor signal makes prose the default;
// the PreToolUse hook denies the flaky tool). Touches the resolver that owns
@@ -128,18 +128,18 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
// Each one tests behavior the SDK harness can't observe (rendered TTY,
// numbered-option lists, multi-phase ordering, idempotency state echo).
'preamble-script-ab': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-brain-sync-block.ts', 'scripts/resolvers/preamble.ts', 'plan-ceo-review/**', 'test/helpers/auq-sdk-capture.ts', 'test/skill-e2e-preamble-script-ab.test.ts'],
'auq-format-gate': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/helpers/llm-judge.ts'],
'auq-format-gate': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/helpers/llm-judge.ts', 'test/skill-e2e-ask-user-question-format-compliance.test.ts'],
'plan-ceo-mode-routing': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-ceo-mode-routing.test.ts'],
'plan-design-with-ui-scope': ['plan-design-review/**', 'test/fixtures/plans/ui-heavy-feature.md', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-plan-design-with-ui.test.ts'],
'budget-regression-pty': ['test/helpers/eval-store.ts', 'test/skill-budget-regression.test.ts'],
'ship-idempotency-pty': ['ship/**', 'bin/gstack-next-version', 'bin/gstack-version-bump', 'scripts/resolvers/sections.ts', 'lib/worktree.ts', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-ship-idempotency.test.ts'],
'ship-section-loading': ['ship/**', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-ship-section-loading.test.ts'],
'plan-ceo-section-loading': ['plan-ceo-review/**', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts'],
'plan-ceo-section-loading': ['plan-ceo-review/**', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-plan-ceo-review-section-loading.test.ts'],
// Data-driven behavioral guard for the 'plan'/'prompt' carves (eng, design,
// devex, office-hours + future PR2 carves). One file iterating CARVE_GUARDS;
// the selector sets GSTACK_CARVE_SKILL=<name> to scope cost to the changed
// skill (D-CODEX A). Touching the registry/helper or sections.ts runs all.
'carve-section-loading': ['design-html/**', 'design-shotgun/**', 'qa/**', 'browse/**', 'retro/**', 'autoplan/**', 'spec/**', 'setup-gbrain/**', 'review/**', 'codex/**', 'land-and-deploy/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'office-hours/**', 'document-release/**', 'design-consultation/**', 'cso/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts'],
'carve-section-loading': ['design-html/**', 'design-shotgun/**', 'qa/**', 'browse/**', 'retro/**', 'autoplan/**', 'spec/**', 'setup-gbrain/**', 'review/**', 'codex/**', 'land-and-deploy/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'office-hours/**', 'document-release/**', 'design-consultation/**', 'cso/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/carve-section-loading.test.ts'],
'autoplan-chain-pty': ['autoplan/**', 'plan-ceo-review/**', 'plan-design-review/**', 'plan-eng-review/**', 'plan-devex-review/**', 'test/fixtures/plans/ui-heavy-feature.md', 'test/helpers/claude-pty-runner.ts', 'test/skill-e2e-autoplan-chain.test.ts'],
'e2e-harness-audit': ['bin/gstack-skill-start', 'bin/gstack-skill-end', 'plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/claude-pty-runner.ts'],
@@ -185,18 +185,18 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
// AskUserQuestion format regression (RECOMMENDATION + Completeness: N/10)
// Fires when either template OR the two preamble resolvers change.
'plan-ceo-review-format-mode': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts'],
'plan-ceo-review-format-approach': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts'],
'plan-eng-review-format-coverage': ['plan-eng-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts'],
'plan-eng-review-format-kind': ['plan-eng-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts'],
'plan-ceo-review-format-mode': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts', 'test/skill-e2e-plan-format.test.ts'],
'plan-ceo-review-format-approach': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts', 'test/skill-e2e-plan-format.test.ts'],
'plan-eng-review-format-coverage': ['plan-eng-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts', 'test/skill-e2e-plan-format.test.ts'],
'plan-eng-review-format-kind': ['plan-eng-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/helpers/llm-judge.ts', 'test/skill-e2e-plan-format.test.ts'],
// v1.7.0.0 Pros/Cons format cadence + format + negative-escape evals.
// Dependencies: same as format-mode + the 4 plan-review templates + overlay.
// All periodic-tier (non-deterministic Opus 4.7 behavior).
'plan-ceo-review-prosons-cadence': ['plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'],
'plan-review-prosons-format': ['plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'],
'plan-review-prosons-hardstop-neg': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'],
'plan-review-prosons-neutral-neg': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'],
'plan-ceo-review-prosons-cadence': ['plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/skill-e2e-plan-prosons.test.ts'],
'plan-review-prosons-format': ['plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**', 'plan-devex-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/skill-e2e-plan-prosons.test.ts'],
'plan-review-prosons-hardstop-neg': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/skill-e2e-plan-prosons.test.ts'],
'plan-review-prosons-neutral-neg': ['plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md', 'test/skill-e2e-plan-prosons.test.ts'],
// Expanded coverage (CT3) — 6 non-plan-review skills inherit Pros/Cons via preamble
'ship-prosons-format': ['ship/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'],
@@ -208,24 +208,24 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'document-release-prosons-format': ['document-release/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble.ts', 'model-overlays/opus-4-7.md'],
// /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-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', 'test/skill-e2e-plan-tune.test.ts'],
// /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/**'],
'plan-tune-hook-capture': ['hosts/claude/hooks/**', 'bin/gstack-question-log', 'bin/gstack-developer-profile', 'plan-tune/**', 'test/skill-e2e-plan-tune-cathedral.test.ts'],
'plan-tune-enforcement': ['hosts/claude/hooks/**', 'bin/gstack-question-preference', 'scripts/question-registry.ts', 'test/skill-e2e-plan-tune-cathedral.test.ts'],
'plan-tune-annotation': ['hosts/claude/hooks/**', 'scripts/declared-annotation.ts', 'scripts/psychographic-signals.ts', 'scripts/question-registry.ts', 'test/skill-e2e-plan-tune-cathedral.test.ts'],
'plan-tune-codex-import': ['bin/gstack-codex-session-import', 'bin/gstack-question-log', 'docs/spikes/codex-session-format.md', 'test/skill-e2e-plan-tune-cathedral.test.ts'],
'plan-tune-dream-cycle': ['bin/gstack-distill-free-text', 'bin/gstack-distill-apply', 'hosts/claude/hooks/**', 'plan-tune/**', 'test/skill-e2e-plan-tune-cathedral.test.ts'],
// 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'],
'codex-offered-design-review': ['plan-design-review/**', 'scripts/gen-skill-docs.ts'],
'codex-offered-eng-review': ['plan-eng-review/**', 'scripts/gen-skill-docs.ts'],
'codex-offered-office-hours': ['office-hours/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
'codex-offered-ceo-review': ['plan-ceo-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
'codex-offered-design-review': ['plan-design-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
'codex-offered-eng-review': ['plan-eng-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-plan.test.ts'],
// Ship
'ship-base-branch': ['ship/**', 'bin/gstack-repo-mode', 'test/skill-e2e-review-attribution.test.ts'],
'ship-local-workflow': ['ship/**', 'scripts/gen-skill-docs.ts'],
'ship-local-workflow': ['ship/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-workflow.test.ts'],
'review-dashboard-via': ['ship/**', 'scripts/resolvers/review.ts', 'codex/**', 'autoplan/**', 'land-and-deploy/**', 'test/skill-e2e-review-attribution.test.ts'],
// Retro
@@ -236,51 +236,51 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'global-discover': ['bin/gstack-global-discover.ts', 'test/global-discover.test.ts'],
// CSO
'cso-full-audit': ['cso/**'],
'cso-diff-mode': ['cso/**'],
'cso-infra-scope': ['cso/**'],
'cso-full-audit': ['cso/**', 'test/skill-e2e-cso.test.ts'],
'cso-diff-mode': ['cso/**', 'test/skill-e2e-cso.test.ts'],
'cso-infra-scope': ['cso/**', 'test/skill-e2e-cso.test.ts'],
// Learnings
'learnings-show': ['learn/**', 'bin/gstack-learnings-search', 'bin/gstack-learnings-log', 'scripts/resolvers/learnings.ts'],
'learnings-show': ['learn/**', 'bin/gstack-learnings-search', 'bin/gstack-learnings-log', 'scripts/resolvers/learnings.ts', 'test/skill-e2e-learnings.test.ts'],
// Session Intelligence (timeline, context recovery, /context-save + /context-restore)
'timeline-event-flow': ['bin/gstack-timeline-log', 'bin/gstack-timeline-read'],
'context-recovery-artifacts': ['scripts/resolvers/preamble.ts', 'bin/gstack-timeline-log', 'bin/gstack-slug', 'learn/**'],
'context-save-writes-file': ['context-save/**', 'bin/gstack-slug'],
'context-restore-loads-latest': ['context-restore/**', 'bin/gstack-slug'],
'timeline-event-flow': ['bin/gstack-timeline-log', 'bin/gstack-timeline-read', 'test/skill-e2e-session-intelligence.test.ts'],
'context-recovery-artifacts': ['scripts/resolvers/preamble.ts', 'bin/gstack-timeline-log', 'bin/gstack-slug', 'learn/**', 'test/skill-e2e-session-intelligence.test.ts'],
'context-save-writes-file': ['context-save/**', 'bin/gstack-slug', 'test/skill-e2e-session-intelligence.test.ts'],
'context-restore-loads-latest': ['context-restore/**', 'bin/gstack-slug', 'test/skill-e2e-session-intelligence.test.ts'],
// Context skills E2E (live-fire, Skill-tool routing path) — see
// test/skill-e2e-context-skills.test.ts. These are periodic-tier because
// each one spawns claude -p and costs ~$0.20-$0.40. Collectively they
// verify the thing the /checkpoint → /context-save rename was for.
'context-save-routing': ['context-save/**', 'scripts/resolvers/preamble.ts'],
'context-save-then-restore-roundtrip': ['context-save/**', 'context-restore/**', 'bin/gstack-slug'],
'context-restore-fragment-match': ['context-restore/**'],
'context-restore-empty-state': ['context-restore/**'],
'context-restore-list-delegates': ['context-restore/**'],
'context-restore-legacy-compat': ['context-restore/**'],
'context-save-list-current-branch': ['context-save/**'],
'context-save-list-all-branches': ['context-save/**'],
'context-save-routing': ['context-save/**', 'scripts/resolvers/preamble.ts', 'test/skill-e2e-context-skills.test.ts'],
'context-save-then-restore-roundtrip': ['context-save/**', 'context-restore/**', 'bin/gstack-slug', 'test/skill-e2e-context-skills.test.ts'],
'context-restore-fragment-match': ['context-restore/**', 'test/skill-e2e-context-skills.test.ts'],
'context-restore-empty-state': ['context-restore/**', 'test/skill-e2e-context-skills.test.ts'],
'context-restore-list-delegates': ['context-restore/**', 'test/skill-e2e-context-skills.test.ts'],
'context-restore-legacy-compat': ['context-restore/**', 'test/skill-e2e-context-skills.test.ts'],
'context-save-list-current-branch': ['context-save/**', 'test/skill-e2e-context-skills.test.ts'],
'context-save-list-all-branches': ['context-save/**', 'test/skill-e2e-context-skills.test.ts'],
// Document-release
'document-release': ['document-release/**'],
'document-release': ['document-release/**', 'test/skill-e2e-workflow.test.ts'],
// Codex (Claude E2E — tests /codex skill via Claude)
'codex-review': ['codex/**'],
'codex-review': ['codex/**', 'test/skill-e2e-workflow.test.ts'],
// Codex E2E (tests skills via Codex CLI + worktree)
'codex-discover-skill': ['codex/**', '.agents/skills/**', 'test/helpers/codex-session-runner.ts', 'lib/worktree.ts'],
'codex-review-findings': ['review/**', '.agents/skills/gstack-review/**', 'codex/**', 'test/helpers/codex-session-runner.ts', 'lib/worktree.ts'],
'codex-discover-skill': ['codex/**', '.agents/skills/**', 'test/helpers/codex-session-runner.ts', 'lib/worktree.ts', 'test/codex-e2e.test.ts'],
'codex-review-findings': ['review/**', '.agents/skills/gstack-review/**', 'codex/**', 'test/helpers/codex-session-runner.ts', 'lib/worktree.ts', 'test/codex-e2e.test.ts'],
// GPT-5.6 Sol scope-termination E2E (Codex CLI, full generated investigate skill)
'codex-sol-scope-termination': ['model-overlays/gpt-5.6-sol.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts', 'scripts/resolvers/preamble/**', 'investigate/**', 'test/helpers/codex-session-runner.ts', 'test/codex-e2e-sol-scope.test.ts'],
// Gemini E2E — smoke test only (Gemini gets lost in worktrees on complex tasks)
'gemini-smoke': ['.agents/skills/**', 'test/helpers/gemini-session-runner.ts', 'lib/worktree.ts'],
'gemini-smoke': ['.agents/skills/**', 'test/helpers/gemini-session-runner.ts', 'lib/worktree.ts', 'test/gemini-e2e.test.ts'],
// Coverage audit (shared fixture) + triage + gates
'ship-coverage-audit': ['ship/**', 'test/fixtures/coverage-audit-fixture.ts', 'bin/gstack-repo-mode'],
'ship-coverage-audit': ['ship/**', 'test/fixtures/coverage-audit-fixture.ts', 'bin/gstack-repo-mode', 'test/skill-e2e-workflow.test.ts'],
'review-coverage-audit': ['review/**', 'test/fixtures/coverage-audit-fixture.ts', 'test/skill-e2e-coverage-audit.test.ts'],
'plan-eng-coverage-audit': ['plan-eng-review/**', 'test/fixtures/coverage-audit-fixture.ts', 'test/skill-e2e-coverage-audit.test.ts'],
'ship-triage': ['ship/**', 'bin/gstack-repo-mode', 'test/skill-e2e-triage.test.ts'],
@@ -292,12 +292,12 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'review-plan-completion': ['review/**', 'scripts/gen-skill-docs.ts'],
// Design
'design-consultation-core': ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/helpers/llm-judge.ts'],
'design-consultation-existing': ['design-consultation/**', 'scripts/gen-skill-docs.ts'],
'design-consultation-research': ['design-consultation/**', 'scripts/gen-skill-docs.ts'],
'design-consultation-preview': ['design-consultation/**', 'scripts/gen-skill-docs.ts'],
'plan-design-review-no-ui-scope': ['plan-design-review/**', 'scripts/gen-skill-docs.ts'],
'design-review-fix': ['design-review/**', 'browse/src/**', 'scripts/gen-skill-docs.ts'],
'design-consultation-core': ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/helpers/llm-judge.ts', 'test/skill-e2e-design.test.ts'],
'design-consultation-existing': ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
'design-consultation-research': ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
'design-consultation-preview': ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
'plan-design-review-no-ui-scope': ['plan-design-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
'design-review-fix': ['design-review/**', 'browse/src/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
// Design Shotgun
'design-shotgun-path': ['design-shotgun/**', 'design/src/**', 'scripts/resolvers/design.ts'],
@@ -306,24 +306,24 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
// /diagram (diagram-render bundle consumers). Triplet = deterministic
// functional (gate); authoring quality = LLM-judged benchmark (periodic).
'diagram-triplet': ['diagram/**', 'lib/diagram-render/**', 'browse/src/write-commands.ts', 'browse/src/read-commands.ts'],
'diagram-authoring-quality': ['diagram/**', 'lib/diagram-render/**', 'test/helpers/llm-judge.ts'],
'diagram-triplet': ['diagram/**', 'lib/diagram-render/**', 'browse/src/write-commands.ts', 'browse/src/read-commands.ts', 'test/skill-e2e-diagram.test.ts'],
'diagram-authoring-quality': ['diagram/**', 'lib/diagram-render/**', 'test/helpers/llm-judge.ts', 'test/skill-e2e-diagram.test.ts'],
// gstack-upgrade
'gstack-upgrade-happy-path': ['gstack-upgrade/**'],
'gstack-upgrade-happy-path': ['gstack-upgrade/**', 'test/skill-e2e-workflow.test.ts'],
// Deploy skills
'land-and-deploy-workflow': ['land-and-deploy/**', 'scripts/gen-skill-docs.ts'],
'land-and-deploy-first-run': ['land-and-deploy/**', 'scripts/gen-skill-docs.ts', 'bin/gstack-slug'],
'land-and-deploy-review-gate': ['land-and-deploy/**', 'bin/gstack-review-read'],
'canary-workflow': ['canary/**', 'browse/src/**'],
'benchmark-workflow': ['benchmark/**', 'browse/src/**'],
'setup-deploy-workflow': ['setup-deploy/**', 'scripts/gen-skill-docs.ts'],
'land-and-deploy-workflow': ['land-and-deploy/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-deploy.test.ts'],
'land-and-deploy-first-run': ['land-and-deploy/**', 'scripts/gen-skill-docs.ts', 'bin/gstack-slug', 'test/skill-e2e-deploy.test.ts'],
'land-and-deploy-review-gate': ['land-and-deploy/**', 'bin/gstack-review-read', 'test/skill-e2e-deploy.test.ts'],
'canary-workflow': ['canary/**', 'browse/src/**', 'test/skill-e2e-deploy.test.ts'],
'benchmark-workflow': ['benchmark/**', 'browse/src/**', 'test/skill-e2e-deploy.test.ts'],
'setup-deploy-workflow': ['setup-deploy/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-deploy.test.ts'],
// Autoplan
'autoplan-core': ['autoplan/**', 'plan-ceo-review/**', 'plan-eng-review/**', 'plan-design-review/**'],
'autoplan-dual-voice': ['autoplan/**', 'codex/**', 'bin/gstack-codex-probe', 'scripts/resolvers/review.ts', 'scripts/resolvers/design.ts'],
'autoplan-dual-voice': ['autoplan/**', 'codex/**', 'bin/gstack-codex-probe', 'scripts/resolvers/review.ts', 'scripts/resolvers/design.ts', 'test/skill-e2e-autoplan-dual-voice.test.ts'],
// Multi-provider benchmark adapters — live API smoke against real claude/codex/gemini CLIs
'benchmark-providers-live': ['bin/gstack-model-benchmark', 'test/helpers/providers/**', 'test/helpers/benchmark-runner.ts', 'test/helpers/pricing.ts', 'test/skill-e2e-benchmark-providers.test.ts'],
@@ -336,41 +336,46 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'scrape-match-path': [
'scrape/**', 'browse/src/browser-skills.ts', 'browse/src/browser-skill-commands.ts',
'browser-skills/hackernews-frontpage/**',
'test/skill-e2e-skillify.test.ts',
],
'scrape-prototype-path': [
'scrape/**', 'browse/src/browser-skills.ts', 'browse/src/browser-skill-commands.ts',
'test/skill-e2e-skillify.test.ts',
],
'skillify-happy-path': [
'skillify/**', 'scrape/**', 'browse/src/browser-skill-write.ts',
'browse/src/browser-skills.ts', 'browse/src/browser-skill-commands.ts',
'test/skill-e2e-skillify.test.ts',
],
'skillify-provenance-refusal': [
'skillify/**', 'browse/src/browser-skill-write.ts',
'test/skill-e2e-skillify.test.ts',
],
'skillify-approval-reject': [
'skillify/**', 'scrape/**', 'browse/src/browser-skill-write.ts',
'test/skill-e2e-skillify.test.ts',
],
// Skill routing — journey-stage tests (depend on ALL skill descriptions)
'journey-ideation': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'journey-plan-eng': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'journey-debug': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'journey-qa': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'journey-code-review': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'journey-ship': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'journey-docs': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'journey-retro': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'journey-design-system': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'journey-visual-qa': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'journey-ideation': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-plan-eng': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-debug': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-qa': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-code-review': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-ship': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-docs': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-retro': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-design-system': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
'journey-visual-qa': ['*/SKILL.md.tmpl', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-routing-e2e.test.ts'],
// Opus 4.7 behavior evals — keys match testName: values in the test file.
// Routing sub-tests use template literal `routing-${c.name}` testNames,
// which the touchfile completeness scanner skips; they inherit selection
// from the file-level touchfile entry via GLOBAL_TOUCHFILES.
'fanout-arm-overlay-on':
['model-overlays/claude.md', 'model-overlays/opus-4-7.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts'],
['model-overlays/claude.md', 'model-overlays/opus-4-7.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-opus-47.test.ts'],
'fanout-arm-overlay-off':
['model-overlays/claude.md', 'model-overlays/opus-4-7.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts'],
['model-overlays/claude.md', 'model-overlays/opus-4-7.md', 'scripts/models.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-opus-47.test.ts'],
// Overlay efficacy harness (SDK) — measures whether overlay nudges change
// behavior under @anthropic-ai/claude-agent-sdk (closer to real Claude Code
@@ -754,49 +759,49 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
* LLM-judge test touchfiles — keyed by test description string.
*/
export const LLM_JUDGE_TOUCHFILES: Record<string, string[]> = {
'command reference table': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts'],
'snapshot flags reference': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/snapshot.ts'],
'browse/SKILL.md reference': ['browse/sections/**', 'browse/SKILL.md', 'browse/SKILL.md.tmpl', 'browse/src/**'],
'setup block': ['SKILL.md', 'SKILL.md.tmpl'],
'regression vs baseline': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts', 'test/fixtures/eval-baselines.json'],
'qa/SKILL.md workflow': ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl'],
'qa/SKILL.md health rubric': ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl'],
'qa/SKILL.md anti-refusal': ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl', 'qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl'],
'cross-skill greptile consistency': ['review/SKILL.md', 'review/SKILL.md.tmpl', 'ship/SKILL.md', 'ship/SKILL.md.tmpl', 'review/greptile-triage.md', 'retro/SKILL.md', 'retro/SKILL.md.tmpl'],
'baseline score pinning': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'test/fixtures/eval-baselines.json'],
'command reference table': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts', 'test/skill-llm-eval.test.ts'],
'snapshot flags reference': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/snapshot.ts', 'test/skill-llm-eval.test.ts'],
'browse/SKILL.md reference': ['browse/sections/**', 'browse/SKILL.md', 'browse/SKILL.md.tmpl', 'browse/src/**', 'test/skill-llm-eval.test.ts'],
'setup block': ['SKILL.md', 'SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'regression vs baseline': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts', 'test/fixtures/eval-baselines.json', 'test/skill-llm-eval.test.ts'],
'qa/SKILL.md workflow': ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'qa/SKILL.md health rubric': ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'qa/SKILL.md anti-refusal': ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl', 'qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'cross-skill greptile consistency': ['review/SKILL.md', 'review/SKILL.md.tmpl', 'ship/SKILL.md', 'ship/SKILL.md.tmpl', 'review/greptile-triage.md', 'retro/SKILL.md', 'retro/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'baseline score pinning': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'test/fixtures/eval-baselines.json', 'test/skill-llm-eval.test.ts'],
// Ship & Release
'ship/SKILL.md workflow': ['ship/SKILL.md', 'ship/SKILL.md.tmpl'],
'document-release/SKILL.md workflow': ['document-release/SKILL.md', 'document-release/SKILL.md.tmpl'],
'ship/SKILL.md workflow': ['ship/SKILL.md', 'ship/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'document-release/SKILL.md workflow': ['document-release/SKILL.md', 'document-release/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
// Plan Reviews
'plan-ceo-review/SKILL.md modes': ['plan-ceo-review/SKILL.md', 'plan-ceo-review/SKILL.md.tmpl'],
'plan-eng-review/SKILL.md sections': ['plan-eng-review/SKILL.md', 'plan-eng-review/SKILL.md.tmpl'],
'plan-ceo-review/SKILL.md modes': ['plan-ceo-review/SKILL.md', 'plan-ceo-review/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'plan-eng-review/SKILL.md sections': ['plan-eng-review/SKILL.md', 'plan-eng-review/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
// /spec authored-spec quality (paid LLM-judge — periodic-tier).
'plan-design-review/SKILL.md passes': ['plan-design-review/SKILL.md', 'plan-design-review/SKILL.md.tmpl'],
'plan-design-review/SKILL.md passes': ['plan-design-review/SKILL.md', 'plan-design-review/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
// Design skills
'design-review/SKILL.md fix loop': ['design-review/SKILL.md', 'design-review/SKILL.md.tmpl'],
'design-consultation/SKILL.md research': ['design-consultation/SKILL.md', 'design-consultation/SKILL.md.tmpl'],
'design-review/SKILL.md fix loop': ['design-review/SKILL.md', 'design-review/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'design-consultation/SKILL.md research': ['design-consultation/SKILL.md', 'design-consultation/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
// Office Hours
'office-hours/SKILL.md spec review': ['office-hours/SKILL.md', 'office-hours/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'office-hours/SKILL.md design sketch': ['office-hours/SKILL.md', 'office-hours/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
// Deploy skills
'land-and-deploy/SKILL.md workflow': ['land-and-deploy/SKILL.md', 'land-and-deploy/SKILL.md.tmpl', 'land-and-deploy/sections/**'],
'canary/SKILL.md monitoring loop': ['canary/SKILL.md', 'canary/SKILL.md.tmpl'],
'benchmark/SKILL.md perf collection': ['benchmark/SKILL.md', 'benchmark/SKILL.md.tmpl'],
'setup-deploy/SKILL.md platform setup': ['setup-deploy/SKILL.md', 'setup-deploy/SKILL.md.tmpl'],
'land-and-deploy/SKILL.md workflow': ['land-and-deploy/SKILL.md', 'land-and-deploy/SKILL.md.tmpl', 'land-and-deploy/sections/**', 'test/skill-llm-eval.test.ts'],
'canary/SKILL.md monitoring loop': ['canary/SKILL.md', 'canary/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'benchmark/SKILL.md perf collection': ['benchmark/SKILL.md', 'benchmark/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'setup-deploy/SKILL.md platform setup': ['setup-deploy/SKILL.md', 'setup-deploy/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
// Other skills
'retro/SKILL.md instructions': ['retro/sections/**', 'retro/SKILL.md', 'retro/SKILL.md.tmpl'],
'qa-only/SKILL.md workflow': ['qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl'],
'gstack-upgrade/SKILL.md upgrade flow': ['gstack-upgrade/SKILL.md', 'gstack-upgrade/SKILL.md.tmpl'],
'retro/SKILL.md instructions': ['retro/sections/**', 'retro/SKILL.md', 'retro/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'qa-only/SKILL.md workflow': ['qa-only/SKILL.md', 'qa-only/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
'gstack-upgrade/SKILL.md upgrade flow': ['gstack-upgrade/SKILL.md', 'gstack-upgrade/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
// Voice directive
'voice directive tone': ['scripts/resolvers/preamble.ts', 'review/SKILL.md', 'review/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts'],
'voice directive tone': ['scripts/resolvers/preamble.ts', 'review/SKILL.md', 'review/SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-llm-eval.test.ts'],
};
/**