From e5e335a96618be276ff1e2bd4da6603375b172a9 Mon Sep 17 00:00:00 2001 From: garrytan Date: Sun, 4 Oct 2026 18:29:18 +0000 Subject: [PATCH] integrate: touchfiles and module-size ratchet entries for the wave's new modules GLOBAL_TOUCHFILES gains session-ledger.ts, published-text.ts and auq-substance-panel.ts; bin/gstack-bun-version.sh joins every entry that lists setup or the updater; auq-matrix stays a rule case with its C4 evidence beside E2E_KINDS; eval-history, published-text and session-ledger are registered new modules. --- test/fixtures/module-size-ratchet.json | 3 +++ test/helpers/touchfiles-data.ts | 18 ++++++++++++++---- 2 files changed, 17 insertions(+), 4 deletions(-) diff --git a/test/fixtures/module-size-ratchet.json b/test/fixtures/module-size-ratchet.json index b2d5b66ae..9376566a8 100644 --- a/test/fixtures/module-size-ratchet.json +++ b/test/fixtures/module-size-ratchet.json @@ -1,6 +1,9 @@ { "newModules": [ { "file": "scripts/lib/shard-engine.ts", "movedFrom": "scripts/test-strict-output.ts" }, + { "file": "scripts/lib/eval-history.ts", "movedFrom": "(new: headroom, red ledger and run triage, kept out of scripts/eval-flake-rank.ts)" }, + { "file": "scripts/lib/published-text.ts", "movedFrom": "(new: one sanitizer for model-written text reaching public reports)" }, + { "file": "test/helpers/session-ledger.ts", "movedFrom": "(new: per-session ledger every paid runner appends to)" }, { "file": "test/helpers/module-size.ts", "movedFrom": "(new: ratchet (c) counter)" }, { "file": "scripts/lib/free-home-guard.ts", "movedFrom": "(new: free-lane home-write tripwire, kept out of scripts/test-free-shards.ts)" }, { "file": "browse/src/routes/activity.ts", "movedFrom": "browse/src/server.ts" }, diff --git a/test/helpers/touchfiles-data.ts b/test/helpers/touchfiles-data.ts index 7178abc6b..e64c09013 100644 --- a/test/helpers/touchfiles-data.ts +++ b/test/helpers/touchfiles-data.ts @@ -92,7 +92,7 @@ export const E2E_TOUCHFILES: Record = { // gate + token→tip map live in bin/gstack-skill-start's emission layer). // SKILL.md setup + preamble (depend on ROOT SKILL.md + gen-skill-docs) - 'skillmd-setup-discovery': [ 'setup', 'bin/gstack-relink', 'SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-bws.test.ts'], + 'skillmd-setup-discovery': [ 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-relink', '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'], @@ -399,7 +399,7 @@ export const E2E_TOUCHFILES: Record = { // devex, office-hours + future PR2 carves). One file iterating CARVE_GUARDS; // the selector sets GSTACK_CARVE_SKILL= to scope cost to the changed // skill (D-CODEX A). Touching the registry/helper or sections.ts runs all. - 'carve-section-loading': [ 'setup','bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', + 'carve-section-loading': [ 'setup', 'bin/gstack-bun-version.sh','bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json','scripts/resolvers/learnings.ts', @@ -683,7 +683,7 @@ export const E2E_TOUCHFILES: Record = { 'codex-review': [ 'test/helpers/outside-voice-evidence.ts', 'lib/outside-review-result.ts', 'lib/gate-outcomes.ts', 'codex/**', 'test/skill-e2e-workflow.test.ts', 'test/fixtures/coverage-audit-fixture.ts', 'test/helpers/coverage-audit.ts', 'test/helpers/coverage-audit-evidence.ts', 'test/helpers/office-hours-attempt.ts', 'bin/gstack-codex-probe', 'scripts/resolve-codex-generation-model.ts', 'scripts/resolvers/constants.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/outside-voice-steps.ts'], // Codex E2E (tests skills via Codex CLI + worktree) - 'codex-discover-skill': [ 'lib/outside-review-result.ts', 'lib/gate-outcomes.ts', 'setup','codex/**', 'scripts/gen-skill-docs.ts', 'test/helpers/codex-session-runner.ts', 'lib/worktree.ts', 'test/codex-e2e.test.ts', + 'codex-discover-skill': [ 'lib/outside-review-result.ts', 'lib/gate-outcomes.ts', 'setup', 'bin/gstack-bun-version.sh','codex/**', 'scripts/gen-skill-docs.ts', 'test/helpers/codex-session-runner.ts', 'lib/worktree.ts', 'test/codex-e2e.test.ts', 'test/helpers/codex-eval.ts', 'bin/gstack-codex-probe', 'scripts/resolve-codex-generation-model.ts', 'scripts/resolvers/constants.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/outside-voice-steps.ts' ], 'codex-review-findings': [ 'lib/outside-review-result.ts', 'lib/gate-outcomes.ts','review/**', 'scripts/gen-skill-docs.ts', 'codex/**', 'test/helpers/codex-session-runner.ts', 'lib/worktree.ts', 'test/codex-e2e.test.ts', @@ -832,7 +832,7 @@ export const E2E_TOUCHFILES: Record = { 'diagram-authoring-quality': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'diagram/**', 'lib/diagram-render/**', 'lib/aside-render.ts', 'bin/gstack-render.ts', 'test/helpers/aside-available.ts', 'browse/src/**', 'test/helpers/llm-judge.ts', 'test/skill-e2e-diagram.test.ts'], // gstack-upgrade - 'gstack-upgrade-happy-path': [ 'test/helpers/outside-voice-evidence.ts', 'setup', 'bin/gstack-relink', 'bin/gstack-session-update', 'gstack-upgrade/**', 'test/skill-e2e-workflow.test.ts', 'test/fixtures/coverage-audit-fixture.ts', 'test/helpers/coverage-audit.ts', 'test/helpers/coverage-audit-evidence.ts', 'test/helpers/office-hours-attempt.ts'], + 'gstack-upgrade-happy-path': [ 'test/helpers/outside-voice-evidence.ts', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-relink', 'bin/gstack-session-update', 'gstack-upgrade/**', 'test/skill-e2e-workflow.test.ts', 'test/fixtures/coverage-audit-fixture.ts', 'test/helpers/coverage-audit.ts', 'test/helpers/coverage-audit-evidence.ts', 'test/helpers/office-hours-attempt.ts'], // Deploy skills 'land-and-deploy-workflow': [ 'bin/gstack-version-bump', 'land-and-deploy/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-deploy.test.ts'], @@ -1538,10 +1538,13 @@ export const GLOBAL_TOUCHFILES = [ 'scripts/lib/paid-cases.ts', // Case/trial shard keys, plan and report moved out of test-paid-shards.ts 'scripts/lib/paid-plan.ts', 'scripts/lib/paid-report.ts', + 'scripts/lib/published-text.ts', // Sanitizes every model-written string paid-report publishes 'scripts/test-pr-profile.ts', 'test/helpers/eval-budgets.ts', 'test/helpers/session-runner.ts', // All E2E tests use this runner + 'test/helpers/session-ledger.ts', // Every runner appends its session facts here + 'test/helpers/auq-substance-panel.ts', // auq-matrix's substance panel; the case has no map key 'test/helpers/session-drain-policy.ts', 'test/helpers/hermetic-env.ts', // Changes every E2E child's environment 'test/helpers/eval-store.ts', // All E2E tests store results here @@ -1566,6 +1569,13 @@ export const GLOBAL_TOUCHFILES = [ * needs a BEHAVIOR_WHY entry naming the tolerated deviation. * judge - an LLM-judge score of a static input, sampled as a panel. * Reclassification is a reviewed diff, never a runtime switch. + * + * auq-matrix- (no map key, template-literal ids) stays `rule`: one + * capture per skill, one trial. C4 (approved 2026-10-04): recommendation + * substance is scored by a 3-sample judgePanel mean on the single capture, + * threshold 4 unchanged; was a single judge sample and red in 6 of 24 + * censuses (37182865432 in the wave set); diagnostic run on wave/d-followups: + * 6/6 skills, panels [5,5,5]. */ export const E2E_KINDS: Record = { 'ship-skipped-queued-finding': 'rule',