diff --git a/CHANGELOG.md b/CHANGELOG.md index f358158a7..c19d516a2 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -15,6 +15,8 @@ ### Gate integrity - No threshold, budget, timeout, trial count or existing case kind changed. The ship skill's parity size stays under its cap (313,277 of 313,281 bytes). The new eval's negative controls are the two /investigate cases, and on the base router the triage cases go red. +- One pin rises with a stated reason: `test/eng-finding-retry-budget.test.ts` counts 110 paid test files (was 109) for the new eval file. +- Each train gate now runs the four new cases, one trial each, for about $0.37 (measured at this head: $0.06, $0.06, $0.11 and $0.14; about 67 s wall when they run in parallel). ## [1.91.186.0] - 2026-10-24 diff --git a/test/eng-finding-retry-budget.test.ts b/test/eng-finding-retry-budget.test.ts index 9d35a6f0a..0320c653d 100644 --- a/test/eng-finding-retry-budget.test.ts +++ b/test/eng-finding-retry-budget.test.ts @@ -141,7 +141,7 @@ test('live periodic census fits the declared CI wall including setup', () => { test('registered allocation is deterministic and preserves every discovered file', () => { const files = collectPaidTestFiles(); - expect(files).toHaveLength(109); // + skill-e2e-dx-error-contract (#3226); + skill-e2e-gate-integrity (HONEST_WORK_GATE_INTEGRITY W8); + skill-e2e-autoplan-schema-canary, -guard-pty and -long-session (Oct 7 wave, CEO-13, ENG-18, CEO-15); + skill-e2e-ship-measure-seeded-flake (v1.91.32.0); W5a: 15 carve wrappers became one case-sharded file; + codex-e2e-multiblock-live and skill-e2e-design-model-smoke (v1.91.30.0); + expect(files).toHaveLength(110); // + skill-e2e-failure-routing (#3157/#3158); + skill-e2e-dx-error-contract (#3226); + skill-e2e-gate-integrity (HONEST_WORK_GATE_INTEGRITY W8); + skill-e2e-autoplan-schema-canary, -guard-pty and -long-session (Oct 7 wave, CEO-13, ENG-18, CEO-15); + skill-e2e-ship-measure-seeded-flake (v1.91.32.0); W5a: 15 carve wrappers became one case-sharded file; + codex-e2e-multiblock-live and skill-e2e-design-model-smoke (v1.91.30.0); expect(files).toContain('test/skill-e2e-ship-skip.test.ts'); const m = livePlan(files); expect(livePlan([...files].reverse())).toEqual(m);