From ce59a327d8d7a6c78c7caa069dcd1876983f5cb9 Mon Sep 17 00:00:00 2001 From: garrytan Date: Mon, 19 Oct 2026 18:47:09 +0000 Subject: [PATCH] test: rebuild the historical cookie approval with the dropped section, record the skill-fixture change as non-behavioral Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --- CHANGELOG.md | 3 ++- scripts/harness-version.json | 2 +- test/helpers/manual-judge-review-fixture.ts | 2 ++ 3 files changed, 5 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 669fd12ab..b9b0965cd 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -14,7 +14,8 @@ - `test/gen-skill-docs.test.ts` (the benchmark routing and CSO voice tests read the template); - `test/skill-validation.test.ts` (trigger and proactive phrases are checked in `SKILL.md.tmpl`); - `test/helpers/parity-harness.ts` (no `## When to invoke` heading required); - - `test/helpers/skill-fixture.ts` and `test/skill-e2e-retro.test.ts` (the section is dropped from the review, review-army and retro E2E section lists). + - `test/helpers/skill-fixture.ts` and `test/skill-e2e-retro.test.ts` (the section is dropped from the review, review-army and retro E2E section lists). `scripts/harness-version.json` records the `skill-fixture.ts` change as non-behavioral: `HARNESS_VERSION` stays 6, and the regenerated SKILL.md bytes already start those cases' new series. + - `test/helpers/manual-judge-review-fixture.ts` puts the removed section back when it rebuilds the historical cookie-workflow approval, so the approved prompt hash and line range still match. The approval itself is unchanged. One new free test checks that the root router routes every voice trigger, and it skips the `connect-chrome` alias symlink. No threshold, trial count, case kind or judge changed. No context-budget ceiling rose except the root router's. diff --git a/scripts/harness-version.json b/scripts/harness-version.json index 4e9d5794e..e5614ecee 100644 --- a/scripts/harness-version.json +++ b/scripts/harness-version.json @@ -48,7 +48,7 @@ "test/helpers/session-drain-policy.ts": {"blob":"6211239dd0485e6495a700b824a7e0e61d1bcd97","since":6}, "test/helpers/session-ledger.ts": {"blob":"425323284a368f5e77937e03884db4dea4e6134e","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"}, "test/helpers/session-runner.ts": {"blob":"cc65a66adafa9c053e3da3c6f17b5ac86c0eade7","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"}, - "test/helpers/skill-fixture.ts": {"blob":"b188064594eb4201a54a80ba1bc6f28e31d7f49e","since":6}, + "test/helpers/skill-fixture.ts": {"blob":"ffece830f35b0f1562005105e9296dc4d8ca50c2","since":6,"nonBehavioral":"skill-fixture.ts drops 'When to invoke this skill' from the review, review-army and retro section lists because #3129 stops generating that heading; extraction would throw otherwise. The fixture bytes follow the regenerated SKILL.md, whose owned prompt bytes already start those cases' new series."}, "test/helpers/test-selection.ts": {"blob":"51655f89f66be7a5ec487e2abfe4744300ebd5f6","since":6}, "test/helpers/touchfiles.ts": {"blob":"15f369056d41b9dc42dcd86f81f60c878074704c","since":6} } diff --git a/test/helpers/manual-judge-review-fixture.ts b/test/helpers/manual-judge-review-fixture.ts index ded8a3508..00349dce2 100644 --- a/test/helpers/manual-judge-review-fixture.ts +++ b/test/helpers/manual-judge-review-fixture.ts @@ -35,6 +35,8 @@ const LATER_WAVE_EDITS: Array<[string, string]> = [ "The skill-start output above already ran artifacts sync. Act on its lines:\nGBrain hint text (if present) tells you when to prefer `gbrain` over Grep;\n`ARTIFACTS_SYNC:` reports sync health (`off`, `mode=... | queue=N`,\n`remote-mode`, or a restore hint naming `gstack-brain-restore`).\n\nThe one-time privacy stop-gate (artifacts-sync consent) arrives as a\n`GSTACK_INSTRUCTION` block from skill-start when consent is actually pending\n\u2014 fire it via AskUserQuestion exactly as the block instructs."], // Oct 8 wave: the tier-1 voice directive gained the reply-language rule (two lines longer). ["Reply in the language of the user's latest message unless asked otherwise. Code, commands, paths, identifiers and quoted output stay verbatim.\n\n", ''], + // #3129 dropped the Claude body's "When to invoke" section above the preamble (seven lines shorter). + ['\n\n## Preamble (run first)\n', '\n\n\n## When to invoke this skill\n\nOpens an interactive picker UI where you select which cookie domains to import.\nUse before QA testing authenticated pages. Use when asked to "import cookies",\n"login to the site", or "authenticate the browser".\n\n## Preamble (run first)\n'], ]; // The honest-install wave (lazy Chromium) made the fallback probe call