From 072e417e423cd6a0a4a0a7aa2b873c9bbe6671e1 Mon Sep 17 00:00:00 2001 From: Claude Date: Tue, 17 Nov 2026 11:39:06 +0000 Subject: [PATCH] Release v2026.11.17 --- CHANGELOG.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index e0950813..5a16d081 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -18,6 +18,8 @@ Sections dated before 2026-09-19 predate the cycle and stay as they are. Named m `docs/RELEASE-PROCESS.md` §8. ## Unreleased + +## v2026.11.17 - fix(exec, ready, gate-check): **unattended mode is recognised by its first word, and an agent cannot approve its own skipped plan** (composition review of the entry-mode PRs): one helper, `mxtk_auto_word` (`project-bin/_position.sh`), now decides "is this Interview mode unattended" for `exec.sh`, `gate-check.sh --adopt` and `ready.sh` — a register line `Interview mode: auto (gate questions go to questions.md …)` was read as attended by the first two, and in a field smoke run the second write of an unattended build got past the plan rule on refuse-once. `ready.sh` reports NOT READY (row `adoption`, named in the evidence file) while any `consentBy: auto-mode` adoption row is unconfirmed — the ✋ only failed Stage 6, which ready.sh does not run before the register reaches Stage 6. Auto is now the STRICTEST of `$CLAUDE_INTERVIEW_MODE`, `.claude/.interview-mode` and the register line, so `CLAUDE_INTERVIEW_MODE=steering` no longer overrides a register that says auto (intended: an override must not quietly switch the unattended guards off). Under auto, a project with no `Entry mode:` is refused like a pipeline mode until build-ready passes or it adopts (attended: banner only, as before). Checkpoint skills no longer describe greenfield as a live mode. Fixtures: `test-mode-contract.sh` W and U, `test-ready.sh` R4 — composition review of #790–#792, Nov 2026 - fix(ci, ready): **review of #788: the toolkit's own text no longer trips its READY check, CI no longer goes red mid-stage, and synced projects start advisory.** The `RESUME.md` starter and `close-task.sh` began a line with READY ("**READY is not written in this file.**"), so every fresh project failed CI and Stage 6 could never pass (now "Only bin/ready.sh writes READY"; a fixture runs init → commit → CI). Check (a) now fails only on stages the register records as passed and warns on the stage in progress (a fresh project at Stage P was red from its first push). `MXTK_CI_ENFORCE` in the workflow: `init-project.sh` installs "1", `sync-project.sh` installs "0" so stage and order checks warn until switched on; the hand-written READY check fails either way — independent review of #788 - fix(ready, ci, gate-check): **field run of the CI gate and `ready.sh` on a six-app copy (#788)**: a hand-written `# READY FOR BENCH (fix round 6, …)` heading passed the `ready` check (READY followed by words now counts; heading markup stripped); `ready.sh` ran over 300 s with no output (every external step now names itself, has stdin closed and a watchdog, `MXTK_READY_STEP_TIMEOUT`, default 120 s; a killed step is NOT MEASURED); the `order` check counted 0 of 234 per-app scripts (`apps//mdlsource/` now counted); and Stage 5 returned an empty verdict on any project with neither a look ledger nor a summary (`rows` unbound under `set -u`, introduced earlier in this PR); on the re-run, claims in a lowercase root `status.md` were not scanned (root status/progress/resume files now matched in any case), and an annotated `- Interview mode: auto (…)` line, which `interview-mode.sh` resolves to steering, waived the independent review (the raw line's first word now decides whether the review is owed) — parent session's field run