Skip to content

Commit 7ff741a

Browse files
committed
Merge #321: PROOF-OF-LOOK per section; final-look not due before derived Stage 6 (closes #155, refs #68 #188)
Review: MERGE (after fix round + confirmation) — NOT YET DUE limited to final-look under gate-check's derived stage readout; master vs head on 9 register states: every other obligation line byte-identical; unresolvable stamp falls back to master behaviour.
2 parents ec90cf3 + 9b73def commit 7ff741a

5 files changed

Lines changed: 251 additions & 20 deletions

File tree

‎CHANGELOG.md‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -23,6 +23,9 @@ Sections dated before 2026-09-19 predate the cycle and stay as they are.
2323
- fix(page-fidelity): **text is matched against what the page shows, on whole words; ButtonStyle counts as `btn btn-<style>`; layout chrome comes from the layout** ([#158](https://github.com/MendixMau/mxcli-project-toolkit/issues/158), [#157](https://github.com/MendixMau/mxcli-project-toolkit/issues/157)). Headings, actions and content were a substring test over the whole page MDL with 60% of the >3-char words enough, so a wireframe H2 "Product overview" counted as present on a page named `Product_Overview`, "Deactivate product" on a button captioned "Deactivate", and an "Add" button passed with no words to test. Each wireframe string is now matched per literal against the page's own captions — headings against Title/Content/non-button Captions, actions against button Captions, content against every displayed literal — on whole words, all of them for a label under three words; bindings keep the identifier corpus. An `actionbutton` now declares `btn` + `btn-<ButtonStyle>` (`btn-default` when DESCRIBE omits it), per the measured DOM contract in `learned-stylegallery.md`. The page's layout, when its MDL is in the input (`describe layout`), or `--chrome a,b`, adds to the fixed chrome set; without either nothing changes. Whole-word matching folds plurals (`Orders` = `Order`) on both sides, and multi-line ALTER `set (…) on w` statements count, including a ButtonStyle that replaces the old one. Scores move: of the 11 page/wireframe pairs already in the repo, 10 are unchanged and a stub page drops 66%→39% (a "Waiting for customer" heading credited from `dgWaiting` + `CustomerQuery`); the new probe pairs fail on the old scorer; a field run on a live project is still owed. — MendixMau
2424
- skill(interaction-model, design-artifacts, runbook): **Stage 3 writes `design/interaction-model.md` before the first wireframe — a home per role, an inbox per user task, and per page how it is reached, its page parameter and its data view source; every wireframe opens with a `wf-contract` block (`Page parameter:`, `Reached from:`, `Drawn as role:`)** ([#291](https://github.com/MendixMau/mxcli-project-toolkit/issues/291), part 1 of 3). Three apps built with the toolkit passed every gate (Stage 3/4 PASS, page fidelity 81-89% on the affected pages, lint 0 errors, e2e 69/69) while one of them rooted 8 pages on a parameterless "current record" retrieve, gave all 6 roles one home page and put 3 process stages in a 6-item menu; the wireframes were drawn as one role with one record, so every downstream check inherited the defect. Routed on demand, Stage 3, lead + ba + architect; the gate facts and the model-side check are follow-ups. — MendixMau
2525
- chore(context): **baseline word budget freed — 79,735 → 75,963 words (−3,772) without dropping a rule.** The always-on tier sat 265 words under its 80,000 cap, so three open PRs could not all merge. Long incident narratives in `conversion-runbook.md`, `source-triage.md` and `interview-protocol.md` became one-line failure examples pointing at new on-demand `process/baseline-incident-history.md`, where the original text is kept verbatim per section (R1–R20, AR1, ST1–ST4, IP1–IP3); the runbook's copy of the open-questions status table now defers to `interview-protocol.md` §4; `agent-roles.md`'s six template shapes (setup-only, ~2,300 words) moved verbatim to `agents/README.md`, which the installers never copy (explicit `MXTK_AGENTS` list). Every STOP, rule, denominator and gate cell stays in place; files touched by open PRs were left alone. — MendixMau
26+
- fix(obligations): **Each `PROOF-OF-LOOK` line is checked against the `VALID AT` stamp of its own section, and the report's newest stamp is chosen by commit time ([#155](https://github.com/MendixMau/mxcli-project-toolkit/issues/155)).** A review file that keeps dated addenda was still FAULTing: every proof line was compared with the single newest stamp, so the first section's honest screenshots read "older than VALID AT". The field project's only way back to green was to re-shoot every page and delete its older proof lines. A citation now belongs to the nearest stamp above it (one above every stamp belongs to the headline's), on pretty-printed and one-line HTML alike. "Newest" was last-in-file, so an addendum written above the original stamp went STALE; it is now the stamp with the newest commit time. If any stamp no longer resolves (squash, rebase, shallow clone), the last stamp in the file is used, as before, and staleness reads as unmeasured. A stale shot inside a section still FAULTs. Motivated by the field report in #155 (a requirements-driven build, 2026-09-26). The checker is proven by fixtures only (`test-obligation-valid-at.sh` T3b, T4-T8; 3 fail on master); no field run against a real report yet — MendixMau
27+
- fix(obligations): **The final LOOK is held to the per-module LOOK's proof rules, and is not owed before Stage 6.** Found in an independent review of #303. `final-look` (from-stage 6) read PENDING on a project still at Stage P, because the from-stage column was only compared with `--adopt`. It now reads `NOT YET DUE` while gate-check's own derived `## Current stage` readout (the line carrying "(derived by gate-check") is below 6. A hand-written or scaffold stage line counts as unreadable, so the row stays owed; hand-written lines disagreed with the gates in 8 of 12 field projects. Every other obligation keeps its verdict. `module-review.md` § "The final LOOK" requires `PROOF-OF-LOOK` lines, but the check ran only for `look`; it now runs for `final-look` too. An unstamped final-look report could never go stale and so passed forever; it is now FAULT ("NO VALID AT"). Fixture `test-obligation-final-look.sh` T4-T11 (3 fail on master). — MendixMau
28+
- learn(brd-to-build-plan): **No `LOOK` row kind; the paragraph next to the Kind list says why ([#68](https://github.com/MendixMau/mxcli-project-toolkit/issues/68), [#188](https://github.com/MendixMau/mxcli-project-toolkit/issues/188) item 6).** A look is a `HARNESS` row naming the LOOK pass. Whether it happened is read from the `look` and `fidelity` obligations and the look-ledger, never from a State cell a person can set by hand. A second record could say "looked at" while the gate says nobody did. — MendixMau
2629
- learn(testing-shape, test-result-audit): **three test-strength rules, each with a denominator: refusals probed on the server, every undeclared 4xx a failure, one clean-database final run** ([#172](https://github.com/MendixMau/mxcli-project-toolkit/issues/172)). A field comparison of two builds against one frozen spec found the toolkit build checked permission refusals only in the client (a hidden menu item), logged unexpected 400/422 responses as information, and reached 20/20 by stitching three runs. `testing-shape.md` §7 gains three report lines (`N of N restricted pairs probed server-side`, `undeclared 4xx/5xx: 0 of M requests — each fails its step`, `one clean-DB run <id>: N of N scenarios incl. timers, not stitched`); `test-result-audit.md` gains check 2e, which carries the reasons and the field evidence and asks for those numbers. Both baseline skills stay inside the 80,000-word baseline budget (79,997): the reasons live in the on-demand audit skill, and two redundant sentences in `testing-shape.md` §4's verdict paragraphs were folded (the empty-set corollary is stated in the Trace row, `harness-architecture.md` and `report-schema.md`). The backing inbox note is trimmed to its unpromoted "Keep" items. — MendixMau
2730
- learn(learned-detection-gaps, module-review): **two UI defects every model gate passes: a lazy-loaded combo box filter hides its preset, and a theme that pins row heights by position lets the next row cover an inserted widget** ([#299](https://github.com/MendixMau/mxcli-project-toolkit/issues/299)). Both passed check, mxbuild, lint and the scripted checks on a 127-module production app and were found only in the running app. Two register rows with the first oracle and the pre-build check (pluggable properties that change *when* data loads; grep the theme for fixed `height` on positional row classes before an insert), and two LOOK lines in `module-review.md` §4c with denominators (`N of N filters show their preset on first load`, `N of N widgets inserted into an existing container fully visible`). — jopterhorst
2831
- fix(app-restart, test-stack-up): **a port held by another process before `run --local` is named and reported as "instrument blocked" (exit 4), never killed** ([#262](https://github.com/MendixMau/mxcli-project-toolkit/issues/262)). Studio Pro had started its own runtime on the app/admin ports a restart needed; `mxcli run --local` then failed with "Authentication failed" (the admin API answering was Studio Pro's), the next journey ran against Studio Pro's runtime, and four more runs were NOT RUN. `app-restart.sh` now checks the app port and the admin port (record's `adminPort`, else app + 10) before stopping anything — a holder outside the recorded process tree exits 4 with its name, pid and parent — and again after the stop, where anything still holding a port is by definition not ours. `test-stack-up.sh` runs the same check wherever it would tell you to start `run --local` (`--no-docker`, no Docker daemon, `--check` with a leftover record), on the record's ports, `RUN_LOCAL_APP_PORT`/`RUN_LOCAL_ADMIN_PORT`, or mxcli's defaults 8080/8090. Holder lookup: lsof, then ss, then netstat + tasklist on Windows; unnamed holders still block when nothing of ours is running. Fixtures: `test-app-restart.sh` +2 cases (14 assertions, all fail on the old script), `test-stack-up-local.sh` T7 (4 of 6 fail on the old script). — AlvinnYeo

0 commit comments

Comments
 (0)