diff --git a/CHANGELOG.md b/CHANGELOG.md index 9968b57c..5aca583f 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -26,6 +26,7 @@ Sections dated before 2026-09-19 predate the cycle and stay as they are. Named m - fix(obligations): **`Must-haves: advisory` for projects already past Stage 5 when the must-haves row arrived (follow-up to #787)**: `sync-project.sh` writes one `Must-haves:` line into `PROJECT.md` when none exists, and only then: `advisory — joined at stage N before the must-haves row existed` when gate-check's derived Current stage or `Adopted at stage:` is 6 or 7, else `bound`. `init-project.sh` writes `bound` for new projects. An advisory project's `Obligation must-haves` row reads `ADVISORY` and is left out of the pending count; `bound` keeps PENDING. It is keyed on the written line, not the project's position: a position check would silence a new project the day it passed Stage 5 without the marks. Fixture `tests/wave2/test-must-haves-advisory.sh` — owner request at the review of #787 - fix(obligations): **a quality floor in every entry mode: no per-module obligation reads PASS by absence, and a new `must-haves` row owes one mode-independent checklist per module**: with no module brief and no verify run, `obligation-check.sh` printed `Obligation look PASS — no module has been opened for work yet; nothing owed` (and the same for fidelity, sweep, journeys) on a project that had built ~78 pages and reviewed 0. Now an empty planned scope falls back to the modules that hold built pages, read from the look ledger (`.claude/loop/look/owed.tsv`), else page statements in the project's `*.mdl` scripts, else `.claude/loop/page-scope.json`, each looked for at the root, `app/` and `apps/*/`; every module row reads PENDING with an `OWED BY WHAT WAS BUILT: N page(s) built in M module(s) (...), K of M module(s) discharged` line. A model that has been built on (exec rows in `docs/BUILD-LOG.md`, `*.mdl` scripts, or a derived stage at 5+) with no countable pages is one FAULT naming `bin/page-scope.sh`, never "0 pages"; a `.mpr` with no build evidence (a fresh scaffold) keeps master's PASS line, so `bin/status.sh` still reads `modules opened: 0`. `existing-app-change` never takes scope from `page-scope.json`, which lists the whole model. A project with briefs keeps every earlier verdict. `skills/must-haves.md` (new, on demand) is the single source of poc-build.md's 12-row must-have checklist, generalised to every build type, plus row 13: every region the design shows is on the built page, counted; `poc-build.md` points to it, `module-review.md` stage 5 requires its mark `docs/progress/must-haves/.md` (first line `13 of 13 rows ticked or NOT DONE with a reason`). Informational, like every obligation row: no gate verdict or exit code changes; synced projects at Stage 5+ gain one `must-haves` PENDING row per module. Always-loaded words 64,984 -> 65,032 (budget 80,000). Fixture `tests/wave2/test-obligation-quality-floor.sh` — two field runs, unattended and requirements-driven, Nov 2026 - process(exec, entry modes): **the entry mode is a declared fact every tool reads, and a pipeline-mode project no longer builds without a plan by default**: with no `Entry mode:` and no `Adopted at stage:` line (register or intake), `bin/status.sh` (both views, plus a NEXT rule), `bin/gate-check.sh`'s summary and every `bin/exec.sh` run print one banner, and the BUILD-LOG row is tagged `no entry mode declared`; warn-only. In `Entry mode: migration` or `requirements-driven`, the first MDL write with no plan evidence is refused ONCE (nothing locked, snapshotted or written; `verdict=refused`), remedy in one line: run stages 1–4, or `gate-check.sh --adopt 5 --reason ...`. Cleared by outside evidence (guard rule 6): adoption at 5+, a reasoned `Waived stage 4:`, gate-check's readout at Stage 5+, or `architecture/build-plan.md` plus a module brief (root or `apps//`); a re-run after the one refusal goes on, tagged `no plan`. Never refused: `a-la-carte` (new explicit mode: no pipeline, audit or tooling use; gate-check reads its stages WAIVED by mode), `greenfield`, `Build type: poc`, change an existing app, `--patch`. The one entry-mode tokeniser moves to `project-bin/_position.sh` (pure bash, no process starts; installed beside exec.sh, `bin/lib/entry-mode.sh` is now a shim) — identical output on 44 inputs against the old one. Runbook: greenfield's "stages 1–4 collapse to whatever plan the user already has" becomes a design front end (`poc-build.md` steps 1–4, then a short plan with a few lines per module); `design-artifacts.md` Step 2a adopts a supplied prototype by mapping every screen in `design/wireframes/PAGE-MAP.tsv`, and `ui-preflight-pages.md`'s wireframe STOP accepts a mapped prototype. Fixture `tests/wave2/test-entry-mode-plan-rule.sh` (single tree + `apps//`, register and intake captured from `init-project.sh`) — two field runs, Nov 2026, requirements-driven with a frozen spec and clickable prototypes: ~78 pages built with no plan or target +- process(entry modes, unattended): **the mode contract, and unattended as the primary case** (stacked on the plan-rule PR): `bin/lib/artifact-manifest.tsv`'s existing modes column (tokens unchanged: `migration`, `requirements`, `greenfield`, `existing-app-change`, as `entry_mode_token` produces them; shared with `obligations.tsv`'s column 10) is documented as the per-mode step list, and a row a mode drops reads "not owed (mode …)" instead of "entry mode … does not owe it"; `Build type: poc` is a separate axis, so gate-check reads Stages 0–4, 6, 7 "not owed (mode: Build type: poc)" instead of PENDING (`poc-build.md` updated). Under `Interview mode: auto`, `exec.sh` refuses EVERY MDL write of a migration/requirements-driven project until `gate-check.sh

build-ready` has passed (its PASS now leaves `.mpr-snapshots/.build-ready-pass`) or the register adopts at 5+ / waives Stage 4 — no refuse-once, and a plan on disk alone does not clear it; interactive runs keep refuse-once. `--adopt` at 4+ under auto on those modes also writes an ASSUMED `consentBy: auto-mode` Stage-3/4 row, so `auto_hand_pending()` lists it and Stage 6 FAILs until a person confirms. "Mode changes are decisions" is stated once, in the runbook's Entry Modes (`poc-build.md` points to it). `init-project.sh` and `sync-project.sh` append the missing register sections (Current stage, Decisions, Open questions, Change log) to a PROJECT.md written by hand before init, loudly, from one template (`bin/lib/register-skeleton.sh`; a fresh scaffold is byte-identical to before), and the generated `CLAUDE.local.md` says init runs before any PROJECT.md or model write. `CONVERSION-RUNBOOK.md` gains "Running unattended", the one kick-off brief a project quotes. Fixture `tests/wave2/test-mode-contract.sh` — owner design input + a research comparison of five field builds that followed the process with the one that did not (Nov 2026) - fix(status, agents): **`bin/status.sh` WATCHes an Agent Editor project whose extension module does not travel with the model (#778)**: Studio Pro reads `agenteditor.agent` from `modules/AgentEditor.mxmodule` beside the `.mpr`, and a sync of only `.mpr` + `mprcontents/` left it out of git, so the builder stayed green while every colleague's clone showed `unknown type 'agenteditor.agent'`. Two WATCH items, warn-only (exit code and every verdict unchanged), local files and `git ls-files` only, root and `app/` layouts: a `modules/*.mxmodule` git does not track, and a project using Agent Editor (`AgentEditorCommons` in `analysis/app-facts/inventory.json`, or a `create agent` statement in `mdlsource/`) with no `modules/AgentEditor*.mxmodule`. `skills/mendix-agents.md` (on demand) gains the rule plus the note that the GenAI key, `Encryption.EncryptionKey` and `GenAICommons.StoreTraces` belong in the Default configuration, not a start script. Empty agent references / missing model version (mendixlabs/mxcli#1867) and unset runtime constants are not checked: they need a captured agent document (option 2). Fixture `tests/wave2/test-status-extension-modules.sh` — field report from an Agent Editor project, Nov 2026 - fix(permissions): **exec approval `auto` no longer prompts on every exec's mode check, and `install-claude-hooks.sh` no longer runs unprompted (#782)**: `install-claude-permissions.sh` now allow-lists `exec-approval.sh`, `interview-mode.sh` and `permission-profile.sh`, so their reads run without a prompt, while their only writers, `--set` and `--clear`, prompt through six `ask` rules (`Bash(*exec-approval.sh*--set*)`, …) in the shared settings under every profile (an ask rule beats an allow rule, `full`'s bare `Bash` included). `install-claude-hooks.sh`, which writes `~/.claude/settings.json` for every repo on the machine, gets no allow rule. A re-install adds the ask rules and removes the hooks-installer rule an earlier install added (sidecar); entries someone else wrote are untouched, and `sync-project.sh`'s permission check names both until then. Field run on claude 2.1.325: the read ran, `--set auto` and `--clear` were refused, and with the ask rules removed `--set` ran — from the two independent reviews of #781 - process(skills): **trim PR, moves only: always-loaded words 66,271 -> 64,984 (budget 80,000); Stage 5 test 21,906 -> 20,619, gate 22,954 -> 21,744, review 31,681 -> 30,394 (#783)**: `testing-shape.md` §5's stack and scratch-copy mechanics move verbatim to `e2e-harness-base.md` § Bringing the stack up (the rule and a one-line list of its rules stay in §5); the three new Unit false-green rows move to `unit-test.md` § False-green rows (a pointer row stays in the register); `module-review.md`'s re-shoot mechanics move to `iterative-build-loop.md` § Pipeline mode (the rule, the denominator and the failure example stay) and its MXTK-AI001 sentence to `marketplace-catalogue.md` § Reviewing a built module. Every removed line is in its destination, checked line by line — weekly word-budget audit (#783) diff --git a/CONVERSION-RUNBOOK.md b/CONVERSION-RUNBOOK.md index 603fb125..33f5a994 100644 --- a/CONVERSION-RUNBOOK.md +++ b/CONVERSION-RUNBOOK.md @@ -24,6 +24,28 @@ Then open your agent (Claude Code or equivalent) in `` and say wha | Just an idea / existing plan | Greenfield | P (light), 5–6 | | A live Mendix app you are changing | Change an existing app | P, 0–6 per change | +## Running unattended — the kick-off brief + +**The single source of the text an unattended run (`Interview mode: auto`) is started with.** A +project brief quotes it, verbatim, instead of writing its own; add the project's own goal and +sources under it, never a different definition of done. + +```text +Follow the toolkit's process: skills/conversion-runbook.md, from Stage P, stage by stage. +1. Run bin/init-project.sh first, before writing PROJECT.md or touching the model. +2. Declare the entry mode and build type at kickoff (intake Q1 and Q16); never switch them later + without a recorded decision (conversion-runbook.md → Entry Modes, "Mode changes are decisions"). +3. Stage 5 only after stages 1-4 pass their gates and bin/gate-check.sh

build-ready passes. +4. Close every stage on a clean gate (bin/gate-check.sh

) and commit its output. +5. Stop at a gate that does not pass; report it, do not route around it. +"Done" is the declared mode's steps done and their gates clean — not only journeys passing. +``` + +*Failure it prevents (two field runs, 2026-11):* the project instructions said "follow the +runbook", but the brief the agent read first defined done as journeys passing under a time +budget and never mentioned stages. The agent built about 78 pages with no plan. Five earlier field +builds, whose briefs said in effect what the lines above say, followed the stages. + ## Where you run this — detected, not asked You do not pick an environment; `bin/doctor.sh` detects it from where the session started, and diff --git a/bin/gate-check.sh b/bin/gate-check.sh index 173afbcd..9a7124df 100755 --- a/bin/gate-check.sh +++ b/bin/gate-check.sh @@ -688,6 +688,8 @@ fi # then excused stages on that label. See bin/lib/entry-mode.sh for why. . "$(cd "$(dirname "${BASH_SOURCE[0]}")/lib" && pwd)/entry-mode.sh" ENTRY_MODE="$(entry_mode_token "$ENTRY_RAW")" +BUILD_TYPE="$(reg_field "build type" 2>/dev/null || true)" +case "$(printf '%s' "$BUILD_TYPE" | tr '[:upper:]' '[:lower:]')" in poc|poc[!a-z]*) BUILD_TYPE=poc ;; *) BUILD_TYPE=full ;; esac # stage_waiver — "|", or nothing. Most specific source of truth first. # @@ -728,24 +730,33 @@ stage_waiver() { "$ADOPTED_AT" "${ADOPTED_REASON:+: $ADOPTED_REASON}" return 0 fi + # The mode contract (conversion-runbook.md → Entry Modes; artifact-manifest.tsv column 6). + # `Build type: poc` is its own contract whatever the entry mode: skills/poc-build.md owes its + # steps and must-haves, not stage gates, so 0-4, 6 and 7 read "not owed (mode)" instead of a + # PENDING row nobody may clear. Stage 5 stays checked (MANUAL), and P (the build-type answer). + if [ "$BUILD_TYPE" = poc ]; then + case "$st" in + [0-4]|6|7) printf 'mode|not owed (mode: Build type: poc) — skills/poc-build.md owes steps 1–9 and its must-haves instead\n'; return 0 ;; + esac + fi # Entry mode. The runbook's Entry Modes table already says these stages do not run; until now # the gate did not know that, so it demanded artifacts the runbook had excused. case "$ENTRY_MODE" in greenfield) case "$st" in - 1|2|3|4) printf 'mode|greenfield entry mode — stages 1–4 collapse into the design front end and short plan (conversion-runbook.md → Entry Modes)\n'; return 0 ;; + 1|2|3|4) printf 'mode|not owed (mode: greenfield) — stages 1–4 collapse into the design front end and short plan (conversion-runbook.md → Entry Modes)\n'; return 0 ;; esac ;; requirements-driven) case "$st" in - 7) printf 'mode|requirements-driven entry mode — no legacy system to cut over from; if legacy data turns up, record a Stage-7 decision and this goes back to being checked (conversion-runbook.md → Entry Modes)\n'; return 0 ;; + 7) printf 'mode|not owed (mode: requirements-driven) — no legacy system to cut over from; if legacy data turns up, record a Stage-7 decision and this goes back to being checked (conversion-runbook.md → Entry Modes)\n'; return 0 ;; esac ;; existing-app-change) case "$st" in - 7) printf 'mode|existing-app entry mode — the app is live and stays live; there is no cutover (existing-app-change.md → Deliverables)\n'; return 0 ;; + 7) printf 'mode|not owed (mode: existing-app) — the app is live and stays live; there is no cutover (existing-app-change.md → Deliverables)\n'; return 0 ;; esac ;; a-la-carte) case "$st" in - [0-7]) printf 'mode|a-la-carte entry mode — no pipeline: audit or tooling use only (existing-app-assurance.md); declare another mode to run the stages\n'; return 0 ;; + [0-7]) printf 'mode|not owed (mode: a-la-carte) — no pipeline: audit or tooling use only (existing-app-assurance.md); declare another mode to run the stages\n'; return 0 ;; esac ;; esac return 1 @@ -2618,10 +2629,16 @@ check_build_ready() { echo " ✓ Fit-gap: not owed — project joined the toolkit at stage $ADOPTED_AT" elif fg_w="$(artifact_waived fit-gap)"; then echo " ✓ Fit-gap: WAIVED — $fg_w" - elif [ -z "$fg_path" ] && fg_w="$(stage_waiver 3)" && [ "${fg_w%%|*}" != "noreason" ]; then - echo " ✓ Fit-gap: not owed — ${fg_w#*|}" elif [ -z "$fg_path" ] && case "$(printf '%s' "$bt_raw" | tr '[:upper:]' '[:lower:]')" in poc|poc[!a-z]*) true ;; *) false ;; esac; then + # Before stage_waiver: that now also excuses Stage 3 for poc, in its own words. echo " ✓ Fit-gap: not owed — Build type: poc (skills/poc-build.md) and no fit-gap exists" + elif [ -z "$fg_path" ] && fg_w="$(stage_waiver 3)" && [ "${fg_w%%|*}" != "noreason" ]; then + # A mode reason reads "not owed (mode: ) — "; this line already says "not owed". + fg_r="${fg_w#*|}" + case "$fg_r" in "not owed (mode: "*) + fg_m="${fg_r#not owed (mode: }"; fg_r="${fg_m%%)*} entry mode ${fg_m#*) }" ;; + esac + echo " ✓ Fit-gap: not owed — $fg_r" else if ! type mxtk_fitgap_review >/dev/null 2>&1; then # shellcheck source=lib/marketplace-check.sh @@ -3227,6 +3244,25 @@ register_set_line() { # register_set_line

build-ready` has PASSed (it leaves .mpr-snapshots/.build-ready-pass), or + # the register adopts at 5+ / waives Stage 4 — an adoption under auto is recorded as a ✋ + # human-pending decision that keeps Stage 6 FAILing until a person confirms it. A plan on disk + # alone does not clear it: nobody has checked it. Neither remedy runs through exec.sh. + _GC="${MXTK_ROOT:-${_TKR:-}}/bin/gate-check.sh" + result_line refused no skipped 1 + echo "✗ Plan rule (Interview mode: auto): Entry mode $POS_ENTRY, and the pre-build steps are not done — $_GC $PROJECT_ROOT build-ready has not passed. NOTHING was written." + echo " Remedy: run stages 1-4, then $_GC $PROJECT_ROOT build-ready; or $_GC $PROJECT_ROOT --adopt 5 --reason \"...\" — under auto that is a ✋ human-pending decision, and Stage 6 FAILs until a person confirms it." + echo " Already building past Stage 5? One build-ready pass clears it: its record is kept per clone (.mpr-snapshots/), so each fresh clone runs it once." + log_build "🚫 blocked" "plan rule (auto): Entry mode $POS_ENTRY, build-ready not passed and no adoption — nothing written" + exit 1 + elif [ "$PATCH_MODE" != "1" ] && [ "$POS_BUILD" != poc ] && [ "$POS_AUTO" != 1 ] \ && { [ "$POS_ENTRY" = migration ] || [ "$POS_ENTRY" = requirements-driven ]; } \ && ! mxtk_plan_evidence "$PROJECT_ROOT"; then _PLAN_STAMP="$PROJECT_ROOT/.mpr-snapshots/.plan-rule-refused" diff --git a/skills/conversion-runbook.md b/skills/conversion-runbook.md index e059dcb5..ea99ac0f 100644 --- a/skills/conversion-runbook.md +++ b/skills/conversion-runbook.md @@ -75,7 +75,9 @@ The stages are the same for everyone; what differs is where you enter and which (Failure: a project with full specs + analyzable source was classified greenfield "because there's nothing to migrate" and proposed skipping 0–4 — `process/baseline-incident-history.md` §R1.) -**Declared, or the toolkit says so.** With no `Entry mode:` and no `Adopted at stage:` line, `bin/status.sh`, `bin/gate-check.sh`'s summary and every `bin/exec.sh` run print one banner: *No entry mode declared: the toolkit treats this project as Stage P, not started.* **Plan before build:** in `migration` or `requirements-driven`, the first `exec.sh` model write before Stage 4 has passed or been adopted is refused — once ever per clone, every later write goes on tagged "no plan" — run stages 1–4, or `bin/gate-check.sh

--adopt 5 --reason "..."` (a register line). A build plan plus a module brief, `Waived stage 4:` or adoption at 5+ clears it; never refused: `a-la-carte`, `greenfield`, `Build type: poc`, change an existing app, `--patch`. *Failure (two field runs, 2026-11): a full frozen spec plus clickable prototypes, "requirements-driven" in the brief, and ~78 pages built with no plan or wireframe target, missing whole sections the prototypes showed; nothing spoke, because nothing was declared.* +**Declared, or the toolkit says so.** With no `Entry mode:` and no `Adopted at stage:` line, `bin/status.sh`, `bin/gate-check.sh`'s summary and every `bin/exec.sh` run print one banner: *No entry mode declared: the toolkit treats this project as Stage P, not started.* **Plan before build:** in `migration` or `requirements-driven`, the first `exec.sh` model write before Stage 4 has passed or been adopted is refused — once ever per clone, every later write goes on tagged "no plan" — run stages 1–4, or `bin/gate-check.sh

--adopt 5 --reason "..."` (a register line). A build plan plus a module brief, `Waived stage 4:` or adoption at 5+ clears it; never refused: `a-la-carte`, `greenfield`, `Build type: poc`, change an existing app, `--patch`. Under `Interview mode: auto` there is no refuse-once: every write waits for `build-ready` to pass, and an `--adopt` past Stage 3 or 4 is recorded as a ✋ human-pending decision (Stage 6 FAILs until a person confirms it). Unattended kick-off text: `CONVERSION-RUNBOOK.md` → "Running unattended". + +**Mode changes are decisions — the single source of this rule.** Each mode (Entry mode + Build type) is a contract: its steps are the rows `bin/lib/artifact-manifest.tsv` lists for it; a step the mode drops reads "not owed (mode)", never PASS. Switching mode after kickoff needs the user to say so, is recorded in `PROJECT.md` as a decision (under auto: ✋ human-pending), and never happens because a step was hard. *Failure: a Stage 5 project whose user mentioned a demo dropped its gates.* *Failure (two field runs, 2026-11): a full frozen spec plus clickable prototypes, "requirements-driven" in the brief, and ~78 pages built with no plan or wireframe target, missing whole sections the prototypes showed; nothing spoke, because nothing was declared.* | You're starting from… | Mode | Stages that run | What changes | |---|---|---|---| diff --git a/skills/poc-build.md b/skills/poc-build.md index 2ceb492c..3dcd8687 100644 --- a/skills/poc-build.md +++ b/skills/poc-build.md @@ -5,7 +5,7 @@ **Status: EXPERIMENTAL.** Two builds driven by this text, one model, small apps. First (fictional visitor-pass app, ~36 min): "nearly demo-ready", function 26 of 29, design ~4.1 of 5 (not blind), journey 22/22. Second (kickoff question asked first, answered POC; ~64 min): a blind grader compared it with the same requirements built in plain plan mode with no toolkit: function 25 of 25 against 24 of 24 testable; refusals in-page 7 of 7 against 2 of 6; must-haves 10 of 10 against 5 of 10 (the list now in `skills/must-haves.md`); visual mean 3.8 against 3.6; hand-over 22 of 24 against 12 of 24; time ~64 against ~27 min (both ran in parallel, inflated). The gain is the must-have list and the hand-over, not the look, and it costs time. NOT proven: a real person answering (answers and approval came from a prepared file). The test cadence (steps 7–8) changed after both builds (#770) and is unmeasured. -**Who asks.** The kickoff interview asks the build type first, at project birth (intake Q16; rendering per `skills/interview-protocol.md` §3). On a POC answer `Build type: poc` is recorded `CONFIRMED` in `PROJECT.md`, and this skill is the flow; the other intake questions are not asked. A missing `Build type:` line means `full`; `Interview mode: auto` never picks `poc`. A project past kickoff whose user only says "we need a demo this week" does NOT switch: the lead says in one line that the build type is chosen at the start and offers to continue the normal build (optionally `Pipeline mode: high-speed`). Switching such a project needs the user to say so explicitly, confirmed once, and is recorded in `PROJECT.md` as a decision. *Failure: a Stage 5 project whose user mentioned a demo dropped its gates.* A POC build does **not** run the nine stage gates. Stage P still checks that every `intake.md` question carries an answer marker, so write them: Q16 `Answered (CONFIRMED): POC build`, and under each of Q1–Q15 exactly `Unverified — how to verify: not asked, POC build (Build type: poc, skills/poc-build.md); ask it if the build continues as a full build`. Then `bin/gate-check.sh` shows Stage P `PASS` (markers present; it says nothing about those answers), Stages 0–4, 6, 7 `PENDING`, Stage 5 `MANUAL`. *Failure: unmarked questions kept Stage P at `FAIL` for the whole build.* No answer: end the turn and wait (`skills/interview-protocol.md` §3); `ASSUMED` only when the user said "you decide" (= `full`). +**Who asks.** The kickoff interview asks the build type first, at project birth (intake Q16; rendering per `skills/interview-protocol.md` §3). On a POC answer `Build type: poc` is recorded `CONFIRMED` in `PROJECT.md`, and this skill is the flow; the other intake questions are not asked. A missing `Build type:` line means `full`; `Interview mode: auto` never picks `poc`. A project past kickoff whose user only says "we need a demo this week" does NOT switch: the lead says in one line that the build type is chosen at the start and offers to continue the normal build (optionally `Pipeline mode: high-speed`). Switching follows the runbook's "Mode changes are decisions" (`conversion-runbook.md` → Entry Modes), the one statement of that rule. A POC build does **not** run the nine stage gates. Stage P still checks that every `intake.md` question carries an answer marker, so write them: Q16 `Answered (CONFIRMED): POC build`, and under each of Q1–Q15 exactly `Unverified — how to verify: not asked, POC build (Build type: poc, skills/poc-build.md); ask it if the build continues as a full build`. Then `bin/gate-check.sh` shows Stage P `PASS` (markers present; it says nothing about those answers), Stages 0–4, 6, 7 `WAIVED` — "not owed (mode: Build type: poc)", the mode contract — and Stage 5 `MANUAL`. *Failure: unmarked questions kept Stage P at `FAIL` for the whole build.* No answer: end the turn and wait (`skills/interview-protocol.md` §3); `ASSUMED` only when the user said "you decide" (= `full`). **Size:** more than 3 entities, 5 pages or 2 roles is unmeasured. Say so once, then continue: a warning, not a refusal (*failure: an agent that refuses, or proceeds without a word*). diff --git a/tests/wave2/test-closeout.sh b/tests/wave2/test-closeout.sh index 4d0cc714..6686b550 100755 --- a/tests/wave2/test-closeout.sh +++ b/tests/wave2/test-closeout.sh @@ -122,7 +122,7 @@ echo "== T8: --closeout without a stage refuses ==" echo "== T9: a row the entry mode does not owe is N/A, never 'still missing' (2026-09-25) ==" P="$(mkproj t9)" OUT="$("$GATE" --closeout "$P" 0 2>&1)" -case "$OUT" in *"⏭ \`app-report\` — N/A: entry mode requirements does not owe it"*) ok "app-report N/A on a requirements-driven register" ;; *) bad "app-report not N/A: $(printf '%s' "$OUT" | grep app-report)" ;; esac +case "$OUT" in *"⏭ \`app-report\` — N/A: not owed (mode requirements)"*) ok "app-report N/A on a requirements-driven register" ;; *) bad "app-report not N/A: $(printf '%s' "$OUT" | grep app-report)" ;; esac if printf '%s\n' "$OUT" | grep 'still missing for this stage' | grep -q 'app-report'; then bad "plain words list app-report as missing"; else ok "plain words do not list a row this mode does not owe"; fi rm -rf "$WORK" diff --git a/tests/wave2/test-entry-mode-plan-rule.sh b/tests/wave2/test-entry-mode-plan-rule.sh index 1b30abba..2e3ad2a7 100755 --- a/tests/wave2/test-entry-mode-plan-rule.sh +++ b/tests/wave2/test-entry-mode-plan-rule.sh @@ -171,7 +171,7 @@ GC="$("$TOOLKIT/bin/gate-check.sh" "$P" 2>&1)" case "$GC" in *"No entry mode declared"*) bad "gate-check silent once declared" ;; *) ok "gate-check silent once declared" ;; esac mkproj single "Entry mode: a-la-carte" GC="$("$TOOLKIT/bin/gate-check.sh" "$P" 3 2>&1)" -case "$GC" in *"a-la-carte entry mode — no pipeline"*) ok "a-la-carte stages read WAIVED with the reason" ;; *) bad "a-la-carte stages read WAIVED with the reason" "$(printf '%s\n' "$GC" | grep -m2 '^Stage [0-3]')" ;; esac +case "$GC" in *"not owed (mode: a-la-carte) — no pipeline"*) ok "a-la-carte stages read WAIVED with the reason" ;; *) bad "a-la-carte stages read WAIVED with the reason" "$(printf '%s\n' "$GC" | grep -m2 '^Stage [0-3]')" ;; esac echo "" echo "== $PASS passed, $FAIL failed" diff --git a/tests/wave2/test-file-bugs.sh b/tests/wave2/test-file-bugs.sh index 3e347284..626c8113 100755 --- a/tests/wave2/test-file-bugs.sh +++ b/tests/wave2/test-file-bugs.sh @@ -469,7 +469,7 @@ sys.exit(not (pats and m("bin/file-bugs.sh --all") and m("bin/file-bugs.sh --fil and m("bin/file-bugs.sh --import b.md") and m("bin/file-bugs.sh --import b.md --dry-run") and m("bin/lib/file-bugs.py --import b.md") and not m("bin/file-bugs.sh --bundle"))) PYX' -chk "init-project ships the opt-in commented out" 'grep -q "