@pmelab/gtd 44.0.0 → 45.1.0

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "gtd",
-  "version": "44.0.0",
+  "version": "45.1.0",
   "description": "Drive the gtd loop inside Claude Code: agent turns run as subagents, gtd decides every beat",
   "author": {
     "name": "Philipp Melab"

package/README.md

@@ -564,6 +564,22 @@ noted in steps 3 and 4 below.
    `gtd judge answer` / conservative-default shape as step 3's own judged
    points.
 
+   **The review learns your taste.** Each won't-fix and each own answer is a
+   candidate standard. A judge (`build.review.standards.judge`) asks whether it
+   is reusable beyond this note; at `standardMinP` (`0.8`) or above it is kept
+   in `.gtd/STANDARDS.md` with no question asked, and the next review lists it
+   under `## Standards added`. Every later agent turn — the lenses, the naive
+   pass, the build, every fix — is handed the kept standards, so a finding you
+   rejected once is not raised again and a rule you wrote is followed, in this
+   process and every later one. One the judge does not confidently rule out
+   contradicting a standard already kept is not applied: it waits under
+   `## Undecided` and becomes a `## Standard conflict <id>` note in the review,
+   with its own three boxes — **keep the new one (drop the old)**, **keep the
+   old one (discard the new)**, or **your own wording**, which replaces both —
+   and the review does not sign off until it is answered. `.gtd/STANDARDS.md` is
+   committed and yours to edit; gtd rewrites it as one bullet per standard when
+   it learns.
+
 You never talk to it. Every exchange is a file in `.gtd/` that you edit in your
 own editor, and every answer you give is a commit. Your test suite is the gate
 throughout: a red baseline stops the process before it starts, and a red build
@@ -721,6 +737,21 @@ hand or leave it for cleanup.
 
 The delivery model these workflows implement: [Delivery model](SDLC.md).
 
+### Reviving skipped tests
+
+The opt-in `tests` workflow revisits tests nobody runs. Export `tests` from
+`@pmelab/gtd/workflows/tests` and run `gtd door tests` (or
+`gtd --workflow tests`). On a green baseline an agent sweeps the whole
+repository — every skipped test plus the `test-audit` skill's findings — into
+`.gtd/TESTS.md`, one section per test file. Each file is then rewritten in its
+own turn until nothing in it is skipped and the suite is green. A test the agent
+calls obsolete stays skipped and is proposed for deletion: the review in
+`.gtd/REVIEW.md` gives each proposal `delete it`, `keep it skipped` or
+`_your answer_`, and refuses sign-off until each holds one tick. An agent turn
+that deletes a test file is refused. Skip detection is a factory option with
+JavaScript/TypeScript and cucumber defaults; see
+[Reviving skipped tests](docs/configuration.md#reviving-skipped-tests).
+
 ## Checking a range for stray files
 
 ```sh
@@ -859,15 +890,15 @@ approvals as `approvals` (`[]` when none), and `gtd history show` prints each as
 gtd is one package, `@pmelab/gtd`, and every entrypoint shares its version and
 [SemVer promise](https://github.com/pmelab/gtd/blob/main/COMPATIBILITY.md).
 
-| Import                                                                                                                                                         | What it is                                                                                                                                                                                             |
-| -------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| `@pmelab/gtd/flows`                                                                                                                                            | The flow API a workflow is written in: the steps (`agent`, `human`, `run`, …), `scope` and `slice` (named spans of a process), workflow factories, `defineConfig` and `FLOWS_PROTOCOL`.                |
-| `@pmelab/gtd/wire`                                                                                                                                             | The driver protocol: `WIRE_SCHEMA`, the exit codes and the types of every `--json` document.                                                                                                           |
-| `@pmelab/gtd/steering`                                                                                                                                         | The steering-file formats (`qa`, `review`) and the review-note readers.                                                                                                                                |
-| `@pmelab/gtd/workflow-kit`                                                                                                                                     | Policy-free building blocks to compose a workflow from: health checks, quality laps, scenario freezing, review tails.                                                                                  |
-| `@pmelab/gtd/workflows`                                                                                                                                        | Every shipped workflow and all its parts in one module; also resolvable as `@pmelab/gtd/workflow`.                                                                                                     |
-| `@pmelab/gtd/workflows/feature`, `@pmelab/gtd/workflows/review`, `@pmelab/gtd/workflows/fix`, `@pmelab/gtd/workflows/rollout`, `@pmelab/gtd/workflows/cleanup` | One shipped workflow each: its factory as the default export, its parts, and the reserved exports (`defaults`, `envDefaults`, `summary`, `steering`, `skills`, `access`). `gtd install` imports these. |
-| `@pmelab/gtd/testkit`                                                                                                                                          | Runs any workflow against the real engine, in an in-memory or a real repository. Needs `vitest` and `quickpickle`, optional peer dependencies.                                                         |
+| Import                                                                                                                                                                                        | What it is                                                                                                                                                                                             |
+| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `@pmelab/gtd/flows`                                                                                                                                                                           | The flow API a workflow is written in: the steps (`agent`, `human`, `run`, …), `scope` and `slice` (named spans of a process), workflow factories, `defineConfig` and `FLOWS_PROTOCOL`.                |
+| `@pmelab/gtd/wire`                                                                                                                                                                            | The driver protocol: `WIRE_SCHEMA`, the exit codes and the types of every `--json` document.                                                                                                           |
+| `@pmelab/gtd/steering`                                                                                                                                                                        | The steering-file formats (`qa`, `review`) and the review-note readers.                                                                                                                                |
+| `@pmelab/gtd/workflow-kit`                                                                                                                                                                    | Policy-free building blocks to compose a workflow from: health checks, quality laps, scenario freezing, review tails.                                                                                  |
+| `@pmelab/gtd/workflows`                                                                                                                                                                       | Every shipped workflow and all its parts in one module; also resolvable as `@pmelab/gtd/workflow`.                                                                                                     |
+| `@pmelab/gtd/workflows/feature`, `@pmelab/gtd/workflows/review`, `@pmelab/gtd/workflows/fix`, `@pmelab/gtd/workflows/rollout`, `@pmelab/gtd/workflows/cleanup`, `@pmelab/gtd/workflows/tests` | One shipped workflow each: its factory as the default export, its parts, and the reserved exports (`defaults`, `envDefaults`, `summary`, `steering`, `skills`, `access`). `gtd install` imports these. |
+| `@pmelab/gtd/testkit`                                                                                                                                                                         | Runs any workflow against the real engine, in an in-memory or a real repository. Needs `vitest` and `quickpickle`, optional peer dependencies.                                                         |
 
 Types come from the TypeScript sources the package ships. Configs never need an
 install for any of these but `./testkit`: gtd resolves a `gtd.config.ts`'s

package/dist/chunks/{reserved-DJk_6-ju.mjs → reserved-ulcSkND6.mjs}

@@ -113,6 +113,108 @@ const requireFlag = (workflow, registryPath, name, defaultOn) => {
 	if (entry.defaultOn !== defaultOn) return refuse(defaultOn ? `gtd: ${workflow}: flag "${name}" is not default-on — roll it out first` : `gtd: ${workflow}: flag "${name}" is already default-on`);
 };
 //#endregion
+//#region src/workflows/shared/standards.ts
+const STANDARDS = ".gtd/STANDARDS.md";
+const UNDECIDED = "Undecided";
+const oneLine = (text) => text.replace(/[\s\x00-\x1f\x7f-\x9f\u2028\u2029]+/g, " ").trim();
+const ITEM = /^(?:[-*+]|\d+[.)])\s+(.*)$/;
+const CONTRADICTS = /^\s+[-*+]\s+contradicts:\s*(.*)$/i;
+const wrapped = (item, line) => {
+	const olds = item.olds;
+	if (olds !== void 0 && olds.length > 0) olds[olds.length - 1] += ` ${line.trim()}`;
+	else item.text += ` ${line.trim()}`;
+};
+/** What tells two standards apart: not the emphasis or spacing a formatter may rewrite. */
+const standardKey = (text) => oneLine(text.replace(/[*_`\\]/g, "")).toLowerCase();
+const toStandards = (items) => {
+	const seen = /* @__PURE__ */ new Set();
+	const fresh = (text) => {
+		const key = standardKey(text);
+		if (key === "" || seen.has(key)) return false;
+		seen.add(key);
+		return true;
+	};
+	const decided = items.filter((i) => i.olds === void 0).map((i) => oneLine(i.text));
+	const undecided = items.flatMap((i) => i.olds === void 0 ? [] : [{
+		text: oneLine(i.text),
+		olds: i.olds.map(oneLine).filter((o) => o !== "")
+	}]);
+	return {
+		decided: decided.filter(fresh),
+		undecided: undecided.filter((c) => fresh(c.text))
+	};
+};
+/**
+* Every top-level bullet is one standard, those under `## Undecided` waiting
+* on the human; a hand-edited file may group the rest under any heading.
+*/
+const parseStandards = (text) => {
+	const items = [];
+	let pending = false;
+	let last;
+	for (const line of text.split("\n")) {
+		const heading = /^(#{1,6})\s+(.*)$/.exec(line);
+		const item = ITEM.exec(line);
+		const old = CONTRADICTS.exec(line);
+		if (heading !== null) {
+			pending = heading[1].length > 1 && heading[2].trim() === UNDECIDED;
+			last = void 0;
+		} else if (item !== null) {
+			last = pending ? {
+				text: item[1],
+				olds: []
+			} : { text: item[1] };
+			items.push(last);
+		} else if (old !== null && last?.olds !== void 0) last.olds.push(old[1]);
+		else if (/^\s+\S/.test(line) && last !== void 0) wrapped(last, line);
+		else if (line.trim() !== "") last = void 0;
+	}
+	return toStandards(items);
+};
+const renderStandards = ({ decided, undecided }) => {
+	return `${[
+		"# Standards",
+		"Kept from your review answers for every agent turn. One standard per bullet.",
+		...decided.length === 0 ? [] : [decided.map((s) => `- ${s}`).join("\n")],
+		...undecided.length === 0 ? [] : [`## ${UNDECIDED}`, undecided.map((c) => [`- ${c.text}`, ...c.olds.map((o) => `  - contradicts: ${o}`)].join("\n")).join("\n")]
+	].join("\n\n")}\n`;
+};
+const hash = (raw) => {
+	const text = standardKey(raw);
+	let h = 2166136261;
+	for (let i = 0; i < text.length; i++) h = Math.imul(h ^ text.charCodeAt(i), 16777619);
+	return (h >>> 0).toString(16).padStart(8, "0");
+};
+const CONFLICT_TITLE = /^Standard conflict ([0-9a-f]{8})$/;
+const conflictTitle = (c) => `Standard conflict ${hash(c.text)}`;
+const conflictFor = (standards, title) => {
+	const id = CONFLICT_TITLE.exec(title)?.[1];
+	return id === void 0 ? void 0 : standards.undecided.find((c) => hash(c.text) === id);
+};
+const isConflictTitle = (title) => CONFLICT_TITLE.test(title);
+const KEEP_NEW = "keep the new one (drop the old)";
+const KEEP_OLD = "keep the old one (discard the new)";
+/** A conflict's chunk body; its three boxes read as fix / won't fix / own answer by position. */
+const conflictBody = (c) => [...c.olds.length === 0 ? [`A standard learned from your answers contradicted ones another answer since replaced in \`${STANDARDS}\`. Keep it, discard it, or reword it.`, `New: ${c.text}`] : [
+	`A standard learned from your answers contradicts ${c.olds.length === 1 ? "one" : "some"} already in \`${STANDARDS}\`. Your own answer replaces both with its wording.`,
+	`New: ${c.text}`,
+	`Old:\n\n${c.olds.map((o) => `- ${o}`).join("\n")}`
+], `${ANSWER_LEAD}\n\n- [ ] ${KEEP_NEW}\n- [ ] ${KEEP_OLD}\n- [ ] ${FREE_TEXT_PLACEHOLDER}`].join("\n\n");
+/** What every agent turn is told while `.gtd/STANDARDS.md` holds decided standards. */
+const standardsBlock = (text) => {
+	const { decided } = parseStandards(text ?? "");
+	if (decided.length === 0) return "";
+	return `## Standards
+
+\`${STANDARDS}\` holds the standards the human set in earlier reviews.
+Follow every one in what you write. Reviewing, never raise a finding a
+standard rules out — a \`Won't fix:\` standard is a finding the human
+rejected, so never raise it or one like it again — and raise breaking a
+standard as a finding.
+
+${decided.map((s) => `- ${s}`).join("\n")}`;
+};
+//#endregion
 //#region src/workflows/shared/vars.ts
 /** The refactor guard's fixed list, and `seamAllow`'s default minus `.gtd/**`. */
 const testFileGlobs = [
@@ -124,6 +226,11 @@ const testFileGlobs = [
 	"**/__tests__/**"
 ];
 const defaultFlagRegistry = "src/flags/index.ts";
+/** The `tests` workflow's own process settings: where it looks for skipped tests, and how a skip reads. */
+const testsDefaults = {
+	testFiles: testFileGlobs.join(", "),
+	skipPattern: "^\\s*(?:(?:describe|context|suite|it|test|specify)\\.(?:skip|todo)\\b|x(?:describe|context|it|test|specify)\\s*\\(|(?:@\\S+\\s+)*@(?:skip|ignore)(?:\\s|$))"
+};
 /** Process settings. */
 const defaults = {
 	reviewBase: "",
@@ -132,6 +239,7 @@ const defaults = {
 	reviewNoteActionable: "0.7",
 	reviewSeverityMinP: "0.7",
 	qualityTriageMinP: "0.7",
+	standardMinP: "0.8",
 	refactorFlagPattern: "\\bGTD_FLAG_\\w+",
 	seamAllow: [...testFileGlobs, ".gtd/**"].join(", "),
 	flagMode: "true",
@@ -391,8 +499,11 @@ const withSkills = (skills, prompt) => {
 };
 /** An `agent()` step whose prompt opens with the preamble naming its scope's skills, then its restricted file access. */
 const agentWithSkills = (name, prompt, options = {}) => {
-	const access = accessPreamble(accessFor(name, options.file));
-	const body = access === "" ? prompt : `${access}\n\n${prompt}`;
+	const body = [
+		accessPreamble(accessFor(name, options.file)),
+		prompt,
+		standardsBlock(read(STANDARDS))
+	].filter((part) => part !== "").join("\n\n");
 	return agent(name, withSkills(skillsFor(name).join(", "), body), options);
 };
 const unwindFailure = (commit) => `gtd could not unwind ${commit} out of your working tree.`;
@@ -432,6 +543,7 @@ const SUMMARY_TITLES = [
 	"Weakened scenarios",
 	"Fixed from your notes",
 	"Fixed automatically",
+	"Standards added",
 	"Dropped as noise",
 	"Nothing to note"
 ];
@@ -451,7 +563,9 @@ const composedReview = (base, report) => {
 		return name;
 	};
 	const chunk = (title, body) => `## ${title}\n\n${body.trim()}`;
-	const answerBoxes = `${ANSWER_LEAD}\n\n- [ ] ${ANSWER_FIX}\n- [ ] ${ANSWER_WONT_FIX}\n- [ ] ${FREE_TEXT_PLACEHOLDER}`;
+	const answerBoxes = ([fix, wontFix] = [ANSWER_FIX, ANSWER_WONT_FIX]) => `${ANSWER_LEAD}\n\n- [ ] ${fix}\n- [ ] ${wontFix}\n- [ ] ${FREE_TEXT_PLACEHOLDER}`;
+	const conflicts = (report.standards?.undecided ?? []).map((c) => chunk(unique(conflictTitle(c)), conflictBody(c)));
+	const added = report.standards?.added ?? [];
 	const notes = report.notes.map((n) => ({
 		...n,
 		title: unique(n.title)
@@ -460,8 +574,10 @@ const composedReview = (base, report) => {
 	const chunks = [
 		...report.nitFix === void 0 ? [] : [chunk("Fixed from your notes", `Your nits and fix-as-suggested notes were worked on in ${short(report.nitFix)}; the notes you answered are left out — check the diff.`)],
 		...weakened.length === 0 ? [] : [chunk("Weakened scenarios", `These scenarios lost an assertion the review base had:\n\n${weakened.join("\n")}`)],
-		...notes.map((n) => chunk(n.title, `${n.unresolved === true ? `_The fixer left this unresolved._\n\n${unboxed(n.body)}` : n.unclear === true ? `_A fix turn removed this while renaming another finding — check whether it was fixed._\n\n${unboxed(n.body)}` : unboxed(n.body) || "_No detail given._"}\n\n${answerBoxes}`)),
+		...conflicts,
+		...notes.map((n) => chunk(n.title, `${n.unresolved === true ? `_The fixer left this unresolved._\n\n${unboxed(n.body)}` : n.unclear === true ? `_A fix turn removed this while renaming another finding — check whether it was fixed._\n\n${unboxed(n.body)}` : unboxed(n.body) || "_No detail given._"}\n\n${answerBoxes(n.answers)}`)),
 		...report.fixed.length === 0 ? [] : [chunk("Fixed automatically", report.fixed.map((f) => `- ${f.title} (${short(f.commit)})`).join("\n"))],
+		...added.length === 0 ? [] : [chunk("Standards added", `Learned from your answers and kept in \`${STANDARDS}\`:\n\n${added.map((s) => `- ${s}`).join("\n")}`)],
 		...report.noise.length === 0 ? [] : [chunk("Dropped as noise", report.noise.map((f) => `- ${f.title} (p=${f.p})`).join("\n"))]
 	];
 	const body = chunks.length > 0 ? chunks : [chunk("Nothing to note", "No quality lens raised anything for you — or none ran. Review the diff yourself.")];
@@ -1765,6 +1881,7 @@ const ShippedOptions = Struct({
 	reviewNoteActionable: setting,
 	reviewSeverityMinP: setting,
 	qualityTriageMinP: setting,
+	standardMinP: setting,
 	refactorFlagPattern: setting,
 	seamAllow: setting,
 	sliceMaxCriteria: setting,
@@ -1827,6 +1944,24 @@ const flagShipped = (flow, name) => defineWorkflow(standardSchemaV1(FlagOptions,
 		base: void 0
 	};
 });
+const TestsOptions = Struct({
+	...ShippedOptions.fields,
+	testFiles: setting,
+	skipPattern: setting
+});
+const testsShipped = (flow) => defineWorkflow(standardSchemaV1(TestsOptions, {
+	onExcessProperty: "error",
+	errors: "all"
+}), ({ contextLimit, ...options }) => ({
+	flow: limited(flow, contextLimit),
+	defaults: over({
+		...defaults,
+		...testsDefaults
+	}, options),
+	envDefaults: over(envDefaults, options),
+	doors: { tests: {} },
+	base: void 0
+}));
 //#endregion
 //#region src/workflows/shared/skills.ts
 const skills = (vars) => {
@@ -1842,6 +1977,8 @@ const skills = (vars) => {
 		design: ["spec-driven-development", "planning-and-task-breakdown"],
 		notes: ["incremental-implementation", "code-simplification"],
 		feedback: ["test-driven-development", "incremental-implementation"],
+		tests: ["test-audit", "test-driven-development"],
+		"tests.health": ["debugging-and-error-recovery"],
 		...build,
 		...Object.fromEntries(Object.entries(build).map(([name, list]) => [`refactor.${name}`, list])),
 		refactor: ["ponytail"],
@@ -1874,4 +2011,4 @@ const steering = {
 	[REVIEW]: "review"
 };
 //#endregion
-export { naiveApplyFailure as $, reviewMissing as A, registryEntry as At, coverageMessage as B, coder as C, unwindFailure as Ct, fixQuality as D, flagMentions as Dt, fixNits as E, testFileGlobs as Et, buildReviewTriageMessage as F, designSystem as G, coveringPrompt as H, builderSystem as I, fixReviewNotesPrompt as J, designTriagePrompt as K, clearCriteriaMessage as L, reviewing as M, agentWithSkills as N, fixRisks as O, flagReferences as Ot, buildReviewCollectingPrompt as P, implementFixPrompt as Q, clearCriteriaQuestion as R, awaitReview as S, unwindFailedMessage as St, fixCheck as T, envDefaults as Tt, criterionLine as U, coverageQuestion as V, designGateAnswerMessage as W, idleMessage as X, handOffAwaitReviewMessage as Y, implementBuildingPrompt as Z, REFACTOR_NOTE as _, seamByHandMessage as _t, flagModeOn as a, qualityUnresolvedMessage as at, SLICES as b, startGateBlockedMessage as bt, baseline as c, refactorFixPrompt as ct, guarded as d, reviewEditNotesCapture as dt, naivePassPrompt as et, healthy as f, reviewEditsCapture as ft, REFACTOR as g, reviewerSystem as gt, QUALITY as h, reviewNotesCapture as ht, skills as i, qualityTriageMessage as it, reviewQuality as j, requireFlag as jt, planner as k, flipProblems as kt, escalation as l, refactorNotePrompt as lt, HANDOFF as m, reviewGateBlockedMessage as mt, summary as n, oversizedMessage as nt, flagShipped as o, refactorBuildingPrompt as ot, FEEDBACK as p, reviewFeedbackFixPrompt as pt, finisherSystem as q, access as r, qualityFindingsFile as rt, shipped as s, refactorDroppedRefusal as st, steering as t, normaliseCriteriaScript as tt, gate as u, refactorRules as ut, REQUIREMENTS as v, seamSteerMessage as vt, collecting as w, defaults as wt, answerReviewQuestions as x, uncoveredMessage as xt, REVIEW as y, slicingPrompt as yt, composedReview as z };
+export { implementFixPrompt as $, planner as A, conflictBody as At, composedReview as B, flipProblems as Bt, awaitReview as C, unwindFailedMessage as Ct, fixNits as D, testFileGlobs as Dt, fixCheck as E, envDefaults as Et, buildReviewCollectingPrompt as F, parseStandards as Ft, designGateAnswerMessage as G, coverageQuestion as H, requireFlag as Ht, buildReviewTriageMessage as I, renderStandards as It, finisherSystem as J, designSystem as K, builderSystem as L, standardKey as Lt, reviewQuality as M, conflictTitle as Mt, reviewing as N, isConflictTitle as Nt, fixQuality as O, testsDefaults as Ot, agentWithSkills as P, oneLine as Pt, implementBuildingPrompt as Q, clearCriteriaMessage as R, flagMentions as Rt, answerReviewQuestions as S, uncoveredMessage as St, collecting as T, defaults as Tt, coveringPrompt as U, coverageMessage as V, registryEntry as Vt, criterionLine as W, handOffAwaitReviewMessage as X, fixReviewNotesPrompt as Y, idleMessage as Z, REFACTOR as _, reviewerSystem as _t, flagModeOn as a, qualityTriageMessage as at, REVIEW as b, slicingPrompt as bt, testsShipped as c, refactorDroppedRefusal as ct, gate as d, refactorRules as dt, naiveApplyFailure as et, guarded as f, reviewEditNotesCapture as ft, QUALITY as g, reviewNotesCapture as gt, HANDOFF as h, reviewGateBlockedMessage as ht, skills as i, qualityFindingsFile as it, reviewMissing as j, conflictFor as jt, fixRisks as k, STANDARDS as kt, baseline as l, refactorFixPrompt as lt, FEEDBACK as m, reviewFeedbackFixPrompt as mt, summary as n, normaliseCriteriaScript as nt, flagShipped as o, qualityUnresolvedMessage as ot, healthy as p, reviewEditsCapture as pt, designTriagePrompt as q, access as r, oversizedMessage as rt, shipped as s, refactorBuildingPrompt as st, steering as t, naivePassPrompt as tt, escalation as u, refactorNotePrompt as ut, REFACTOR_NOTE as v, seamByHandMessage as vt, coder as w, unwindFailure as wt, SLICES as x, startGateBlockedMessage as xt, REQUIREMENTS as y, seamSteerMessage as yt, clearCriteriaQuestion as z, flagReferences as zt };

package/dist/chunks/{review-X7Jfz0dY.mjs → review-Da2ndnB1.mjs}

@@ -1,7 +1,159 @@
-import { answered, changesSince, head, judge, numeric, requireRevert, restoreScript, run, showScript, vars, writeScript } from "../flows.mjs";
+import { answered, changesSince, head, judge, numeric, read, removeScript, requireRevert, restoreScript, run, showScript, vars, writeScript } from "../flows.mjs";
 import { removedAssertions, review } from "../workflow-kit.mjs";
-import { A as reviewMissing, E as fixNits, F as buildReviewTriageMessage, O as fixRisks, S as awaitReview, T as fixCheck, d as guarded, dt as reviewEditNotesCapture, f as healthy, ft as reviewEditsCapture, h as QUALITY, ht as reviewNotesCapture, w as collecting, x as answerReviewQuestions, y as REVIEW, z as composedReview } from "./reserved-DJk_6-ju.mjs";
-import { i as isOptionalObject, n as closeReview, o as tail, s as NO_FINDINGS } from "./tail-5w5mxGTq.mjs";
+import { At as conflictBody, B as composedReview, C as awaitReview, D as fixNits, E as fixCheck, Ft as parseStandards, I as buildReviewTriageMessage, It as renderStandards, J as finisherSystem, Lt as standardKey, Mt as conflictTitle, Nt as isConflictTitle, P as agentWithSkills, Pt as oneLine, S as answerReviewQuestions, T as collecting, b as REVIEW, f as guarded, ft as reviewEditNotesCapture, g as QUALITY, gt as reviewNotesCapture, j as reviewMissing, jt as conflictFor, k as fixRisks, kt as STANDARDS, mt as reviewFeedbackFixPrompt, p as healthy, pt as reviewEditsCapture, w as coder, y as REQUIREMENTS } from "./reserved-ulcSkND6.mjs";
+import { i as isOptionalObject, n as closeReview, o as tail, s as NO_FINDINGS } from "./tail-BW030xz_.mjs";
+//#region src/workflows/shared/learn.ts
+const SUMMARY_MAX = 200;
+const BANNER = /^_(?:The fixer left this unresolved\.|A fix turn removed this while renaming another finding — check whether it was fixed\.|No detail given\.)_\s*/;
+const summary = (body) => {
+	const text = oneLine(body).replace(BANNER, "");
+	return text.length > SUMMARY_MAX ? `${text.slice(0, SUMMARY_MAX - 1)}…` : text;
+};
+/** The standard a won't-fix or an own answer would make; a fix states none. */
+const candidateOf = (d) => {
+	const anchor = oneLine(d.anchor);
+	if (d.choice === "wontfix") {
+		const why = summary(d.body);
+		return [{
+			decision: d,
+			text: `Won't fix: ${anchor}${why === "" ? "" : ` — ${why}`}`
+		}];
+	}
+	if (d.choice === "answer") return [{
+		decision: d,
+		text: `${oneLine(d.text)} (re: ${anchor})`
+	}];
+	return [];
+};
+const without = (list, drop) => {
+	const keys = new Set(drop.map(standardKey));
+	return list.filter((s) => !keys.has(standardKey(s)));
+};
+const adding = (list, text) => list.some((s) => standardKey(s) === standardKey(text)) ? [...list] : [...list, text];
+/**
+* Keep the new one, keep the old one, or replace both with the human's own
+* wording. Another open conflict stops naming a replaced standard: the human
+* never judged it against the replacement, so keeping it must not drop that.
+*/
+const resolve = (standards, d) => {
+	const c = conflictFor(standards, d.anchor);
+	if (c === void 0) return standards;
+	const others = standards.undecided.filter((u) => u !== c);
+	if (d.choice === "wontfix") return {
+		decided: standards.decided,
+		undecided: others
+	};
+	const kept = d.choice === "fix" ? c.text : oneLine(d.text);
+	const undecided = others.map((u) => ({
+		text: u.text,
+		olds: without(u.olds, c.olds)
+	}));
+	return {
+		decided: adding(without(standards.decided, c.olds), kept),
+		undecided
+	};
+};
+const contradicts = (i, id, other) => ({
+	id: `standard-${i}.contradicts-${id}`,
+	primitive: "noul",
+	instructions: `Does the "Standard:" line of evidence "standard-${i}" contradict ${other}?`,
+	criteria: "yes: following one breaks the other. no: both can be followed — they are compatible or unrelated."
+});
+const questionsFor = (i, anchor, decided) => [
+	{
+		id: `standard-${i}`,
+		primitive: "noul",
+		instructions: `Is the human's answer to review note "${anchor}" (evidence "standard-${i}") a reusable standard for this codebase — a rule later changes and reviews should follow — rather than a call about this one note? Its "Standard:" line is the wording gtd would keep.`,
+		criteria: "yes: it states a rule or preference that applies beyond this note. no: it is specific to this note, a one-off call, or unclear."
+	},
+	...decided.map((_, k) => contradicts(i, `${k + 1}`, `kept standard ${k + 1} (evidence "kept-${k + 1}")`)),
+	...Array.from({ length: i - 1 }, (_, j) => contradicts(i, `new-${j + 1}`, `the "Standard:" line of evidence "standard-${j + 1}"`))
+];
+const evidenceOf = (c) => [
+	`Note: ${c.decision.anchor}`,
+	`Reviewer's text: ${c.decision.body}`,
+	`Human's answer: ${c.decision.choice === "wontfix" ? "won't fix" : c.decision.text}`,
+	`Standard: ${c.text}`
+].join("\n");
+/**
+* One judge rest over every candidate. Only a confident `yes` on uncut
+* evidence makes a standard; a contradiction the judge does not confidently
+* rule out goes to the human instead of overwriting what they decided before.
+* A cut kept standard leaves the round unlearned: raise `judgeBudgetBytes`.
+*/
+const judged = async (candidates, decided, minP) => {
+	const { answers, truncated } = await judge("review.standards.judge", {
+		questions: candidates.flatMap((c, i) => questionsFor(i + 1, c.decision.anchor, decided)),
+		evidence: Object.fromEntries([...candidates.map((c, i) => [`standard-${i + 1}`, evidenceOf(c)]), ...decided.map((s, k) => [`kept-${k + 1}`, s])]),
+		message: "Judging whether your answers are standards to keep: run `gtd judge run`, or land without a verdict, which keeps none.",
+		label: "Learning your standards"
+	});
+	const ruledOut = (i, id) => answered(answers[`standard-${i}.contradicts-${id}`], "no", minP);
+	const added = [];
+	const raised = [];
+	candidates.forEach((c, n) => {
+		const i = n + 1;
+		if (truncated.includes(`standard-${i}`)) return;
+		if (decided.some((_, k) => truncated.includes(`kept-${k + 1}`))) return;
+		if (!answered(answers[`standard-${i}`], "yes", minP)) return;
+		const olds = [...decided.filter((_, k) => !ruledOut(i, `${k + 1}`)), ...added.filter((a) => !ruledOut(i, `new-${a.i}`)).map((a) => a.text)];
+		if (olds.length === 0) added.push({
+			i,
+			text: c.text
+		});
+		else raised.push({
+			text: c.text,
+			olds
+		});
+	});
+	return {
+		added: added.map((a) => a.text),
+		raised
+	};
+};
+/**
+* Settles every answer to a standard conflict, then learns standards from
+* the won't-fix ticks and own answers: kept in `.gtd/STANDARDS.md`, a
+* contradicting one as a new conflict note in `.gtd/REVIEW.md`.
+*/
+const learnStandards = async (decisions) => {
+	const before = parseStandards(read(".gtd/STANDARDS.md") ?? "");
+	const rest = decisions.filter((d) => !isConflictTitle(d.anchor));
+	const settled = decisions.filter((d) => isConflictTitle(d.anchor)).reduce(resolve, before);
+	const known = new Set([...settled.decided, ...settled.undecided.map((c) => c.text)].map(standardKey));
+	const candidates = rest.flatMap(candidateOf).filter((c) => {
+		const key = standardKey(c.text);
+		if (known.has(key)) return false;
+		known.add(key);
+		return true;
+	});
+	const minP = numeric(vars.standardMinP, Infinity);
+	const { added, raised } = candidates.length === 0 || !Number.isFinite(minP) ? {
+		added: [],
+		raised: []
+	} : await judged(candidates, settled.decided, minP);
+	const after = {
+		decided: [...settled.decided, ...added],
+		undecided: [...settled.undecided, ...raised]
+	};
+	if (renderStandards(after) !== renderStandards(before)) await run("review.standards.recording", writeScript(STANDARDS, renderStandards(after)), { label: "Recording your standards" });
+	if (raised.length > 0) {
+		const chunks = raised.map((c) => `## ${conflictTitle(c)}\n\n${conflictBody(c)}`);
+		await run("review.standards.raising", writeScript(REVIEW, `${(read(".gtd/REVIEW.md") ?? "").trimEnd()}\n\n${chunks.join("\n\n")}\n`), {
+			label: "Asking about a contradicting standard",
+			file: REVIEW
+		});
+	}
+};
+const settlesStandard = (d) => isConflictTitle(d.anchor);
+const standardsPending = () => parseStandards(read(".gtd/STANDARDS.md") ?? "").undecided.length > 0;
+const standardsAddedSince = (base) => {
+	const change = changesSince(base).get(STANDARDS);
+	if (change === void 0) return [];
+	const was = new Set(parseStandards(change.before ?? "").decided);
+	return parseStandards(change.after ?? "").decided.filter((s) => !was.has(s));
+};
+//#endregion
 //#region src/workflows/shared/review.ts
 const VERDICTS = [
 	"edit",
@@ -132,7 +284,11 @@ const composing = (base, report, carry, nitFix, answered = /* @__PURE__ */ new S
 	...report,
 	weakened: removedAssertions(changesSince(base)),
 	nitFix,
-	answered
+	answered,
+	standards: {
+		added: standardsAddedSince(base),
+		undecided: parseStandards(read(".gtd/STANDARDS.md") ?? "").undecided
+	}
 }), [QUALITY]) : showScript(carry, REVIEW, REVIEW), {
 	label: "Composing the review",
 	file: REVIEW,
@@ -147,7 +303,7 @@ const composing = (base, report, carry, nitFix, answered = /* @__PURE__ */ new S
 * praise dropped.
 */
 const humanReview = (base, escalations = { rounds: 0 }, options = {}) => {
-	const { guard, guardRests, fixAccess, rules } = options;
+	const { guard, guardRests, fixAccess, rules, awaitMessage } = options;
 	const feedback = options.feedback ?? {
 		file: ".gtd/REQUIREMENTS.md",
 		collecting,
@@ -172,11 +328,14 @@ const humanReview = (base, escalations = { rounds: 0 }, options = {}) => {
 			guardRests,
 			rules
 		}),
-		awaitReview: (b) => awaitReview(b),
+		awaitReview: (b) => awaitReview(b, awaitMessage?.(b)),
 		reviewMissing,
 		collecting: feedback.collecting,
 		triage: triage(severities),
 		decided: (decisions) => decisions.forEach((d) => answered.add(d.anchor)),
+		settles: settlesStandard,
+		learn: learnStandards,
+		pending: standardsPending,
 		answerQuestions: answerReviewQuestions,
 		fixNits: async (notes) => {
 			await guarded((n) => fixNits(n, fixAccess, rules), guard)(notes);
@@ -229,6 +388,17 @@ const callForm = (first, second, [third, fourth, ...extra]) => {
 	if (typeof second === "string") return legacyForm(first, second, third, fourth);
 	if (typeof first === "string") return currentForm(first, second, third, fourth);
 };
+/** Build the concerns a review round collected into `.gtd/REQUIREMENTS.md`, then remove it. */
+const fixFeedback = async () => {
+	await agentWithSkills("feedback.fixing", reviewFeedbackFixPrompt(), {
+		label: "Fixing your review feedback",
+		file: REQUIREMENTS,
+		model: coder(),
+		system: finisherSystem(),
+		allowEmpty: true
+	});
+	await run("feedback.closing", removeScript([REQUIREMENTS]), { label: "Closing the feedback" });
+};
 /**
 * Undo the human's review-round code edits. A path changed since the human
 * left it is not overwritten; requireRevert names it instead.
@@ -246,4 +416,4 @@ const reUnwind = async (feedback) => {
 	requireRevert(edited, base);
 };
 //#endregion
-export { reUnwind as i, humanReview as n, isCode as r, buildTail as t };
+export { reUnwind as a, isCode as i, fixFeedback as n, humanReview as r, buildTail as t };

package/dist/chunks/{tail-5w5mxGTq.mjs → tail-BW030xz_.mjs}

@@ -1,6 +1,6 @@
 import { answered, head, judge, mark, numeric, read, refuse, removeScript, run, scope, sectionBodies, showScript, vars, writeScript } from "../flows.mjs";
 import { fixFindings, lensEntriesOf, lensOf, qualityLap as qualityLap$1, reviewToHandOff } from "../workflow-kit.mjs";
-import { A as reviewMissing, D as fixQuality, M as reviewing, O as fixRisks, S as awaitReview, T as fixCheck, Y as handOffAwaitReviewMessage, d as guarded, f as healthy, h as QUALITY, it as qualityTriageMessage, j as reviewQuality, l as escalation, rt as qualityFindingsFile, y as REVIEW } from "./reserved-DJk_6-ju.mjs";
+import { C as awaitReview, E as fixCheck, M as reviewQuality, N as reviewing, O as fixQuality, X as handOffAwaitReviewMessage, at as qualityTriageMessage, b as REVIEW, f as guarded, g as QUALITY, it as qualityFindingsFile, j as reviewMissing, k as fixRisks, p as healthy, u as escalation } from "./reserved-ulcSkND6.mjs";
 //#region src/workflows/shared/lenses.ts
 const NO_FINDINGS = {
 	notes: [],

package/dist/gtd.bundle.mjs

@@ -21606,10 +21606,11 @@ rather than starting the review; \`gtd-door fix\` on a GREEN suite is a no-op
 straight back to \`idle\` — the exec'd \`gtd-build\` exits immediately on it.
 \`gtd doors\` lists the doors a repository offers (those of the workflows its
 config exports — the bundled \`fix\` and \`review [base]\`, plus the opt-in
-\`rollout <flag>\` (turn a release flag default-on) and \`cleanup <flag>\`
-(remove it), which a config adds by exporting \`rollout\` from
-\`@pmelab/gtd/workflows/rollout\` and \`cleanup\` from
-\`@pmelab/gtd/workflows/cleanup\` — plus any it declares). Refuses with
+\`rollout <flag>\` (turn a release flag default-on), \`cleanup <flag>\`
+(remove it) and \`tests\` (revive skipped tests), which a config adds by
+exporting \`rollout\` from \`@pmelab/gtd/workflows/rollout\`, \`cleanup\` from
+\`@pmelab/gtd/workflows/cleanup\` and \`tests\` from
+\`@pmelab/gtd/workflows/tests\` — plus any it declares). Refuses with
 \`usage: gtd-door <name> [args...]\` on stderr and exit \`2\` when the name is
 missing — nothing was even attempted. Default path: \`~/.local/bin/gtd-door\`.
 
@@ -21722,7 +21723,8 @@ const CONFIG_SCAFFOLD = `// The workflows gtd runs here: gtd's shipped feature,
 // its own doors: \`gtd door review [base]\` and \`gtd door fix\`. Export \`rollout\`
 // from \`@pmelab/gtd/workflows/rollout\` and \`cleanup\` from
 // \`@pmelab/gtd/workflows/cleanup\` to add \`gtd door rollout <flag>\` and
-// \`gtd door cleanup <flag>\`.
+// \`gtd door cleanup <flag>\`, and \`tests\` from \`@pmelab/gtd/workflows/tests\`
+// to add \`gtd door tests\`.
 export {
   feature as default,
   feature,

package/dist/testkit.mjs

@@ -6643,10 +6643,11 @@ rather than starting the review; \`gtd-door fix\` on a GREEN suite is a no-op
 straight back to \`idle\` — the exec'd \`gtd-build\` exits immediately on it.
 \`gtd doors\` lists the doors a repository offers (those of the workflows its
 config exports — the bundled \`fix\` and \`review [base]\`, plus the opt-in
-\`rollout <flag>\` (turn a release flag default-on) and \`cleanup <flag>\`
-(remove it), which a config adds by exporting \`rollout\` from
-\`@pmelab/gtd/workflows/rollout\` and \`cleanup\` from
-\`@pmelab/gtd/workflows/cleanup\` — plus any it declares). Refuses with
+\`rollout <flag>\` (turn a release flag default-on), \`cleanup <flag>\`
+(remove it) and \`tests\` (revive skipped tests), which a config adds by
+exporting \`rollout\` from \`@pmelab/gtd/workflows/rollout\`, \`cleanup\` from
+\`@pmelab/gtd/workflows/cleanup\` and \`tests\` from
+\`@pmelab/gtd/workflows/tests\` — plus any it declares). Refuses with
 \`usage: gtd-door <name> [args...]\` on stderr and exit \`2\` when the name is
 missing — nothing was even attempted. Default path: \`~/.local/bin/gtd-door\`.
 
@@ -6759,7 +6760,8 @@ const CONFIG_SCAFFOLD = `// The workflows gtd runs here: gtd's shipped feature,
 // its own doors: \`gtd door review [base]\` and \`gtd door fix\`. Export \`rollout\`
 // from \`@pmelab/gtd/workflows/rollout\` and \`cleanup\` from
 // \`@pmelab/gtd/workflows/cleanup\` to add \`gtd door rollout <flag>\` and
-// \`gtd door cleanup <flag>\`.
+// \`gtd door cleanup <flag>\`, and \`tests\` from \`@pmelab/gtd/workflows/tests\`
+// to add \`gtd door tests\`.
 export {
   feature as default,
   feature,