shapeup-sdlc 3.17.1 → 3.17.2

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "shapeup-sdlc-plugin",
   "displayName": "ShapeUp SDLC Plugin",
-  "version": "3.17.1",
+  "version": "3.17.2",
   "description": "Shape Up SDLC harness for Claude Code: shaping, intake, orient, scope-mapping, building (T0-verified, sandboxed, scope-contracted), evaluation and QA skills orchestrated by a tech-lead.",
   "author": {
     "name": "Liberty Nguyen",

package/AGENTS.md

@@ -62,7 +62,7 @@ Everything discovered funnels into `.shapeup/<slug>/discovery/ledger.md` (Orient
 - **Ledger = single source of truth** — every discovery flow writes only its own section.
 - **QA is a level-up, not a gate** — `--no-qa` skips it; circuit breaker outranks the Hunter.
 - **Role separation** — Evaluator grades, task-executor fixes, QA discovers.
-- **The requirements matrix is a projection, never a verdict** — `REQ → AC → criterion → verdict` is derived from files for one named run (the registry, the board's `covers:` clauses, the run's verdict rows, the T0 citations), never narrated and never passed in. `covers:` is the authoritative join: a criterion anchored to a requirement no AC covers is printed for reconciliation and counted as nothing. L4 reads one line off it, GATE H's census takes the clauses with no evidence, `REPORT.md` freezes the table — and none of that blocks a ship. A clause with no PASS evidence is a fact the baseline comparison weighs, not a veto.
+- **The requirements matrix is a projection, never a verdict** — `REQ → AC → criterion → verdict` is derived from files for one named run (the registry, the board's `covers:` clauses, the run's verdict rows, the T0 citations), never narrated and never passed in. `covers:` is the authoritative join: a criterion anchored to a requirement no AC covers is printed for reconciliation and counted as nothing. A verdict that anchors no criterion at all, beside a board whose ACs carry `covers:`, is sent back to the judge once. L4 reads one line off it, GATE H's census takes the clauses with no evidence, `REPORT.md` freezes the table — and none of that blocks a ship. A clause with no PASS evidence is a fact the baseline comparison weighs, not a veto.
 - **Hill phase is mechanical ✦** — derived only from T0/T1 artifacts, never self-reported, and a T0-green from a round whose build gate ⚙ is red moves no dot (a green fixture in a round the feature did not build is evidence about the fixture); the evaluator cites a T0 artifact it re-hashes itself, from the list its order carries. A scoped verdict citing none is refused: its round stays open and is evaluated again, never advanced.
 - **Envelope port (v1.0)** — every dispatch is WorkOrder in / WorkResult out; shared state has exactly one writer (the ingest step); malformed envelopes are hook-denied. Workers: stateless, craft-only, pipeline-blind.
 

package/kernel/probe/eval.mjs

@@ -36,6 +36,8 @@ import { join, resolve, resolve as resolvePath, sep } from "node:path";
 import { createHash } from "node:crypto";
 import { runArgs } from "../lib/argv.mjs";
 import { resultsDir, scopesDir, readRunId, verdictsDir, specDir } from "../lib/paths.mjs";
+import { readBoard } from "../compile.mjs";
+import { coveringAcs } from "./requirements.mjs";
 
 /** Longest `reason` reported. A deviation is prose written by a worker and can run to paragraphs. */
 const REASON_MAX = 400;
@@ -253,6 +255,33 @@ export function coverageProblem(cwd, slug, verdict) {
     `each row is its own criterion, its id in the criterion or its traces_to; ungraded: ${shown}`;
 }
 
+/**
+ * Whether a verdict anchors any criterion to a requirement when the board says which ones it could.
+ *
+ * `traces_to` is copied from the `(covers: REQ-…)` clauses of the acceptance criteria a criterion
+ * grades, and the requirements matrix is joined along it. Two judges on the same spec and the same
+ * instruction differed: one anchored every row and the matrix read 5/5, the next anchored none and it
+ * read 0/5 over the same passes. Held only to the all-empty case: which requirement a criterion
+ * traces to is the judge's reading, but none at all, beside a board that covers some, is a copy
+ * step skipped.
+ *
+ * @param {string} cwd - Project root.
+ * @param {string} slug - Feature slug.
+ * @param {object} verdict - The WorkResult's `verdict`.
+ * @returns {(string|null)} A reason phrased for the judge, or null.
+ */
+export function tracesProblem(cwd, slug, verdict) {
+  if (verdict?.overall !== "PASS" && verdict?.overall !== "FAIL") return null;
+  const criteria = Array.isArray(verdict.criteria) ? verdict.criteria : [];
+  if (!criteria.length) return null;
+  if (criteria.some((c) => Array.isArray(c?.traces_to) && c.traces_to.length)) return null;
+  let covered = 0;
+  try { covered = coveringAcs(readBoard(cwd, slug)).size; } catch { return null; }
+  if (!covered) return null;
+  return `the verdict anchors none of its ${criteria.length} criteria to a requirement while the board's acceptance ` +
+    `criteria cover ${covered} — copy each graded AC's (covers: REQ-…) clause into that criterion's traces_to`;
+}
+
 export function citationProblem(cwd, slug, verdict, { round = null } = {}) {
   if (verdict?.overall !== "PASS" && verdict?.overall !== "FAIL") return null;
   if (!isScoped(cwd, slug)) return null;
@@ -297,7 +326,7 @@ export function evalVerdict(cwd, slug, round) {
       ? `the evaluator returned ${status || "no status"}: ${first}`
       : `status ${status || "unknown"} with no PASS/FAIL verdict`), status);
   }
-  const problem = verdictProblem(v) || coverageProblem(cwd, slug, v) || citationProblem(cwd, slug, v, { round });
+  const problem = verdictProblem(v) || coverageProblem(cwd, slug, v) || tracesProblem(cwd, slug, v) || citationProblem(cwd, slug, v, { round });
   if (problem) return unfit(problem, status, overall);
   return {
     found: true,

package/kernel/reduce/ingest.mjs

@@ -37,7 +37,7 @@ import { fileURLToPath } from "node:url";
 import { validate } from "../verify/envelope.mjs";
 import { runArgs } from "../lib/argv.mjs";
 import { tasksDir, localRoot, dispatchReceipts, legLedger, readRunId, qaDir } from "../lib/paths.mjs";
-import { citationProblem, coverageProblem, verdictProblem } from "../probe/eval.mjs";
+import { citationProblem, coverageProblem, tracesProblem, verdictProblem } from "../probe/eval.mjs";
 import { huntProblem } from "../probe/hunt.mjs";
 
 const HERE = dirname(fileURLToPath(import.meta.url));
@@ -702,7 +702,7 @@ export async function cli(rawArgv) {
     const evalSlug = String(result.order_id).split("/")[0];
     const evalRound = Number((String(result.order_id).match(/-r(\d+)$/) || [])[1]) || null;
     const problem = verdictProblem(result.verdict) || coverageProblem(cwd, evalSlug, result.verdict)
-      || citationProblem(cwd, evalSlug, result.verdict, { round: evalRound });
+      || tracesProblem(cwd, evalSlug, result.verdict) || citationProblem(cwd, evalSlug, result.verdict, { round: evalRound });
     if (problem) {
       console.error(`ingest-result: result refused — ${problem}.`);
       console.error(`  The round stays open: re-dispatch the evaluator against its order, which lists`);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "shapeup-sdlc",
-  "version": "3.17.1",
+  "version": "3.17.2",
   "description": "Shape Up for coding agents \u2014 with gates the agent can't talk its way past. Harness for Claude Code.",
   "bin": {
     "shapeup-sdlc": "bin/init.mjs"

package/skills/spec-evaluator/SKILL.md

@@ -188,7 +188,7 @@ clause yields no anchor — leave the array empty rather than guessing, and neve
 supply one. This changes nothing you grade: the anchor is a navigation path, never a grading input,
 and a criterion passes or fails on its evidence exactly as before. It matters downstream because
 the requirement matrix at GATE L4 and the census at GATE H are projected from these anchors; a
-verdict that drops them grades the build and says nothing about what the pitch asked for.
+verdict that drops them grades the build and says nothing about what the pitch asked for. Ingest refuses a verdict that anchors no criterion at all while the board's ACs carry `covers:` clauses, and you are sent back once.
 
 **Every FAIL criterion's `evidence` MUST carry a `file:line` locator** — schema-enforced, not
 advice: the envelope is validated against `work-result.schema.json` at ingest and a locatorless