shapeup-sdlc 3.11.0 → 3.12.0

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "shapeup-sdlc-plugin",
   "displayName": "ShapeUp SDLC Plugin",
-  "version": "3.11.0",
+  "version": "3.12.0",
   "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/SECURITY.md

@@ -58,7 +58,10 @@ test against machines you don't own.
 6. **Every hook decision is recorded.** `hooks/lib/decision.mjs` is the only exit path a hook
    has, so allow, deny, block and error each leave a row in `.shapeup/decisions.jsonl`. An
    inert hook and a permitting hook are therefore distinguishable — which matters, because
-   "exit 0, no output" is what both used to look like.
+   "exit 0, no output" is what both used to look like. A permitted Bash call's row names the
+   programs the command runs, by basename (`hdc`, `curl | jq`) — never the arguments, which is
+   where a secret, a token or a private path would be. A denied call's row keeps the first 200
+   characters of the command, as it always has, because a denial must be reviewable.
 
 If you find any of these to be false, that is a vulnerability — report it as claim #ⁿ.
 

package/hooks/safety-spine.mjs

@@ -96,6 +96,32 @@ function tokens(segment) {
     .map((t) => t.replace(/^['"]|['"]$/g, ""));
 }
 
+/**
+ * The programs a command runs — the executable of each `&&`/`;`/`|` segment, by basename, and
+ * nothing else.
+ *
+ * WHY AN ALLOW ROW NAMES THE PROGRAM. Every permitted Bash call used to be recorded with no subject,
+ * so "did this worker ever call the device tool, and was it refused?" had no answer in the ledger:
+ * a sub-agent that never tried and one whose call was stopped above this hook left the same rows.
+ * The program names answer it. Arguments are never recorded — they are where a secret, a token or a
+ * private path would be — and a basename says which tool ran without saying where it lives.
+ *
+ * @param {string} command - The raw Bash command.
+ * @returns {(string|null)} Program basenames joined by " | ", in order, duplicates kept; null when
+ *   no segment yields one.
+ */
+export function programsOf(command) {
+  if (!command || typeof command !== "string") return null;
+  const names = [];
+  for (const segment of command.split(/\s*(?:\|\||&&|;|\||\n)\s*/).filter(Boolean)) {
+    const first = commandTokens(segment)[0];
+    if (!first) continue;
+    const base = first.replace(/^["']|["']$/g, "").split("/").pop();
+    if (base && !/^[({]$/.test(base)) names.push(base.slice(0, 64));
+  }
+  return names.length ? names.join(" | ") : null;
+}
+
 /** Strip leading env assignments and privilege/no-op wrappers to find the real command. */
 function commandTokens(segment) {
   const ts = tokens(segment);
@@ -217,8 +243,9 @@ async function main() {
   const raw = await readStdin();
   let p;
   /** Fail-open, with the reason on the record (hooks/lib/decision.mjs). */
-  const defer = (reason, rule) => settle({
+  const defer = (reason, rule, subject = null) => settle({
     verdict: "allow", event: "PreToolUse", tool: p?.tool_name ?? null, cwd: p?.cwd, reason, rule,
+    ...(subject ? { subject } : {}),
   });
   try { p = JSON.parse(raw || "{}"); }
   catch (e) { settle({ verdict: "error", event: "PreToolUse", reason: `unparseable payload: ${e.message}` }); }
@@ -258,7 +285,7 @@ async function main() {
   if (p.tool_name === "Bash") {
     const command = p.tool_input?.command || "";
     const verdict = classifyCommand(command, overrides);
-    if (!verdict.deny) defer("command matched no destructive rule — inspected and permitted", "bash-clean");
+    if (!verdict.deny) defer("command matched no destructive rule — inspected and permitted", "bash-clean", programsOf(command));
     if (commandOverridden(command, overrides)) {
       // Exercised override: allowed, but never invisible.
       logPathology(metricsPath, {

package/kernel/probe/digest.mjs

@@ -33,6 +33,12 @@ const PATTERNS = [
   // ("ERROR in the build pipeline", "ERROR in test suite failed to run") is left unmatched
   // instead of handing back a fabricated file.
   { re: /^(?:ERROR|WARNING)\s+in\s+(\.{1,2}\/[^\s:]*|[^\s:]+\.[A-Za-z0-9]{1,10})\b/i, kind: "compiler-diagnostic" },
+  // A test that FAILED BY NAME, with no file:line: "FAIL TS-05-05 step 4: no text 'Bread' on screen"
+  // or jest's "FAIL src/cart.test.js". Runners that drive an app from outside it (a device flow, an
+  // end-to-end script) report a case this way and nothing else, and the line is the whole signal —
+  // dropping it handed the next attempt an empty error list over a red fixture. The name is kept as
+  // the file only when it looks like a path; an id like TS-05-05 is not one.
+  { re: /^(?:FAIL|FAILED)\s+(\S+)(?:\s+.*)?$/, kind: "named-test-failure" },
   // Generic "Error: message" line followed later by a stack — capture the message alone.
   { re: /^\s*(?:Error|TypeError|ReferenceError|AssertionError)\s*:\s*(.+)$/, kind: "error-message" },
 ];
@@ -71,8 +77,9 @@ export function digest(rawText) {
         pendingMessage = coreMessage(m[1]);
         continue; // wait for the stack frame that follows to get a file:line
       }
-      const file = m[1]?.trim();
-      const lineNo = m[2] ? Number(m[2]) : null;
+      const named = kind === "named-test-failure";
+      const file = named ? (/[\\/]|\.[A-Za-z0-9]{1,10}$/.test(m[1]) ? m[1] : null) : m[1]?.trim();
+      const lineNo = !named && m[2] ? Number(m[2]) : null;
       triples.push({
         file: file || null,
         line: lineNo,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "shapeup-sdlc",
-  "version": "3.11.0",
+  "version": "3.12.0",
   "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

@@ -83,6 +83,11 @@ Done-when statements; `_index.md` Non-Go list. Which UCs are in scope comes from
   freeze through the judge). Ugly-but-correct PASSes; pretty-but-wrong-`data-state` FAILs.
 - `[data]`: query the DB/storage, capture actual state.
 - Contract work: send real requests, compare field-by-field.
+- **A fixture that names a row is evidence for that row.** When a T0 artifact you cite, or the
+  build gate, carries output that names a Test Surface row by id — `PASS TS-05-05`, or
+  `FAIL TS-05-05 step 4: …` — grade that row on it: a named PASS confirms, a named FAIL is a
+  FAIL whose bug is that line. This is how a device row is evidenced when you cannot drive the
+  app yourself; it is never a reason to skip driving it when you can.
 - No evidence collected = recorded "NO EVIDENCE" → FAILs at verdict.
 
 **VERDICT.**

package/skills/task-executor/SKILL.md

@@ -25,7 +25,7 @@ rely on (anything absent = **unknown**; never invent it):
 | `payload.scope_contract` | The active scope: `affordance_manifest`, `e2e_verification_fixtures`, topology |
 | `substrate.allowed` / `substrate.shared` | The ONLY globs you may write. A needed file outside them → ESCALATE, never a write (a sandbox hook blocks it anyway) |
 | `payload.decisions[]` | Adjudicated answers from prior escalations — binding precedent, apply them |
-| `payload.digested_errors[]` | `{file, line, core_message}` triples from the previous attempt's failed verification — your starting bug list |
+| `payload.digested_errors[]` | `{file, line, core_message}` triples from the previous attempt's failed verification (a test that failed by name with no file:line — `FAIL TS-05-05 step 4: …` — arrives with `file: null` and the whole line as its message) — your starting bug list |
 | `payload.trial_history[]` | Up to 8 prior attempts on this scope, oldest first, CROSSING the round boundary: `{score, status, delta, digest}`. `status: "reverted"` is a change that was tried and made things WORSE — do not re-propose it. `status: "kept"` with a still-red score is the tree you are building ON, not a failure to undo. Absent on the first attempt |
 | `payload.verify.test_cmd` | The command that verifies your work. No test_cmd → command-verifiable ACs still need *some* observable check; say what you used |
 | `payload.kb_rules_path` | Team guidelines (read if the file exists) — steering, never spec; conflict → the AC wins, note it in `deviations` |