pi-goal-list-loop-audit 0.38.40 → 0.38.42

package/CHANGELOG.md

@@ -1,5 +1,26 @@
 # Changelog
 
+## 0.38.42 — trailer cleanup: model-free folded approval (2026-09-09)
+
+### Fixed
+
+- **One canonical approval bullet in chat and transcript (field 20260909_140404):** the `provider/model` slug leaves both surfaces — chat shows `auditor approved on the provider retry (1 verdict).`, via-retry news kept. A lone approval folds with the verdict count; the standalone audit bullet survives only with news (multiple, disapproved, or impossible verdicts). The full model ID stays in the archive record; machine-path layering (chat stripped, transcript full) unchanged.
+
+### Verification
+
+- Render-unit pins both ways (fold + survive) and both surfaces (no model ID) plus an archive-keeps-model source pin; full `release:check` 0 failures; `tsc --noEmit` clean.
+
+## 0.38.41 — grilling standard codified (2026-09-09)
+
+### Fixed
+
+- **Questionnaire discipline is now GLLA behavior, not an agreement:** all three drafting prompts (`goal-loop-draft.md`, `goal-loop-forever-draft.md`, `goal-loop-plan.md`) carry the roadmap-then-stages rule (batch independent questions, sequence dependent ones with the roadmap stated first), the rich-option standard (concrete-consequence descriptions + preview pane where end-states matter, never padded to four), and the explicit Esc-correction invitation.
+- **Pin test:** `tests/drafting-questionnaire.test.ts` (9 pins) fails if any prompt drops any part of the rule.
+
+### Verification
+
+- New pin test green; full `release:check` 0 failures; `tsc --noEmit` clean.
+
 ## 0.38.40 — provider overflow errors count as starvation (2026-09-09)
 
 ### Fixed

package/docs/INDEX.md

@@ -18,7 +18,7 @@ For shipped docs, the relevant entry points are:
   failback; v0.35.9 hardened cross-version npm tarball checks; v0.35.10
   handles multi-entry npm dry-run reports; v0.35.11 accepts both npm report
   shapes; v0.35.12 supports npm 12's keyed pack reports; v0.35.13 fixes stale-API recovery loops.
-  v0.35.14–v0.38.40 continue through the supervisor freeze (`/glla pause`),
+  v0.35.14–v0.38.42 continue through the supervisor freeze (`/glla pause`),
   load hold, auditor picker parity, Windows launch fix, zombie-watchdog
   subagent carve-out, due-wait backstop, the `/glla agents` visibility panel,
   durable state-root selection, blank-until-resume auditor context, frozen

package/extensions/completion-summary.ts

@@ -237,7 +237,10 @@ export function withoutStaleNext(details: string[] | undefined): string[] {
  * Five 120-char label lines scan as soup, not a summary (field
  * 2026-09-04); the stale Next never reaches the chat.
  * v0.38.25: optional `counts` audit-goal counts line rides between the
- * approval trailer and the record pointer (the pointer stays last). */
+ * approval trailer and the record pointer (the pointer stays last).
+ * v0.38.42: retained for backward compatibility + direct unit tests —
+ * buildTerminalApprovalRender constructs chat lines inline because the
+ * fold changes trailer arity, which this fixed-shape helper cannot express. */
 export function buildApprovalChatLines(notice: {
   outcome: string;
   details: string[] | undefined;
@@ -262,7 +265,15 @@ export function buildApprovalChatLines(notice: {
 /** v0.38.39 (field 20260909_013733): the trailer rides as bullets too —
  * the Codex close is uniform `•` lines (`• Changed:` … `• record:`),
  * never a `•` block followed by dangling `—` lines. The `— ` sigil is
- * stripped at render; the input strings keep it for non-chat surfaces. */
+ * stripped at render; the input strings keep it for non-chat surfaces.
+ * v0.38.42 (field 20260909_140404): the chat/transcript approval bullet
+ * carries no model ID — the `provider/model` slug is machine trivia
+ * outside an audit (the full model ID stays in the archive record).
+ * The `auditor <model> approved` shape collapses to `auditor approved`;
+ * any other approval voice passes through untouched. */
+function stripApprovalModel(line: string): string {
+  return line.replace(/auditor\s+\S+\s+approved/, "auditor approved");
+}
 function trailerBullet(line: string): string {
   return `• ${line.replace(/^—\s*/, "")}`;
 }
@@ -343,19 +354,33 @@ export function buildTerminalApprovalRender(input: TerminalApprovalRenderInput):
     ? { ...baseBrief, details: [...baseBrief.details, `Left out: ${clipSummaryValue(leftOutContent, 120)}`] }
     : baseBrief;
   const countsLine = input.countsLine ?? buildAuditCountsLine(input.goal, input.auditNote);
+  // v0.38.42 (field 20260909_140404): one canonical approval bullet in
+  // chat and transcript — no model ID in either, via-retry news kept. A
+  // lone approval says the same thing as the counts line, so they fold
+  // into one bullet carrying the verdict count; the standalone audit
+  // bullet survives only with news (multiple, disapproved, or impossible
+  // verdicts). The returned `approval` field keeps the full input string
+  // for archive/persist consumers — the model ID leaves chat/transcript,
+  // never the record.
+  const history = input.goal.auditHistory ?? [];
+  const chatApproval = stripApprovalModel(input.approval);
+  const foldCounts = history.length === 1
+    && history[0]?.approved === true
+    && /approved/.test(chatApproval);
+  const approvalBullet = foldCounts
+    ? `• ${chatApproval.replace(/^—\s*/, "").replace(/\.\s*$/, "")} (${history.length} verdict).`
+    : trailerBullet(chatApproval);
   return {
     chatLines: [
-      ...buildApprovalChatLines({
-        outcome: brief.outcome,
-        details: brief.details,
-        approval: input.approval,
-        record: input.record,
-        counts: countsLine,
-      }),
+      `✓ done — ${brief.outcome}`,
+      ...withoutStaleNext(brief.details).map((detail) => `• ${detail}`),
+      approvalBullet,
+      ...(foldCounts ? [] : [trailerBullet(countsLine)]),
+      trailerBullet(input.record),
       ...(input.extras ?? []),
     ],
     recap,
-    transcriptLines: [...withoutStaleNext(brief.details).map((detail) => `• ${detail}`), trailerBullet(input.approval)],
+    transcriptLines: [...withoutStaleNext(brief.details).map((detail) => `• ${detail}`), approvalBullet],
     countsLine,
     outcome: brief.outcome,
     approval: input.approval,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-goal-list-loop-audit",
-  "version": "0.38.40",
+  "version": "0.38.42",
   "description": "Mission control for autonomous pi: interview-drafted goals, an audited task queue, and forever-loops (metric, spec, project-audit) that run for hours. A detached extension-less auditor process re-verifies every completion with raw evidence without holding the main pi turn; confirmed drafts, decision pauses and consent gates keep you in charge.",
   "license": "AGPL-3.0-only",
   "author": "dracon",

package/prompts/goal-loop-draft.md

@@ -78,6 +78,14 @@ request into a **confirmed goal contract**. Do NOT start substantive work yet.
    If an `ask_user_question` tool is available in this session, prefer it for
    structured choices (it renders proper option lists); plain conversation is
    fine otherwise and for free-form answers.
+   **Questionnaire discipline — roadmap, then stages:** batch independent
+   questions upfront in one `ask_user_question` call; when a later question
+   depends on an earlier answer, state the full roadmap first, then ask
+   stage-by-stage so every option makes sense when answered. Every option
+   description states its concrete consequence, plus a preview pane wherever
+   what the option produces matters — two honest options beat four padded
+   guesses. Close every batch by inviting correction: if any of this is off,
+   Esc and say what's wrong, and you re-ask.
 2. Targeted read-only research is allowed when it helps define a better
    contract (read a file, check the repo layout). Do NOT implement anything.
    **Default to subagents for research**: use the `subagent` tool to spawn a `scout` subagent

package/prompts/goal-loop-forever-draft.md

@@ -56,6 +56,15 @@ stops it.
      genuinely endless (an ever-improving spec, continuous hardening).
 3. Clarify the **direction**: is lower better (min) or higher better (max)?
    (Skip this for a metricless loop — there is no direction without a metric.)
+   **Questionnaire discipline — roadmap, then stages:** batch independent
+   questions upfront in one `ask_user_question` call; when a later question
+   depends on an earlier answer (bounds depend on the metric, metricless
+   depends on no-number), state the full roadmap first, then ask
+   stage-by-stage so every option makes sense when answered. Every option
+   description states its concrete consequence, plus a preview pane wherever
+   what the option produces matters — two honest options beat four padded
+   guesses. Close every batch by inviting correction: if any of this is off,
+   Esc and say what's wrong, and you re-ask.
 4. Optional tuning: `window` (plateau stop after N non-improving iterations,
    default 5 — meaningless for metricless), `max` (iteration cap: default 50
    for METRIC loops; default UNBOUNDED (`max=0`) for metricless loops,

package/prompts/goal-loop-plan.md

@@ -27,7 +27,14 @@ confirms.
    - **Verification strategy** — how each milestone proves itself done.
    Ask one focused question at a time within a round; offer a recommended
    default with each question so the user can answer "yes". Prefer
-   `ask_user_question` for structured choices when available.
+   `ask_user_question` for structured choices when available. The rounds
+   ARE the stages: state the full round roadmap first, then work it
+   round-by-round (later rounds depend on earlier answers — never batch a
+   later round's questions upfront). Every option description states its
+   concrete consequence, plus a preview pane wherever what the option
+   produces matters — two honest options beat four padded guesses. Close
+   every round by inviting correction: if any of this is off, Esc and say
+   what's wrong, and you re-ask.
 3. **The proposal is a structured expanded objective.** Use this shape
    inside the objective text:
    - **Current state** — what exists today, with file/module references.