pi-goal-list-loop-audit 0.38.97 → 0.38.98

package/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 0.38.98 — audited lifecycle hardening and change-first completion (2026-09-24)
+
+- Fresh audit repairs make goal/list/loop state durable across persistence failures, session replacement, compaction failure, repair promotion, and branch-mode completion. Confirmed loop refinements now apply atomically instead of mutating live state before the spec is safely written.
+- Draft, task, repair, and queue proposals validate their durable contract before side effects; empty or malformed work cannot silently become an active goal. Managed subagent paths are constrained and vision fallback arguments are safely quoted.
+- Terminal output is change-first: approved objectives lead with the delivered behavior, explicit remaining work, and one next action. Verification remains available in the durable archive and is shown in chat only when requested. Status/history and provider diagnostics are sanitized for terminal control bytes.
+- The shipped contract now matches current Pi usage and GLLA state: Bun is documented for development gates, bare `/list` is shown as Confirm-gated drafting, the historical plan is clearly non-authoritative, and the published goal schema is exercised through real JSON Schema validation.
+- The npm package explicitly advertises its Pi extension/skill manifest and gallery preview image. `pi install npm:pi-goal-list-loop-audit` remains the supported install path; the official `pi.dev/packages` gallery indexes the `pi-package` release automatically.
+
 ## 0.38.97 — pause_goal redirect: park-and-continue for user interruptions (2026-09-23)
 
 - Field: a mid-goal redirect ("can we get to this first") parked via pause_goal, whose abort + "do NOT continue working" stranded the new task until the user nudged. New optional `redirect` param parks the goal WITHOUT ending the turn and orders the redirect worked immediately, goal resumed after; redirect parks ledger distinctly as `pause_goal_redirect`. Plain pauses still abort (audit/PAUSE-REDIRECT-2026-09-23.md).

package/INSTALL.md

@@ -14,8 +14,8 @@ installation path.
 - [pi](https://github.com/badlogic/pi-mono) with extension support;
 - Node `22.19.0+` for the detached auditor and helper scripts;
 - a model/provider that pi can authenticate normally;
-- optionally, [Bun](https://bun.sh/) if you are developing GLLA or running its
-  test suite.
+- [Bun](https://bun.sh/) only for development, tests, and `npm run release:check`
+  (runtime goal/loop/list operation needs Node + pi, not Bun).
 
 ## Install from npm
 
@@ -31,8 +31,10 @@ GLLA loads into new pi sessions. If pi is already open, reload that session:
 
 ## Updating
 
-The status line always shows the running version (`glla: … · vX.Y.Z`).
-When the npm registry is ahead, it also nudges:
+While a goal/list/loop is supervised, the status line shows the running
+version (`glla: … · vX.Y.Z`). Idle or hold-only sessions intentionally keep the
+version segment clear; use `/glla version` there. When the npm registry is
+ahead, an active supervised status also nudges:
 
 ```text
 glla: … · vX.Y.Z · update vA.B.C available

package/PLAN.md

@@ -1,9 +1,13 @@
 # PLAN — pi-goal-list-loop-audit
 
-Living plan for the project. Update this file as decisions land or milestones close.
-New here? Start with README.md and INSTALL.md — this file is the historical
-plan, not the onboarding path.
-Last updated: v0.29.6 (header refresh). The milestones
+> **Historical scaffold plan — not runnable onboarding or current product
+> documentation.** The command/state examples below describe the v0.1–v0.7 era
+> (for example `.pi-gla/` and the former five-minute backoff cap). Use
+> [`README.md`](README.md) and [`INSTALL.md`](INSTALL.md) for current setup and
+> commands. The milestones below record how the project reached its current
+> architecture; later decisions live in `CHANGELOG.md` and `docs/DESIGN.md`.
+>
+> The milestones
 below cover the v0.1.0–v0.7.0 scaffold era; later decisions live in CHANGELOG.md
 (current through v0.29.6) and the current-state addendum in docs/DESIGN.md.
 
@@ -58,8 +62,8 @@ pi -e /home/dracon/Dev/pi-goal-list-loop-audit
 > /goal "Create file hello.txt containing the word world. Done when: grep -q world hello.txt"
 # expect: agent writes file, calls complete_goal, auditor approves, goal archived
 > /goal status        # expect: complete, audit history shows 1 approved
-cat .pi-gla/active.jsonl | tail -3
-ls .pi-gla/archive/   # expect: one .md file
+cat .pi-glla/active.jsonl | tail -3
+ls .pi-glla/archive/   # expect: one .md file
 ```
 
 ### M2 — v0.2.0 (list + drafting + regression_shield) ✅ (2026-07-20)

package/docs/DESIGN-long-running-supervision.md

@@ -111,25 +111,29 @@ path. It says `not recorded` when a changed-file manifest or test result is not
 available. It never infers a passing test or invents a commit.
 
 The full six-label recap lives verbatim in the archive (`## Completion summary`)
-and the status/history surfaces. The human layer in chat, transcript, and the
-archive's `## Terminal summary` renders the same facts as rich sections
-(`## Done: <objective> — <outcome>`, duration line, Key Findings grouped by area
-or tabulated at 4+ groups with per-finding `Test Results:` proof lines,
-Verification Summary table — widened to Quality Gate | Command | Scope |
-Status | Notes when any gate row carries a repro command, else Quality
-Gate | Scope | Status | Notes — with derived statuses when the agent
-supplies a gate inventory — uncapped findings/values (Next keeps the
-one-concrete-action rule), and a Final
-Repository State section (branch, HEAD, tree) closing the card behind a
-verdict banner that opens it (`## Done — auditor approved (N verdicts)`
-and siblings). Width-bound and external surfaces (status line, widget card,
-external notifies) use the compact single-line projection of all six labels.
-Every terminal goal notification, including version-bearing already-shipped claims,
-explicit goal/list cancellation, and `/glla wipe`, carries either the rich sections
-or the compact projection; loop notifications do the same. The terminal
-notification may use a compact excerpt. The executor recap and independent
-auditor verdict stay separate: an approval is not manufactured from the
-presence of a summary.
+and the status/history surfaces. The human layer follows two different purposes:
+
+- Chat and transcript explain **what happened**: outcome first, then a
+  change-first `What Changed` account grouped by area, followed by material
+  `Remaining` limitations and one concrete `Next` action. Tests, verification,
+  gate tables, commands, hashes, and machine evidence stay out of the default
+  user view. If the user explicitly asks for verification, the terminal render
+  may add one compact `Verification` sentence; the archive always retains the
+  complete evidence.
+- The archive's `## Terminal summary` remains forensic and complete: detailed
+  findings grouped or tabulated at 4+ groups, per-finding proof, the full
+  Verification Summary table (Quality Gate | Command | Scope | Status | Notes
+  when supplied), and Final Repository State.
+
+Both surfaces retain the independent auditor verdict and the full six-label
+machine recap. A lone approval may be promoted to the chat headline because
+it is a durable verdict fact, not because tests passed. Width-bound and
+external surfaces use the compact single-line projection of all six labels.
+Every terminal goal notification, including version-bearing already-shipped
+claims and explicit cancellation, carries the change-first human view or the
+compact projection; loop notifications do the same. The executor recap and
+independent auditor verdict stay separate: an approval is not manufactured from
+the presence of a summary.
 
 Metric-loop stops use the same six-label contract in their durable loop state
 and `/loop status`, and every terminal loop notification carries a compact

package/docs/INDEX.md

@@ -16,7 +16,7 @@ Policy contracts and recent changes live in the `audit/` directory of the
   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–v0.38.97 continue through the supervisor freeze (`/glla pause`),
+  v0.35.14–v0.38.98 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/examples/example-objective.md

@@ -46,7 +46,8 @@ Useful commands: `/goal status`, `/goal pause`, `/goal resume`, `/goal cancel`,
 ```
 /list Create one.txt containing one. Done when: grep -q one one.txt
 /list Create two.txt containing two. Done when: grep -q two two.txt
-/list            # show active + waiting items
+/list show       # show active + waiting items
+/list            # draft new list items from the current context (Confirm-gated)
 /list next       # skip current item
 /list remove 2   # drop item 2
 /list clear      # empty the list