chore(voyage): release v5.6.0 — /trekexecute loop hardening

Bump plugin.json, package.json, package-lock.json, and the README badge
to 5.6.0; prepend CHANGELOG v5.6.0 entry + README "What's new" block for
the S38 loop-hardening work (machine-verifiable completion gate, bounded
recovery cap hierarchy + global budget, iterations_remaining signal,
fan-out hedge harmonization).

Additive — no breaking change. Canonical node --test stays 756 (0 fail);
version-consistency test green across all five version refs.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "voyage",
   "description": "Voyage — brief, research, plan, execute, review, continue. Contract-driven Claude Code pipeline. /trekbrief, /trekplan, and /trekreview each end by building a self-contained operator-annotation HTML (scripts/annotate.mjs, modelled on claude-code-100x): select text or click any element, pick intent (Fiks/Endre/Spørsmål), write comment, copy structured prompt, paste back, Claude revises the .md.",
-  "version": "5.5.0",
+  "version": "5.6.0",
   "author": {
     "name": "Kjell Tore Guttormsen"
   },

CHANGELOG.md

@@ -4,6 +4,27 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 
+## v5.6.0 — 2026-06-20 — `/trekexecute` loop hardening: machine-verifiable completion + bounded recovery
+
+Additive — no breaking change. Hardens the `/trekexecute` execution loop so termination is *machine-verifiable* and recovery is *bounded by an explicit budget*, closing the "runs forever" and "declares done without proof" failure modes. Five focused changes; canonical `node --test` 744 → **756** (0 fail).
+
+### Machine-verifiable completion gate (the headline)
+
+- **Stop-signal contract** — `/trekexecute` reports `completed` only when a machine-checkable contract holds: the Phase 7.5 manifest audit PASSes, the stop signal exits 0, and the success criteria are green. **Hard Rule 18** is promoted from prose guidance to an enforced gate, anchored in the Phase 7.5 audit rather than the model's self-assessment.
+
+### Bounded recovery — cap hierarchy + global budget
+
+- **`TREKEXECUTE_MAX_RECOVERY_ITERATIONS`** — a global recovery-iteration budget (default **25**, env-overridable) sits above the per-step caps as a three-axis cap hierarchy (recovery depth · per-step retry · global budget), codified as **Hard Rule 20**. Stops an unbounded recover→retry→recover spiral that the per-step caps alone could not bound.
+- **`iterations_remaining` signal** — surfaced in the progress schema and the summary JSON, with a deterministic gate cross-check (`iterations_remaining == cap − (recovery_depth + Σ attempts-beyond-first)`) that catches a never-decremented counter. Shape-validated in `lib/.../progress-validator.mjs` (`PROGRESS_ITERATIONS_REMAINING_INVALID`: non-negative integer, additive-optional — never required at top level).
+
+### Doc consistency
+
+- **Fan-out hedge harmonized** — the `CLAUDE.md` design-principle line is aligned to the measured claim (parallel wall-clock + structured artifact handoffs as the load-bearing benefit; main-context relief stays explicitly *not demonstrated*), with a banned-phrase **forward-guard** in `tests/lib/doc-consistency.test.mjs` so the over-claim cannot reappear.
+
+### Release hygiene
+
+- **Version sync** — `plugin.json`, `package.json`, `package-lock.json`, the README badge, and the CHANGELOG top entry all at `5.6.0`, guarded by the version-consistency test in `tests/lib/doc-consistency.test.mjs`.
+
 ## v5.5.0 — 2026-06-18 — Coordinated release: brief framing enforcement (2.2) + W1–W3 narrow wins
 
 The coordinated release held since the framing work. Supersedes the unreleased internal milestones **v5.2–v5.4** (W2 model/effort alignment, W3 guardrail hardening, the Handover-1 public-contract formalization), landing them together with the `brief_version 2.2` schema badge and the W1 narrow wins. **Additive — no breaking change for existing consumers:** every `2.0`/`2.1` brief still validates; the new requirements gate only on briefs that *declare* `brief_version: "2.2"`.

README.md

@@ -1,6 +1,6 @@
 # trekplan — Brief, Research, Plan, Execute, Review, Continue
 
-![Version](https://img.shields.io/badge/version-5.5.0-blue)
+![Version](https://img.shields.io/badge/version-5.6.0-blue)
 ![License](https://img.shields.io/badge/license-MIT-green)
 ![Platform](https://img.shields.io/badge/platform-Claude%20Code-purple)
 
@@ -10,6 +10,11 @@
 
 A [Claude Code](https://docs.anthropic.com/en/docs/claude-code) plugin for deep implementation planning, multi-source research, autonomous execution, independent post-hoc review, and zero-friction multi-session resumption. Six commands, one pipeline:
 
+> **What's new in v5.6.0 — `/trekexecute` loop hardening** — execution-loop termination is now **machine-verifiable** and recovery is **bounded by an explicit budget**:
+> - **Machine-verifiable completion gate** — a session reports `completed` only when the Phase 7.5 manifest audit PASSes, the stop signal exits 0, and the success criteria are green (**Hard Rule 18**, promoted from prose to an enforced stop-signal contract anchored in the audit, not the model's self-assessment).
+> - **Bounded recovery** — a global `TREKEXECUTE_MAX_RECOVERY_ITERATIONS` budget (default **25**, env-overridable) sits atop the per-step caps as a three-axis cap hierarchy (**Hard Rule 20**), with an `iterations_remaining` signal in the progress + summary JSON and a deterministic cross-check that catches a never-decremented counter.
+> Additive — no breaking change. Full detail in [CHANGELOG.md](CHANGELOG.md).
+>
 > **What's new in v5.5.0 — brief framing enforcement (`brief_version 2.2`) + narrow wins** — `/trekbrief` now opens with a **framing declaration** (Phase 2.5): every brief records `framing: preserve | refine | replace | new-direction` *before* any prose is written, so the plan can't quietly polish a wrong premise. Three version-gated layers ship at `brief_version ≥ 2.2`:
 > - **Framing field** — a required `framing` enum in frontmatter; enum-checked on any version, and a missing value at `≥ 2.2` is a blocker. Collected in Phase 2.5 before prose, non-skippable even in `--quick`.
 > - **Memory alignment** — a new `brief-reviewer` dimension compares the brief's Intent/Goal + framing against operator memory and flags *explicit* contradictions (a no-op that scores N/A when no memory is supplied).

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "voyage",
-  "version": "5.5.0",
+  "version": "5.6.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "voyage",
-      "version": "5.5.0",
+      "version": "5.6.0",
       "license": "MIT",
       "engines": {
         "node": ">=18"

package.json

@@ -1,6 +1,6 @@
 {
   "name": "voyage",
-  "version": "5.5.0",
+  "version": "5.6.0",
   "description": "Voyage — brief, research, plan, execute, review, continue. Contract-driven Claude Code pipeline. /trekbrief, /trekplan, and /trekreview each end by building a self-contained operator-annotation HTML (scripts/annotate.mjs, modelled on claude-code-100x): select text or click any heading/paragraph/list-item, pick intent (Fiks/Endre/Spørsmål), write comment, copy structured prompt, paste back, Claude revises the .md.",
   "type": "module",
   "engines": {