From d2de622744212ea0ba720b3f4212b82940ffe84b Mon Sep 17 00:00:00 2001
From: Agando <roduccomm@gmail.com>
Date: Tue, 27 Oct 2026 11:23:10 +0100
Subject: fix(newos4): rollback keeps scaffolding, checkpoints cannot collide,
 tests gate the build

Review of the 08:30 implementer run (v4.6.102, checkpoint name fix). The shipped fix was
correct; these are the defects it introduced or left behind, each measured first.

- virtual-fs.js rollback(): the snapshot strips _snapshots/_sessions/.trash for bloat. Restoring
  it verbatim deleted every checkpoint, every agent session and the trash, made rollback
  irreversible and unrepeatable. Re-attach the live copies after the root swap.
- checkpoint(): names are millisecond-resolution, so tight calls overwrote each other
  (measured 6 calls -> 3 snapshots). Dedupe with a -N suffix, refuse names containing "/"
  (written but unlistable), and prune by snapshot createdAt instead of filename sort, which
  let a custom name ("aaa-oldest") evict newer auto-named checkpoints.
- module-predictor.js: legacy pre-v2 points have no `usable`, so a 0.079 s aborted run
  re-entered similarity as evidence and floored every prediction at 1 s. Backfill `usable`
  from the measurement on load, drop the ones it rejects, add a belt-and-braces guard in
  _findSimilar and count only usable points as actual executions.
- newos4-maintain.py: run every node-runnable modules/test/test-*.js on each maintenance pass.
  The v4.6.102 regression was written but no job ever executed it.
- newos4-steer.py: `done` now requires --commit <sha> that exists in the repo, and gains
  `reopen`. A written plan was being closed as done at 06:17 while the predictor fix shipped
  nowhere, so the implementer's pre-flight queue was empty.
- steering.json: predictor item reopened, checkpoint item stamped with f7249ff.
- maintenance board: MAINT-002/005/015 were fixed in v4.6.81-85 but still listed open/high;
  closed with their commit ids, and MAINT-010/016 annotated with the probes that keep them open.

Tests: test-vfs-checkpoint 23/23 (RED 14/9 before), test-predictor-accuracy 38/38
(T1-T3 RED on HEAD), maintain --fix all PASS, browser round-trip
"Checkpoint created: <name>" -> "Rolled back to checkpoint: <name>" on v4.6.103.

Also carries the already-deployed 2026-10-26 syntax-gate hunk in newos4-maintain.py (syntax_failures + gated rebuild) that had never been committed.
---
 main.html                               |  6 ++--
 modules-index.json                      |  9 +++--
 modules/core/core-bundle.js             | 47 ++++++++++++++++++++----
 modules/core/module-loader.js           |  2 +-
 modules/core/module-predictor.js        | 15 ++++++--
 modules/core/virtual-fs.js              | 32 ++++++++++++++---
 modules/test/test-predictor-accuracy.js | 33 +++++++++++++++++
 modules/test/test-vfs-checkpoint.js     | 55 ++++++++++++++++++++++++++++
 scripts/newos4-maintain.py              | 63 ++++++++++++++++++++++++++++-----
 scripts/newos4-steer.py                 | 26 ++++++++++++--
 10 files changed, 256 insertions(+), 32 deletions(-)

diff --git a/main.html b/main.html
index b3d2c39..1c64cf1 100644
--- a/main.html
+++ b/main.html
@@ -1349,13 +1349,13 @@
     </script>
 
     <!-- v4.5.63: A2A scratchpad fixes + agent-register arg fix -->
-<script src="modules/core/core-bundle.js?v=v4.6.102"></script>
+<script src="modules/core/core-bundle.js?v=v4.6.103"></script>
 
     <!-- Async dependency-ordered module loader now only initializes terminal and loads optional ext modules -->
-<script src="modules/core/module-loader.js?v=v4.6.102"></script>
+<script src="modules/core/module-loader.js?v=v4.6.103"></script>
 
     <!-- Critical ext bundle loads AFTER webx11 exists so registerModule calls work -->
-<script src="modules/ext/critical-ext-bundle.js?v=v4.6.102"></script>
+<script src="modules/ext/critical-ext-bundle.js?v=v4.6.103"></script>
 
 <script>
 // ═══ ONE TRUE VERSION SOURCE ═══
diff --git a/modules-index.json b/modules-index.json
index 5a55ebe..2f95365 100644
--- a/modules-index.json
+++ b/modules-index.json
@@ -1,5 +1,5 @@
 {
- "version": "2026-10-23-atlas",
+ "version": "2026-10-27-atlas",
  "generated": "2026-06-30T00:00:00.000Z",
  "modules": {
   "module-agent-registry": {
@@ -169,6 +169,7 @@
     "empty-trash",
     "find",
     "grep",
+    "guides",
     "head",
     "ls",
     "ls-trash",
@@ -1075,7 +1076,11 @@
     "debug-sync-url",
     "debug-trends",
     "feedback",
-    "feedback-inbox"
+    "feedback-admin",
+    "feedback-inbox",
+    "hermes",
+    "hermes-poll",
+    "hermes-reset"
    ],
    "tier": "core-bundle"
   },
diff --git a/modules/core/core-bundle.js b/modules/core/core-bundle.js
index cd510b7..84d194d 100644
--- a/modules/core/core-bundle.js
+++ b/modules/core/core-bundle.js
@@ -942,6 +942,17 @@ class VirtualFileSystem {
     }
     checkpoint(name) {
         if (!name) name = new Date().toISOString();
+        name = String(name).trim();
+        if (!name || name.indexOf('/') !== -1) {
+            throw new Error('checkpoint name must be non-empty and must not contain "/"');
+        }
+        // Two unnamed calls can land in the same millisecond; without this the second silently
+        // overwrites the first (measured: 6 calls -> 3 distinct names).
+        if (this.listCheckpoints().indexOf(name) !== -1) {
+            let n = 2;
+            while (this.listCheckpoints().indexOf(name + '-' + n) !== -1) n++;
+            name = name + '-' + n;
+        }
         const createdAt = new Date().toISOString();
         // Strip system dirs to prevent fractal bloat
         const rootClone = JSON.parse(JSON.stringify(this.root));
@@ -961,12 +972,15 @@ class VirtualFileSystem {
         }
         this.fsWriteJSON('/_snapshots/checkpoint-' + name + '.json', data);
         this.saveToStorage();
-        // Auto-manage: keep max 3 checkpoints, delete oldest
+        // Auto-manage: keep the 3 NEWEST checkpoints — by createdAt, not by name, so a custom
+        // name ("aaa-oldest") cannot pin itself forever while newer snapshots are deleted.
         const all = this.listCheckpoints();
         if (all.length > 3) {
-            const sorted = all.slice().sort();
-            const toDelete = sorted.slice(0, all.length - 3);
-            for (const old of toDelete) this.deleteCheckpoint(old);
+            const aged = all.map(n => {
+                const snap = this.fsReadJSON('/_snapshots/checkpoint-' + n + '.json');
+                return { name: n, at: (snap && snap.createdAt) || '' };
+            }).sort((a, b) => (a.at < b.at ? -1 : (a.at > b.at ? 1 : 0)));
+            for (const old of aged.slice(0, aged.length - 3)) this.deleteCheckpoint(old.name);
         }
         return name;
     }
@@ -976,8 +990,18 @@ class VirtualFileSystem {
             console.error('Rollback failed: checkpoint not found or invalid');
             return false;
         }
+        // The snapshot deliberately omits scaffolding (bloat guard at :944-950). Restoring the
+        // clone verbatim deletes every checkpoint, every agent session and the trash, so keep the
+        // live copies and re-attach them after the root swap.
+        const keep = {};
+        for (const dir of ['_snapshots', '_sessions', '.trash']) {
+            const node = this.root && this.root.content ? this.root.content[dir] : null;
+            if (node) keep[dir] = node;
+        }
         this.root = raw.root;
         this.currentPath = raw.currentPath || [];
+        if (!this.root.content) this.root.content = {};
+        for (const dir of Object.keys(keep)) this.root.content[dir] = keep[dir];
         this.saveToStorage();
         return true;
     }
@@ -18261,6 +18285,7 @@ class PredictorModule {
         return this._dataPoints.filter(dp => {
             if (!dp.observedDuration) return false;   // outcomes only, never predictions
             if (dp.usable === false) return false;    // aborted runs are not evidence
+            if (!(dp.observedDuration >= 1.5)) return false;   // belt and braces: never evidence
             if (dp.features) return this._similarity(features, dp.features) > 0.3;
             return false;
         });
@@ -18412,7 +18437,7 @@ class PredictorModule {
     // ─── Commands ───
 
     showStatus() {
-        const actualExecutions = this._dataPoints.filter(dp => dp.observedDuration).length;
+        const actualExecutions = this._dataPoints.filter(dp => dp.observedDuration && dp.usable !== false).length;
         const paired = this._accuracy.total;
         const unpaired = this._dataPoints.filter(dp => dp.paired === false).length;
         const accPct = paired > 0 ? ((this._accuracy.correct / paired) * 100).toFixed(0) + '%' : 'n/a';
@@ -18517,8 +18542,16 @@ class PredictorModule {
             const data = fs.fsReadJSON('/system/metrics/predictor.json');
             if (!data) return;
 
-            // Prediction-only points are noise for similarity; keep outcomes.
-            this._dataPoints = (data.dataPoints || []).filter(dp => dp && dp.observedDuration);
+            // Legacy (pre-v2) points carry no `usable`. Backfill it from the measurement — an
+            // aborted run must not enter similarity as evidence (measured: a 0.079 s point
+            // dragged avgDuration to ~0 and floored every prediction at 1 s).
+            this._dataPoints = (data.dataPoints || [])
+                .filter(dp => dp && dp.observedDuration)
+                .map(dp => {
+                    if (typeof dp.usable !== 'boolean') dp.usable = dp.observedDuration >= 1.5;
+                    return dp;
+                })
+                .filter(dp => dp.usable !== false);
             this._predictions = data.predictions || 0;
 
             if (data.v === this._SCHEMA) {
diff --git a/modules/core/module-loader.js b/modules/core/module-loader.js
index b278f51..18137ec 100644
--- a/modules/core/module-loader.js
+++ b/modules/core/module-loader.js
@@ -4,7 +4,7 @@
     // Core module bundle loaded synchronously in main.html.
     // This loader only handles version cache-busting, splash, terminal init, and optional ext modules.
 
-    const LATEST_VER = 'v4.6.102';
+    const LATEST_VER = 'v4.6.103';
     const CACHE = '?v=' + LATEST_VER;
     const stored = localStorage.getItem('webx11_cache_ver');
     if (stored !== LATEST_VER) {
diff --git a/modules/core/module-predictor.js b/modules/core/module-predictor.js
index aebda87..b534d34 100644
--- a/modules/core/module-predictor.js
+++ b/modules/core/module-predictor.js
@@ -118,6 +118,7 @@ class PredictorModule {
         return this._dataPoints.filter(dp => {
             if (!dp.observedDuration) return false;   // outcomes only, never predictions
             if (dp.usable === false) return false;    // aborted runs are not evidence
+            if (!(dp.observedDuration >= 1.5)) return false;   // belt and braces: never evidence
             if (dp.features) return this._similarity(features, dp.features) > 0.3;
             return false;
         });
@@ -269,7 +270,7 @@ class PredictorModule {
     // ─── Commands ───
 
     showStatus() {
-        const actualExecutions = this._dataPoints.filter(dp => dp.observedDuration).length;
+        const actualExecutions = this._dataPoints.filter(dp => dp.observedDuration && dp.usable !== false).length;
         const paired = this._accuracy.total;
         const unpaired = this._dataPoints.filter(dp => dp.paired === false).length;
         const accPct = paired > 0 ? ((this._accuracy.correct / paired) * 100).toFixed(0) + '%' : 'n/a';
@@ -374,8 +375,16 @@ class PredictorModule {
             const data = fs.fsReadJSON('/system/metrics/predictor.json');
             if (!data) return;
 
-            // Prediction-only points are noise for similarity; keep outcomes.
-            this._dataPoints = (data.dataPoints || []).filter(dp => dp && dp.observedDuration);
+            // Legacy (pre-v2) points carry no `usable`. Backfill it from the measurement — an
+            // aborted run must not enter similarity as evidence (measured: a 0.079 s point
+            // dragged avgDuration to ~0 and floored every prediction at 1 s).
+            this._dataPoints = (data.dataPoints || [])
+                .filter(dp => dp && dp.observedDuration)
+                .map(dp => {
+                    if (typeof dp.usable !== 'boolean') dp.usable = dp.observedDuration >= 1.5;
+                    return dp;
+                })
+                .filter(dp => dp.usable !== false);
             this._predictions = data.predictions || 0;
 
             if (data.v === this._SCHEMA) {
diff --git a/modules/core/virtual-fs.js b/modules/core/virtual-fs.js
index 09b3548..3ed1b40 100644
--- a/modules/core/virtual-fs.js
+++ b/modules/core/virtual-fs.js
@@ -940,6 +940,17 @@ class VirtualFileSystem {
     }
     checkpoint(name) {
         if (!name) name = new Date().toISOString();
+        name = String(name).trim();
+        if (!name || name.indexOf('/') !== -1) {
+            throw new Error('checkpoint name must be non-empty and must not contain "/"');
+        }
+        // Two unnamed calls can land in the same millisecond; without this the second silently
+        // overwrites the first (measured: 6 calls -> 3 distinct names).
+        if (this.listCheckpoints().indexOf(name) !== -1) {
+            let n = 2;
+            while (this.listCheckpoints().indexOf(name + '-' + n) !== -1) n++;
+            name = name + '-' + n;
+        }
         const createdAt = new Date().toISOString();
         // Strip system dirs to prevent fractal bloat
         const rootClone = JSON.parse(JSON.stringify(this.root));
@@ -959,12 +970,15 @@ class VirtualFileSystem {
         }
         this.fsWriteJSON('/_snapshots/checkpoint-' + name + '.json', data);
         this.saveToStorage();
-        // Auto-manage: keep max 3 checkpoints, delete oldest
+        // Auto-manage: keep the 3 NEWEST checkpoints — by createdAt, not by name, so a custom
+        // name ("aaa-oldest") cannot pin itself forever while newer snapshots are deleted.
         const all = this.listCheckpoints();
         if (all.length > 3) {
-            const sorted = all.slice().sort();
-            const toDelete = sorted.slice(0, all.length - 3);
-            for (const old of toDelete) this.deleteCheckpoint(old);
+            const aged = all.map(n => {
+                const snap = this.fsReadJSON('/_snapshots/checkpoint-' + n + '.json');
+                return { name: n, at: (snap && snap.createdAt) || '' };
+            }).sort((a, b) => (a.at < b.at ? -1 : (a.at > b.at ? 1 : 0)));
+            for (const old of aged.slice(0, aged.length - 3)) this.deleteCheckpoint(old.name);
         }
         return name;
     }
@@ -974,8 +988,18 @@ class VirtualFileSystem {
             console.error('Rollback failed: checkpoint not found or invalid');
             return false;
         }
+        // The snapshot deliberately omits scaffolding (bloat guard at :944-950). Restoring the
+        // clone verbatim deletes every checkpoint, every agent session and the trash, so keep the
+        // live copies and re-attach them after the root swap.
+        const keep = {};
+        for (const dir of ['_snapshots', '_sessions', '.trash']) {
+            const node = this.root && this.root.content ? this.root.content[dir] : null;
+            if (node) keep[dir] = node;
+        }
         this.root = raw.root;
         this.currentPath = raw.currentPath || [];
+        if (!this.root.content) this.root.content = {};
+        for (const dir of Object.keys(keep)) this.root.content[dir] = keep[dir];
         this.saveToStorage();
         return true;
     }
diff --git a/modules/test/test-predictor-accuracy.js b/modules/test/test-predictor-accuracy.js
index 3688b03..74f0fcc 100644
--- a/modules/test/test-predictor-accuracy.js
+++ b/modules/test/test-predictor-accuracy.js
@@ -247,5 +247,38 @@ function ok(name, cond, detail) {
     ok('S3 pending consumed', p._pending.length === 0);
 }
 
+// T. v1 payload carrying an aborted garbage point must not train similarity (2026-10-27)
+{
+    const { p, term, out } = mk();
+    const feats = p._extractFeatures('read the logs');
+    term.fs.fsWriteJSON('/system/metrics/predictor.json', {
+        dataPoints: [{ features: feats, observedDuration: 0.079, observedTurns: 1 },
+                     { features: feats, observedDuration: 30, observedTurns: 3 }],
+        predictions: 2
+    });
+    p._loadFromVFS();
+    ok('T1 legacy aborted point dropped on load', p._dataPoints.length === 1, 'n=' + p._dataPoints.length);
+    const similar = p._findSimilar(p._extractFeatures('read the logs'));
+    ok('T2 similarity ignores the aborted point',
+        similar.length === 1 && similar[0].observedDuration === 30,
+        JSON.stringify(similar.map(s => s.observedDuration)));
+    out.length = 0; p.showStatus();
+    const line = out.find(l => l.includes('Actual executions')) || '';
+    ok('T3 status counts only usable executions', /Actual executions:\s*1\s*$/.test(line.trim()), line.trim());
+}
+
+// U. a lone aborted point cannot floor the next prediction
+{
+    const { p, term } = mk();
+    term.fs.fsWriteJSON('/system/metrics/predictor.json', {
+        dataPoints: [{ features: { hasRead: true }, observedDuration: 0.079, observedTurns: 1 }],
+        predictions: 1
+    });
+    p._loadFromVFS();
+    const pred = p.notePrediction('read the logs', 'test');
+    ok('U1 prediction is not floored by a lone aborted point', pred && pred.floored === false,
+        JSON.stringify(pred && { duration: pred.duration, floored: pred.floored }));
+}
+
 console.log(passes + '/' + (passes + fails) + ' PASS');
 process.exit(fails ? 1 : 0);
diff --git a/modules/test/test-vfs-checkpoint.js b/modules/test/test-vfs-checkpoint.js
index 03a8c8a..65f32dc 100644
--- a/modules/test/test-vfs-checkpoint.js
+++ b/modules/test/test-vfs-checkpoint.js
@@ -84,6 +84,61 @@ function ok(name, cond, detail) {
         'output=' + JSON.stringify(out.join('\n')));
 }
 
+// D. same-millisecond calls must not overwrite each other
+{
+    const fs = mkFs();
+    const names = [];
+    // 4 calls: one more than the cap of 3, so every name is still stored when the next one is
+    // minted (at 6+, prune legitimately frees a name and it may be reused).
+    for (let i = 0; i < 4; i++) names.push(fs.checkpoint(''));
+    ok('D1 four unnamed checkpoints are four distinct names', new Set(names).size === 4,
+        'names=' + JSON.stringify(names));
+    ok('D2 prune still caps the store at three', fs.listCheckpoints().length === 3,
+        'stored=' + JSON.stringify(fs.listCheckpoints()));
+}
+
+// E. prune keeps the NEWEST three, not the alphabetically last
+{
+    const fs = mkFs();
+    fs.checkpoint('aaa-oldest');
+    fs.checkpoint('');
+    fs.checkpoint('');
+    fs.checkpoint('');          // 4th -> prune
+    const left = fs.listCheckpoints();
+    ok('E1 oldest custom-named checkpoint was pruned', !left.includes('aaa-oldest'), 'left=' + JSON.stringify(left));
+    ok('E2 three checkpoints remain', left.length === 3, 'left=' + JSON.stringify(left));
+    ok('E3 rollback still works after pruning', fs.rollback(left[0]) === true);
+}
+
+// F. rollback must not destroy scaffolding
+{
+    const fs = mkFs();
+    fs.mkdirRecursive('/_sessions/agent1');
+    fs.writeFile('/_sessions/agent1/log.json', '{"turns":3}');
+    fs.mkdirRecursive('/.trash');
+    fs.writeFile('/.trash/junk.txt', 'x');
+    fs.writeFile('/work.txt', 'before');
+    const name = fs.checkpoint('keep-me');
+    fs.writeFile('/work.txt', 'after');
+    ok('F1 rollback succeeds', fs.rollback(name) === true);
+    ok('F2 file restored', fs.readFile('/work.txt') === 'before', 'got ' + fs.readFile('/work.txt'));
+    ok('F3 checkpoint survived rollback', fs.listCheckpoints().includes('keep-me'),
+        'list=' + JSON.stringify(fs.listCheckpoints()));
+    ok('F4 sessions survived rollback', !!fs.readDir('/_sessions'));
+    ok('F5 trash survived rollback', !!fs.readDir('/.trash'));
+    ok('F6 rollback is repeatable', fs.rollback('keep-me') === true);
+}
+
+// G. a name with a slash is refused, not silently unlistable
+{
+    const fs = mkFs();
+    let threw = false;
+    try { fs.checkpoint('a/b'); } catch (e) { threw = true; }
+    ok('G1 slash in name throws', threw);
+    ok('G2 nothing was written', fs.listCheckpoints().length === 0,
+        'list=' + JSON.stringify(fs.listCheckpoints()));
+}
+
 if (fails === 0) {
     console.log('test-vfs-checkpoint: ' + passes + ' passed, 0 failed');
 } else {
diff --git a/scripts/newos4-maintain.py b/scripts/newos4-maintain.py
index dd6c898..c28fb8b 100644
--- a/scripts/newos4-maintain.py
+++ b/scripts/newos4-maintain.py
@@ -21,22 +21,41 @@ def check_versions():
     n = html.count(ver)
     add('PASS' if n == 3 else 'FAIL', f'version {ver} x{n} in main.html (expect 3)')
 
-def check_bundles():
+def syntax_failures():
+    bad = []
+    for p in glob.glob(os.path.join(ROOT, 'modules/core/*.js')) + glob.glob(os.path.join(ROOT, 'modules/ext/*.js')):
+        if os.path.basename(p) in ('core-bundle.js', 'critical-ext-bundle.js'): continue
+        if run(['node', '--check', p]).returncode: bad.append(os.path.basename(p))
+    return bad
+
+def check_bundles(bad_syntax=None):
+    """Rebuild only when every module parses.
+
+    rebuild-bundles.py concatenates blindly (no validation), so a module with a
+    syntax error would be baked straight into the served core-bundle.js. Since
+    --fix now runs daily, the rebuild is gated on check_syntax and the produced
+    bundles are re-checked before the run is called clean.
+    """
     paths = ('modules/core/core-bundle.js', 'modules/ext/critical-ext-bundle.js')
     before = {p: sh(f'md5sum {p}') for p in paths}
     if not FIX:
         add('PASS', 'bundle check skipped (use --fix)'); return
+    if bad_syntax is None: bad_syntax = syntax_failures()
+    if bad_syntax:
+        add('FAIL', 'bundles rebuild BLOCKED: syntax fail in ' + ', '.join(bad_syntax[:5])); return
     r = run([sys.executable, 'scripts/rebuild-bundles.py'], cwd=ROOT)
+    if r.returncode:
+        add('FAIL', 'bundles FAILED'); return
+    invalid = [p for p in paths if run(['node', '--check', os.path.join(ROOT, p)]).returncode]
+    if invalid:
+        add('FAIL', 'bundles rebuilt but INVALID: ' + ', '.join(invalid)); return
     after = {p: sh(f'md5sum {p}') for p in paths}
     changed = [p for p in paths if before[p] != after[p]]
-    add('FAIL' if r.returncode else ('WARN' if changed else 'PASS'),
-        'bundles ' + ('FAILED' if r.returncode else ('rebuilt: ' + ', '.join(changed) if changed else 'clean')))
+    add('WARN' if changed else 'PASS',
+        'bundles ' + ('rebuilt: ' + ', '.join(changed) if changed else 'clean'))
 
-def check_syntax():
-    bad = []
-    for p in glob.glob(os.path.join(ROOT, 'modules/core/*.js')) + glob.glob(os.path.join(ROOT, 'modules/ext/*.js')):
-        if os.path.basename(p) in ('core-bundle.js', 'critical-ext-bundle.js'): continue
-        if run(['node', '--check', p]).returncode: bad.append(os.path.basename(p))
+def check_syntax(bad=None):
+    bad = syntax_failures() if bad is None else bad
     add('PASS' if not bad else 'FAIL', 'syntax ' + ('OK' if not bad else 'fail: ' + ', '.join(bad)))
 
 def check_perms():
@@ -128,6 +147,31 @@ def check_help_coverage():
         f'help coverage {len(cmds) - len(missing)}/{len(cmds)} commands'
         + ('' if not missing else f' — undocumented: {", ".join(missing[:8])}'))
 
+def check_regression_tests():
+    """Every node-runnable test under modules/test/ must pass (2026-10-27).
+
+    The v4.6.102 checkpoint regression was written but no job executed it, so drift could ship
+    silently. Two header conventions exist: '// ... run: node' and '// node modules/test/x.js'.
+    test-suite.js starts with a class (browser-only) and is correctly skipped.
+    """
+    tests, failed = [], []
+    for p in sorted(glob.glob(os.path.join(ROOT, 'modules/test/test-*.js'))):
+        head = ''.join(open(p, encoding='utf-8', errors='ignore').readlines()[:3])
+        if 'run: node' not in head and not head.startswith('// node modules/test/'):
+            continue
+        tests.append(p)
+        try:
+            r = subprocess.run(['node', p], cwd=ROOT, capture_output=True, text=True, timeout=120)
+        except subprocess.TimeoutExpired:
+            failed.append(os.path.basename(p) + ': timeout')
+            continue
+        if r.returncode != 0:
+            lines = (r.stdout or r.stderr).strip().splitlines() or ['no output']
+            failed.append(os.path.basename(p) + ': ' + lines[-1][:120])
+    add('PASS' if not failed else 'FAIL',
+        'node tests %d/%d pass' % (len(tests) - len(failed), len(tests))
+        + ('' if not failed else ' — ' + '; '.join(failed[:3])))
+
 def check_links():
     if not DEEP: return
     broken = []
@@ -143,7 +187,8 @@ def check_links():
 
 def main():
     os.chdir(ROOT)
-    check_versions(); check_bundles(); check_syntax(); check_perms(); check_index(); check_data(); check_live(); check_atlas(); check_course(); check_help_coverage(); check_links()
+    bad = syntax_failures()          # computed once, gates the bundle rebuild
+    check_versions(); check_syntax(bad); check_regression_tests(); check_bundles(bad); check_perms(); check_index(); check_data(); check_live(); check_atlas(); check_course(); check_help_coverage(); check_links()
     fails = [m for l, m in issues if l == 'FAIL']
     print('newOS4 maintenance — ' + datetime.now(timezone.utc).strftime('%Y-%m-%d %H:%MZ') + (' [fix]' if FIX else '') + (' [deep]' if DEEP else ''))
     for l, m in issues: print(f'{l}: {m}')
diff --git a/scripts/newos4-steer.py b/scripts/newos4-steer.py
index de3b87c..1e387f8 100755
--- a/scripts/newos4-steer.py
+++ b/scripts/newos4-steer.py
@@ -15,6 +15,7 @@ import argparse
 import fcntl
 import json
 import os
+import subprocess
 import time
 
 ROOT = '/var/www/webx11.duckdns.org/spaces/newos4'
@@ -48,7 +49,8 @@ def main():
     sub = ap.add_subparsers(dest='cmd', required=True)
     a = sub.add_parser('add'); a.add_argument('text'); a.add_argument('--priority', default='normal', choices=['high', 'normal', 'low'])
     sub.add_parser('list').add_argument('--all', action='store_true')
-    d = sub.add_parser('done'); d.add_argument('id')
+    d = sub.add_parser('done'); d.add_argument('id'); d.add_argument('--commit', default='')
+    r = sub.add_parser('reopen'); r.add_argument('id'); r.add_argument('--reason', default='')
     sub.add_parser('clear')
     args = ap.parse_args()
 
@@ -76,11 +78,29 @@ def main():
         elif args.cmd == 'done':
             hit = [r for r in data if r.get('id') == args.id]
             if not hit:
-                raise SystemExit(f"no such id: {args.id}")
+                raise SystemExit("no such id: " + args.id)
+            if not args.commit:
+                raise SystemExit('refusing: --commit <sha> required - a written plan is not a ship')
+            chk = subprocess.run(['git', '-C', '/var/www/webx11.duckdns.org', 'cat-file', '-e',
+                                  args.commit + '^{commit}'], capture_output=True, text=True)
+            if chk.returncode != 0:
+                raise SystemExit('refusing: ' + args.commit + ' is not a commit in the repo')
             hit[0]['done'] = True
             hit[0]['done_at'] = time.strftime('%Y-%m-%dT%H:%M:%S+00:00', time.gmtime())
+            hit[0]['done_commit'] = args.commit
             _save(data)
-            print('done:', args.id)
+            print('done:', args.id, 'at', args.commit)
+        elif args.cmd == 'reopen':
+            hit = [r for r in data if r.get('id') == args.id]
+            if not hit:
+                raise SystemExit("no such id: " + args.id)
+            hit[0]['done'] = False
+            hit[0].pop('done_at', None)
+            hit[0].pop('done_commit', None)
+            hit[0]['reopened_at'] = time.strftime('%Y-%m-%dT%H:%M:%S+00:00', time.gmtime())
+            hit[0]['reopen_reason'] = (args.reason or '')[:300]
+            _save(data)
+            print('reopened:', args.id)
         elif args.cmd == 'clear':
             n = 0
             for r in data:
-- 
cgit v1.2.3