feat(webapp): cheap connect, opt-in event walk, and a Diagnostics tab
Connecting to a unit fired /device/events automatically, which walks the whole event chain — every event header over a cellular link. On BE12599 that took minutes and then 500'd outright, because its buffer has wrapped past 0xFFFF and the uint16 offset arithmetic goes negative. Wanting to know whether ACH was on should not require reading every event the unit has stored. Connect now uses only cheap probes: /device/info (which already carries the compliance config the event walk was re-reading) plus /device/events/storage_ range. The chain walk moves behind a "Load events" button in the Events toolbar, and the Device tab gains an Event Chain card showing the first/last keys. Adds a Diagnostics tab for the endpoints that previously existed only as curl: storage_range and events/index alongside monitor/status, then stop monitoring, disable ACH (rescue?erase=false, so events survive), and erase. The wedged-unit ladder — slow drip and blind stop — sits under its own heading pointing at the runbook, with the reminder that slow_drip's success signal is bytes_received>0 and not a clean duration. Erase is guarded by typing the unit's serial. Auth answers who, not whether you meant it, and Swagger's try-it-out button on /device/events/erase is live on :8200/docs — the realistic risk here is an accident. Lifetime events is displayed but labelled unreliable: SUB 0x08 reports 0 on units with years of history, which is a decode bug we have not chased yet. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Qcu9ByJfuKBQxmrWb8rSrN
This commit is contained in:
Claude Opus 5
+295
-20
@@ -108,6 +108,12 @@
|
||||
color: var(--text);
|
||||
}
|
||||
.btn-ghost:hover { border-color: var(--blue-lt); color: var(--blue-lt); }
|
||||
.btn-danger { background: var(--red); color: #fff; }
|
||||
.btn-danger:hover:not(:disabled) { filter: brightness(1.15); }
|
||||
.diag-result { display:block; margin-top:6px; font-size:12px; opacity:.85;
|
||||
white-space:pre-wrap; word-break:break-word; }
|
||||
.diag-result.ok { color: var(--green); }
|
||||
.diag-result.error { color: var(--red); }
|
||||
.btn:disabled { background: var(--surface2) !important; color: var(--text-mute) !important; cursor: not-allowed; border-color: var(--border2) !important; }
|
||||
|
||||
/* #connect-btn styles moved to #live-connect-bar block */
|
||||
@@ -910,6 +916,7 @@
|
||||
<button class="tab-btn" data-tab="events" onclick="switchTab('events')">Events</button>
|
||||
<button class="tab-btn" data-tab="config" onclick="switchTab('config')">Config</button>
|
||||
<button class="tab-btn" data-tab="call-home" onclick="switchTab('call-home')">Call Home</button>
|
||||
<button class="tab-btn" data-tab="diagnostics" onclick="switchTab('diagnostics')">Diagnostics</button>
|
||||
</div>
|
||||
|
||||
<!-- ════════════════════════════════════════════════════════════════
|
||||
@@ -938,6 +945,10 @@
|
||||
<div id="tab-events" class="tab-pane" style="display:flex; flex-direction:column; overflow:hidden;">
|
||||
|
||||
<div class="event-toolbar">
|
||||
<button class="btn btn-ghost" id="load-events-btn" onclick="loadEventList()" disabled
|
||||
title="Walk the device's event chain and list its stored events. This is the slow one — it reads every event header over the cellular link.">
|
||||
⟳ Load events
|
||||
</button>
|
||||
<button class="btn btn-ghost" id="load-btn" onclick="loadWaveform()" disabled>Load Waveform</button>
|
||||
<button class="btn btn-ghost" id="save-btn" onclick="saveEventToDb()" disabled
|
||||
title="Download the full waveform from the device and save it to the SFM database + waveform store. Honors the Force refresh toggle.">
|
||||
@@ -1205,6 +1216,77 @@
|
||||
|
||||
</div><!-- end #tab-call-home -->
|
||||
|
||||
<!-- ════════════════════════════════════════════════════════════════
|
||||
TAB: Diagnostics
|
||||
═══════════════════════════════════════════════════════════════════ -->
|
||||
<div id="tab-diagnostics" class="tab-pane">
|
||||
|
||||
<div class="cfg-grid">
|
||||
|
||||
<div class="cfg-section">
|
||||
<div class="cfg-section-title">Device State</div>
|
||||
<div class="hint" style="margin-bottom:10px">
|
||||
Fast probes — POLL plus one read each, about 2 s. None of these walk the event chain.
|
||||
</div>
|
||||
<div class="dev-table" id="diag-table"></div>
|
||||
<div class="cfg-actions" style="margin-top:12px">
|
||||
<button class="btn btn-ghost" id="diag-refresh-btn" onclick="refreshDiagnostics()" disabled>Refresh</button>
|
||||
<span id="diag-status"></span>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="cfg-section">
|
||||
<div class="cfg-section-title">Actions</div>
|
||||
|
||||
<div class="cfg-field">
|
||||
<label>Stop Monitoring</label>
|
||||
<button class="btn btn-ghost" id="diag-stop-btn" onclick="diagStopMonitoring()" disabled>Send Stop (SUB 0x97)</button>
|
||||
<div class="hint">Halts recording. On a unit triggering continuously, this is what breaks the call-home loop.</div>
|
||||
<span class="diag-result" id="diag-stop-result"></span>
|
||||
</div>
|
||||
|
||||
<div class="cfg-field">
|
||||
<label>Disable Auto Call Home</label>
|
||||
<button class="btn btn-ghost" id="diag-ach-btn" onclick="diagDisableAch()" disabled>Disable ACH</button>
|
||||
<div class="hint">Stored events are left untouched (<code>rescue?erase=false</code>). The unit stops dialing out until ACH is re-enabled.</div>
|
||||
<span class="diag-result" id="diag-ach-result"></span>
|
||||
</div>
|
||||
|
||||
<div class="cfg-field">
|
||||
<label>Erase All Events</label>
|
||||
<input type="text" id="diag-erase-confirm" placeholder="Type the serial to enable"
|
||||
oninput="diagCheckEraseConfirm()" autocomplete="off" />
|
||||
<button class="btn btn-danger" id="diag-erase-btn" onclick="diagEraseEvents()" disabled>Erase Events</button>
|
||||
<div class="hint">⚠ Permanent, and resets the event chain to key <code>0x01110000</code>. Download anything worth keeping first.</div>
|
||||
<span class="diag-result" id="diag-erase-result"></span>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="cfg-section">
|
||||
<div class="cfg-section-title">Unresponsive Unit</div>
|
||||
<div class="hint" style="margin-bottom:10px">
|
||||
The escalation ladder from <code>docs/runbooks/wedged_unit_recovery.md</code>, for a unit too busy
|
||||
to answer normal request/response. Prefer <b>Method A</b> — point the modem at an
|
||||
<code>ach_server</code> and answer its call — before racing it with these.
|
||||
</div>
|
||||
|
||||
<div class="cfg-field">
|
||||
<label>Slow drip <span class="hint" style="display:inline">(one held session, a stop every 3 s)</span></label>
|
||||
<button class="btn btn-ghost" id="diag-drip-btn" onclick="diagSlowDrip()" disabled>Run 120 s drip</button>
|
||||
<div class="hint">Success is <code>bytes_received > 0</code>. A full duration with <code>send_error: null</code> is <b>not</b> success on its own.</div>
|
||||
<span class="diag-result" id="diag-drip-result"></span>
|
||||
</div>
|
||||
|
||||
<div class="cfg-field">
|
||||
<label>Blind stop <span class="hint" style="display:inline">(fire-and-forget, one attempt)</span></label>
|
||||
<button class="btn btn-ghost" id="diag-blind-btn" onclick="diagBlindStop()" disabled>Send blind stop</button>
|
||||
<span class="diag-result" id="diag-blind-result"></span>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div><!-- end #tab-diagnostics -->
|
||||
|
||||
</div><!-- end #section-live -->
|
||||
|
||||
<!-- ════════════════════════════════════════════════════════════════
|
||||
@@ -1361,6 +1443,8 @@
|
||||
// ── State ──────────────────────────────────────────────────────────────────────
|
||||
let unitInfo = null;
|
||||
let eventList = [];
|
||||
let storageInfo = null; // /device/events/storage_range — cheap, read on connect
|
||||
let eventsLoaded = false; // the event chain walk is opt-in; see loadEventList()
|
||||
let currentEvent = 0;
|
||||
let charts = {};
|
||||
let geoAdcScale = 6.206;
|
||||
@@ -1458,6 +1542,7 @@ function switchTab(name) {
|
||||
if (name === 'units') { if (!unitsLoaded) loadUnits(); }
|
||||
if (name === 'monlog') { if (!monlogLoaded) loadMonitorLog(); }
|
||||
if (name === 'sessions') { if (!sessLoaded) loadSessions(); }
|
||||
if (name === 'diagnostics' && devHost() && unitInfo) refreshDiagnostics();
|
||||
}
|
||||
|
||||
// ── Connect ────────────────────────────────────────────────────────────────────
|
||||
@@ -1478,18 +1563,13 @@ async function connectUnit() {
|
||||
btn.disabled = false; btn.textContent = 'Connect'; return;
|
||||
}
|
||||
|
||||
setStatus('Fetching event list…', 'loading');
|
||||
try {
|
||||
const r = await fetch(`${api()}/device/events?${deviceParams()}`);
|
||||
if (!r.ok) { const e = await r.json().catch(() => ({})); throw new Error(e.detail || r.statusText); }
|
||||
const evData = await r.json();
|
||||
eventList = evData.events || [];
|
||||
// Merge compliance from /device/events response (it re-reads it)
|
||||
if (evData.device) unitInfo = { ...unitInfo, ...evData.device };
|
||||
} catch (e) {
|
||||
setStatus(`Event fetch failed: ${e.message}`, 'error');
|
||||
btn.disabled = false; btn.textContent = 'Reconnect'; return;
|
||||
}
|
||||
// Connecting deliberately does NOT walk the event chain. That walk reads
|
||||
// every event header over the cellular link and can take minutes — or fail
|
||||
// outright on a unit whose buffer has wrapped past 0xFFFF. Use the ~2 s
|
||||
// probes instead; the event list is opt-in via loadEventList().
|
||||
eventList = []; eventsLoaded = false;
|
||||
setStatus('Reading device state…', 'loading');
|
||||
storageInfo = await fetchJson(`/device/events/storage_range`).catch(() => null);
|
||||
|
||||
populateDeviceBar();
|
||||
populateDeviceTab();
|
||||
@@ -1498,11 +1578,9 @@ async function connectUnit() {
|
||||
|
||||
document.getElementById('device-bar').style.display = 'flex';
|
||||
document.getElementById('monitor-panel').style.display = 'flex';
|
||||
document.getElementById('load-btn').disabled = eventList.length === 0;
|
||||
document.getElementById('save-btn').disabled = eventList.length === 0;
|
||||
document.getElementById('download-btn').disabled = eventList.length === 0;
|
||||
document.getElementById('prev-btn').disabled = true;
|
||||
document.getElementById('next-btn').disabled = eventList.length <= 1;
|
||||
setEventButtonsEnabled();
|
||||
document.getElementById('load-events-btn').disabled = false;
|
||||
setDiagButtonsEnabled(true);
|
||||
document.getElementById('cfg-read-btn').disabled = false;
|
||||
document.getElementById('cfg-write-btn').disabled = false;
|
||||
document.getElementById('ch-read-btn').disabled = false;
|
||||
@@ -1510,7 +1588,9 @@ async function connectUnit() {
|
||||
|
||||
btn.disabled = false; btn.textContent = 'Reconnect';
|
||||
|
||||
setStatus(`Connected — ${eventList.length} event${eventList.length !== 1 ? 's' : ''} stored.`, 'ok');
|
||||
setStatus(storageInfo && storageInfo.is_empty
|
||||
? 'Connected — no events stored.'
|
||||
: 'Connected. Event list not loaded (Events → Load events).', 'ok');
|
||||
|
||||
// Fetch monitor status in background (non-blocking)
|
||||
refreshMonitorStatus().catch(() => {});
|
||||
@@ -1522,6 +1602,48 @@ async function connectUnit() {
|
||||
}
|
||||
}
|
||||
|
||||
// ── Shared fetch helper ────────────────────────────────────────────────────────
|
||||
async function fetchJson(path, opts) {
|
||||
const sep = path.includes('?') ? '&' : '?';
|
||||
const r = await fetch(`${api()}${path}${sep}${deviceParams()}`, opts);
|
||||
const body = await r.json().catch(() => ({}));
|
||||
if (!r.ok) throw new Error(body.detail || r.statusText);
|
||||
return body;
|
||||
}
|
||||
|
||||
function setEventButtonsEnabled() {
|
||||
const n = eventList.length;
|
||||
document.getElementById('load-btn').disabled = n === 0;
|
||||
document.getElementById('save-btn').disabled = n === 0;
|
||||
document.getElementById('download-btn').disabled = n === 0;
|
||||
document.getElementById('prev-btn').disabled = true;
|
||||
document.getElementById('next-btn').disabled = n <= 1;
|
||||
}
|
||||
|
||||
// ── Event list (opt-in — this is the slow chain walk) ──────────────────────────
|
||||
async function loadEventList() {
|
||||
if (!devHost()) { setStatus('Connect to a device first.', 'error'); return; }
|
||||
const btn = document.getElementById('load-events-btn');
|
||||
btn.disabled = true;
|
||||
setStatus('Walking the event chain — this can take a while…', 'loading');
|
||||
try {
|
||||
const evData = await fetchJson('/device/events');
|
||||
eventList = evData.events || [];
|
||||
eventsLoaded = true;
|
||||
// /device/events re-reads compliance; fold it in.
|
||||
if (evData.device) unitInfo = { ...unitInfo, ...evData.device };
|
||||
} catch (e) {
|
||||
setStatus(`Event fetch failed: ${e.message}`, 'error');
|
||||
btn.disabled = false; return;
|
||||
}
|
||||
populateDeviceBar();
|
||||
populateDeviceTab();
|
||||
populateEventChips();
|
||||
setEventButtonsEnabled();
|
||||
btn.disabled = false;
|
||||
setStatus(`${eventList.length} event${eventList.length !== 1 ? 's' : ''} stored.`, 'ok');
|
||||
}
|
||||
|
||||
// ── Device bar ─────────────────────────────────────────────────────────────────
|
||||
function populateDeviceBar() {
|
||||
qs('di-serial').textContent = unitInfo.serial || '—';
|
||||
@@ -1530,7 +1652,7 @@ function populateDeviceBar() {
|
||||
qs('di-sr').textContent = cc.sample_rate ? `${cc.sample_rate} sps` : '—';
|
||||
qs('di-rt').textContent = cc.record_time != null ? `${cc.record_time.toFixed(1)} s` : '—';
|
||||
qs('di-trig').textContent = cc.trigger_level_geo != null ? `${cc.trigger_level_geo.toFixed(3)} in/s` : '—';
|
||||
qs('di-count').textContent = eventList.length;
|
||||
qs('di-count').textContent = eventsLoaded ? eventList.length : '—';
|
||||
qs('di-project').textContent = cc.project || '—';
|
||||
qs('di-client').textContent = cc.client || '—';
|
||||
qs('di-operator').textContent = cc.operator || '—';
|
||||
@@ -1660,7 +1782,8 @@ function populateDeviceTab() {
|
||||
{ label:'DSP', value: unitInfo.dsp_version || '—' },
|
||||
{ label:'Model', value: unitInfo.model || '—' },
|
||||
{ label:'Manufacturer', value: unitInfo.manufacturer || '—' },
|
||||
{ label:'Stored Events', value: eventList.length },
|
||||
{ label:'Stored Events', value: eventsLoaded ? eventList.length : 'not loaded' },
|
||||
{ label:'Storage Used', value: storageUsedLabel() },
|
||||
];
|
||||
for (const {label, value} of cardData) {
|
||||
const c = document.createElement('div');
|
||||
@@ -1707,6 +1830,158 @@ function renderTable(id, rows) {
|
||||
}
|
||||
}
|
||||
|
||||
// ── Diagnostics ────────────────────────────────────────────────────────────────
|
||||
// Everything here is a cheap probe (POLL + one read) or a single write. None of
|
||||
// it walks the event chain. See docs/runbooks/wedged_unit_recovery.md.
|
||||
|
||||
function storageUsedLabel() {
|
||||
if (!storageInfo) return '—';
|
||||
if (storageInfo.is_empty) return 'empty';
|
||||
const f = storageInfo.first_key, l = storageInfo.last_key;
|
||||
return (f && l) ? `${f} → ${l}` : '—';
|
||||
}
|
||||
|
||||
function setDiagButtonsEnabled(on) {
|
||||
for (const id of ['diag-refresh-btn','diag-stop-btn','diag-ach-btn',
|
||||
'diag-drip-btn','diag-blind-btn']) {
|
||||
const el = document.getElementById(id);
|
||||
if (el) el.disabled = !on;
|
||||
}
|
||||
diagCheckEraseConfirm();
|
||||
}
|
||||
|
||||
// Erase is guarded by typing the serial — auth answers "who", not "did you mean it".
|
||||
function diagCheckEraseConfirm() {
|
||||
const box = document.getElementById('diag-erase-confirm');
|
||||
const btn = document.getElementById('diag-erase-btn');
|
||||
if (!box || !btn) return;
|
||||
const serial = (unitInfo && unitInfo.serial) || '';
|
||||
btn.disabled = !serial || box.value.trim().toUpperCase() !== serial.toUpperCase();
|
||||
}
|
||||
|
||||
function diagResult(id, text, cls) {
|
||||
const el = document.getElementById(id);
|
||||
if (!el) return;
|
||||
el.textContent = text;
|
||||
el.className = 'diag-result' + (cls ? ' ' + cls : '');
|
||||
}
|
||||
|
||||
async function refreshDiagnostics() {
|
||||
if (!devHost()) return;
|
||||
const st = document.getElementById('diag-status');
|
||||
if (st) { st.textContent = 'Reading…'; st.className = 'loading'; }
|
||||
|
||||
const [mon, store, idx] = await Promise.all([
|
||||
fetchJson('/device/monitor/status?force=true').catch(e => ({ _err: e.message })),
|
||||
fetchJson('/device/events/storage_range').catch(e => ({ _err: e.message })),
|
||||
fetchJson('/device/events/index').catch(e => ({ _err: e.message })),
|
||||
]);
|
||||
|
||||
if (!store._err) storageInfo = store;
|
||||
|
||||
const err = v => `<span style="color:var(--red)">${v}</span>`;
|
||||
const rows = [];
|
||||
|
||||
rows.push(['Monitoring', mon._err ? err(mon._err)
|
||||
: (mon.is_monitoring ? '<b>MONITORING</b>' : 'idle')]);
|
||||
if (!mon._err) {
|
||||
rows.push(['Battery', mon.battery_v != null ? `${mon.battery_v.toFixed(2)} V` : '—']);
|
||||
if (mon.memory_total_bytes) {
|
||||
const used = mon.memory_total_bytes - (mon.memory_free_bytes ?? 0);
|
||||
const pct = (used / mon.memory_total_bytes * 100).toFixed(1);
|
||||
rows.push(['Memory used', `${used.toLocaleString()} / ${mon.memory_total_bytes.toLocaleString()} bytes (${pct}%)`]);
|
||||
}
|
||||
}
|
||||
|
||||
rows.push(['Event chain', store._err ? err(store._err) : storageUsedLabel()]);
|
||||
if (!store._err) rows.push(['Chain empty', store.is_empty ? 'yes' : 'no']);
|
||||
|
||||
// SUB 0x08. Known to report 0 on units with years of history — suspected
|
||||
// field-offset bug in the decode, so show it but do not trust it.
|
||||
rows.push(['Lifetime events', idx._err ? err(idx._err)
|
||||
: `${idx.lifetime_count} <span class="hint" style="display:inline">(unreliable — see CHANGELOG)</span>`]);
|
||||
|
||||
renderTable('diag-table', rows);
|
||||
populateDeviceTab();
|
||||
if (st) { st.textContent = ''; st.className = ''; }
|
||||
}
|
||||
|
||||
async function diagStopMonitoring() {
|
||||
const btn = document.getElementById('diag-stop-btn');
|
||||
btn.disabled = true; diagResult('diag-stop-result', 'Sending…');
|
||||
try {
|
||||
await fetchJson('/device/monitor/stop', { method: 'POST' });
|
||||
diagResult('diag-stop-result', 'Stop acknowledged — recording halted.', 'ok');
|
||||
refreshDiagnostics();
|
||||
} catch (e) {
|
||||
diagResult('diag-stop-result', `Failed: ${e.message}`, 'error');
|
||||
}
|
||||
btn.disabled = false;
|
||||
}
|
||||
|
||||
async function diagDisableAch() {
|
||||
const btn = document.getElementById('diag-ach-btn');
|
||||
btn.disabled = true; diagResult('diag-ach-result', 'Writing call-home config…');
|
||||
try {
|
||||
const r = await fetchJson('/device/rescue?erase=false', { method: 'POST' });
|
||||
const steps = (r.steps || []).map(s => s.step).join(' → ') || 'done';
|
||||
diagResult('diag-ach-result', `ACH disabled (${steps}). Events untouched.`, 'ok');
|
||||
} catch (e) {
|
||||
diagResult('diag-ach-result', `Failed: ${e.message}`, 'error');
|
||||
}
|
||||
btn.disabled = false;
|
||||
}
|
||||
|
||||
async function diagEraseEvents() {
|
||||
const serial = (unitInfo && unitInfo.serial) || 'this unit';
|
||||
if (!confirm(`Permanently erase ALL events on ${serial}?\n\nThis cannot be undone.`)) return;
|
||||
const btn = document.getElementById('diag-erase-btn');
|
||||
btn.disabled = true; diagResult('diag-erase-result', 'Erasing…');
|
||||
try {
|
||||
await fetchJson('/device/events/erase', { method: 'POST' });
|
||||
diagResult('diag-erase-result', 'Events erased — chain reset to 0x01110000.', 'ok');
|
||||
document.getElementById('diag-erase-confirm').value = '';
|
||||
eventList = []; eventsLoaded = false;
|
||||
setEventButtonsEnabled(); populateEventChips();
|
||||
refreshDiagnostics();
|
||||
} catch (e) {
|
||||
diagResult('diag-erase-result', `Failed: ${e.message}`, 'error');
|
||||
}
|
||||
diagCheckEraseConfirm();
|
||||
}
|
||||
|
||||
async function diagSlowDrip() {
|
||||
const btn = document.getElementById('diag-drip-btn');
|
||||
btn.disabled = true;
|
||||
diagResult('diag-drip-result', 'Holding a session for 120 s…');
|
||||
try {
|
||||
const r = await fetchJson('/device/stop_monitoring_slow_drip?duration_s=120&interval_s=3',
|
||||
{ method: 'POST' });
|
||||
const good = (r.bytes_received || 0) > 0;
|
||||
diagResult('diag-drip-result',
|
||||
`drips ${r.drips_sent} · held ${r.duration_s}s · bytes back ${r.bytes_received}` +
|
||||
(r.send_error ? ` · ${r.send_error}` : '') +
|
||||
(good ? ' → device responded' : ' → no response; the modem may not be bridging'),
|
||||
good ? 'ok' : 'error');
|
||||
} catch (e) {
|
||||
diagResult('diag-drip-result', `Failed: ${e.message}`, 'error');
|
||||
}
|
||||
btn.disabled = false;
|
||||
}
|
||||
|
||||
async function diagBlindStop() {
|
||||
const btn = document.getElementById('diag-blind-btn');
|
||||
btn.disabled = true; diagResult('diag-blind-result', 'Sending…');
|
||||
try {
|
||||
const r = await fetchJson('/device/stop_monitoring_blind', { method: 'POST' });
|
||||
diagResult('diag-blind-result',
|
||||
`Sent ${r.bytes_sent ?? '?'} bytes, no response read (fire-and-forget).`, 'ok');
|
||||
} catch (e) {
|
||||
diagResult('diag-blind-result', `Failed: ${e.message}`, 'error');
|
||||
}
|
||||
btn.disabled = false;
|
||||
}
|
||||
|
||||
// ── Config form ────────────────────────────────────────────────────────────────
|
||||
function populateConfigFromDeviceInfo() {
|
||||
if (!unitInfo) return;
|
||||
|
||||
Reference in New Issue
Block a user