hyperhive/frontend/packages/dashboard/src/core.js

// C0R3 page entry (/core.html). The host/coordinator surface carved out
// of the dashboard's old SYST3M tab into its own standalone page so the
// dashboard tab strip stays lean. Two sub-tabs via <hive-tab-strip>
// (default = K3PT ST4T3): kept state (tombstones) and container load.
//
// Rebuild queue + meta inputs have moved to /builds.html (the build
// lifecycle hub). This page is its own esbuild bundle with its own
// runtime: it cold-loads /api/state and subscribes to /dashboard/stream
// (the same broker event channel the dashboard uses), maintaining its
// own copy of the tombstones state.

import { $, form, openStream, initServerWarnings } from './common.js';
import { el } from '@hive/shared/dom.js';
import { asyncBtn, bindAsyncForms } from '@hive/shared/forms.js';
import '@hive/shared/hive-tab-strip.js';

// ─── derived state (own copies; this bundle has its own runtime) ──────────
let tombstonesState = [];
// ContainerView list from the last /api/state snapshot — used by renderContainerLoad
// to splice in the configured cpu_quota/memory_max limits alongside live cgroup data.
let containersState = [];
function syncFromSnapshot(s) {
  tombstonesState = (s.tombstones || []).slice();
  containersState = (s.containers || []).slice();
}

// ─── kept state (tombstones) ──────────────────────────────────────────────
function renderTombstones(s) {
  const root = $('tombstones-section');
  if (!root) return;
  root.replaceChildren();
  if (!s.tombstones || !s.tombstones.length) {
    root.append(el('p', { class: 'empty' }, 'no kept state — clean'));
    return;
  }
  const fmtBytes = (n) => {
    if (n < 1024) return n + ' B';
    if (n < 1024 * 1024) return (n / 1024).toFixed(1) + ' KB';
    if (n < 1024 * 1024 * 1024) return (n / (1024 * 1024)).toFixed(1) + ' MB';
    return (n / (1024 * 1024 * 1024)).toFixed(2) + ' GB';
  };
  const fmtAgeDays = (ts) => {
    if (!ts) return '?';
    const d = Math.floor((Date.now() / 1000 - ts) / 86400);
    if (d <= 0) return 'today';
    if (d === 1) return '1 day ago';
    return d + ' days ago';
  };
  // Only shown alongside actual rows — a caveat over an empty list is noise.
  // Wording is deliberately about what the list *is* rather than what it
  // isn't: nothing records a destroy, so "container absent" is the only thing
  // the backend can actually tell.
  const warn = el('hive-warn', { level: 'warning' });
  warn.append(
    el('strong', {}, 'shows every agent whose container is absent'),
    ' — not only destroyed ones. An agent part-way through being spawned ' +
    'looks identical here, because nothing records a destroy. Check it is ' +
    'really gone before you PURG3.',
  );
  root.append(warn);
  const ul = el('ul', { class: 'containers' });
  for (const t of s.tombstones) {
    const li = el('li', { class: 'container-row tombstone' });
    const head = el('div', { class: 'head' });
    head.append(
      el('span', { class: 'name' }, t.name),
      // Was `destroyed`, which the backend cannot actually know — see the
      // caveat above. `offline` is what the absence of a container proves.
      el('span', { class: 'hive-pill-sm badge-muted' }, 'offline'),
    );
    if (t.has_creds) head.append(el('span', { class: 'hive-pill-sm badge-muted' }, 'creds kept'));
    head.append(el('span', { class: 'meta' },
      `${fmtBytes(t.state_bytes)} · ${fmtAgeDays(t.last_seen)}`));
    li.append(head);

    const actions = el('div', { class: 'actions' });
    const respawn = el('form', {
      method: 'POST', action: '/api/request-spawn',
      class: 'inline', 'data-async': '',
      'data-confirm': 'queue spawn approval for ' + t.name + '? state will be reused.',
    });
    respawn.append(
      el('input', { type: 'hidden', name: 'name', value: t.name }),
      el('button', { type: 'submit', class: 'btn btn-start' }, '⊕ R3V1V3'),
    );
    actions.append(respawn);
    actions.append(form(
      '/api/purge-tombstone/' + t.name, 'btn-destroy', 'PURG3',
      'PURGE ' + t.name + '? config history, claude creds, '
      + 'and notes are all WIPED. no undo.',
      {}, { noRefresh: true },
    ));
    li.append(actions);
    ul.append(li);
  }
  root.append(ul);
}

// ─── stale permission entries (K3PT ST4T3 pane sub-section) ──────────────
// Agents with explicit capability / tool-group JSON entries but no live
// container AND no kept-state tombstone (e.g. renamed agents like the old
// "root" manager name). Ghost detection is server-side via
// GET /api/permissions/stale so the client doesn't need to maintain a
// container-roster cache or perform set arithmetic. Lazy-loaded on first
// "kept" tab activation; refreshed when perm data changes via SSE.
let stalePermsLoaded = false;

function renderStalePerms(root, ghosts) {
  root.replaceChildren();
  if (!ghosts.length) return;
  root.append(el('p', { class: 'tombstones-stale-heading' }, 'stale permission entries'));
  root.append(el('p', { class: 'meta' },
    'agents with explicit capability or tool-group entries but no live container '
    + 'or kept state (typically renamed or manually-deleted agents whose JSON entries persisted).'));
  const errP = el('p', { class: 'tombstones-stale-err', hidden: true });
  const ul = el('ul', { class: 'tombstones-stale-list' });
  for (const name of ghosts) {
    const li = el('li', { class: 'tombstones-stale-row' });
    li.append(el('span', { class: 'tombstones-stale-name' }, name));
    li.append(el('span', { class: 'hive-pill-sm badge-muted' }, 'stale perms'));
    const btn = el('button', {
      type: 'button',
      class: 'btn btn-destroy',
      title: 'remove explicit capability and tool-group entries for ' + name,
    }, '✕ clear perms');
    btn.addEventListener('click', () => asyncBtn(btn, async () => {
      errP.hidden = true;
      try {
        const resp = await fetch('/api/permissions/' + encodeURIComponent(name), { method: 'DELETE' });
        if (!resp.ok) {
          const msg = await resp.text().catch(() => String(resp.status));
          errP.textContent = 'failed to clear perms for ' + name + ': ' + msg;
          errP.hidden = false;
          return;
        }
        await fetchAndRenderStalePerms();
      } catch (err) {
        errP.textContent = 'failed to clear perms for ' + name + ': ' + err;
        errP.hidden = false;
      }
    }));
    li.append(btn);
    ul.append(li);
  }
  root.append(ul, errP);
}

// Ghost detection is entirely server-side: GET /api/permissions/stale
// returns the computed list of agent names that have explicit JSON entries
// but are absent from both the live roster and the kept-state tombstones.
// One call, no client-side roster cache, always authoritative.
async function fetchAndRenderStalePerms() {
  const root = $('tombstones-stale-perms');
  if (!root) return;
  try {
    const resp = await fetch('/api/permissions/stale');
    if (!resp.ok) throw new Error('http ' + resp.status);
    const data = await resp.json();
    renderStalePerms(root, data.stale || []);
  } catch (err) {
    root.replaceChildren();
    root.append(el('p', { class: 'meta' }, 'failed to load stale perm data: ' + err));
  }
  stalePermsLoaded = true;
}

// ─── container load (live cgroup poll while the LOAD sub-tab is open) ──────
let containerLoadTimer = null;

function cloadFmtBytes(n) {
  if (!Number.isFinite(n) || n <= 0) return '0';
  const u = ['B', 'KiB', 'MiB', 'GiB', 'TiB'];
  let i = 0; let v = n;
  while (v >= 1024 && i < u.length - 1) { v /= 1024; i += 1; }
  return v.toFixed(v < 10 && i > 0 ? 1 : 0) + ' ' + u[i];
}
function cloadMeter(pct) {
  const p = Math.max(0, Math.min(100, pct));
  const cls = p >= 90 ? 'hot' : (p >= 70 ? 'warn' : '');
  const m = document.createElement('span');
  m.className = 'cload-meter';
  m.title = p.toFixed(0) + '%';
  const fill = document.createElement('span');
  fill.className = 'fill' + (cls ? ' ' + cls : '');
  fill.style.width = p + '%';
  m.append(fill);
  return m;
}

// Stash the last load rows so re-renders triggered by SSE state updates can
// call renderContainerLoad(lastLoadRows) without waiting for the next poll.
let lastLoadRows = [];

function renderContainerLoad(rows) {
  lastLoadRows = rows;
  const root = $('container-load-section');
  if (!root) return;
  if (!Array.isArray(rows) || rows.length === 0) {
    root.replaceChildren();
    const p = document.createElement('p'); p.className = 'meta';
    p.textContent = 'no running agent containers'; root.append(p);
    return;
  }

  // Build a name→ContainerView lookup so we can splice in the configured
  // cpu_quota / memory_max limits (set in meta/resource-limits.json and
  // resolved by the server) next to the live cgroup readings.
  const cvByName = new Map(containersState.map((c) => [c.name, c]));

  const table = document.createElement('table');
  table.className = 'hive-stats-table';
  // "cpu cap" / "mem cap" show the configured ceilings from ContainerView
  // (effective drop-in values, take effect on next start/restart).
  // "limit" remains the live cgroup memory ceiling from /api/container-resources.
  table.innerHTML = '<thead><tr><th>agent</th><th>cpu</th><th>memory</th>'
    + '<th>peak</th><th>limit</th><th>disk</th>'
    + '<th class="cload-cap-th" title="configured ceiling — takes effect on next start">cpu cap</th>'
    + '<th class="cload-cap-th" title="configured ceiling — takes effect on next start">mem cap</th>'
    + '<th></th></tr></thead>';
  const tb = document.createElement('tbody');
  for (const r of rows) {
    const cv = cvByName.get(r.name);
    const tr = document.createElement('tr');
    const name = document.createElement('td'); name.textContent = r.name; tr.append(name);
    const cpu = document.createElement('td'); cpu.className = 'num';
    cpu.append((Number(r.cpu_pct) || 0).toFixed(1) + '%', cloadMeter(Number(r.cpu_pct) || 0));
    tr.append(cpu);
    const mem = document.createElement('td'); mem.className = 'num';
    const memCur = Number(r.mem_current_bytes) || 0;
    if (r.mem_max_bytes) {
      mem.append(cloadFmtBytes(memCur), cloadMeter(100 * memCur / r.mem_max_bytes));
    } else {
      mem.textContent = cloadFmtBytes(memCur);
    }
    tr.append(mem);
    const peak = document.createElement('td'); peak.className = 'num';
    peak.textContent = r.mem_peak_bytes ? cloadFmtBytes(Number(r.mem_peak_bytes)) : '—';
    tr.append(peak);
    const lim = document.createElement('td'); lim.className = 'num';
    lim.textContent = r.mem_max_bytes ? cloadFmtBytes(Number(r.mem_max_bytes)) : '∞';
    tr.append(lim);
    // Disk: on-disk footprint (state dir + container writable rootfs, shared
    // nix store excluded). Sampled out-of-band every few minutes server-side,
    // so it's null until the first sample lands — show an em-dash then.
    const disk = document.createElement('td'); disk.className = 'num';
    disk.title = 'state dir + container writable rootfs (shared nix store excluded); sampled every few minutes';
    disk.textContent = (r.disk_bytes != null) ? cloadFmtBytes(Number(r.disk_bytes)) : '—';
    tr.append(disk);

    // Configured CPU / memory caps from ContainerView (resolved effective
    // values: per-agent override when set, hive-wide default otherwise).
    const cpuCap = document.createElement('td'); cpuCap.className = 'num cload-cap';
    cpuCap.title = 'configured ceiling — takes effect on next start';
    cpuCap.textContent = cv?.cpu_quota || '—';
    tr.append(cpuCap);
    const memCap = document.createElement('td'); memCap.className = 'num cload-cap';
    memCap.title = 'configured ceiling — takes effect on next start';
    memCap.textContent = cv?.memory_max || '—';
    tr.append(memCap);

    // S3T button toggles the inline edit row for this agent.
    const actTd = document.createElement('td');
    const setBtn = document.createElement('button');
    setBtn.type = 'button';
    setBtn.className = 'btn btn-sm cload-set-btn';
    setBtn.textContent = 'S3T';
    setBtn.title = 'set CPU / memory cap for ' + r.name;
    tr.append(actTd);
    actTd.append(setBtn);
    tb.append(tr);

    // Inline edit row (hidden by default, toggled by the S3T button).
    const editRow = document.createElement('tr');
    editRow.className = 'cload-edit-row';
    editRow.hidden = true;
    const editTd = document.createElement('td');
    editTd.colSpan = 9;
    editTd.className = 'cload-edit-cell';

    const editForm = document.createElement('form');
    editForm.className = 'cload-edit-form';
    editForm.addEventListener('submit', async (e) => {
      e.preventDefault();
      const cpuInput = editForm.querySelector('.cload-cpu-input');
      const memInput = editForm.querySelector('.cload-mem-input');
      const errSpan = editForm.querySelector('.cload-edit-err');
      const submitBtn = editForm.querySelector('[type="submit"]');
      errSpan.hidden = true;
      submitBtn.disabled = true;
      try {
        const body = new URLSearchParams({
          cpu_quota: cpuInput.value.trim(),
          memory_max: memInput.value.trim(),
        });
        const resp = await fetch(
          '/api/resource-limits/' + encodeURIComponent(r.name),
          { method: 'POST', body },
        );
        if (!resp.ok) {
          errSpan.textContent = await resp.text().catch(() => 'error ' + resp.status);
          errSpan.hidden = false;
          return;
        }
        // Success: collapse the edit row. The SSE rescan will push updated
        // ContainerView data (cpu_quota/memory_max) to containersState,
        // triggering a re-render of the cap columns via refreshContainerLoad.
        editRow.hidden = true;
        setBtn.textContent = 'S3T';
      } catch (err) {
        errSpan.textContent = String(err);
        errSpan.hidden = false;
      } finally {
        submitBtn.disabled = false;
      }
    });

    const cpuLabel = document.createElement('label');
    cpuLabel.className = 'cload-edit-label';
    cpuLabel.textContent = 'cpu quota';
    const cpuInput = document.createElement('input');
    cpuInput.type = 'text'; cpuInput.className = 'cload-cpu-input';
    cpuInput.placeholder = cv ? cv.cpu_quota : 'e.g. 200%';
    cpuInput.title = 'systemd CPUQuota= value (e.g. "400%"). empty = use hive default';
    cpuLabel.append(cpuInput);

    const memLabel = document.createElement('label');
    memLabel.className = 'cload-edit-label';
    memLabel.textContent = 'mem max';
    const memInput = document.createElement('input');
    memInput.type = 'text'; memInput.className = 'cload-mem-input';
    memInput.placeholder = cv ? cv.memory_max : 'e.g. 8G';
    memInput.title = 'systemd MemoryMax= value (e.g. "8G", "50%", "infinity"). empty = use hive default';
    memLabel.append(memInput);

    const submitBtn = document.createElement('button');
    submitBtn.type = 'submit'; submitBtn.className = 'btn btn-restart cload-save-btn';
    submitBtn.textContent = 'S4V3';

    const hintSpan = document.createElement('span');
    hintSpan.className = 'meta cload-edit-hint';
    hintSpan.textContent = '↺ restart to apply to a running container';

    const errSpan = document.createElement('span');
    errSpan.className = 'cload-edit-err'; errSpan.hidden = true;

    editForm.append(cpuLabel, memLabel, submitBtn, hintSpan, errSpan);
    editTd.append(editForm);
    editRow.append(editTd);
    tb.append(editRow);

    setBtn.addEventListener('click', () => {
      const open = !editRow.hidden;
      editRow.hidden = open;
      setBtn.textContent = open ? 'S3T' : '✕';
    });
  }
  table.append(tb);
  root.replaceChildren(table);
}

async function refreshContainerLoad() {
  try {
    const resp = await fetch('/api/container-resources');
    if (!resp.ok) throw new Error('http ' + resp.status);
    renderContainerLoad(await resp.json());
  } catch (e) {
    const root = $('container-load-section');
    if (root) {
      root.replaceChildren();
      const p = document.createElement('p'); p.className = 'meta';
      p.textContent = 'container load fetch failed: ' + e; root.append(p);
    }
  }
}
function startContainerLoadPolling() {
  refreshContainerLoad();
  if (containerLoadTimer) return;
  containerLoadTimer = setInterval(refreshContainerLoad, 5000);
}
function stopContainerLoadPolling() {
  if (containerLoadTimer) { clearInterval(containerLoadTimer); containerLoadTimer = null; }
}

// ─── infra containers (start/stop/restart the 4 hive infra containers) ────
let infraTimer = null;

function renderInfraContainers(rows) {
  const root = $('infra-containers-section');
  if (!root) return;
  root.replaceChildren();
  if (!Array.isArray(rows) || !rows.length) {
    root.append(el('p', { class: 'meta' }, 'no infra container data'));
    return;
  }
  const ul = el('ul', { class: 'containers' });
  for (const c of rows) {
    const li = el('li', { class: 'container-row' });
    const head = el('div', { class: 'head' });
    head.append(
      el('span', { class: 'name' }, c.name),
      el('span', { class: 'hive-pill-sm ' + (c.running ? 'badge-ok' : 'badge-fail') },
        c.running ? 'running' : 'stopped'),
    );
    li.append(head);

    const actions = el('div', { class: 'actions' });
    const base = '/api/infra-container/' + encodeURIComponent(c.name) + '/';
    if (c.running) {
      actions.append(form(base + 'restart', 'btn-restart', '↺ R3ST4RT',
        'restart ' + c.name + '?'));
      actions.append(form(base + 'stop', 'btn-stop', '■ ST0P',
        'stop ' + c.name + '?'));
    } else {
      actions.append(form(base + 'start', 'btn-start', '▶ ST4RT',
        'start ' + c.name + '?'));
    }
    li.append(actions);
    ul.append(li);
  }
  root.append(ul);
}

async function refreshInfraContainers() {
  try {
    const resp = await fetch('/api/state');
    if (!resp.ok) throw new Error('http ' + resp.status);
    const s = await resp.json();
    renderInfraContainers(s.infra_containers || []);
  } catch (e) {
    const root = $('infra-containers-section');
    if (root) {
      root.replaceChildren();
      root.append(el('p', { class: 'meta' }, 'infra container fetch failed: ' + e));
    }
  }
}
function startInfraPolling() {
  refreshInfraContainers();
  if (infraTimer) return;
  infraTimer = setInterval(refreshInfraContainers, 5000);
}
function stopInfraPolling() {
  if (infraTimer) { clearInterval(infraTimer); infraTimer = null; }
}

// ─── render-all (cold load + any full re-render) ──────────────────────────
function renderAll() {
  renderTombstones({ tombstones: tombstonesState });
}

// ─── live SSE handlers ───────────────────────────────────────────────────
const SSE_HANDLERS = {
  tombstones_changed(ev) {
    tombstonesState = (ev.tombstones || []).slice();
    renderTombstones({ tombstones: tombstonesState });
  },
  // When a container's state changes (e.g. after resource-limits update
  // triggers rescan_containers_and_emit), update containersState in place
  // so the cap columns in the LOAD table reflect the new configured values.
  container_state_changed(ev) {
    if (!ev.container) return;
    const idx = containersState.findIndex((c) => c.name === ev.container.name);
    if (idx >= 0) {
      containersState[idx] = ev.container;
    } else {
      containersState.push(ev.container);
    }
    if (lastLoadRows.length) renderContainerLoad(lastLoadRows);
  },
  // Refresh the stale-perms sub-section when perm data changes (a ghost
  // was cleared, or perms were saved for an agent whose name collides).
  capabilities_changed(_ev) {
    if (stalePermsLoaded) fetchAndRenderStalePerms();
  },
  tool_groups_changed(_ev) {
    if (stalePermsLoaded) fetchAndRenderStalePerms();
  },
};

// ─── boot ─────────────────────────────────────────────────────────────────
// Re-fetch /api/state, re-sync the derived state, re-render. Used for the
// cold load and as the post-submit refresh for `data-async` forms whose
// mutation doesn't arrive via an SSE event (e.g. the meta-update / spawn /
// purge actions that opt out of `data-no-refresh`).
async function refreshState() {
  try {
    const resp = await fetch('/api/state');
    if (resp.ok) syncFromSnapshot(await resp.json());
  } catch {
    // best-effort: the page keeps its last-rendered state
  }
  renderAll();
}

async function init() {
  initServerWarnings();

  // `data-async` form submit interceptor — without this the meta-update /
  // cancel / respawn / purge buttons POST natively and the browser navigates
  // to the bare `ok` response page.
  bindAsyncForms(() => refreshState());

  // Hash-routed sub-tab strip; default K3PT ST4T3. Container-load
  // polling runs only while the LOAD sub-tab is open (cpu is a short
  // two-sample read each refresh on the server).
  document.getElementById('core-tabbar').configure({
    tabs: [
      { id: 'kept', label: 'K3PT ST4T3' },
      { id: 'load', label: 'C0NT41N3R L04D' },
      { id: 'infra', label: '1NFR4' },
    ],
    defaultId: 'kept',
    onShow: (id) => {
      if (id === 'load') startContainerLoadPolling();
      else stopContainerLoadPolling();
      if (id === 'infra') startInfraPolling();
      else stopInfraPolling();
      // Lazy-load stale-perms on first K3PT ST4T3 activation; always
      // re-fetch on subsequent visits in case perms changed.
      if (id === 'kept') fetchAndRenderStalePerms();
    },
  });

  await refreshState();

  // kinds= matches SSE_HANDLERS below verbatim — narrows this from all
  // 17 wire kinds down to the 4 this page acts on. This page was one
  // of 4 unfiltered `/api/dashboard/stream` subscribers before this
  // (subscription discipline, part 1 of the dashboard-event-stream-
  // split issue).
  const es = openStream(
    '/api/dashboard/stream?kinds=tombstones_changed,container_state_changed,' +
      'capabilities_changed,tool_groups_changed',
  );
  if (es) {
    es.onmessage = (e) => {
      let ev;
      try { ev = JSON.parse(e.data); } catch { return; }
      const h = SSE_HANDLERS[ev.kind];
      if (h) h(ev);
    };
  }
}

init();