[grade=A urn:ump:qszwspay7vhx7wcpqekkkidni3ehhgidvze5qk2y22fvg2wqz3ja] fix(DC-170): reliability batch — hangs, atomicity, fail-closed, SW (audit batch 6)

8 reliability fixes across 8 files (AUDIT-2026-10-27.md findings
9/11/12/13/14/16/20 + calendar credential item):

- dns.js check-update/update HANGS: bare returns + empty else/catch
  branches left requests hanging until client timeout; every path now
  answers (502 with message); upstream JSON.parse wrapped (non-JSON ->
  502)
- calendar.js ICS fetch timeout actually applies: fetchT ignores
  opts.timeout (undici) — was running at 5s default, not the intended
  15s; now timeoutMs third arg
- calendar.js PUT /sources: updating pass no longer nulls the stored
  token (and vice versa) — existing credential record loaded, only the
  provided field overwritten
- state-manager.js ATOMIC WRITES: _atomicWrite = tmp file + fs.rename
  (POSIX-atomic); write()/update() no longer truncate-then-write the
  live file (crash mid-write corrupted services.json/config.json with
  no recovery path). Test mock extended to the tmp+rename contract
- dashboard-ws.js auth fallback FAIL-CLOSED: missing authVerifier used
  to accept any non-empty session cookie (DC-061 footgun on unwired
  boot paths); now rejects + loud CRITICAL log
- middleware.js tailscale gate: new tailscale.failClosed config (default
  off = unchanged); when set, outages/errors deny (503) instead of
  silently disabling the gate; fail-open path now logs the exact key
- sw.js: offline fallback actually works ((await match) || (await
  match) — old Promise||Promise was always truthy); only 2xx cached
  (5xx pages were stored and served as the app shell); install is
  per-URL tolerant (one bad asset kept the stale SW alive forever)
- config/settings.js GET /config (public): corrupt config.json degrades
  to {setupComplete:false, corrupt:true} instead of 500 on every load

SCOPE CORRECTION: audit finding #10 (7 reversed-arg errorResponse
sites) was a FALSE POSITIVE — those files alias message-first error();
see lesson #14. Full suite 173/173 suites, 3740/3740 tests.

dashcaddy-api/src/managers/state-manager.js

@@ -36,6 +36,24 @@ class StateManager {
     this._ensureFileExists();
   }
 
+  /**
+   * Atomic write (DC-170): serialize to a temp file in the same directory,
+   * then rename over the live file. rename(2) is atomic on POSIX, so a crash
+   * mid-write can no longer leave a truncated JSON file behind (the old
+   * truncate-then-write corrupted services.json/config.json unrecoverably —
+   * read() only special-cases ENOENT). Caller must hold the file lock.
+   */
+  async _atomicWrite(data) {
+    const tmpPath = `${this.filePath}.tmp-${process.pid}-${Date.now()}`;
+    await fs.writeFile(tmpPath, JSON.stringify(data, null, 2), 'utf8');
+    try {
+      await fs.rename(tmpPath, this.filePath);
+    } catch (err) {
+      try { await fs.unlink(tmpPath); } catch (_) { /* best effort */ }
+      throw err;
+    }
+  }
+
   /**
    * Ensure the state file exists, create with empty array if not
    * @private
@@ -81,8 +99,10 @@ class StateManager {
       // Acquire lock
       release = await lockfile.lock(this.filePath, this.lockOptions);
 
-      // Write data with pretty formatting
-      await fs.writeFile(this.filePath, JSON.stringify(data, null, 2), 'utf8');
+      // Write data atomically (DC-170): truncate-then-write on the live file
+      // corrupted services.json/config.json on crash mid-write with no recovery
+      // path (read() only special-cases ENOENT). tmp + rename is atomic on POSIX.
+      await this._atomicWrite(data);
     } catch (error) {
       if (error.code === 'ELOCKED') {
         throw new Error('State file is locked by another process. Try again.');
@@ -134,8 +154,8 @@ class StateManager {
       // Apply update function
       const updatedData = await updateFn(currentData);
 
-      // Write updated data
-      await fs.writeFile(this.filePath, JSON.stringify(updatedData, null, 2), 'utf8');
+      // Write updated data atomically (DC-170, same rationale as write())
+      await this._atomicWrite(updatedData);
 
       return updatedData;
     } catch (error) {

dashcaddy-api/src/utilities/middleware.js

@@ -138,7 +138,15 @@ module.exports = function configureMiddleware(app, {
 
   async function isIPInTailnet(clientTailscaleIP) {
     const status = await getTailscaleStatus();
-    if (!status) return true; // no status = can't verify = allow
+    if (!status) {
+      // DC-170: 'no status' previously meant ALLOW — a tailscaled outage
+      // silently disabled the tailnet gate while the config claimed
+      // enforcement. With tailscaleConfig.failClosed set, deny instead;
+      // otherwise allow but say it loudly on stderr.
+      if (tailscaleConfig.failClosed) return false;
+      process.stderr.write('[tailscale] status unavailable — failing OPEN (set tailscale.failClosed=true to deny during outages)\n');
+      return true;
+    }
 
     const knownIPs = new Set();
     for (const ip of (status.Self?.TailscaleIPs || [])) knownIPs.add(ip);
@@ -179,7 +187,13 @@ module.exports = function configureMiddleware(app, {
           });
         }
       } catch (e) {
-        log.warn('tailscale', 'Tailnet verification failed, allowing request', { error: e.message });
+        if (tailscaleConfig.failClosed) {
+          return errorResponse(res, 503, '[DC-121] Tailnet verification unavailable (fail-closed mode).', {
+            requiresTailscale: true,
+            clientIP
+          });
+        }
+        log.warn('tailscale', 'Tailnet verification failed, allowing request (set tailscale.failClosed=true to deny during outages)', { error: e.message });
       }
     }
 

dashcaddy-api/src/websocket/dashboard-ws.js

@@ -75,13 +75,12 @@ function createDashboardWS(server, deps = {}) {
   const authVerifier = typeof deps.authVerifier === 'function'
     ? deps.authVerifier
     : (req) => {
-        // Last-resort fallback: presence-only check on a non-empty
-        // session-cookie value. Used only when the caller didn't inject
-        // a real verifier (e.g. tests, unusual boot paths). Production
-        // wires the real one from app.locals.ctx.session.isValid.
-        const parsed = parseCookieHeader(req && req.headers && req.headers.cookie);
-        const raw = parsed.dashcaddy_session || parsed.sid;
-        return typeof raw === 'string' && raw.length > 0;
+        // DC-170 FAIL-CLOSED (audit 2026-10-27): the old fallback accepted ANY
+        // non-empty session cookie — the exact DC-061 footgun, resurfacing on
+        // boot paths that miss the verifier wiring. A missing verifier is a
+        // wiring bug: refuse everything and say so loudly.
+        process.stderr.write('[dashboard-ws] CRITICAL: no authVerifier injected — rejecting WS connection (fail closed). Wire ctx.session.isValid into deps.authVerifier.\n');
+        return false;
       };
 
   // Track connected clients and their subscriptions