Add license checks to JobScheduler and AuthoritativeDNSServer

messages/en-US.json

@@ -3477,7 +3477,8 @@
     },
     "priority": "Priority",
     "priorityDescription": "Higher priority routes are evaluated first. Priority = 100 means automatic ordering (system decides). Use another number to enforce manual priority.",
-    "instanceName": "Instance Name",
+    "instanceName": "Server ID",
+    "clearInstanceName": "Reset Server Association",
     "pathMatchModalTitle": "Configure Path Matching",
     "pathMatchModalDescription": "Set up how incoming requests should be matched based on their path.",
     "pathMatchType": "Match Type",

package-lock.json

@@ -50,6 +50,7 @@
                 "@xterm/addon-fit": "^0.11.0",
                 "@xterm/addon-web-links": "^0.12.0",
                 "@xterm/xterm": "^6.0.0",
+                "acme-client": "^5.4.0",
                 "arctic": "3.7.0",
                 "axios": "1.20.0",
                 "better-sqlite3": "11.9.1",
@@ -61,6 +62,7 @@
                 "cors": "2.8.6",
                 "crypto-js": "4.2.0",
                 "d3": "7.9.0",
+                "dns-packet": "^5.6.1",
                 "drizzle-orm": "0.45.2",
                 "express": "5.2.1",
                 "express-rate-limit": "8.7.0",
@@ -124,6 +126,7 @@
                 "@types/cors": "2.8.19",
                 "@types/crypto-js": "4.2.2",
                 "@types/d3": "7.4.3",
+                "@types/dns-packet": "^5.6.5",
                 "@types/express": "5.0.6",
                 "@types/express-session": "1.19.0",
                 "@types/jmespath": "0.15.2",
@@ -2445,6 +2448,12 @@
                 "@jridgewell/sourcemap-codec": "^1.4.14"
             }
         },
+        "node_modules/@leichtgewicht/ip-codec": {
+            "version": "2.0.5",
+            "resolved": "https://registry.npmjs.org/@leichtgewicht/ip-codec/-/ip-codec-2.0.5.tgz",
+            "integrity": "sha512-Vo+PSpZG2/fmgmiNzYK9qWRh8h/CHrwD0mo1h1DzL4yzHNSfWYujGTYsWGreD000gcgmZ7K4Ys6Tx9TxtsKdDw==",
+            "license": "MIT"
+        },
         "node_modules/@levischuck/tiny-cbor": {
             "version": "0.2.11",
             "resolved": "https://registry.npmjs.org/@levischuck/tiny-cbor/-/tiny-cbor-0.2.11.tgz",
@@ -6764,6 +6773,16 @@
                 "@types/d3-selection": "*"
             }
         },
+        "node_modules/@types/dns-packet": {
+            "version": "5.6.5",
+            "resolved": "https://registry.npmjs.org/@types/dns-packet/-/dns-packet-5.6.5.tgz",
+            "integrity": "sha512-qXOC7XLOEe43ehtWJCMnQXvgcIpv6rPmQ1jXT98Ad8A3TB1Ue50jsCbSSSyuazScEuZ/Q026vHbrOTVkmwA+7Q==",
+            "dev": true,
+            "license": "MIT",
+            "dependencies": {
+                "@types/node": "*"
+            }
+        },
         "node_modules/@types/esrecurse": {
             "version": "4.3.1",
             "resolved": "https://registry.npmjs.org/@types/esrecurse/-/esrecurse-4.3.1.tgz",
@@ -7435,6 +7454,22 @@
                 "node": ">= 0.6"
             }
         },
+        "node_modules/acme-client": {
+            "version": "5.4.0",
+            "resolved": "https://registry.npmjs.org/acme-client/-/acme-client-5.4.0.tgz",
+            "integrity": "sha512-mORqg60S8iML6XSmVjqjGHJkINrCGLMj2QvDmFzI9vIlv1RGlyjmw3nrzaINJjkNsYXC41XhhD5pfy7CtuGcbA==",
+            "license": "MIT",
+            "dependencies": {
+                "@peculiar/x509": "^1.11.0",
+                "asn1js": "^3.0.5",
+                "axios": "^1.7.2",
+                "debug": "^4.3.5",
+                "node-forge": "^1.3.1"
+            },
+            "engines": {
+                "node": ">= 16"
+            }
+        },
         "node_modules/acorn": {
             "version": "8.16.0",
             "resolved": "https://registry.npmjs.org/acorn/-/acorn-8.16.0.tgz",
@@ -9261,6 +9296,18 @@
                 "node": ">=8"
             }
         },
+        "node_modules/dns-packet": {
+            "version": "5.6.1",
+            "resolved": "https://registry.npmjs.org/dns-packet/-/dns-packet-5.6.1.tgz",
+            "integrity": "sha512-l4gcSouhcgIKRvyy99RNVOgxXiicE+2jZoNmaNmZ6JXiGajBOJAesk1OBlJuM5k2c+eudGdLxDqXuPCKIj6kpw==",
+            "license": "MIT",
+            "dependencies": {
+                "@leichtgewicht/ip-codec": "^2.0.1"
+            },
+            "engines": {
+                "node": ">=6"
+            }
+        },
         "node_modules/doctrine": {
             "version": "2.1.0",
             "resolved": "https://registry.npmjs.org/doctrine/-/doctrine-2.1.0.tgz",
@@ -13140,6 +13187,15 @@
                 "semver": "bin/semver.js"
             }
         },
+        "node_modules/node-forge": {
+            "version": "1.4.0",
+            "resolved": "https://registry.npmjs.org/node-forge/-/node-forge-1.4.0.tgz",
+            "integrity": "sha512-LarFH0+6VfriEhqMMcLX2F7SwSXeWwnEAJEsYm5QKWchiVYVvJyV9v7UDvUv+w5HO23ZpQTXDv/GxdDdMyOuoQ==",
+            "license": "(BSD-3-Clause OR GPL-2.0)",
+            "engines": {
+                "node": ">= 6.13.0"
+            }
+        },
         "node_modules/node-releases": {
             "version": "2.0.54",
             "resolved": "https://registry.npmjs.org/node-releases/-/node-releases-2.0.54.tgz",

package.json

@@ -73,6 +73,7 @@
         "@xterm/addon-fit": "^0.11.0",
         "@xterm/addon-web-links": "^0.12.0",
         "@xterm/xterm": "^6.0.0",
+        "acme-client": "^5.4.0",
         "arctic": "3.7.0",
         "axios": "1.20.0",
         "better-sqlite3": "11.9.1",
@@ -84,6 +85,7 @@
         "cors": "2.8.6",
         "crypto-js": "4.2.0",
         "d3": "7.9.0",
+        "dns-packet": "^5.6.1",
         "drizzle-orm": "0.45.2",
         "express": "5.2.1",
         "express-rate-limit": "8.7.0",
@@ -147,6 +149,7 @@
         "@types/cors": "2.8.19",
         "@types/crypto-js": "4.2.2",
         "@types/d3": "7.4.3",
+        "@types/dns-packet": "^5.6.5",
         "@types/express": "5.0.6",
         "@types/express-session": "1.19.0",
         "@types/jmespath": "0.15.2",

server/certificates.ts

@@ -0,0 +1,8 @@
+export async function startCertificateManager() {
+    // No-op: ACME certificate generation/management is only available in
+    // builds that include the private/enterprise feature set.
+}
+
+export async function stopCertificateManager() {
+    // No-op counterpart to startCertificateManager.
+}

server/dns.ts

@@ -0,0 +1,8 @@
+export async function startDnsServer() {
+    // No-op: the authoritative DNS server is only available in builds
+    // that include the private/enterprise feature set.
+}
+
+export async function stopDnsServer() {
+    // No-op counterpart to startDnsServer.
+}

server/index.ts

@@ -25,6 +25,8 @@ import { setHostMeta } from "@server/lib/hostMeta";
 import { TraefikConfigManager } from "@server/lib/traefik/TraefikConfigManager";
 import { initCleanup } from "#dynamic/cleanup";
 import { startSchedulers } from "#dynamic/startSchedulers";
+import { startDnsServer } from "#dynamic/dns";
+import { startCertificateManager } from "#dynamic/certificates";
 import license from "#dynamic/license/license";
 import { fetchServerIp } from "@server/lib/serverIpService";
 import { initAiModelCatalog } from "@server/lib/aiModelCatalog";
@@ -45,6 +47,10 @@ async function startServers() {
 
     startSchedulers();
 
+    await startDnsServer();
+
+    await startCertificateManager();
+
     // Start all servers
     const apiServer = createApiServer();
     const internalServer = createInternalServer();

server/lib/dbRetry.ts

@@ -71,7 +71,7 @@ export async function withRetry<T>(
                 const jitter = Math.random() * baseDelay;
                 const delay = baseDelay + jitter;
                 logger.warn(
-                    `Transient DB error in ${context}, retrying attempt ${attempt}/${maxRetries} after ${delay.toFixed(0)}ms`,
+                    `Transient DB issue in ${context}, retrying attempt ${attempt}/${maxRetries} after ${delay.toFixed(0)}ms`,
                     { code: error?.code ?? error?.cause?.code }
                 );
                 await new Promise((resolve) => setTimeout(resolve, delay));

server/lib/dns/generateDomains.ts

@@ -0,0 +1,3 @@
+export function createCname(domainId: string, baseDomain: string) {}
+
+export function createNs() {}

server/lib/exitNodes/exitNodeCheckIn.ts

@@ -0,0 +1,14 @@
+// Tracks, per process lifetime, whether a given exit node has ever checked in
+// (called /gerbil/get-config) since this Pangolin instance started. This lets
+// callers distinguish "gerbil hasn't come up yet" (expected briefly after a
+// restart, since gerbil depends on pangolin's container starting first) from
+// "gerbil was reachable and now isn't" (a real problem worth an error log).
+const checkedInExitNodeIds = new Set<number>();
+
+export function markExitNodeCheckedIn(exitNodeId: number): void {
+    checkedInExitNodeIds.add(exitNodeId);
+}
+
+export function hasExitNodeCheckedIn(exitNodeId: number): boolean {
+    return checkedInExitNodeIds.has(exitNodeId);
+}

server/lib/exitNodes/exitNodeComms.ts

@@ -1,6 +1,7 @@
 import axios from "axios";
 import logger from "@server/logger";
 import { ExitNode } from "@server/db";
+import { hasExitNodeCheckedIn } from "./exitNodeCheckIn";
 
 interface ExitNodeRequest {
     remoteType?: string;
@@ -72,13 +73,19 @@ export async function sendToExitNode(
 
         return response.data;
     } catch (error) {
-        if (axios.isAxiosError(error)) {
-            logger.error(
-                `Error making ${method} request (can Pangolin see Gerbil HTTP API?) for exit node at ${exitNode.reachableAt} (status: ${error.response?.status}): ${error.message}`
-            );
+        const message = axios.isAxiosError(error)
+            ? `Error making ${method} request (can Pangolin see Gerbil HTTP API?) for exit node at ${exitNode.reachableAt} (status: ${error.response?.status}): ${error.message}`
+            : `Error making ${method} request for exit node at ${exitNode.reachableAt}: ${error}`;
+
+        // The exit node (gerbil) may still be starting up and not yet
+        // reachable. Until it has checked in at least once, log this at a
+        // lower level since it's expected; once it has checked in, a
+        // connection failure is a real problem.
+        if (hasExitNodeCheckedIn(exitNode.exitNodeId)) {
+            logger.error(message);
         } else {
-            logger.error(
-                `Error making ${method} request for exit node at ${exitNode.reachableAt}: ${error}`
+            logger.warn(
+                `${message} (exit node has not checked in yet since startup, this is expected briefly)`
             );
         }
         throw error;

server/lib/exitNodes/index.ts

@@ -1,5 +1,6 @@
 export * from "./exitNodes";
 export * from "./exitNodeComms";
+export * from "./exitNodeCheckIn";
 export * from "./subnet";
 export * from "./getCurrentExitNodeId";
 export * from "./calculateExitNodeWeight";

server/lib/readConfigFile.ts

@@ -348,8 +348,8 @@ export const configSchema = z
                     .optional()
                     .pipe(z.string())
                     .transform((url) => url.toLowerCase()),
-                subnet_group: z.string().optional().default("100.89.137.0/20"),
-                block_size: z.number().positive().gt(0).optional().default(24),
+                subnet_group: z.string().optional().default("100.89.137.0/18"),
+                block_size: z.number().positive().gt(0).optional().default(22),
                 site_block_size: z
                     .number()
                     .positive()
@@ -493,23 +493,6 @@ export const configSchema = z
                     .prefault({})
             })
             .optional()
-            .prefault({}),
-        dns: z
-            .object({
-                nameservers: z
-                    .array(z.string().optional().optional())
-                    .optional()
-                    .default([
-                        "ns1.pangolin.net",
-                        "ns2.pangolin.net",
-                        "ns3.pangolin.net"
-                    ]),
-                cname_extension: z
-                    .string()
-                    .optional()
-                    .default("cname.pangolin.net")
-            })
-            .optional()
             .prefault({})
     })
     .refine(

server/lib/retry.ts

@@ -0,0 +1,72 @@
+import logger from "@server/logger";
+
+export async function withRetry<T>(
+    fn: () => Promise<T>,
+    options: {
+        retries?: number;
+        baseDelayMs?: number;
+        label?: string;
+        // Called with each caught error to decide whether it's worth
+        // retrying. Defaults to retrying everything (existing behavior) -
+        // pass this to exclude errors that are known to be permanent (e.g.
+        // an upstream rate limit or validation rejection) rather than
+        // transient, so they fail fast instead of wasting retry attempts.
+        shouldRetry?: (error: unknown) => boolean;
+    } = {}
+): Promise<T> {
+    const {
+        retries = 3,
+        baseDelayMs = 250,
+        label = "operation",
+        shouldRetry = () => true
+    } = options;
+
+    let attempt = 0;
+    while (true) {
+        try {
+            return await fn();
+        } catch (error) {
+            attempt++;
+            if (attempt > retries || !shouldRetry(error)) {
+                throw error;
+            }
+
+            // Exponential backoff with jitter so retries don't all land at once.
+            const delay =
+                baseDelayMs * 2 ** (attempt - 1) * (0.5 + Math.random());
+
+            logger.warn(
+                `${label} failed (attempt ${attempt}/${retries + 1}), retrying in ${delay.toFixed(0)}ms`,
+                error
+            );
+
+            await new Promise((resolve) => setTimeout(resolve, delay));
+        }
+    }
+}
+
+// Bounds an operation that has no timeout of its own (e.g. acme-client's
+// axios instance never sets one, so a stalled TCP connection to the ACME
+// server hangs forever instead of erroring). Without this, a single hung
+// call can leave its caller's promise permanently unsettled - fatal for
+// code that gates future work on that promise resolving, like the
+// scheduler's runExclusive() waiting on a batch's Promise.all.
+export async function withTimeout<T>(
+    promise: Promise<T>,
+    ms: number,
+    label = "operation"
+): Promise<T> {
+    let timer: NodeJS.Timeout;
+    const timeout = new Promise<never>((_, reject) => {
+        timer = setTimeout(
+            () => reject(new Error(`${label} timed out after ${ms}ms`)),
+            ms
+        );
+    });
+
+    try {
+        return await Promise.race([promise, timeout]);
+    } finally {
+        clearTimeout(timer!);
+    }
+}

server/lib/traefik/TraefikConfigManager.ts

@@ -6,7 +6,10 @@ import * as yaml from "js-yaml";
 import axios from "axios";
 import { db, exitNodes } from "@server/db";
 import { eq } from "drizzle-orm";
-import { getCurrentExitNodeId } from "@server/lib/exitNodes";
+import {
+    getCurrentExitNodeId,
+    hasExitNodeCheckedIn
+} from "@server/lib/exitNodes";
 import { getTraefikConfig } from "#dynamic/lib/traefik";
 import { getValidCertificatesForDomains } from "@server/lib/certificates";
 import { sendToExitNode } from "#dynamic/lib/exitNodes";
@@ -341,10 +344,6 @@ export class TraefikConfigManager {
 
             const { domains, traefikConfig } = getTraefikConfig;
 
-            // Add static domains from config
-            // const staticDomains = [config.getRawConfig().app.dashboard_url];
-            // staticDomains.forEach((domain) => domains.add(domain));
-
             // Log if domains changed
             if (
                 this.lastActiveDomains.size !== domains.size ||
@@ -358,7 +357,7 @@ export class TraefikConfigManager {
                 this.lastActiveDomains = new Set(domains);
             }
 
-            if (process.env.USE_PANGOLIN_DNS === "true" && build != "oss") {
+            if (process.env.CERT_MODE === "pangolin" && build != "oss") {
                 // Scan current local certificate state
                 this.lastLocalCertificateState =
                     await this.scanLocalCertificateState();
@@ -439,13 +438,13 @@ export class TraefikConfigManager {
                     // Always ensure all existing certificates (including wildcards) are in the config
                     await this.updateDynamicConfigFromLocalCerts(domains);
                 } else {
-                    const timeSinceLastFetch = this.lastCertificateFetch
-                        ? Math.round(
-                              (Date.now() -
-                                  this.lastCertificateFetch.getTime()) /
-                                  (1000 * 60)
-                          )
-                        : 0;
+                    // const timeSinceLastFetch = this.lastCertificateFetch
+                    //     ? Math.round(
+                    //           (Date.now() -
+                    //               this.lastCertificateFetch.getTime()) /
+                    //               (1000 * 60)
+                    //       )
+                    //     : 0;
 
                     // logger.debug(
                     //     `Skipping certificate fetch - no changes detected and within 24-hour window (last fetch: ${timeSinceLastFetch} minutes ago)`
@@ -466,32 +465,51 @@ export class TraefikConfigManager {
             await this.writeTraefikDynamicConfig(traefikConfig);
 
             // Send domains to SNI proxy
+            let exitNodeForSni: typeof exitNodes.$inferSelect | undefined;
             try {
-                let exitNode;
                 if (config.getRawConfig().gerbil.exit_node_name) {
                     const exitNodeName =
                         config.getRawConfig().gerbil.exit_node_name!;
-                    [exitNode] = await db
+                    [exitNodeForSni] = await db
                         .select()
                         .from(exitNodes)
                         .where(eq(exitNodes.name, exitNodeName))
                         .limit(1);
                 } else {
-                    [exitNode] = await db.select().from(exitNodes).limit(1);
+                    [exitNodeForSni] = await db
+                        .select()
+                        .from(exitNodes)
+                        .limit(1);
                 }
-                if (exitNode) {
-                    await sendToExitNode(exitNode, {
+                if (exitNodeForSni) {
+                    await sendToExitNode(exitNodeForSni, {
                         localPath: "/update-local-snis",
                         method: "POST",
-                        data: { fullDomains: Array.from(domains) }
+                        data: {
+                            fullDomains: [
+                                ...Array.from(domains),
+                                ...config.getRawConfig().traefik.static_domains
+                            ]
+                        }
                     });
                 } else {
-                    logger.error(
+                    logger.warn(
                         "No exit node found. Has gerbil registered yet?"
                     );
                 }
             } catch (err) {
-                logger.error("Failed to post domains to SNI proxy:", err);
+                // sendToExitNode already logs the underlying connection
+                // error at the appropriate level (warn before the exit node
+                // has checked in since startup, error after), so avoid
+                // double-logging it as an error here.
+                if (
+                    exitNodeForSni &&
+                    !hasExitNodeCheckedIn(exitNodeForSni.exitNodeId)
+                ) {
+                    logger.warn("Failed to post domains to SNI proxy:", err);
+                } else {
+                    logger.error("Failed to post domains to SNI proxy:", err);
+                }
             }
 
             // Update active domains tracking

server/lib/traefik/rule.ts

@@ -1,7 +1,5 @@
-/**
- * Build the Host()/HostRegexp() Traefik rule for a resource's domain.
- * Wildcard resources match any single subdomain via HostRegexp.
- */
+// Build the Host()/HostRegexp() Traefik rule for a resource's domain.
+// Wildcard resources match any single subdomain via HostRegexp.
 export function buildHostRule(
     fullDomain: string,
     wildcard?: boolean | null
@@ -14,10 +12,8 @@ export function buildHostRule(
     return `Host(\`${fullDomain}\`)`;
 }
 
-/**
- * Append a path-matching clause to a Traefik rule based on the resource's
- * configured path and pathMatchType.
- */
+// Append a path-matching clause to a Traefik rule based on the resource's
+// configured path and pathMatchType.
 export function appendPathMatch(
     rule: string,
     path: string | null | undefined,
@@ -40,10 +36,8 @@ export function appendPathMatch(
     return rule;
 }
 
-/**
- * Compute the router priority for a resource, favoring an explicit override
- * and otherwise deriving it from the path match specificity.
- */
+// Compute the router priority for a resource, favoring an explicit override
+// and otherwise deriving it from the path match specificity.
 export function computeRoutePriority(
     priority: number | null | undefined,
     path: string | null | undefined,

server/private/certificates.ts

@@ -0,0 +1,17 @@
+/*
+ * This file is part of a proprietary work.
+ *
+ * Copyright (c) 2025-2026 Fossorial, Inc.
+ * All rights reserved.
+ *
+ * This file is licensed under the Fossorial Commercial License.
+ * You may not use this file except in compliance with the License.
+ * Unauthorized use, copying, modification, or distribution is strictly prohibited.
+ *
+ * This file is not licensed under the AGPLv3.
+ */
+
+export {
+    startCertificateManager,
+    stopCertificateManager
+} from "./lib/certificates";

server/private/cleanup.ts

@@ -20,6 +20,8 @@ import { flushSiteBandwidthToDb } from "@server/routers/gerbil/receiveBandwidth"
 import { stopPingAccumulator } from "@server/routers/newt/pingAccumulator";
 import { shutdownUsageRecorder } from "@server/lib/aiBudgetEnforcement";
 import { shutdownAiSessionLogger } from "@server/routers/aiGateway/logAiSession";
+import { stopDnsServer } from "./dns";
+import { stopCertificateManager } from "./certificates";
 
 async function cleanup() {
     await stopPingAccumulator();
@@ -31,6 +33,8 @@ async function cleanup() {
     await rateLimitService.cleanup();
     await wsCleanup();
     await logStreamingManager.shutdown();
+    await stopDnsServer();
+    await stopCertificateManager();
 
     process.exit(0);
 }

server/private/dns.ts

@@ -0,0 +1,44 @@
+/*
+ * This file is part of a proprietary work.
+ *
+ * Copyright (c) 2025-2026 Fossorial, Inc.
+ * All rights reserved.
+ *
+ * This file is licensed under the Fossorial Commercial License.
+ * You may not use this file except in compliance with the License.
+ * Unauthorized use, copying, modification, or distribution is strictly prohibited.
+ *
+ * This file is not licensed under the AGPLv3.
+ */
+
+import { AuthoritativeDNSServer } from "#private/lib/dns";
+import { privateConfig } from "#private/lib/config";
+
+let dnsServer: AuthoritativeDNSServer | undefined;
+
+export async function startDnsServer() {
+    const dnsConfig = privateConfig.getRawPrivateConfig().dns;
+    if (!dnsConfig || !dnsConfig.enabled) {
+        return;
+    }
+
+    const cacheOptions = {
+        stdTTL: 300, // 5 minutes default TTL
+        checkperiod: 60, // Check for expired keys every 60 seconds
+        useClones: false // Better performance
+    };
+
+    // Create DNS server
+    dnsServer = new AuthoritativeDNSServer(dnsConfig.listen_port, cacheOptions);
+
+    await dnsServer.start();
+}
+
+export async function stopDnsServer() {
+    if (!dnsServer) {
+        return;
+    }
+
+    await dnsServer.stop();
+    dnsServer = undefined;
+}

server/private/lib/cache.ts

@@ -13,7 +13,7 @@
 
 import NodeCache from "node-cache";
 import logger from "@server/logger";
-import { redisManager, regionalRedisManager } from "@server/private/lib/redis";
+import { redisManager, regionalRedisManager } from "#private/lib/redis";
 
 // Create local cache with maxKeys limit to prevent memory leaks
 // With ~10k requests/day and 5min TTL, 10k keys should be more than sufficient
@@ -97,11 +97,11 @@ class AdaptiveCache {
                 const value = await redisManager.get(key);
 
                 if (value !== null) {
-                    logger.debug(`Cache hit in Redis: ${key}`);
+                    // logger.debug(`Cache hit in Redis: ${key}`);
                     return JSON.parse(value) as T;
                 }
 
-                logger.debug(`Cache miss in Redis: ${key}`);
+                // logger.debug(`Cache miss in Redis: ${key}`);
                 return undefined;
             } catch (error) {
                 logger.error(`Redis get error for key ${key}:`, error);
@@ -134,7 +134,7 @@ class AdaptiveCache {
                     const success = await redisManager.del(k);
                     if (success) {
                         deletedCount++;
-                        logger.debug(`Deleted key from Redis: ${k}`);
+                        // logger.debug(`Deleted key from Redis: ${k}`);
                     }
                 }
 
@@ -161,7 +161,7 @@ class AdaptiveCache {
             const success = localCache.del(k);
             if (success > 0) {
                 deletedCount++;
-                logger.debug(`Deleted key from local cache: ${k}`);
+                // logger.debug(`Deleted key from local cache: ${k}`);
             }
         }
 
@@ -229,7 +229,7 @@ class AdaptiveCache {
         }
 
         localCache.flushAll();
-        logger.debug("Flushed local cache");
+        // logger.debug("Flushed local cache");
     }
 
     /**
@@ -332,7 +332,7 @@ class RegionalAdaptiveCache {
                     redisTtl
                 );
                 if (success) {
-                    logger.debug(`[regional] Set key in Redis: ${key}`);
+                    // logger.debug(`[regional] Set key in Redis: ${key}`);
                     return true;
                 }
             } catch (error) {
@@ -353,10 +353,10 @@ class RegionalAdaptiveCache {
             try {
                 const value = await regionalRedisManager.get(key);
                 if (value !== null) {
-                    logger.debug(`[regional] Cache hit in Redis: ${key}`);
+                    // logger.debug(`[regional] Cache hit in Redis: ${key}`);
                     return JSON.parse(value) as T;
                 }
-                logger.debug(`[regional] Cache miss in Redis: ${key}`);
+                // logger.debug(`[regional] Cache miss in Redis: ${key}`);
                 return undefined;
             } catch (error) {
                 logger.error(
@@ -385,7 +385,7 @@ class RegionalAdaptiveCache {
                     const success = await regionalRedisManager.del(k);
                     if (success) {
                         deletedCount++;
-                        logger.debug(`[regional] Deleted key from Redis: ${k}`);
+                        // logger.debug(`[regional] Deleted key from Redis: ${k}`);
                     }
                 }
                 if (deletedCount === keys.length) return deletedCount;
@@ -400,7 +400,7 @@ class RegionalAdaptiveCache {
             const count = regionalLocalCache.del(k);
             if (count > 0) {
                 deletedCount++;
-                logger.debug(`[regional] Deleted key from local cache: ${k}`);
+                // logger.debug(`[regional] Deleted key from local cache: ${k}`);
             }
         }
         return deletedCount;

server/private/lib/certificates/acme-client.ts

@@ -0,0 +1,298 @@
+/*
+ * This file is part of a proprietary work.
+ *
+ * Copyright (c) 2025-2026 Fossorial, Inc.
+ * All rights reserved.
+ *
+ * This file is licensed under the Fossorial Commercial License.
+ * You may not use this file except in compliance with the License.
+ * Unauthorized use, copying, modification, or distribution is strictly prohibited.
+ *
+ * This file is not licensed under the AGPLv3.
+ */
+
+import * as acme from "acme-client";
+import * as fs from "fs";
+import { eq } from "drizzle-orm/sql";
+import { privateConfig as config } from "#private/lib/config";
+import { DnsChallenge, db, dnsChallenge } from "@server/db";
+import { withRetry } from "@server/lib/retry";
+import logger from "@server/logger";
+import { acmeRateLimiter } from "./acmeRateLimiter";
+
+// acme-client's own retry/backoff logging (429 retries, 5xx retries, each
+// status-poll tick in waitForValidStatus) is a no-op by default - it only
+// activates via DEBUG=acme-client or this call, neither of which was wired
+// up. Without it, a cert silently retrying a Let's Encrypt rate limit for
+// several minutes is indistinguishable in our logs from one that's actually
+// hung, since our own logging only wraps the call, not what happens inside
+// it. Must run before any AcmeClient method is called.
+acme.setLogger((msg: string) => logger.info(`[acme-client] ${msg}`));
+
+// acme-client's axios retry wrapper treats any response-less request error
+// (timeout, connection reset, DNS blip reaching the ACME server) as
+// retryable, but once its internal retries are exhausted it falls through to
+// `validateStatus(response)` with `response` still undefined, throwing this
+// uninformative TypeError instead of the real network error.
+// https://github.com/publishlab/node-acme-client/blob/master/src/axios.js
+function isUnresponsiveAcmeError(error: unknown): boolean {
+    return (
+        error instanceof TypeError &&
+        error.message ===
+            "Cannot read properties of undefined (reading 'config')"
+    );
+}
+
+function normalizeAcmeError(error: unknown): Error {
+    if (isUnresponsiveAcmeError(error)) {
+        return new Error(
+            "ACME server did not respond after repeated attempts (network error reaching the ACME endpoint)",
+            { cause: error }
+        );
+    }
+    return error instanceof Error ? error : new Error(String(error));
+}
+
+export class AcmeClientManager {
+    private client: acme.Client | null = null;
+    private accountKey: string | null = null;
+
+    async initialize() {
+        try {
+            this.accountKey = await this.loadAccountKey();
+
+            this.client = new acme.Client({
+                directoryUrl: config.getRawConfig().acme!.acme_directory_url,
+                accountKey: this.accountKey
+            });
+
+            // Try to create account or get existing one
+            await this.client.createAccount({
+                termsOfServiceAgreed: true,
+                contact: [`mailto:${config.getRawConfig().acme!.contact_email}`]
+            });
+
+            logger.info("ACME client initialized successfully");
+        } catch (error) {
+            logger.error("Failed to initialize ACME client:", error);
+            throw error;
+        }
+    }
+
+    private async loadAccountKey(): Promise<string> {
+        const keyPath = config.getRawConfig().acme!.acme_account_key_path;
+
+        if (fs.existsSync(keyPath)) {
+            logger.info("Loading existing account key");
+            return fs.readFileSync(keyPath, "utf8");
+        } else {
+            logger.info("Generating new account key");
+            const privateKey = await acme.crypto.createPrivateKey();
+            const privateKeyString = privateKey.toString();
+            fs.writeFileSync(keyPath, privateKeyString);
+            return privateKeyString;
+        }
+    }
+
+    getClient(): acme.Client {
+        if (!this.client) {
+            throw new Error("ACME client not initialized");
+        }
+        return this.client;
+    }
+
+    async createOrder(domain: string, wildcard: boolean = false): Promise<any> {
+        const client = this.getClient();
+
+        const identifiers = wildcard
+            ? [
+                  { type: "dns", value: domain },
+                  { type: "dns", value: `*.${domain}` }
+              ]
+            : [{ type: "dns", value: domain }];
+
+        await acmeRateLimiter.acquire();
+        const order = await client.createOrder({
+            identifiers
+        });
+
+        if (wildcard) {
+            logger.info(`Created wildcard order for domain: ${domain}`);
+        } else {
+            logger.info(`Created order for domain: ${domain}`);
+        }
+        return order;
+    }
+
+    async getAuthorizations(order: any): Promise<any[]> {
+        const client = this.getClient();
+        await acmeRateLimiter.acquire();
+        return client.getAuthorizations(order);
+    }
+
+    async handleDnsChallenge(
+        dnsChallenges: {
+            authz: any;
+            challenge: any;
+        }[]
+    ): Promise<void> {
+        const client = this.getClient();
+
+        let challengeDomains: DnsChallenge[] = [];
+
+        for (const { authz, challenge } of dnsChallenges) {
+            const keyAuthorization =
+                await client.getChallengeKeyAuthorization(challenge);
+
+            // Extract the domain from authorization
+            const domain = authz.identifier.value;
+
+            // Store challenge in database for DNS server to pick up
+            challengeDomains = await withRetry(
+                () =>
+                    db
+                        .insert(dnsChallenge)
+                        .values({
+                            domain: domain,
+                            token: challenge.token,
+                            keyAuthorization,
+                            createdAt: Math.floor(Date.now() / 1000),
+                            expiresAt: Math.floor(
+                                (Date.now() +
+                                    config.getRawConfig().acme!
+                                        .challenge_ttl_ms) /
+                                    1000
+                            )
+                        })
+                        .returning(),
+                { label: `insert dnsChallenge for domain ${domain}` }
+            );
+
+            logger.info(
+                `DNS challenge stored for domain: ${domain} as token ${challenge.token} and keyAuthorization`
+            );
+        }
+
+        await new Promise((resolve) => setTimeout(resolve, 2000));
+
+        const failedDomains: string[] = [];
+
+        for (const { authz, challenge } of dnsChallenges) {
+            const domain = authz.identifier.value;
+            const challengeDomain = `_acme-challenge.${domain}`;
+
+            try {
+                // The ACME server occasionally has a transient network blip
+                // mid-sequence; retry the whole verify/complete/wait sequence
+                // rather than just the DNS challenge propagation wait, since
+                // these calls are safe to repeat against the ACME server.
+                await withRetry(
+                    async () => {
+                        // Verify challenge
+                        await acmeRateLimiter.acquire();
+                        await client.verifyChallenge(authz, challenge);
+
+                        // Complete challenge
+                        logger.info(
+                            `Completing challenge for domain: ${challengeDomain}`
+                        );
+                        await acmeRateLimiter.acquire();
+                        await client.completeChallenge(challenge);
+
+                        // Wait for validation
+                        logger.info(
+                            `Waiting for challenge to be validated for domain: ${challengeDomain}...`
+                        );
+                        await acmeRateLimiter.acquire();
+                        await client.waitForValidStatus(challenge);
+                    },
+                    {
+                        retries: 2,
+                        baseDelayMs: 5000,
+                        label: `ACME challenge completion for domain ${domain}`,
+                        // Only retry the known network-blip crash - a
+                        // genuine validation failure (e.g. challenge marked
+                        // "invalid" because the DNS record wasn't found) is
+                        // permanent and should fail immediately instead of
+                        // burning Let's Encrypt's per-hostname failed-
+                        // validation rate limit on retries that can't help.
+                        shouldRetry: isUnresponsiveAcmeError
+                    }
+                );
+
+                logger.info(`Challenge completed for domain: ${domain}`);
+            } catch (error) {
+                logger.error(
+                    `Failed to complete challenge for domain ${domain}:`,
+                    normalizeAcmeError(error)
+                );
+                failedDomains.push(domain);
+            }
+        }
+
+        for (const challengeDomain of challengeDomains) {
+            await this.removeDnsChallenge(challengeDomain.dnsChallengeId);
+            logger.info(
+                `Removed DNS challenge for domain: ${challengeDomain.domain}`
+            );
+        }
+
+        // A failed dns-01 challenge leaves the order stuck in "pending" -
+        // finalizing it would just fail with a confusing ACME error, so
+        // stop here and let the caller mark the certificate as failed.
+        if (failedDomains.length > 0) {
+            throw new Error(
+                `DNS-01 challenge validation failed for domain(s): ${failedDomains.join(", ")}`
+            );
+        }
+    }
+
+    async removeDnsChallenge(dnsChallengeId: number): Promise<void> {
+        try {
+            await withRetry(
+                () =>
+                    db
+                        .delete(dnsChallenge)
+                        .where(eq(dnsChallenge.dnsChallengeId, dnsChallengeId)),
+                { label: `delete dnsChallenge ${dnsChallengeId}` }
+            );
+        } catch (error) {
+            logger.error(
+                `Failed to clean up DNS challenge for id ${dnsChallengeId}:`,
+                error
+            );
+        }
+    }
+
+    async finalizeCertificate(
+        order: any,
+        domain: string,
+        wildcard: boolean = false
+    ): Promise<{ certificate: string; privateKey: string }> {
+        const client = this.getClient();
+
+        const altNames = wildcard ? [`*.${domain}`, domain] : [domain];
+
+        // Create CSR
+        const [privateKey, csr] = await acme.crypto.createCsr({
+            altNames
+        });
+
+        // Finalize order
+        await acmeRateLimiter.acquire();
+        const finalizedOrder = await client.finalizeOrder(order, csr);
+
+        // Get certificate
+        await acmeRateLimiter.acquire();
+        const certificate = await client.getCertificate(finalizedOrder);
+
+        logger.info(`Certificate obtained for domain: ${domain}`);
+
+        return {
+            certificate: certificate.toString(),
+            privateKey: privateKey.toString()
+        };
+    }
+}
+
+export const acmeClientManager = new AcmeClientManager();

server/private/lib/certificates/acmeRateLimiter.ts

@@ -0,0 +1,71 @@
+/*
+ * This file is part of a proprietary work.
+ *
+ * Copyright (c) 2025-2026 Fossorial, Inc.
+ * All rights reserved.
+ *
+ * This file is licensed under the Fossorial Commercial License.
+ * You may not use this file except in compliance with the License.
+ * Unauthorized use, copying, modification, or distribution is strictly prohibited.
+ *
+ * This file is not licensed under the AGPLv3.
+ */
+
+import { privateConfig as config } from "#private/lib/config";
+import logger from "@server/logger";
+import { redis } from "../redis";
+// Caps outgoing ACME API calls to a fixed budget per wall-clock second,
+// shared across all pops workers via Redis (mirrors the lockManager pattern
+// in @lib/lock) - a per-process limiter wouldn't be enough since multiple
+// workers issue certificates against the same Let's Encrypt account.
+const ACQUIRE_SCRIPT = `
+local key = KEYS[1]
+local limit = tonumber(ARGV[1])
+local current = redis.call('INCR', key)
+if current == 1 then
+    redis.call('PEXPIRE', key, 2000)
+end
+if current > limit then
+    return 0
+else
+    return 1
+end
+`;
+
+class AcmeRateLimiter {
+    async acquire(): Promise<void> {
+        const limit =
+            config.getRawConfig().acme?.acme_requests_per_second ?? 15;
+
+        for (;;) {
+            const bucket = Math.floor(Date.now() / 1000);
+            const key = `acme_rate_limit:${bucket}`;
+
+            let allowed: number;
+            try {
+                allowed = (await redis.eval(
+                    ACQUIRE_SCRIPT,
+                    1,
+                    key,
+                    limit.toString()
+                )) as number;
+            } catch (error) {
+                logger.error(
+                    "ACME rate limiter check failed, proceeding without throttling:",
+                    error
+                );
+                return;
+            }
+
+            if (allowed === 1) {
+                return;
+            }
+
+            // Budget for this second is spent - wait for the next window.
+            const waitMs = 1000 - (Date.now() % 1000) + 10;
+            await new Promise((resolve) => setTimeout(resolve, waitMs));
+        }
+    }
+}
+
+export const acmeRateLimiter = new AcmeRateLimiter();

server/private/lib/certificates/certificate-service.ts

@@ -0,0 +1,511 @@
+/*
+ * This file is part of a proprietary work.
+ *
+ * Copyright (c) 2025-2026 Fossorial, Inc.
+ * All rights reserved.
+ *
+ * This file is licensed under the Fossorial Commercial License.
+ * You may not use this file except in compliance with the License.
+ * Unauthorized use, copying, modification, or distribution is strictly prohibited.
+ *
+ * This file is not licensed under the AGPLv3.
+ */
+
+import { acmeClientManager } from "./acme-client";
+import { dnsValidator } from "./dns-validator";
+import { getTableColumns } from "drizzle-orm";
+import { eq, and, or, isNull, lt, asc } from "drizzle-orm/sql";
+import { config } from "@server/lib/config";
+import { db, certificates, domains, Certificate } from "@server/db";
+import { encrypt } from "@server/lib/crypto";
+import { withTimeout, withRetry } from "@server/lib/retry";
+import logger from "@server/logger";
+import { lockManager } from "../lock";
+import { pushCertUpdateToAffectedNewts } from "@server/lib/acmeCertSync";
+import crypto from "crypto";
+
+// Number of on-demand DNS validation attempts made right before a
+// certificate is (re)issued, to avoid burning Let's Encrypt rate limits on
+// domains whose DNS has drifted since they were last verified.
+const PRE_CERT_DNS_VALIDATION_ATTEMPTS = 3;
+
+// Hard ceiling on a single certificate's issuance/renewal flow. acme-client's
+// axios instance never sets a request timeout, so a stalled connection to
+// the ACME server hangs forever instead of erroring - and since
+// processPendingCertificates/processRenewalCandidates gate the *next* batch
+// on Promise.all(...) over the current one, one hung certificate would
+// otherwise stall every other domain permanently. Sized generously above the
+// legitimate worst case (acme-client's own bounded backoff is ~3.6min per
+// status-polling loop, and a wildcard cert's two identifiers plus order
+// finalization can chain a few of those) so this only fires on a genuine hang.
+const CERTIFICATE_ISSUANCE_TIMEOUT_MS = 20 * 60 * 1000;
+
+// "requested" is set the instant a cert starts processing and is never
+// queried anywhere else - processPendingCertificates only selects "pending"
+// and processRenewalCandidates only selects "valid". So if the *process*
+// dies mid-flight (OOM, node eviction, a rolling deploy) rather than just
+// hanging, the row is orphaned in "requested" permanently with nothing to
+// ever pick it back up, no matter how good the in-process timeouts are.
+// Threshold is set comfortably above CERTIFICATE_ISSUANCE_TIMEOUT_MS plus the
+// scheduler's own outer backstop so this never reclaims a cert that's still
+// genuinely being worked on.
+const STUCK_CERTIFICATE_THRESHOLD_MS = 40 * 60 * 1000;
+
+export class CertificateService {
+    // Runs at the top of every processPendingCertificates tick so an
+    // interrupted worker's leftovers always get put back in the queue
+    // instead of sitting invisible to every query forever.
+    private async reclaimStuckCertificates(): Promise<void> {
+        const staleBefore =
+            Math.floor(Date.now() / 1000) -
+            Math.floor(STUCK_CERTIFICATE_THRESHOLD_MS / 1000);
+
+        const reclaimed = await db
+            .update(certificates)
+            .set({
+                status: "pending",
+                errorMessage:
+                    'Reclaimed after being stuck in "requested" state - the worker processing it likely restarted or crashed',
+                updatedAt: Math.floor(Date.now() / 1000)
+            })
+            .where(
+                and(
+                    eq(certificates.status, "requested"),
+                    lt(certificates.updatedAt, staleBefore)
+                )
+            )
+            .returning({ domain: certificates.domain });
+
+        if (reclaimed.length > 0) {
+            logger.warn(
+                `Reclaimed ${reclaimed.length} certificate(s) stuck in "requested" state: ${reclaimed
+                    .map((c) => c.domain)
+                    .join(", ")}`
+            );
+        }
+    }
+
+    async processPendingCertificates(): Promise<void> {
+        logger.debug("Checking for pending certificates...");
+
+        await this.reclaimStuckCertificates();
+
+        const pendingCerts = await db
+            .select(getTableColumns(certificates))
+            .from(certificates)
+            .leftJoin(domains, eq(certificates.domainId, domains.domainId))
+            .where(
+                and(
+                    eq(certificates.status, "pending"),
+                    or(
+                        // Certs with no linked domain row (e.g. legacy certs
+                        // imported from acme.json) aren't gated on domain
+                        // verification since there's nothing to check.
+                        isNull(certificates.domainId),
+                        and(
+                            eq(domains.verified, true),
+                            eq(domains.failed, false)
+                        )
+                    )
+                )
+            )
+            .limit(10);
+
+        if (pendingCerts.length === 0) {
+            logger.debug("No pending certificates found");
+            return;
+        }
+
+        logger.info(`Found ${pendingCerts.length} pending certificates`);
+
+        // Process the batch concurrently so one domain stuck retrying a slow
+        // DNS-01 challenge (the ACME client's waitForValidStatus can spend
+        // minutes on a bad domain) doesn't stall the rest of the batch.
+        // processSingleCertificate catches its own errors and each cert uses
+        // an independent per-domain lock, so this is safe to parallelize.
+        await Promise.all(
+            pendingCerts.map((cert) => this.processSingleCertificate(cert))
+        );
+    }
+
+    async processRenewalCandidates(): Promise<void> {
+        logger.debug("Checking for certificates needing renewal...");
+
+        const now = Math.floor(Date.now() / 1000);
+
+        const renewalCandidates = await db
+            .select(getTableColumns(certificates))
+            .from(certificates)
+            .leftJoin(domains, eq(certificates.domainId, domains.domainId))
+            .where(
+                and(
+                    eq(certificates.status, "valid"),
+                    lt(certificates.expiresAt, now + 15 * 24 * 60 * 60), // 15 days from now
+                    or(
+                        // Certs with no linked domain row (e.g. legacy certs
+                        // imported from acme.json) aren't gated on domain
+                        // verification since there's nothing to check.
+                        isNull(certificates.domainId),
+                        and(
+                            eq(domains.verified, true),
+                            eq(domains.failed, false)
+                        )
+                    )
+                )
+            )
+            // Most urgent first, so already-expired certs aren't starved
+            // behind the limit by certs that still have weeks of runway.
+            .orderBy(asc(certificates.expiresAt))
+            .limit(50);
+
+        if (renewalCandidates.length === 0) {
+            logger.debug("No certificates need renewal");
+            return;
+        }
+
+        logger.info(
+            `Found ${renewalCandidates.length} certificates needing renewal`
+        );
+
+        for (const cert of renewalCandidates) {
+            if (cert.expiresAt !== null && cert.expiresAt < now) {
+                logger.warn(
+                    `Certificate for ${cert.domain} is marked "valid" but already expired at ${new Date(cert.expiresAt * 1000).toISOString()} (bad state) - renewing immediately`
+                );
+            }
+        }
+
+        // Process the batch concurrently - see processPendingCertificates for why.
+        await Promise.all(
+            renewalCandidates.map((cert) => this.renewCertificate(cert))
+        );
+    }
+
+    private async processSingleCertificate(cert: Certificate): Promise<void> {
+        const lockKey = `cert:${cert.domain}`;
+
+        const lockToken = await lockManager.acquireLock(lockKey);
+        if (!lockToken) {
+            logger.debug(
+                `Could not acquire lock for certificate: ${cert.domain}`
+            );
+            return;
+        }
+
+        try {
+            logger.info(`Processing certificate for domain: ${cert.domain}`);
+
+            // Update status to processing
+            await db
+                .update(certificates)
+                .set({
+                    status: "requested",
+                    updatedAt: Math.floor(Date.now() / 1000)
+                })
+                .where(eq(certificates.certId, cert.certId));
+            //
+
+            await withTimeout(
+                this.obtainCertificate(cert),
+                CERTIFICATE_ISSUANCE_TIMEOUT_MS,
+                `certificate issuance for ${cert.domain}`
+            );
+        } catch (error) {
+            logger.error(
+                `Failed to process certificate for ${cert.domain}:`,
+                error
+            );
+
+            await db
+                .update(certificates)
+                .set({
+                    status: "failed",
+                    errorMessage:
+                        error instanceof Error
+                            ? error.message
+                            : "Unknown error",
+                    updatedAt: Math.floor(Date.now() / 1000)
+                })
+                .where(eq(certificates.certId, cert.certId));
+        } finally {
+            await lockManager.releaseLock(lockKey, lockToken);
+        }
+    }
+
+    private async renewCertificate(cert: Certificate): Promise<void> {
+        const lockKey = `cert:${cert.domain}`;
+
+        const lockToken = await lockManager.acquireLock(lockKey);
+        if (!lockToken) {
+            logger.debug(
+                `Could not acquire lock for certificate renewal: ${cert.domain}`
+            );
+            return;
+        }
+
+        try {
+            logger.info(`Renewing certificate for domain: ${cert.domain}`);
+
+            // Update last renewal attempt
+            await db
+                .update(certificates)
+                .set({
+                    lastRenewalAttempt: Math.floor(Date.now() / 1000),
+                    updatedAt: Math.floor(Date.now() / 1000)
+                })
+                .where(eq(certificates.certId, cert.certId));
+
+            await withTimeout(
+                this.obtainCertificate(cert),
+                CERTIFICATE_ISSUANCE_TIMEOUT_MS,
+                `certificate renewal for ${cert.domain}`
+            );
+        } catch (error) {
+            logger.error(
+                `Failed to renew certificate for ${cert.domain}:`,
+                error
+            );
+
+            await db
+                .update(certificates)
+                .set({
+                    status: "failed",
+                    errorMessage:
+                        error instanceof Error
+                            ? error.message
+                            : "Unknown error",
+                    lastRenewalAttempt: Math.floor(Date.now() / 1000),
+                    updatedAt: Math.floor(Date.now() / 1000)
+                })
+                .where(eq(certificates.certId, cert.certId));
+        } finally {
+            await lockManager.releaseLock(lockKey, lockToken);
+        }
+    }
+
+    // Re-checks the domain's DNS records right before we spend a Let's
+    // Encrypt order on it, so drift that happened after the domain was
+    // originally verified doesn't burn ACME rate limits. Certs with no
+    // linked domain row (e.g. legacy/manually-managed certs) skip this and
+    // proceed as before, since there are no tracked DNS records to check.
+    private async verifyDomainBeforeIssuance(cert: Certificate): Promise<void> {
+        if (!cert.domainId) {
+            return;
+        }
+
+        const [domain] = await db
+            .select()
+            .from(domains)
+            .where(eq(domains.domainId, cert.domainId))
+            .limit(1);
+
+        if (!domain) {
+            return;
+        }
+
+        for (
+            let attempt = 1;
+            attempt <= PRE_CERT_DNS_VALIDATION_ATTEMPTS;
+            attempt++
+        ) {
+            // Offset `tries` so each attempt round-robins to a different
+            // privateConfigured DNS resolver instead of re-querying the same one.
+            const probe = { ...domain, tries: domain.tries + attempt - 1 };
+            if (
+                await dnsValidator.validateDomain(probe, {
+                    forceRecheck: true
+                })
+            ) {
+                await db
+                    .update(domains)
+                    .set({ verified: true, failed: false, errorMessage: null })
+                    .where(eq(domains.domainId, domain.domainId));
+                return;
+            }
+
+            logger.warn(
+                `Pre-certificate DNS check ${attempt}/${PRE_CERT_DNS_VALIDATION_ATTEMPTS} failed for domain ${domain.baseDomain} (cert: ${cert.domain})`
+            );
+        }
+
+        const errorMessage = `Domain failed DNS validation ${PRE_CERT_DNS_VALIDATION_ATTEMPTS} times before certificate issuance`;
+        await db
+            .update(domains)
+            .set({ verified: false, failed: true, errorMessage })
+            .where(eq(domains.domainId, domain.domainId));
+
+        throw new Error(errorMessage);
+    }
+
+    private async obtainCertificate(cert: Certificate): Promise<void> {
+        await this.verifyDomainBeforeIssuance(cert);
+
+        // Create order
+        const order = await acmeClientManager.createOrder(
+            cert.domain,
+            cert.wildcard || false
+        );
+
+        // Update with order ID
+        await withRetry(
+            () =>
+                db
+                    .update(certificates)
+                    .set({
+                        orderId: order.url,
+                        updatedAt: Math.floor(Date.now() / 1000)
+                    })
+                    .where(eq(certificates.certId, cert.certId)),
+            { label: `update orderId for certificate ${cert.domain}` }
+        );
+
+        // Get authorizations
+        const authorizations = await acmeClientManager.getAuthorizations(order);
+
+        // Aggregate all DNS-01 challenges
+        const dnsChallenges = authorizations.map((authz: any) => {
+            const dnsChallenge = authz.challenges.find(
+                (c: any) => c.type === "dns-01"
+            );
+            if (!dnsChallenge) {
+                throw new Error(
+                    `No DNS-01 challenge found for ${authz.identifier.value}`
+                );
+            }
+            return {
+                authz,
+                challenge: dnsChallenge
+            };
+        });
+
+        // Send all DNS-01 challenges in one request to handleDnsChallenge
+        await acmeClientManager.handleDnsChallenge(dnsChallenges);
+
+        // Finalize certificate
+        const { certificate, privateKey } =
+            await acmeClientManager.finalizeCertificate(
+                order,
+                cert.domain,
+                cert.wildcard || false
+            );
+
+        const encryptionKey = config.getRawConfig().server.secret;
+        if (!encryptionKey) {
+            throw new Error("Encryption key not provided");
+        }
+
+        // Encrypt certificate and private key
+        const encryptedCert = encrypt(certificate, encryptionKey);
+        const encryptedKey = encrypt(privateKey, encryptionKey);
+
+        // Parse certificate to get expiration date
+        const expiresAt = this.extractExpirationDate(certificate);
+
+        // Update database record. This persists the certificate we just
+        // obtained from the ACME server, so it's retried aggressively -
+        // losing this write means re-issuing the cert from scratch.
+        await withRetry(
+            () =>
+                db
+                    .update(certificates)
+                    .set({
+                        status: "valid",
+                        expiresAt: Math.floor(expiresAt.getTime() / 1000),
+                        renewalCount: (cert.renewalCount || 0) + 1,
+                        errorMessage: null,
+                        updatedAt: Math.floor(Date.now() / 1000),
+                        certFile: encryptedCert,
+                        keyFile: encryptedKey
+                    })
+                    .where(eq(certificates.certId, cert.certId)),
+            {
+                retries: 5,
+                label: `persist issued certificate for ${cert.domain}`
+            }
+        );
+
+        logger.info(
+            `Certificate successfully obtained/renewed for domain: ${cert.domain}`
+        );
+
+        await pushCertUpdateToAffectedNewts(
+            cert.domain,
+            cert.domainId ?? null,
+            certificate,
+            privateKey
+        );
+    }
+
+    private extractExpirationDate(certificate: string): Date {
+        try {
+            // Extract the certificate block
+            const pem = certificate
+                .replace(/-----BEGIN CERTIFICATE-----/g, "")
+                .replace(/-----END CERTIFICATE-----/g, "")
+                .replace(/\s+/g, "");
+            const der = Buffer.from(pem, "base64");
+
+            // Use Node.js crypto to parse the certificate
+            const x509 = new crypto.X509Certificate(der);
+            return new Date(x509.validTo);
+        } catch (error) {
+            logger.warn(
+                "Failed to parse certificate expiration date, using default",
+                error
+            );
+            // Default to 90 days from now (Let's Encrypt default)
+            return new Date(Date.now() + 90 * 24 * 60 * 60 * 1000);
+        }
+    }
+
+    async addCertificateRequest(domain: string): Promise<void> {
+        try {
+            await db.insert(certificates).values({
+                domain,
+                status: "pending",
+                createdAt: Math.floor(Date.now() / 1000),
+                updatedAt: Math.floor(Date.now() / 1000)
+            });
+            logger.info(`Certificate request added for domain: ${domain}`);
+        } catch (error) {
+            if (error instanceof Error && error.message.includes("unique")) {
+                logger.warn(
+                    `Certificate request already exists for domain: ${domain}`
+                );
+            } else {
+                throw error;
+            }
+        }
+    }
+
+    async getCertificateStatus(domain: string) {
+        const cert = await db
+            .select()
+            .from(certificates)
+            .where(eq(certificates.domain, domain))
+            .limit(1);
+
+        return cert[0] || null;
+    }
+
+    async cleanupExpiredChallenges(): Promise<void> {
+        try {
+            const result = await db
+                .delete(certificates)
+                .where(
+                    lt(certificates.expiresAt, Math.floor(Date.now() / 1000))
+                )
+                .returning();
+
+            if (result.length > 0) {
+                logger.info(
+                    `Cleaned up ${result.length} expired DNS challenges`
+                );
+            }
+        } catch (error) {
+            logger.error("Failed to cleanup expired challenges:", error);
+        }
+    }
+}
+
+export const certificateService = new CertificateService();

server/private/lib/certificates/dns-validator.ts

@@ -0,0 +1,334 @@
+/*
+ * This file is part of a proprietary work.
+ *
+ * Copyright (c) 2025-2026 Fossorial, Inc.
+ * All rights reserved.
+ *
+ * This file is licensed under the Fossorial Commercial License.
+ * You may not use this file except in compliance with the License.
+ * Unauthorized use, copying, modification, or distribution is strictly prohibited.
+ *
+ * This file is not licensed under the AGPLv3.
+ */
+
+import { eq, and, lt } from "drizzle-orm";
+import * as dns from "dns/promises";
+import { privateConfig as config } from "#private/lib/config";
+import { db, domains, DnsRecord, dnsRecords, Domain } from "@server/db";
+import logger from "@server/logger";
+import { lockManager } from "../lock";
+
+export const DNS_VALIDATOR_MAX_TRIES = 300;
+
+export class DNSValidator {
+    private static readonly MAX_TRIES = DNS_VALIDATOR_MAX_TRIES;
+
+    constructor() {}
+
+    async validateAll(): Promise<void> {
+        // Get all domains that are not yet verified and haven't exceeded max tries
+        const unverifiedDomains: Domain[] = await db
+            .select()
+            .from(domains)
+            .where(
+                and(
+                    eq(domains.verified, false),
+                    lt(domains.tries, DNSValidator.MAX_TRIES)
+                )
+            );
+
+        if (unverifiedDomains.length === 0) {
+            logger.debug("No unverified domains found for DNS validation");
+            return;
+        }
+
+        logger.info(`Validating ${unverifiedDomains.length} DNS records`);
+
+        for (const domain of unverifiedDomains) {
+            const lockKey = `dns:${domain.baseDomain}`;
+            const lockToken = await lockManager.acquireLock(lockKey);
+            if (!lockToken) {
+                logger.debug(
+                    `Could not acquire lock for DNS validation: ${domain.baseDomain}`
+                );
+                continue;
+            }
+            try {
+                const isValid = await this.validateDomain(domain);
+                if (isValid) {
+                    await db
+                        .update(domains)
+                        .set({
+                            verified: true,
+                            failed: false,
+                            tries: 0,
+                            errorMessage: null
+                        })
+                        .where(eq(domains.domainId, domain.domainId));
+                    logger.info(
+                        `Domain ${domain.baseDomain} validated successfully`
+                    );
+                } else {
+                    const newTries = domain.tries + 1;
+                    const shouldMarkAsFailed =
+                        newTries >= DNSValidator.MAX_TRIES;
+
+                    await db
+                        .update(domains)
+                        .set({
+                            tries: newTries,
+                            failed: shouldMarkAsFailed
+                        })
+                        .where(eq(domains.domainId, domain.domainId));
+
+                    if (shouldMarkAsFailed) {
+                        logger.warn(
+                            `Domain ${domain.baseDomain} exceeded maximum tries (${DNSValidator.MAX_TRIES}), marking as failed`
+                        );
+                    } else {
+                        logger.debug(
+                            `Domain ${domain.baseDomain} did not validate (attempt ${newTries}/${DNSValidator.MAX_TRIES})`
+                        );
+                    }
+                }
+            } catch (err) {
+                logger.warn(
+                    `Error validating domain ${domain.baseDomain}:`,
+                    err
+                );
+                // Increment tries even on error
+                const newTries = domain.tries + 1;
+                const shouldMarkAsFailed = newTries >= DNSValidator.MAX_TRIES;
+
+                await db
+                    .update(domains)
+                    .set({
+                        tries: newTries,
+                        failed: shouldMarkAsFailed
+                    })
+                    .where(eq(domains.domainId, domain.domainId));
+            } finally {
+                await lockManager.releaseLock(lockKey, lockToken);
+            }
+        }
+    }
+
+    async validateDomain(
+        domain: Domain,
+        opts: { forceRecheck?: boolean } = {}
+    ): Promise<boolean> {
+        const { forceRecheck = false } = opts;
+        const resolver = new dns.Resolver();
+        const servers = config.getRawConfig().acme?.dns_resolvers;
+        if (!servers || servers.length === 0) {
+            throw new Error("No DNS resolvers configured");
+        }
+        const dnsServer = servers[domain.tries % servers.length]!;
+        resolver.setServers([dnsServer]);
+        logger.debug(
+            `Using DNS server ${dnsServer} for domain ${domain.baseDomain} (try ${domain.tries})`
+        );
+
+        // Get all DNS records for this domain
+        const records: DnsRecord[] = await db
+            .select()
+            .from(dnsRecords)
+            .where(eq(dnsRecords.domainId, domain.domainId));
+
+        if (records.length === 0) {
+            logger.warn(`No DNS records found for domain ${domain.baseDomain}`);
+            return false;
+        }
+
+        if (!forceRecheck && records.every((r) => r.verified)) {
+            logger.info(
+                `All DNS records already verified for domain ${domain.baseDomain}`
+            );
+            return true;
+        }
+
+        logger.info(
+            `Validating ${records.length} DNS records for domain ${domain.baseDomain}`
+        );
+
+        // Collect the full set of expected NS values for this domain so we can
+        // detect extra records that are present in DNS but not in our DB.
+        const expectedNsValues = new Set<string>(
+            records.filter((r) => r.recordType === "NS").map((r) => r.value)
+        );
+
+        // Cache resolved NS records across iterations — there will be 3 NS
+        // records in the DB and we don't need to hit the upstream server 3 times.
+        let previousNs: string[] | null = null;
+
+        for (const record of records) {
+            // Skip already verified records, unless a live recheck was requested
+            if (record.verified && !forceRecheck) {
+                continue;
+            }
+
+            let isValid = false;
+
+            try {
+                if (record.recordType === "NS") {
+                    let nsRecords: string[] | null = previousNs;
+                    if (!nsRecords) {
+                        nsRecords = await resolver.resolveNs(
+                            record.baseDomain || domain.baseDomain
+                        );
+                    }
+                    logger.info(
+                        `NS records for ${
+                            record.baseDomain || domain.baseDomain
+                        }:`,
+                        nsRecords
+                    );
+
+                    // Check if this expected NS value is present in the live records.
+                    // A stale/legacy expected value (e.g. left over from a
+                    // nameserver rebrand) is also accepted as long as the live
+                    // records resolve to some other known-valid nameserver —
+                    // the specific literal hostname stored per-domain isn't
+                    // meaningful once it's a recognized alias.
+                    isValid = nsRecords.some((ns) => ns === record.value);
+
+                    previousNs = nsRecords;
+                } else if (record.recordType === "CNAME") {
+                    const cnameRecords = await resolver.resolveCname(
+                        record.baseDomain || domain.baseDomain
+                    );
+                    logger.info(
+                        `CNAME records for ${
+                            record.baseDomain || domain.baseDomain
+                        }:`,
+                        cnameRecords
+                    );
+
+                    // Check if the CNAME record matches the expected value
+                    isValid =
+                        cnameRecords.length === 1 &&
+                        cnameRecords[0] === record.value;
+                } else if (record.recordType === "TXT") {
+                    const txtRecords = await resolver.resolveTxt(
+                        record.baseDomain || domain.baseDomain
+                    );
+                    logger.info(
+                        `TXT records for ${
+                            record.baseDomain || domain.baseDomain
+                        }:`,
+                        txtRecords
+                    );
+
+                    // TXT records come as an array of arrays, flatten and check
+                    const flatTxtRecords = txtRecords.flat();
+                    isValid = flatTxtRecords.includes(record.value);
+                } else if (record.recordType === "A") {
+                    const aRecords = await resolver.resolve4(
+                        record.baseDomain || domain.baseDomain
+                    );
+                    logger.info(
+                        `A records for ${
+                            record.baseDomain || domain.baseDomain
+                        }:`,
+                        aRecords
+                    );
+
+                    // Check if the A record matches the expected value
+                    isValid = aRecords.includes(record.value);
+                } else {
+                    logger.warn(
+                        `Unsupported record type: ${record.recordType}`
+                    );
+                    continue;
+                }
+            } catch (error) {
+                isValid = false;
+                logger.debug(
+                    `Did not resolve ${record.recordType} record for ${
+                        record.baseDomain || domain.baseDomain
+                    }:`,
+                    error
+                );
+            }
+
+            // Update the individual record verification status. Runs for
+            // both a mismatched value and a failed/thrown DNS lookup, so a
+            // previously-verified record that stops resolving (e.g. NXDOMAIN
+            // after NS delegation is dropped) gets downgraded instead of
+            // leaving stale `verified: true` state behind.
+            if (isValid) {
+                await db
+                    .update(dnsRecords)
+                    .set({ verified: true })
+                    .where(eq(dnsRecords.id, record.id));
+                logger.info(
+                    `DNS record ${record.id} (${record.recordType}) for ${
+                        record.baseDomain || domain.baseDomain
+                    } verified successfully`
+                );
+            } else {
+                if (record.verified) {
+                    await db
+                        .update(dnsRecords)
+                        .set({ verified: false })
+                        .where(eq(dnsRecords.id, record.id));
+                }
+                logger.debug(
+                    `DNS record ${record.id} (${record.recordType}) for ${
+                        record.baseDomain || domain.baseDomain
+                    } does not match expected value: ${record.value}`
+                );
+            }
+        }
+
+        // --- Extra NS record check ---
+        // If we resolved NS records during this pass, verify that the live DNS
+        // has no nameservers beyond the ones we expect.  Individual records may
+        // already be marked verified above, but we must block full domain
+        // verification until the extra records are removed.
+        if (previousNs !== null && expectedNsValues.size > 0) {
+            const extraNsRecords = previousNs.filter(
+                (ns) => !expectedNsValues.has(ns)
+            );
+
+            if (extraNsRecords.length > 0) {
+                const errorMessage = `Extra NS records found that are not expected: ${extraNsRecords.join(", ")}. Remove these nameservers to complete domain verification.`;
+
+                await db
+                    .update(domains)
+                    .set({ errorMessage })
+                    .where(eq(domains.domainId, domain.domainId));
+
+                logger.warn(
+                    `Domain ${domain.baseDomain} has extra NS records that prevent verification: ${extraNsRecords.join(", ")}`
+                );
+
+                return false;
+            }
+
+            // No extras — clear any stale error that was previously written
+            await db
+                .update(domains)
+                .set({ errorMessage: null })
+                .where(eq(domains.domainId, domain.domainId));
+        }
+
+        // Check if all records are now verified
+        const updatedRecords: DnsRecord[] = await db
+            .select()
+            .from(dnsRecords)
+            .where(eq(dnsRecords.domainId, domain.domainId));
+
+        const allRecordsVerified = updatedRecords.every((r) => r.verified);
+
+        logger.info(
+            `Domain ${domain.baseDomain}: ${
+                updatedRecords.filter((r) => r.verified).length
+            }/${updatedRecords.length} records verified`
+        );
+
+        return allRecordsVerified;
+    }
+}
+
+export const dnsValidator = new DNSValidator();

server/private/lib/certificates/domain-reverifier.ts

@@ -0,0 +1,233 @@
+/*
+ * This file is part of a proprietary work.
+ *
+ * Copyright (c) 2025-2026 Fossorial, Inc.
+ * All rights reserved.
+ *
+ * This file is licensed under the Fossorial Commercial License.
+ * You may not use this file except in compliance with the License.
+ * Unauthorized use, copying, modification, or distribution is strictly prohibited.
+ *
+ * This file is not licensed under the AGPLv3.
+ */
+
+import { eq, and, or, isNull, lt } from "drizzle-orm";
+import * as dns from "dns/promises";
+import { DNS_VALIDATOR_MAX_TRIES } from "./dns-validator";
+import { db, domains, DnsRecord, dnsRecords, Domain } from "@server/db";
+import logger from "@server/logger";
+import { lockManager } from "../lock";
+import { privateConfig as config } from "#private/lib/config";
+
+// Module-level counter so successive domains in a batch round-robin across servers.
+let serverIndex = 0;
+
+export class DomainReverifier {
+    async reverifyAll(): Promise<void> {
+        const certConfig = config.getRawConfig().acme;
+        if (!certConfig) {
+            logger.debug(
+                "No certificate config — skipping domain reverification"
+            );
+            return;
+        }
+
+        const windowMs = certConfig.domain_reverification_window_ms;
+        const batchSize = certConfig.domain_reverification_batch_size;
+        const windowSecs = Math.floor(windowMs / 1000);
+        const cutoff = Math.floor(Date.now() / 1000) - windowSecs;
+
+        const domainsToCheck: Domain[] = await db
+            .select()
+            .from(domains)
+            .where(
+                and(
+                    eq(domains.verified, true),
+                    or(
+                        isNull(domains.lastCheckedAt),
+                        lt(domains.lastCheckedAt, cutoff)
+                    )
+                )
+            )
+            .limit(batchSize);
+
+        if (domainsToCheck.length === 0) {
+            logger.debug("No verified domains due for reverification");
+            return;
+        }
+
+        logger.info(`Reverifying ${domainsToCheck.length} domains`);
+
+        for (const domain of domainsToCheck) {
+            const lockKey = `dns-reverify:${domain.baseDomain}`;
+            const lockToken = await lockManager.acquireLock(lockKey);
+            if (!lockToken) {
+                logger.debug(
+                    `Could not acquire lock for domain reverification: ${domain.baseDomain}`
+                );
+                continue;
+            }
+
+            try {
+                await this.reverifyDomain(domain, certConfig.dns_resolvers);
+            } catch (err) {
+                logger.warn(
+                    `Unexpected error reverifying domain ${domain.baseDomain}:`,
+                    err
+                );
+                // Still stamp lastCheckedAt so we don't hammer a broken domain every run.
+                await db
+                    .update(domains)
+                    .set({ lastCheckedAt: Math.floor(Date.now() / 1000) })
+                    .where(eq(domains.domainId, domain.domainId));
+            } finally {
+                await lockManager.releaseLock(lockKey, lockToken);
+            }
+        }
+    }
+
+    private async reverifyDomain(
+        domain: Domain,
+        servers: string[]
+    ): Promise<void> {
+        if (!servers || servers.length === 0) {
+            throw new Error("No DNS resolvers configured");
+        }
+
+        // Round-robin across servers; advance the global counter so the next
+        // domain in the same batch gets a different server.
+        const dnsServer = servers[serverIndex % servers.length]!;
+        serverIndex++;
+
+        const resolver = new dns.Resolver();
+        resolver.setServers([dnsServer]);
+
+        logger.debug(
+            `Reverifying domain ${domain.baseDomain} using DNS server ${dnsServer}`
+        );
+
+        const records: DnsRecord[] = await db
+            .select()
+            .from(dnsRecords)
+            .where(eq(dnsRecords.domainId, domain.domainId));
+
+        if (records.length === 0) {
+            logger.warn(
+                `No DNS records found for domain ${domain.baseDomain} during reverification — marking failed`
+            );
+            await this.markFailed(
+                domain.domainId,
+                "No DNS records found during periodic reverification"
+            );
+            return;
+        }
+
+        const expectedNsValues = new Set<string>(
+            records.filter((r) => r.recordType === "NS").map((r) => r.value)
+        );
+
+        let allValid = true;
+        let errorMessage: string | null = null;
+        let resolvedNs: string[] | null = null;
+
+        for (const record of records) {
+            let isValid = false;
+
+            try {
+                if (record.recordType === "NS") {
+                    if (!resolvedNs) {
+                        resolvedNs = await resolver.resolveNs(
+                            record.baseDomain || domain.baseDomain
+                        );
+                    }
+                    isValid = resolvedNs.some((ns) => ns === record.value);
+                } else if (record.recordType === "CNAME") {
+                    const cnameRecords = await resolver.resolveCname(
+                        record.baseDomain || domain.baseDomain
+                    );
+                    isValid =
+                        cnameRecords.length === 1 &&
+                        cnameRecords[0] === record.value;
+                } else if (record.recordType === "TXT") {
+                    const txtRecords = await resolver.resolveTxt(
+                        record.baseDomain || domain.baseDomain
+                    );
+                    isValid = txtRecords.flat().includes(record.value);
+                } else if (record.recordType === "A") {
+                    const aRecords = await resolver.resolve4(
+                        record.baseDomain || domain.baseDomain
+                    );
+                    isValid = aRecords.includes(record.value);
+                } else {
+                    logger.warn(
+                        `Unsupported record type ${record.recordType} during reverification of ${domain.baseDomain}`
+                    );
+                    continue;
+                }
+            } catch (err) {
+                logger.debug(
+                    `DNS lookup failed for ${record.recordType} record on ${record.baseDomain || domain.baseDomain}:`,
+                    err
+                );
+                isValid = false;
+            }
+
+            if (!isValid) {
+                allValid = false;
+                errorMessage = `${record.recordType} record for ${record.baseDomain || domain.baseDomain} no longer resolves to expected value "${record.value}"`;
+                break;
+            }
+        }
+
+        // Check for extra NS records beyond what we expect.
+        if (allValid && resolvedNs !== null && expectedNsValues.size > 0) {
+            const extraNs = resolvedNs.filter(
+                (ns) => !expectedNsValues.has(ns)
+            );
+            if (extraNs.length > 0) {
+                allValid = false;
+                errorMessage = `Extra NS records found: ${extraNs.join(", ")}. Remove these nameservers.`;
+            }
+        }
+
+        const now = Math.floor(Date.now() / 1000);
+
+        if (allValid) {
+            await db
+                .update(domains)
+                .set({ lastCheckedAt: now, errorMessage: null })
+                .where(eq(domains.domainId, domain.domainId));
+            logger.debug(
+                `Domain ${domain.baseDomain} passed periodic reverification`
+            );
+        } else {
+            await this.markFailed(domain.domainId, errorMessage);
+            logger.warn(
+                `Domain ${domain.baseDomain} failed periodic reverification: ${errorMessage}`
+            );
+        }
+    }
+
+    private async markFailed(
+        domainId: string,
+        errorMessage: string | null
+    ): Promise<void> {
+        await db
+            .update(domains)
+            .set({
+                verified: false,
+                failed: true,
+                // Three below MAX_TRIES: keeps the domain out of the DNS
+                // validator's immediate retry loop, while still leaving it
+                // eligible (tries < MAX_TRIES) for a few more validation
+                // passes instead of being excluded forever once tries hits
+                // MAX_TRIES.
+                tries: DNS_VALIDATOR_MAX_TRIES - 3,
+                lastCheckedAt: Math.floor(Date.now() / 1000),
+                errorMessage
+            })
+            .where(eq(domains.domainId, domainId));
+    }
+}
+
+export const domainReverifier = new DomainReverifier();

server/private/lib/certificates/index.ts

@@ -0,0 +1,45 @@
+/*
+ * This file is part of a proprietary work.
+ *
+ * Copyright (c) 2025-2026 Fossorial, Inc.
+ * All rights reserved.
+ *
+ * This file is licensed under the Fossorial Commercial License.
+ * You may not use this file except in compliance with the License.
+ * Unauthorized use, copying, modification, or distribution is strictly prohibited.
+ *
+ * This file is not licensed under the AGPLv3.
+ */
+
+import logger from "@server/logger";
+import { privateConfig } from "#private/lib/config";
+import { acmeClientManager } from "./acme-client";
+import { jobScheduler } from "./scheduler";
+
+export async function startCertificateManager() {
+    const acmeConfig = privateConfig.getRawPrivateConfig().acme;
+    if (
+        acmeConfig &&
+        acmeConfig.cert_mode === "pangolin" &&
+        acmeConfig.enable_acme_client
+    ) {
+        logger.info("Starting certificate management server...");
+
+        // Initialize ACME client
+        await acmeClientManager.initialize();
+
+        // Start certificate issuance/renewal jobs
+        await jobScheduler.start();
+    }
+
+    if (privateConfig.getRawPrivateConfig().flags.use_pangolin_dns) {
+        // DNS record validation/reverification doesn't require certs, so it
+        // runs whenever Pangolin is acting as the authoritative DNS server,
+        // independent of the cert manager above.
+        await jobScheduler.startDnsJobs();
+    }
+}
+
+export async function stopCertificateManager() {
+    await jobScheduler.stop();
+}

server/private/lib/certificates/scheduler.ts

@@ -0,0 +1,197 @@
+/*
+ * This file is part of a proprietary work.
+ *
+ * Copyright (c) 2025-2026 Fossorial, Inc.
+ * All rights reserved.
+ *
+ * This file is licensed under the Fossorial Commercial License.
+ * You may not use this file except in compliance with the License.
+ * Unauthorized use, copying, modification, or distribution is strictly prohibited.
+ *
+ * This file is not licensed under the AGPLv3.
+ */
+
+import { withTimeout } from "@server/lib/retry";
+import logger from "@server/logger";
+import { certificateService } from "./certificate-service";
+import { privateConfig as config } from "#private/lib/config";
+import { dnsValidator } from "./dns-validator";
+import { domainReverifier } from "./domain-reverifier";
+import license from "#private/license/license";
+
+// Backstop for runExclusive: no single job's own internal timeouts (e.g.
+// certificate-service's per-cert issuance timeout) are relied on here. This
+// is the last line of defense - if *anything* inside a job hangs with no
+// error (a stalled Redis/DB call, a future code path that forgets to bound
+// itself, etc.), state.active must still reset so the next tick can run.
+// Without it, one hung run permanently skips every future tick for that job,
+// since runExclusive only clears state.active after the job promise settles.
+const RUN_EXCLUSIVE_TIMEOUT_MS = 30 * 60 * 1000;
+
+export class JobScheduler {
+    private certIntervals: NodeJS.Timeout[] = [];
+    private dnsIntervals: NodeJS.Timeout[] = [];
+    private certRunning = false;
+    private dnsRunning = false;
+
+    // Guards against a slow batch (e.g. 10 certs whose DNS challenges take a
+    // while) still being processed when the next interval tick fires -
+    // without this, overlapping ticks would each pull their own batch of up
+    // to 10 pending/renewal certs and process them concurrently instead of
+    // waiting for the prior batch to finish.
+    private runExclusive(
+        job: () => Promise<void>,
+        state: { active: boolean },
+        label: string
+    ): () => Promise<void> {
+        return async () => {
+            if (!(await license.isUnlocked())) {
+                logger.debug(
+                    `Skipping ${label} tick - license is not subscribed`
+                );
+                return;
+            }
+            if (state.active) {
+                logger.debug(
+                    `Skipping ${label} tick - previous run still in progress`
+                );
+                return;
+            }
+            state.active = true;
+            try {
+                await withTimeout(job(), RUN_EXCLUSIVE_TIMEOUT_MS, label);
+            } catch (error) {
+                logger.error(`Error in ${label}:`, error);
+            } finally {
+                state.active = false;
+            }
+        };
+    }
+
+    // Certificate issuance/renewal - requires an ACME client, so this is
+    // only started when Pangolin is actually managing certs.
+    async start(): Promise<void> {
+        if (this.certRunning) {
+            logger.warn("Certificate job scheduler is already running");
+            return;
+        }
+
+        this.certRunning = true;
+        logger.info("Starting certificate job scheduler");
+
+        const newCertState = { active: false };
+        const renewalState = { active: false };
+
+        const runNewCertCheck = this.runExclusive(
+            () => certificateService.processPendingCertificates(),
+            newCertState,
+            "processing pending certificates"
+        );
+        const runRenewalCheck = this.runExclusive(
+            () => certificateService.processRenewalCandidates(),
+            renewalState,
+            "processing renewal candidates"
+        );
+
+        // Schedule new certificate processing
+        const newCertInterval = setInterval(
+            runNewCertCheck,
+            config.getRawConfig().acme!.new_cert_check_interval_ms
+        );
+
+        // Schedule renewal processing (every 24 hours)
+        const renewalInterval = setInterval(
+            runRenewalCheck,
+            config.getRawConfig().acme!.renewal_check_interval_ms
+        );
+
+        this.certIntervals.push(newCertInterval, renewalInterval);
+
+        // Run initial checks
+        setTimeout(async () => {
+            try {
+                await runNewCertCheck();
+                // await runRenewalCheck();
+            } catch (error) {
+                logger.error("Error in initial certificate processing:", error);
+            }
+        }, 1000); // Wait 1 second after startup
+
+        logger.info("Certificate job scheduler started successfully");
+    }
+
+    // DNS record validation/reverification - doesn't touch certs at all, so
+    // this runs independently whenever Pangolin is acting as the
+    // authoritative DNS server, regardless of cert_mode.
+    async startDnsJobs(): Promise<void> {
+        if (this.dnsRunning) {
+            logger.warn("DNS validation job scheduler is already running");
+            return;
+        }
+
+        this.dnsRunning = true;
+        logger.info("Starting DNS validation job scheduler");
+
+        const dnsValidationState = { active: false };
+        const reverifyState = { active: false };
+
+        const runDnsValidation = this.runExclusive(
+            () => dnsValidator.validateAll(),
+            dnsValidationState,
+            "validating DNS records"
+        );
+        const runReverify = this.runExclusive(
+            () => domainReverifier.reverifyAll(),
+            reverifyState,
+            "reverifying domains"
+        );
+
+        // Schedule DNS validation
+        const dnsValidationInterval = setInterval(
+            runDnsValidation,
+            config.getRawConfig().acme?.dns_check_interval_ms ?? 60000
+        );
+
+        // Schedule periodic reverification of already-verified domains
+        const reverifyInterval = setInterval(
+            runReverify,
+            config.getRawConfig().acme?.domain_reverification_interval_ms ??
+                3600000
+        );
+
+        this.dnsIntervals.push(dnsValidationInterval, reverifyInterval);
+
+        // Run an initial validation pass shortly after startup
+        setTimeout(async () => {
+            try {
+                await runDnsValidation();
+            } catch (error) {
+                logger.error("Error in initial DNS validation:", error);
+            }
+        }, 1000);
+
+        logger.info("DNS validation job scheduler started successfully");
+    }
+
+    async stop(): Promise<void> {
+        if (this.certRunning) {
+            logger.info("Stopping certificate job scheduler");
+            this.certRunning = false;
+            this.certIntervals.forEach((interval) => clearInterval(interval));
+            this.certIntervals = [];
+        }
+
+        if (this.dnsRunning) {
+            logger.info("Stopping DNS validation job scheduler");
+            this.dnsRunning = false;
+            this.dnsIntervals.forEach((interval) => clearInterval(interval));
+            this.dnsIntervals = [];
+        }
+    }
+
+    isRunning(): boolean {
+        return this.certRunning || this.dnsRunning;
+    }
+}
+
+export const jobScheduler = new JobScheduler();

server/private/lib/config.ts

@@ -146,12 +146,20 @@ export class PrivateConfig {
             process.env.USE_PANGOLIN_DNS =
                 this.rawPrivateConfig.flags.use_pangolin_dns.toString();
         }
+
+        if (this.rawPrivateConfig.acme?.cert_mode) {
+            process.env.CERT_MODE = this.rawPrivateConfig.acme.cert_mode;
+        }
     }
 
     public getRawPrivateConfig() {
         return this.rawPrivateConfig;
     }
 
+    public getRawConfig() {
+        return this.getRawPrivateConfig();
+    }
+
     // `flags.enable_acme_cert_sync`, `flags.disable_private_http_placeholder`,
     // and `acme` used to live in the private config file. They now live in
     // the public config file. If an operator still has them set in the

server/private/lib/dns/generateDomains.ts

@@ -0,0 +1,47 @@
+/*
+ * This file is part of a proprietary work.
+ *
+ * Copyright (c) 2025-2026 Fossorial, Inc.
+ * All rights reserved.
+ *
+ * This file is licensed under the Fossorial Commercial License.
+ * You may not use this file except in compliance with the License.
+ * Unauthorized use, copying, modification, or distribution is strictly prohibited.
+ *
+ * This file is not licensed under the AGPLv3.
+ */
+
+import { build } from "@server/build";
+import privateConfig from "#private/lib/config";
+
+export function createCname(domainId: string, baseDomain: string) {
+    if (!privateConfig.getRawPrivateConfig().dns?.cname_extension) {
+        throw new Error("CNAME extension not configured");
+    }
+
+    let cnameRecords = [
+        {
+            value: `${domainId}.${privateConfig.getRawPrivateConfig().dns?.cname_extension}`,
+            baseDomain: baseDomain
+        },
+        {
+            value: `_acme-challenge.${domainId}.${privateConfig.getRawPrivateConfig().dns?.cname_extension}`,
+            baseDomain: `_acme-challenge.${baseDomain}`
+        }
+    ];
+
+    return cnameRecords;
+}
+
+export function createNs() {
+    if (!privateConfig.getRawPrivateConfig().dns?.nameserver_name) {
+        throw new Error("Nameservers not configured");
+    }
+
+    const nsRecords = [
+        privateConfig.getRawPrivateConfig().dns?.nameserver_name,
+        ...(privateConfig.getRawPrivateConfig().dns?.alternate_nameservers ||
+            [])
+    ] as string[];
+    return nsRecords;
+}

server/private/lib/dns/index.ts

@@ -0,0 +1,14 @@
+/*
+ * This file is part of a proprietary work.
+ *
+ * Copyright (c) 2025-2026 Fossorial, Inc.
+ * All rights reserved.
+ *
+ * This file is licensed under the Fossorial Commercial License.
+ * You may not use this file except in compliance with the License.
+ * Unauthorized use, copying, modification, or distribution is strictly prohibited.
+ *
+ * This file is not licensed under the AGPLv3.
+ */
+
+export * from "./server";

server/private/lib/exitNodes/exitNodeComms.ts

@@ -18,6 +18,7 @@ import { eq } from "drizzle-orm";
 import { sendToClient } from "#private/routers/ws";
 import privateConfig from "#private/lib/config";
 import config from "@server/lib/config";
+import { hasExitNodeCheckedIn } from "@server/lib/exitNodes";
 
 interface ExitNodeRequest {
     remoteType?: string;
@@ -138,13 +139,19 @@ export async function sendToExitNode(
 
             return response.data;
         } catch (error) {
-            if (axios.isAxiosError(error)) {
-                logger.error(
-                    `Error making ${method} request (can Pangolin see Gerbil HTTP API?) for exit node at ${hostname} (status: ${error.response?.status}): ${error.message}`
-                );
+            const message = axios.isAxiosError(error)
+                ? `Error making ${method} request (can Pangolin see Gerbil HTTP API?) for exit node at ${hostname} (status: ${error.response?.status}): ${error.message}`
+                : `Error making ${method} request for exit node at ${hostname}: ${error}`;
+
+            // The exit node (gerbil) may still be starting up and not yet
+            // reachable. Until it has checked in at least once, log this at a
+            // lower level since it's expected; once it has checked in, a
+            // connection failure is a real problem.
+            if (hasExitNodeCheckedIn(exitNode.exitNodeId)) {
+                logger.error(message);
             } else {
-                logger.error(
-                    `Error making ${method} request for exit node at ${hostname}: ${error}`
+                logger.warn(
+                    `${message} (exit node has not checked in yet since startup, this is expected briefly)`
                 );
             }
         }

server/private/lib/readConfigFile.ts

@@ -95,6 +95,70 @@ export const privateConfigSchema = z
                     .optional()
             })
             .optional(),
+        dns: z
+            .object({
+                enabled: z.boolean().optional().default(false),
+                listen_port: z.number().int().positive().optional().default(53),
+                nameserver_name: z.string(),
+                cname_extension: z.string(),
+                site_extension: z.string().optional(),
+                cname_alternate_extensions: z
+                    .array(z.string())
+                    .optional()
+                    .default([]),
+                alternate_nameservers: z
+                    .array(z.string())
+                    .optional()
+                    .default([]),
+                rate_limit: z
+                    .object({
+                        enabled: z.boolean().optional().default(true),
+                        window_ms: z
+                            .number()
+                            .int()
+                            .min(1000)
+                            .max(600000)
+                            .optional()
+                            .default(60000),
+                        max_requests: z
+                            .number()
+                            .int()
+                            .min(50)
+                            .max(100000)
+                            .optional()
+                            .default(1200),
+                        max_requests_per_query_type: z
+                            .number()
+                            .int()
+                            .min(10)
+                            .max(50000)
+                            .optional()
+                            .default(600)
+                    })
+                    .default({
+                        enabled: true,
+                        window_ms: 60000,
+                        max_requests: 1200,
+                        max_requests_per_query_type: 600
+                    }),
+                static_records: z
+                    .array(
+                        z.object({
+                            domain: z.string(),
+                            type: z.enum(["TXT", "CNAME", "A", "NS"]),
+                            value: z.string(),
+                            ttl: z
+                                .number()
+                                .int()
+                                .positive()
+                                .optional()
+                                .default(300)
+                        })
+                    )
+                    .optional()
+                    .default([])
+            })
+            .optional(),
         gerbil: z
             .object({
                 local_exit_node_reachable_at: z
@@ -125,15 +189,86 @@ export const privateConfigSchema = z
             })
             .optional()
             .prefault({}),
-        // @deprecated Moved to the public config file as `acme`
-        // (server/lib/readConfigFile.ts). Kept here only so existing private
-        // config files keep parsing; any value set here is migrated into the
-        // public config at startup by PrivateConfig (server/private/lib/config.ts).
         acme: z
             .object({
+                cert_mode: z
+                    .enum(["traefik", "pangolin"])
+                    .optional()
+                    .default("traefik"),
+                enable_acme_client: z.boolean().optional().default(false),
+                // @deprecated Moved to the public config file
+                // (server/lib/readConfigFile.ts). Kept here only so existing private
+                // config files keep parsing; any value set here is migrated into the
+                // public config at startup by PrivateConfig (server/private/lib/config.ts).
                 acme_json_path: z.string().optional(),
+                // @deprecated Moved to the public config file
+                // (server/lib/readConfigFile.ts). Kept here only so existing private
+                // config files keep parsing; any value set here is migrated into the
+                // public config at startup by PrivateConfig (server/private/lib/config.ts).
                 acme_http_endpoint: z.string().optional(),
-                sync_interval_ms: z.number().optional()
+                // @deprecated Moved to the public config file
+                // (server/lib/readConfigFile.ts). Kept here only so existing private
+                // config files keep parsing; any value set here is migrated into the
+                // public config at startup by PrivateConfig (server/private/lib/config.ts).
+                sync_interval_ms: z.number().optional(),
+                acme_directory_url: z
+                    .string()
+                    .url()
+                    .default("https://acme-v02.api.letsencrypt.org/directory"),
+                contact_email: z.string().email(),
+                acme_account_key_path: z
+                    .string()
+                    .default("./config/account.key"),
+                challenge_ttl_ms: z.number().int().positive().default(300000),
+                renewal_check_interval_ms: z
+                    .number()
+                    .int()
+                    .positive()
+                    .default(3600000),
+                new_cert_check_interval_ms: z
+                    .number()
+                    .int()
+                    .positive()
+                    .default(5000),
+                // Kept safely under Let's Encrypt's ~20 req/s limit since this
+                // budget is shared across all pops workers and only covers the
+                // request-issuing calls we make directly (not every request
+                // acme-client makes internally, e.g. while polling for
+                // challenge/order status).
+                acme_requests_per_second: z
+                    .number()
+                    .int()
+                    .positive()
+                    .default(15),
+                dns_check_interval_ms: z
+                    .number()
+                    .int()
+                    .positive()
+                    .default(60000),
+                domain_reverification_interval_ms: z
+                    .number()
+                    .int()
+                    .positive()
+                    .default(3600000), // 1 hour — how often to run the reverification pass
+                domain_reverification_window_ms: z
+                    .number()
+                    .int()
+                    .positive()
+                    .default(259200000), // 72 hours — how old checkedAt must be before rechecking
+                domain_reverification_batch_size: z
+                    .number()
+                    .int()
+                    .positive()
+                    .default(20), // max domains to recheck per pass
+                dns_resolvers: z
+                    .array(z.string())
+                    .optional()
+                    .default([
+                        "8.8.8.8",
+                        "1.1.1.1",
+                        "9.9.9.9",
+                        "208.67.222.222"
+                    ])
             })
             .optional(),
         branding: z

server/private/lib/traefik/getTraefikConfig.ts

@@ -396,7 +396,7 @@ export async function getTraefikConfig(
         );
 
     let validCerts: CertificateResult[] = [];
-    if (privateConfig.getRawPrivateConfig().flags.use_pangolin_dns) {
+    if (privateConfig.getRawPrivateConfig().acme?.cert_mode == "pangolin") {
         // create a list of all domains to get certs for
         const domains = new Set<string>();
         for (const resource of resourcesMap.values()) {
@@ -522,7 +522,10 @@ export async function getTraefikConfig(
             );
 
             let tls = {};
-            if (!privateConfig.getRawPrivateConfig().flags.use_pangolin_dns) {
+            if (
+                privateConfig.getRawPrivateConfig().acme?.cert_mode !=
+                "pangolin"
+            ) {
                 tls = buildWildcardTls({
                     fullDomain,
                     hasSubdomain: !!resource.subdomain,
@@ -789,7 +792,8 @@ export async function getTraefikConfig(
                 preferWildcardCert
             }) => {
                 if (
-                    !privateConfig.getRawPrivateConfig().flags.use_pangolin_dns
+                    privateConfig.getRawPrivateConfig().acme?.cert_mode !=
+                    "pangolin"
                 ) {
                     return buildWildcardTls({
                         fullDomain,
@@ -832,7 +836,8 @@ export async function getTraefikConfig(
             redirectHttpsMiddlewareName,
             resolveTls: (fullDomain) => {
                 if (
-                    !privateConfig.getRawPrivateConfig().flags.use_pangolin_dns
+                    privateConfig.getRawPrivateConfig().acme?.cert_mode !=
+                    "pangolin"
                 ) {
                     // siteResource aliases don't have a per-domain cert
                     // resolver stored, so always fall back to the global
@@ -924,7 +929,10 @@ export async function getTraefikConfig(
             const rule = buildHostRule(fullDomain, ir.wildcard);
 
             let tls: any = {};
-            if (!privateConfig.getRawPrivateConfig().flags.use_pangolin_dns) {
+            if (
+                privateConfig.getRawPrivateConfig().acme?.cert_mode !=
+                "pangolin"
+            ) {
                 tls = buildWildcardTls({
                     fullDomain,
                     hasSubdomain: !!ir.subdomain,
@@ -1005,7 +1013,8 @@ export async function getTraefikConfig(
 
                 let tls: any = {};
                 if (
-                    !privateConfig.getRawPrivateConfig().flags.use_pangolin_dns
+                    privateConfig.getRawPrivateConfig().acme?.cert_mode !=
+                    "pangolin"
                 ) {
                     // siteResource aliases don't have a per-domain cert
                     // resolver stored, so always fall back to the global
@@ -1080,7 +1089,7 @@ export async function getTraefikConfig(
             .where(eq(exitNodes.exitNodeId, exitNodeId));
 
         let validCertsLoginPages: CertificateResult[] = [];
-        if (privateConfig.getRawPrivateConfig().flags.use_pangolin_dns) {
+        if (privateConfig.getRawPrivateConfig().acme?.cert_mode == "pangolin") {
             // create a list of all domains to get certs for
             const domains = new Set<string>();
             for (const lp of exitNodeLoginPages) {
@@ -1126,7 +1135,8 @@ export async function getTraefikConfig(
 
                 const tls = {};
                 if (
-                    !privateConfig.getRawPrivateConfig().flags.use_pangolin_dns
+                    privateConfig.getRawPrivateConfig().acme?.cert_mode !=
+                    "pangolin"
                 ) {
                     // TODO: we need to add the wildcard logic here too
                 } else {

server/private/routers/alertRule/testAlertRule.ts

@@ -14,7 +14,7 @@
 import { getRandomItemInArray } from "@app/lib/getRandomItemInArray";
 import response from "@server/lib/response";
 import logger from "@server/logger";
-import { processTestAlerts } from "@server/private/lib/alerts/processTestAlerts";
+import { processTestAlerts } from "#private/lib/alerts/processTestAlerts";
 import { type AlertAction } from "@server/routers/alertRule/types";
 import HttpCode from "@server/types/HttpCode";
 import { NextFunction, Request, Response } from "express";

server/private/routers/alertRule/updateAlertRule.ts

@@ -33,8 +33,11 @@ import { OpenAPITags, registry } from "@server/openApi";
 import { and, eq } from "drizzle-orm";
 import { encrypt } from "@server/lib/crypto";
 import config from "@server/lib/config";
-import { HC_EVENT_TYPES, SITE_EVENT_TYPES, RESOURCE_EVENT_TYPES } from "./createAlertRule";
-import { invalidateAllRemoteExitNodeSessions } from "@server/private/auth/sessions/remoteExitNode";
+import {
+    HC_EVENT_TYPES,
+    SITE_EVENT_TYPES,
+    RESOURCE_EVENT_TYPES
+} from "./createAlertRule";
 
 const paramsSchema = z
     .object({
@@ -85,35 +88,57 @@ const bodySchema = z
         const isHcEvent = (HC_EVENT_TYPES as readonly string[]).includes(
             val.eventType
         );
-        const isResourceEvent = (RESOURCE_EVENT_TYPES as readonly string[]).includes(
-            val.eventType
-        );
+        const isResourceEvent = (
+            RESOURCE_EVENT_TYPES as readonly string[]
+        ).includes(val.eventType);
 
-        if (isSiteEvent && val.siteIds !== undefined && val.siteIds.length === 0 && !val.allSites) {
+        if (
+            isSiteEvent &&
+            val.siteIds !== undefined &&
+            val.siteIds.length === 0 &&
+            !val.allSites
+        ) {
             ctx.addIssue({
                 code: z.ZodIssueCode.custom,
-                message: "At least one siteId is required for site event types when allSites is false",
+                message:
+                    "At least one siteId is required for site event types when allSites is false",
                 path: ["siteIds"]
             });
         }
 
-        if (isHcEvent && val.healthCheckIds !== undefined && val.healthCheckIds.length === 0 && !val.allHealthChecks) {
+        if (
+            isHcEvent &&
+            val.healthCheckIds !== undefined &&
+            val.healthCheckIds.length === 0 &&
+            !val.allHealthChecks
+        ) {
             ctx.addIssue({
                 code: z.ZodIssueCode.custom,
-                message: "At least one healthCheckId is required for health check event types when allHealthChecks is false",
+                message:
+                    "At least one healthCheckId is required for health check event types when allHealthChecks is false",
                 path: ["healthCheckIds"]
             });
         }
 
-        if (isResourceEvent && val.resourceIds !== undefined && val.resourceIds.length === 0 && !val.allResources) {
+        if (
+            isResourceEvent &&
+            val.resourceIds !== undefined &&
+            val.resourceIds.length === 0 &&
+            !val.allResources
+        ) {
             ctx.addIssue({
                 code: z.ZodIssueCode.custom,
-                message: "At least one resourceId is required for resource event types when allResources is false",
+                message:
+                    "At least one resourceId is required for resource event types when allResources is false",
                 path: ["resourceIds"]
             });
         }
 
-        if (isSiteEvent && val.healthCheckIds !== undefined && val.healthCheckIds.length > 0) {
+        if (
+            isSiteEvent &&
+            val.healthCheckIds !== undefined &&
+            val.healthCheckIds.length > 0
+        ) {
             ctx.addIssue({
                 code: z.ZodIssueCode.custom,
                 message: "healthCheckIds must not be set for site event types",
@@ -129,7 +154,11 @@ const bodySchema = z
             });
         }
 
-        if (isResourceEvent && val.siteIds !== undefined && val.siteIds.length > 0) {
+        if (
+            isResourceEvent &&
+            val.siteIds !== undefined &&
+            val.siteIds.length > 0
+        ) {
             ctx.addIssue({
                 code: z.ZodIssueCode.custom,
                 message: "siteIds must not be set for resource event types",
@@ -137,10 +166,15 @@ const bodySchema = z
             });
         }
 
-        if (isResourceEvent && val.healthCheckIds !== undefined && val.healthCheckIds.length > 0) {
+        if (
+            isResourceEvent &&
+            val.healthCheckIds !== undefined &&
+            val.healthCheckIds.length > 0
+        ) {
             ctx.addIssue({
                 code: z.ZodIssueCode.custom,
-                message: "healthCheckIds must not be set for resource event types",
+                message:
+                    "healthCheckIds must not be set for resource event types",
                 path: ["healthCheckIds"]
             });
         }
@@ -153,7 +187,6 @@ const UpdateAlertRuleResponseDataSchema = z.object({
     alertRuleId: z.number()
 });
 
-
 registry.registerPath({
     method: "post",
     path: "/org/{orgId}/alert-rule/{alertRuleId}",
@@ -174,7 +207,9 @@ registry.registerPath({
             description: "Successful response",
             content: {
                 "application/json": {
-                    schema: createApiResponseSchema(UpdateAlertRuleResponseDataSchema)
+                    schema: createApiResponseSchema(
+                        UpdateAlertRuleResponseDataSchema
+                    )
                 }
             }
         }
@@ -250,9 +285,11 @@ export async function updateAlertRule(
         if (name !== undefined) updateData.name = name;
         if (eventType !== undefined) updateData.eventType = eventType;
         if (enabled !== undefined) updateData.enabled = enabled;
-        if (cooldownSeconds !== undefined) updateData.cooldownSeconds = cooldownSeconds;
+        if (cooldownSeconds !== undefined)
+            updateData.cooldownSeconds = cooldownSeconds;
         if (allSites !== undefined) updateData.allSites = allSites;
-        if (allHealthChecks !== undefined) updateData.allHealthChecks = allHealthChecks;
+        if (allHealthChecks !== undefined)
+            updateData.allHealthChecks = allHealthChecks;
         if (allResources !== undefined) updateData.allResources = allResources;
 
         await db
@@ -273,7 +310,11 @@ export async function updateAlertRule(
 
             // Only insert junction rows when allSites is not true
             const effectiveAllSites = allSites ?? false;
-            if (!effectiveAllSites && siteIds !== undefined && siteIds.length > 0) {
+            if (
+                !effectiveAllSites &&
+                siteIds !== undefined &&
+                siteIds.length > 0
+            ) {
                 await db.insert(alertSites).values(
                     siteIds.map((siteId) => ({
                         alertRuleId,
@@ -290,7 +331,11 @@ export async function updateAlertRule(
                 .where(eq(alertHealthChecks.alertRuleId, alertRuleId));
 
             const effectiveAllHealthChecks = allHealthChecks ?? false;
-            if (!effectiveAllHealthChecks && healthCheckIds !== undefined && healthCheckIds.length > 0) {
+            if (
+                !effectiveAllHealthChecks &&
+                healthCheckIds !== undefined &&
+                healthCheckIds.length > 0
+            ) {
                 await db.insert(alertHealthChecks).values(
                     healthCheckIds.map((healthCheckId) => ({
                         alertRuleId,
@@ -307,7 +352,11 @@ export async function updateAlertRule(
                 .where(eq(alertResources.alertRuleId, alertRuleId));
 
             const effectiveAllResources = allResources ?? false;
-            if (!effectiveAllResources && resourceIds !== undefined && resourceIds.length > 0) {
+            if (
+                !effectiveAllResources &&
+                resourceIds !== undefined &&
+                resourceIds.length > 0
+            ) {
                 await db.insert(alertResources).values(
                     resourceIds.map((resourceId) => ({
                         alertRuleId,
@@ -392,7 +441,10 @@ export async function updateAlertRule(
                     webhookActions.map((wa) => ({
                         alertRuleId,
                         webhookUrl: wa.webhookUrl,
-                        config: wa.config != null ? encrypt(wa.config, serverSecret) : null,
+                        config:
+                            wa.config != null
+                                ? encrypt(wa.config, serverSecret)
+                                : null,
                         enabled: wa.enabled
                     }))
                 );

server/private/routers/generatedLicense/clearInstanceName.ts

@@ -31,7 +31,9 @@ export async function clearInstanceName(
     next: NextFunction
 ): Promise<any> {
     try {
-        const parsedParams = clearInstanceNameParamsSchema.safeParse(req.params);
+        const parsedParams = clearInstanceNameParamsSchema.safeParse(
+            req.params
+        );
         if (!parsedParams.success) {
             return next(
                 createHttpError(
@@ -63,7 +65,8 @@ export async function clearInstanceName(
             return next(
                 createHttpError(
                     data.status || HttpCode.BAD_REQUEST,
-                    data.message || "Failed to clear instance name from Fossorial API"
+                    data.message ||
+                        "Failed to clear server ID from Fossorial API"
                 )
             );
         }
@@ -72,7 +75,7 @@ export async function clearInstanceName(
             data: null,
             success: true,
             error: false,
-            message: "Instance name cleared successfully",
+            message: "Server ID cleared successfully",
             status: HttpCode.OK
         });
     } catch (error) {
@@ -80,8 +83,8 @@ export async function clearInstanceName(
         return next(
             createHttpError(
                 HttpCode.INTERNAL_SERVER_ERROR,
-                "An error occurred while clearing the instance name."
+                "An error occurred while clearing the server ID."
             )
         );
     }
-}
+}

server/private/routers/hybrid.ts

@@ -2478,7 +2478,12 @@ hybridRouter.post(
                 destinations: destinations
             });
         } catch (error) {
-            logger.error(error);
+            if (!(
+                error instanceof Error &&
+                error.message === "Exit node not allowed"
+            )) {
+                logger.error(error);
+            }
             return next(
                 createHttpError(
                     HttpCode.INTERNAL_SERVER_ERROR,

server/private/routers/remoteExitNode/exitNodeEvents.ts

@@ -0,0 +1,23 @@
+/*
+ * This file is part of a proprietary work.
+ *
+ * Copyright (c) 2025-2026 Fossorial, Inc.
+ * All rights reserved.
+ *
+ * This file is licensed under the Fossorial Commercial License.
+ * You may not use this file except in compliance with the License.
+ * Unauthorized use, copying, modification, or distribution is strictly prohibited.
+ *
+ * This file is not licensed under the AGPLv3.
+ */
+
+import { EventEmitter } from "events";
+
+export interface ExitNodeOnlineEvent {
+    exitNodeId: number;
+    endpoint: string;
+}
+
+export const EXIT_NODE_ONLINE_EVENT = "exit-node-online";
+
+export const exitNodeEvents = new EventEmitter();

server/private/routers/remoteExitNode/exitNodeReconnectScheduler.ts

@@ -12,11 +12,27 @@
  */
 
 import axios from "axios";
-import { db, exitNodes, newts, sites } from "@server/db";
+import { db, newts, sites } from "@server/db";
 import { eq } from "drizzle-orm";
 import logger from "@server/logger";
 import redisManager from "#private/lib/redis";
-// import { sendToClient } from "#private/routers/ws";
+import { sendToClient } from "../ws";
+import {
+    exitNodeEvents,
+    EXIT_NODE_ONLINE_EVENT,
+    ExitNodeOnlineEvent
+} from "./exitNodeEvents";
+
+exitNodeEvents.on(
+    EXIT_NODE_ONLINE_EVENT,
+    ({ exitNodeId, endpoint }: ExitNodeOnlineEvent) => {
+        scheduleExitNodeReconnect(exitNodeId, endpoint).catch((error) => {
+            logger.error("Failed to schedule exit node reconnect", {
+                error
+            });
+        });
+    }
+);
 
 const INITIAL_DELAY_MS = 15 * 1000; // 15 seconds before first check
 const CHECK_INTERVAL_MS = 10 * 1000; // Check every 10 seconds
@@ -26,7 +42,7 @@ const REDIS_HASH_PREFIX = "exit-node-reconnect:";
 
 interface PendingReconnect {
     startTime: number;
-    reachableAt: string;
+    endpoint: string;
 }
 
 // In-memory tracking for this node
@@ -40,15 +56,15 @@ let schedulerInterval: NodeJS.Timeout | null = null;
  */
 export async function scheduleExitNodeReconnect(
     exitNodeId: number,
-    reachableAt: string
+    endpoint: string
 ): Promise<void> {
     logger.info(
-        `Scheduling newt reconnect for exit node ${exitNodeId} (reachableAt: ${reachableAt})`
+        `Scheduling newt reconnect for exit node ${exitNodeId} (endpoint: ${endpoint})`
     );
 
     const entry: PendingReconnect = {
         startTime: Date.now(),
-        reachableAt
+        endpoint
     };
 
     pendingReconnects.set(exitNodeId, entry);
@@ -63,8 +79,8 @@ export async function scheduleExitNodeReconnect(
         );
         await redisManager.hset(
             `${REDIS_HASH_PREFIX}${exitNodeId}`,
-            "reachableAt",
-            reachableAt
+            "endpoint",
+            endpoint
         );
     }
 }
@@ -101,14 +117,14 @@ async function processPendingReconnects(): Promise<void> {
                     `${REDIS_HASH_PREFIX}${id}`,
                     "startTime"
                 );
-                const reachableAt = await redisManager.hget(
+                const endpoint = await redisManager.hget(
                     `${REDIS_HASH_PREFIX}${id}`,
-                    "reachableAt"
+                    "endpoint"
                 );
-                if (startTimeStr && reachableAt) {
+                if (startTimeStr && endpoint) {
                     toProcess.set(id, {
                         startTime: parseInt(startTimeStr, 10),
-                        reachableAt
+                        endpoint
                     });
                 }
             }
@@ -135,7 +151,7 @@ async function processPendingReconnects(): Promise<void> {
         }
 
         // Check if the exit node HTTP endpoint is reachable
-        const pingUrl = `${entry.reachableAt}/ping`;
+        const pingUrl = `http://${entry.endpoint}/ping`;
         try {
             await axios.get(pingUrl, { timeout: 5000 });
         } catch {
@@ -150,47 +166,47 @@ async function processPendingReconnects(): Promise<void> {
             `Exit node ${exitNodeId} is reachable. Sending newt/wg/reconnect to connected newts.`
         );
 
-        // await sendReconnectToNewts(exitNodeId);
+        await sendReconnectToNewts(exitNodeId);
         await removePending(exitNodeId);
     }
 }
 
-// async function sendReconnectToNewts(exitNodeId: number): Promise<void> {
-// try {
-//         const connectedNewts = await db
-//             .select({ newtId: newts.newtId })
-//             .from(newts)
-//             .innerJoin(sites, eq(newts.siteId, sites.siteId))
-//             .where(eq(sites.exitNodeId, exitNodeId));
+async function sendReconnectToNewts(exitNodeId: number): Promise<void> {
+    try {
+        const connectedNewts = await db
+            .select({ newtId: newts.newtId })
+            .from(newts)
+            .innerJoin(sites, eq(newts.siteId, sites.siteId))
+            .where(eq(sites.exitNodeId, exitNodeId));
 
-//         if (connectedNewts.length === 0) {
-//             logger.debug(
-//                 `No newts found for exit node ${exitNodeId}, nothing to reconnect`
-//             );
-//             return;
-//         }
+        if (connectedNewts.length === 0) {
+            logger.debug(
+                `No newts found for exit node ${exitNodeId}, nothing to reconnect`
+            );
+            return;
+        }
 
-//         logger.info(
-//             `Sending newt/wg/reconnect to ${connectedNewts.length} newt(s) for exit node ${exitNodeId}`
-//         );
+        logger.info(
+            `Sending newt/wg/reconnect to ${connectedNewts.length} newt(s) for exit node ${exitNodeId}`
+        );
 
-//         const reconnectMessage = {
-//             type: "newt/wg/reconnect",
-//             data: {}
-//         };
+        const reconnectMessage = {
+            type: "newt/wg/reconnect",
+            data: {}
+        };
 
-//         await Promise.allSettled(
-//             connectedNewts.map(({ newtId }) =>
-//                 sendToClient(newtId, reconnectMessage)
-//             )
-//         );
-//     } catch (error) {
-//         logger.error(
-//             `Failed to send reconnect messages for exit node ${exitNodeId}`,
-//             { error }
-//         );
-//     }
-// }
+        await Promise.allSettled(
+            connectedNewts.map(({ newtId }) =>
+                sendToClient(newtId, reconnectMessage)
+            )
+        );
+    } catch (error) {
+        logger.error(
+            `Failed to send reconnect messages for exit node ${exitNodeId}`,
+            { error }
+        );
+    }
+}
 
 async function removePending(exitNodeId: number): Promise<void> {
     pendingReconnects.delete(exitNodeId);

server/private/routers/remoteExitNode/getRemoteExitNodeToken.ts

@@ -26,7 +26,7 @@ import {
     validateRemoteExitNodeSessionToken,
     EXPIRES
 } from "#private/auth/sessions/remoteExitNode";
-import { getOrCreateCachedToken } from "@server/private/lib/tokenCache";
+import { getOrCreateCachedToken } from "#private/lib/tokenCache";
 import { verifyPassword } from "@server/auth/password";
 import logger from "@server/logger";
 import config from "@server/lib/config";

server/private/routers/remoteExitNode/handleRemoteExitNodePingMessage.ts

@@ -16,7 +16,7 @@ import { MessageHandler } from "@server/routers/ws";
 import { RemoteExitNode } from "@server/db";
 import { eq } from "drizzle-orm";
 import logger from "@server/logger";
-import { scheduleExitNodeReconnect } from "./exitNodeReconnectScheduler";
+import { exitNodeEvents, EXIT_NODE_ONLINE_EVENT } from "./exitNodeEvents";
 
 /**
  * Handles ping messages from clients and responds with pong
@@ -40,7 +40,7 @@ export const handleRemoteExitNodePingMessage: MessageHandler = async (
     try {
         // Fetch the current state before updating so we can detect the offline→online transition
         const [currentExitNode] = await db
-            .select({ online: exitNodes.online, reachableAt: exitNodes.reachableAt })
+            .select({ online: exitNodes.online, endpoint: exitNodes.endpoint })
             .from(exitNodes)
             .where(eq(exitNodes.exitNodeId, remoteExitNode.exitNodeId))
             .limit(1);
@@ -55,12 +55,14 @@ export const handleRemoteExitNodePingMessage: MessageHandler = async (
             .where(eq(exitNodes.exitNodeId, remoteExitNode.exitNodeId));
 
         // If the exit node was offline and is now coming online, schedule newt reconnects
-        if (currentExitNode && !currentExitNode.online && currentExitNode.reachableAt) {
-            scheduleExitNodeReconnect(
-                remoteExitNode.exitNodeId,
-                currentExitNode.reachableAt
-            ).catch((error) => {
-                logger.error("Failed to schedule exit node reconnect", { error });
+        if (
+            currentExitNode &&
+            !currentExitNode.online &&
+            currentExitNode.endpoint
+        ) {
+            exitNodeEvents.emit(EXIT_NODE_ONLINE_EVENT, {
+                exitNodeId: remoteExitNode.exitNodeId,
+                endpoint: currentExitNode.endpoint
             });
         }
     } catch (error) {

server/routers/domain/createOrgDomain.ts

@@ -21,6 +21,7 @@ import { LimitId } from "@server/lib/billing";
 import { isSecondLevelDomain, isValidDomain } from "@server/lib/validators";
 import { build } from "@server/build";
 import config from "@server/lib/config";
+import { createNs, createCname } from "#dynamic/lib/dns/generateDomains";
 
 const paramsSchema = z.strictObject({
     orgId: z.string()
@@ -283,8 +284,7 @@ export async function createOrgDomain(
 
             // TODO: This needs to be cross region and not hardcoded
             if (type === "ns") {
-                nsRecords = config.getRawConfig().dns.nameservers as string[];
-
+                nsRecords = createNs();
                 // Save NS records to database
                 for (const nsValue of nsRecords) {
                     recordsToInsert.push({
@@ -296,16 +296,7 @@ export async function createOrgDomain(
                     });
                 }
             } else if (type === "cname") {
-                cnameRecords = [
-                    {
-                        value: `${domainId}.${config.getRawConfig().dns.cname_extension}`,
-                        baseDomain: baseDomain
-                    },
-                    {
-                        value: `_acme-challenge.${domainId}.${config.getRawConfig().dns.cname_extension}`,
-                        baseDomain: `_acme-challenge.${baseDomain}`
-                    }
-                ];
+                cnameRecords = createCname(domainId, baseDomain);
 
                 // Save CNAME records to database
                 for (const cnameRecord of cnameRecords) {

server/routers/gerbil/getConfig.ts

@@ -10,6 +10,7 @@ import config from "@server/lib/config";
 import { fromError } from "zod-validation-error";
 import { getAllowedIps } from "../target/helpers";
 import { createExitNode } from "#dynamic/routers/gerbil/createExitNode";
+import { markExitNodeCheckedIn } from "@server/lib/exitNodes";
 
 // Define Zod schema for request validation
 const getConfigSchema = z.object({
@@ -65,6 +66,8 @@ export async function getConfig(
             );
         }
 
+        markExitNodeCheckedIn(exitNode.exitNodeId);
+
         const configResponse = await generateGerbilConfig(exitNode);
 
         logger.debug("Sending config: ", configResponse);

server/routers/newt/handleRequestLogMessage.ts

@@ -1,16 +1,3 @@
-/*
- * This file is part of a proprietary work.
- *
- * Copyright (c) 2025-2026 Fossorial, Inc.
- * All rights reserved.
- *
- * This file is licensed under the Fossorial Commercial License.
- * You may not use this file except in compliance with the License.
- * Unauthorized use, copying, modification, or distribution is strictly prohibited.
- *
- * This file is not licensed under the AGPLv3.
- */
-
 import { db } from "@server/db";
 import { MessageHandler } from "@server/routers/ws";
 import { sites, Newt, orgs, clients, clientSitesAssociationsCache, users } from "@server/db";

server/routers/olm/handleOlmServerInitAddPeerHandshake.ts

@@ -85,7 +85,7 @@ export const handleOlmServerInitAddPeerHandshake: MessageHandler = async (
             );
 
         if (!resources || resources.length === 0) {
-            logger.error(
+            logger.warn(
                 `handleOlmServerInitAddPeerHandshake: Resource not found`
             );
             await sendCancel();
@@ -94,7 +94,7 @@ export const handleOlmServerInitAddPeerHandshake: MessageHandler = async (
 
         if (resources.length > 1) {
             // error but this should not happen because the nice id cant contain a dot and the alias has to have a dot and both have to be unique within the org so there should never be multiple matches
-            logger.error(
+            logger.warn(
                 `handleOlmServerInitAddPeerHandshake: Multiple resources found matching the criteria`
             );
             return;
@@ -119,7 +119,7 @@ export const handleOlmServerInitAddPeerHandshake: MessageHandler = async (
             );
 
         if (currentResourceAssociationCaches.length === 0) {
-            logger.error(
+            logger.warn(
                 `handleOlmServerInitAddPeerHandshake: Client ${client.clientId} does not have access to resource ${resource.siteResourceId}`
             );
             await sendCancel();
@@ -127,7 +127,7 @@ export const handleOlmServerInitAddPeerHandshake: MessageHandler = async (
         }
 
         if (!resource.networkId) {
-            logger.error(
+            logger.warn(
                 `handleOlmServerInitAddPeerHandshake: Resource ${resource.siteResourceId} has no network`
             );
             await sendCancel();
@@ -141,7 +141,7 @@ export const handleOlmServerInitAddPeerHandshake: MessageHandler = async (
             .where(eq(siteNetworks.networkId, resource.networkId));
 
         if (!siteRows || siteRows.length === 0) {
-            logger.error(
+            logger.warn(
                 `handleOlmServerInitAddPeerHandshake: No sites found for resource ${resource.siteResourceId}`
             );
             await sendCancel();
@@ -164,9 +164,7 @@ export const handleOlmServerInitAddPeerHandshake: MessageHandler = async (
     }
 
     if (sitesToProcess.length === 0) {
-        logger.error(
-            `handleOlmServerInitAddPeerHandshake: No sites to process`
-        );
+        logger.warn(`handleOlmServerInitAddPeerHandshake: No sites to process`);
         await sendCancel();
         return;
     }
@@ -193,7 +191,7 @@ export const handleOlmServerInitAddPeerHandshake: MessageHandler = async (
         }
 
         if (!site.exitNodeId) {
-            logger.error(
+            logger.warn(
                 `handleOlmServerInitAddPeerHandshake: Site ${site.siteId} has no exit node, skipping`
             );
             continue;
@@ -205,7 +203,7 @@ export const handleOlmServerInitAddPeerHandshake: MessageHandler = async (
             .where(eq(exitNodes.exitNodeId, site.exitNodeId));
 
         if (!exitNode) {
-            logger.error(
+            logger.warn(
                 `handleOlmServerInitAddPeerHandshake: Exit node not found for site ${site.siteId}, skipping`
             );
             continue;
@@ -229,7 +227,7 @@ export const handleOlmServerInitAddPeerHandshake: MessageHandler = async (
     }
 
     if (!handshakeInitiated) {
-        logger.error(
+        logger.warn(
             `handleOlmServerInitAddPeerHandshake: No accessible sites with valid exit nodes found, cancelling chain`
         );
         await sendCancel();

src/app/[orgId]/layout.tsx

@@ -104,7 +104,7 @@ export default async function OrgLayout(props: {
             subscriptionStatus = subRes.data.data;
         } catch (error) {
             // If subscription fetch fails, keep subscriptionStatus as null
-            console.error("Failed to fetch subscription status:", error);
+            // console.error("Failed to fetch subscription status:", error);
         }
     }
 

src/components/GenerateLicenseKeysTable.tsx

@@ -78,13 +78,16 @@ export default function GenerateLicenseKeysTable({
             );
             toast({
                 title: t("success"),
-                description: "Instance name cleared successfully"
+                description: "Server ID cleared successfully"
             });
             await refreshData();
         } catch (error) {
             toast({
                 title: t("error"),
-                description: formatAxiosError(error, "Failed to clear instance name"),
+                description: formatAxiosError(
+                    error,
+                    "Failed to clear server ID"
+                ),
                 variant: "destructive"
             });
         } finally {
@@ -291,7 +294,7 @@ export default function GenerateLicenseKeysTable({
                                         clearInstanceName(key.licenseKey)
                                     }
                                 >
-                                    Clear Instance Name
+                                    {t("clearInstanceName")}
                                 </DropdownMenuItem>
                             </DropdownMenuContent>
                         </DropdownMenu>

src/lib/pullEnv.ts

@@ -1,3 +1,4 @@
+import { build } from "@server/build";
 import { Env } from "./types/env";
 
 export function pullEnv(): Env {
@@ -34,9 +35,7 @@ export function pullEnv(): Env {
                         : false
             },
             identityProviderMode: process.env.IDENTITY_PROVIDER_MODE as
-                | "org"
-                | "global"
-                | undefined
+                "org" | "global" | undefined
         },
         email: {
             emailEnabled: process.env.EMAIL_ENABLED === "true" ? true : false

tsconfig.enterprise.json

@@ -14,7 +14,7 @@
         "moduleResolution": "bundler",
         "resolveJsonModule": true,
         "isolatedModules": true,
-        "jsx": "preserve",
+        "jsx": "react-jsx",
         "incremental": true,
         "paths": {
             "@server/*": [