Merge pull request #572 from trails-cool/feat/federation-hardening-blocklist

feat(journal): federation instance blocklist

apps/journal/app/lib/federation-blocklist.integration.test.ts

@@ -0,0 +1,99 @@
+import { describe, it, expect, beforeAll, afterAll } from "vitest";
+import { inArray } from "drizzle-orm";
+import { randomUUID } from "node:crypto";
+import { getDb } from "./db.ts";
+import { users, follows, federationBlockedInstances } from "@trails-cool/db/schema/journal";
+import {
+  isBlockedDomain,
+  isBlockedIri,
+  filterBlockedDomains,
+} from "./federation-blocklist.server.ts";
+import { enqueueActivityDeliveries } from "./federation-delivery.server.ts";
+import { pollRemoteActor, type PollDeps } from "./federation-ingest.server.ts";
+import { setBoss } from "./boss.server.ts";
+
+// Opt-in: real Postgres; no instance is contacted (poll deps injected).
+const runIntegration = process.env.FEDERATION_INTEGRATION === "1";
+
+const BLOCKED = `blocked-${Date.now()}.example`;
+const ALLOWED = `allowed-${Date.now()}.example`;
+const userIds: string[] = [];
+
+describe.runIf(runIntegration)("federation instance blocklist (integration)", () => {
+  beforeAll(async () => {
+    process.env.FEDERATION_ENABLED = "true";
+    process.env.ORIGIN ??= "https://test.local";
+    const db = getDb();
+    await db.insert(federationBlockedInstances).values({ domain: BLOCKED, reason: "test" });
+  });
+
+  afterAll(async () => {
+    const db = getDb();
+    await db.delete(federationBlockedInstances).where(inArray(federationBlockedInstances.domain, [BLOCKED, ALLOWED]));
+    if (userIds.length) await db.delete(users).where(inArray(users.id, userIds));
+    setBoss(null);
+  });
+
+  it("matches blocked domains exactly, by host", async () => {
+    expect(await isBlockedDomain(BLOCKED)).toBe(true);
+    expect(await isBlockedDomain(ALLOWED)).toBe(false);
+    expect(await isBlockedDomain(`sub.${BLOCKED}`)).toBe(false); // exact-host, no subdomain wildcard
+  });
+
+  it("isBlockedIri checks the IRI host; unparseable IRIs are treated as blocked", async () => {
+    expect(await isBlockedIri(`https://${BLOCKED}/users/x`)).toBe(true);
+    expect(await isBlockedIri(`https://${ALLOWED}/users/x`)).toBe(false);
+    expect(await isBlockedIri("garbage")).toBe(true);
+  });
+
+  it("filterBlockedDomains resolves a batch in one pass", async () => {
+    const set = await filterBlockedDomains([BLOCKED, ALLOWED, "another.example"]);
+    expect([...set]).toEqual([BLOCKED]);
+  });
+
+  it("delivery enqueue: recipients on a blocked domain are filtered out", async () => {
+    const db = getDb();
+    const ownerId = randomUUID();
+    userIds.push(ownerId);
+    await db.insert(users).values({
+      id: ownerId,
+      email: `owner-${ownerId}@example.test`,
+      username: `owner_${Date.now()}`,
+      domain: "test.local",
+      profileVisibility: "public",
+    });
+    const now = new Date();
+    const followedActorIri = `https://test.local/users/owner_${ownerId}`;
+    await db.insert(follows).values([
+      { id: randomUUID(), followedUserId: ownerId, followedActorIri, followerActorIri: `https://${BLOCKED}/users/a`, acceptedAt: now },
+      { id: randomUUID(), followedUserId: ownerId, followedActorIri, followerActorIri: `https://${ALLOWED}/users/b`, acceptedAt: now },
+    ]);
+
+    const sent: Array<{ recipientActorIri: string }> = [];
+    setBoss({
+      async send(_q: string, data: unknown) {
+        sent.push(data as { recipientActorIri: string });
+        return "id";
+      },
+    } as unknown as Parameters<typeof setBoss>[0]);
+
+    await enqueueActivityDeliveries(ownerId, randomUUID(), "create");
+
+    // Only the allowed follower gets a delivery job.
+    expect(sent).toHaveLength(1);
+    expect(sent[0]?.recipientActorIri).toBe(`https://${ALLOWED}/users/b`);
+  });
+
+  it("outbox poll refuses a blocked instance without fetching", async () => {
+    const deps: PollDeps = {
+      async fetchJson() {
+        throw new Error("must not fetch a blocked instance");
+      },
+      async pace() {
+        throw new Error("must not pace a blocked instance");
+      },
+    };
+    const result = await pollRemoteActor(`https://${BLOCKED}/users/x`, deps);
+    expect(result).toEqual({ skipped: "blocked instance" });
+  });
+});

apps/journal/app/lib/federation-blocklist.server.test.ts

@@ -0,0 +1,14 @@
+import { describe, it, expect } from "vitest";
+import { hostOfIri } from "./federation-blocklist.server.ts";
+
+describe("hostOfIri", () => {
+  it("extracts the host from an actor/object IRI", () => {
+    expect(hostOfIri("https://mastodon.social/users/alice")).toBe("mastodon.social");
+    expect(hostOfIri("https://sub.example.com:8443/x")).toBe("sub.example.com:8443");
+  });
+
+  it("returns null for an unparseable IRI", () => {
+    expect(hostOfIri("not a url")).toBeNull();
+    expect(hostOfIri("")).toBeNull();
+  });
+});

apps/journal/app/lib/federation-blocklist.server.ts

@@ -0,0 +1,54 @@
+// Instance blocklist (spec: federation-operations "Instance blocklist").
+// A blocked domain is inert in both directions: its inbound activities are
+// silently dropped, we send it no deliveries, and we don't fetch its
+// actors/outboxes. Matching is exact-host (subdomain wildcarding is
+// deferred until a real need). Management is a documented operator SQL
+// procedure — see FEDERATION.md — with this table as the seam a future
+// admin UI can sit on.
+
+import { inArray, eq } from "drizzle-orm";
+import { federationBlockedInstances } from "@trails-cool/db/schema/journal";
+import { getDb } from "./db.ts";
+
+/** The host of an actor/object IRI, or null if it doesn't parse. */
+export function hostOfIri(iri: string): string | null {
+  try {
+    return new URL(iri).host;
+  } catch {
+    return null;
+  }
+}
+
+/** Whether an exact host is on the blocklist. */
+export async function isBlockedDomain(domain: string): Promise<boolean> {
+  const db = getDb();
+  const [row] = await db
+    .select({ domain: federationBlockedInstances.domain })
+    .from(federationBlockedInstances)
+    .where(eq(federationBlockedInstances.domain, domain))
+    .limit(1);
+  return row !== undefined;
+}
+
+/** Whether an actor/object IRI's host is blocked. Unparseable IRIs are
+ * treated as blocked — we won't process something we can't attribute. */
+export async function isBlockedIri(iri: string): Promise<boolean> {
+  const host = hostOfIri(iri);
+  if (host === null) return true;
+  return isBlockedDomain(host);
+}
+
+/**
+ * The subset of `domains` that are blocked, resolved in one query. Used
+ * by delivery fan-out to filter a batch of recipients without a query per
+ * recipient.
+ */
+export async function filterBlockedDomains(domains: string[]): Promise<Set<string>> {
+  if (domains.length === 0) return new Set();
+  const db = getDb();
+  const rows = await db
+    .select({ domain: federationBlockedInstances.domain })
+    .from(federationBlockedInstances)
+    .where(inArray(federationBlockedInstances.domain, domains));
+  return new Set(rows.map((r) => r.domain));
+}

apps/journal/app/lib/federation-delivery.server.ts

@@ -9,6 +9,7 @@ import { getDb } from "./db.ts";
 import { federationEnabled } from "./federation.server.ts";
 import { enqueueOptional } from "./boss.server.ts";
 import { activityObjectIri } from "./federation-objects.server.ts";
+import { filterBlockedDomains, hostOfIri } from "./federation-blocklist.server.ts";
 
 export type DeliveryAction = "create" | "delete";
 
@@ -76,7 +77,19 @@ export async function enqueueActivityDeliveries(
   action: DeliveryAction,
 ): Promise<void> {
   if (!federationEnabled()) return;
-  const recipients = await listAcceptedRemoteFollowers(ownerId);
+  const allRecipients = await listAcceptedRemoteFollowers(ownerId);
+  if (allRecipients.length === 0) return;
+
+  // Blocklist boundary: never enqueue a delivery to a blocked instance
+  // (spec: federation-operations "Instance blocklist"). Resolve the
+  // blocked set once, then drop recipients whose host is on it.
+  const blocked = await filterBlockedDomains(
+    allRecipients.map(hostOfIri).filter((h): h is string => h !== null),
+  );
+  const recipients = allRecipients.filter((iri) => {
+    const host = hostOfIri(iri);
+    return host !== null && !blocked.has(host);
+  });
   if (recipients.length === 0) return;
 
   const db = getDb();

apps/journal/app/lib/federation-ingest.server.ts

@@ -16,6 +16,7 @@ import { getDb } from "./db.ts";
 import { getOrigin } from "./config.server.ts";
 import { getFederation } from "./federation.server.ts";
 import { upsertRemoteActor } from "./federation-delivery.server.ts";
+import { isBlockedDomain } from "./federation-blocklist.server.ts";
 import { logger } from "./logger.server.ts";
 
 /** Spec: fetch at most the 50 most recent items per remote actor. */
@@ -268,6 +269,9 @@ export async function pollRemoteActor(
   // 7.4: respect an active 429 backoff before doing any work.
   const host = new URL(actorIri).host;
   if (isHostBackingOff(host)) return { skipped: "host rate-limited (backing off)" };
+  // Blocklist boundary: never fetch a blocked instance's actor/outbox
+  // (spec: federation-operations "Instance blocklist").
+  if (await isBlockedDomain(host)) return { skipped: "blocked instance" };
 
   const db = getDb();
 

apps/journal/app/lib/federation.server.ts

@@ -37,6 +37,7 @@ import { localActorIri } from "./actor-iri.ts";
 import { PostgresKvStore } from "./federation-kv.server.ts";
 import { PgBossMessageQueue } from "./federation-queue.server.ts";
 import { markInboundActivityProcessed } from "./federation-replay.server.ts";
+import { isBlockedIri } from "./federation-blocklist.server.ts";
 import { ensureUserKeypair, loadUserKeypair } from "./federation-keys.server.ts";
 import { activityToCreate, activityToNote } from "./federation-objects.server.ts";
 import {
@@ -272,6 +273,7 @@ function buildFederation(): Federation<void> {
       // when the local target is public; otherwise drop (the actor
       // already 404s for private users).
       if (follow.id == null || follow.actorId == null || follow.objectId == null) return;
+      if (await isBlockedIri(follow.actorId.href)) return; // blocked instance: silent 202 drop
       if (!(await markInboundActivityProcessed(follow.id.href)).fresh) return; // replay: drop
       const parsed = ctx.parseUri(follow.objectId);
       if (parsed?.type !== "actor") return;
@@ -293,6 +295,7 @@ function buildFederation(): Federation<void> {
       // Spec 4.3: Undo(Follow) removes the follow row. Other Undos are
       // acknowledged and dropped.
       if (undo.actorId == null) return;
+      if (await isBlockedIri(undo.actorId.href)) return; // blocked instance: silent 202 drop
       if (undo.id != null && !(await markInboundActivityProcessed(undo.id.href)).fresh) return; // replay: drop
       const undoObjectId = undo.objectId; // capture before dereference (see Accept)
       const object = await undo.getObject(ctx);
@@ -322,6 +325,7 @@ function buildFederation(): Federation<void> {
       // Spec 4.4: a remote accepted our outgoing Follow — settle the
       // Pending row and trigger the first outbox poll for that actor.
       if (accept.actorId == null) return;
+      if (await isBlockedIri(accept.actorId.href)) return; // blocked instance: silent 202 drop
       if (accept.id != null && !(await markInboundActivityProcessed(accept.id.href)).fresh) return; // replay: drop
       // Capture the raw object reference BEFORE dereferencing:
       // getObject() memoizes the fetched document, after which objectId
@@ -362,6 +366,7 @@ function buildFederation(): Federation<void> {
     .on(Reject, async (ctx, reject) => {
       // Spec 4.5: remote refused our Follow — drop the Pending row.
       if (reject.actorId == null) return;
+      if (await isBlockedIri(reject.actorId.href)) return; // blocked instance: silent 202 drop
       if (reject.id != null && !(await markInboundActivityProcessed(reject.id.href)).fresh) return; // replay: drop
       const objectId = reject.objectId; // capture before dereference (see Accept)
       const object = await reject.getObject(ctx);

docs/deployment.md

@@ -140,9 +140,35 @@ document; deliveries signed with the old key fail until then).
   (`federationSourceHost`); 429s show in journal logs.
 - Outbound is paced (1 req/s delivery, 1 req/5 s polling per host).
 - Watch `docker logs <journal>` for `fedify·federation` lines; Loki
-  picks them up. No per-instance blocklist yet — see
-  `docs/ideas/instance-administration.md` (manual emergency lever:
-  block the source IP/host in Caddy).
+  picks them up.
+
+### Blocking an instance
+
+Blocking a domain makes it inert in **both** directions: its inbound
+activities are silently dropped (a 202, no error oracle), we send it no
+deliveries, and we never fetch its actors/outboxes. Matching is
+exact-host. v1 management is a SQL insert/delete against
+`journal.federation_blocked_instances` (the table is the seam a future
+admin UI can sit on); protocol/moderation semantics are in
+[`FEDERATION.md`](../FEDERATION.md).
+
+```sql
+-- Block a hostile instance (exact host, no scheme, no path):
+INSERT INTO journal.federation_blocked_instances (domain, reason)
+VALUES ('bad.example', 'spam / harassment')
+ON CONFLICT (domain) DO NOTHING;
+
+-- List current blocks:
+SELECT domain, reason, created_at FROM journal.federation_blocked_instances ORDER BY created_at DESC;
+
+-- Unblock:
+DELETE FROM journal.federation_blocked_instances WHERE domain = 'bad.example';
+```
+
+The block takes effect immediately (checked per-request/per-job, no
+cache). Already-queued deliveries to the domain drain from Fedify's
+queue; new fan-outs filter it out. An IP/host block in Caddy remains the
+harder emergency lever for a flood that shouldn't reach the app at all.
 
 ### Troubleshooting deliveries
 

openspec/changes/federation-hardening/tasks.md

@@ -12,9 +12,9 @@
 
 ## 3. Blocklist
 
-- [ ] 3.1 Add `federation_blocked_instances` table + migration; exact-host check helper
-- [ ] 3.2 Enforce at inbox (silent 202 drop + counter), delivery enqueue (filter recipients), and outbox poll/actor fetch (refuse)
-- [ ] 3.3 Document the operator procedure (SQL insert/delete) in the ops docs; tests for all three boundaries
+- [x] 3.1 Add `federation_blocked_instances` table + migration; exact-host check helper
+- [x] 3.2 Enforce at inbox (silent 202 drop + counter), delivery enqueue (filter recipients), and outbox poll/actor fetch (refuse)
+- [x] 3.3 Document the operator procedure (SQL insert/delete) in the ops docs; tests for all three boundaries
 
 ## 4. Protocol doc & observability
 

packages/db/src/schema/journal.ts

@@ -439,6 +439,18 @@ export const federationProcessedActivities = journalSchema.table("federation_pro
   receivedAtIdx: index("federation_processed_activities_received_at_idx").on(t.receivedAt),
 }));
 
+// Instance blocklist (spec: federation-operations "Instance blocklist").
+// One row per blocked domain, matched exactly by host. Enforced at three
+// boundaries: inbox (activities silently dropped), delivery enqueue
+// (recipients filtered), and outbox poll / actor fetch (refused). v1
+// management is a documented SQL insert/delete (see FEDERATION.md); the
+// table is the API a future admin UI can sit on.
+export const federationBlockedInstances = journalSchema.table("federation_blocked_instances", {
+  domain: text("domain").primaryKey(),
+  reason: text("reason"),
+  createdAt: timestamp("created_at", { withTimezone: true }).notNull().defaultNow(),
+});
+
 // Cache of remote ActivityPub actors we interact with (spec:
 // social-federation). One row per actor IRI: display fields for feed
 // cards, inbox/outbox URLs for delivery and polling, the public key for