fix(mcp): сброс collab-токена на WS-auth-failure с ретраем (#486)

Кэш collab-токена (#435) инвалидировался только на HTTP-401/403 (REST-
интерцептор и login()); отклонённый Hocuspocus-handshake оставлял протухший
токен в кэше — каждая последующая мутация переотправляла тот же битый токен до
истечения TTL (минуты) без self-heal. collab-session помечает ошибку
onAuthenticationFailed маркером; клиентские write-швы (mutatePage/replacePage/
mutateLiveContentUnlocked) обёрнуты в writeWithCollabAuthRetry: на помеченной
ошибке кэш сбрасывается и запись ретраится ровно один раз со свежим токеном —
симметрично HTTP-пути.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

packages/mcp/src/client/context.ts

@@ -19,7 +19,10 @@ import {
   assertYjsEncodable,
   MutationResult,
 } from "../lib/collaboration.js";
-import { acquireCollabSession } from "../lib/collab-session.js";
+import {
+  acquireCollabSession,
+  isCollabAuthFailedError,
+} from "../lib/collab-session.js";
 import { withPageLock, isUuid } from "../lib/page-lock.js";
 import { getCollabToken, performLogin } from "../lib/auth-utils.js";
 import { formatDocmostAxiosError } from "./errors.js";
@@ -484,6 +487,37 @@ export abstract class DocmostClientContext {
     );
   }
 
+  /**
+   * Run a collab write and, on a Hocuspocus HANDSHAKE auth failure, self-heal
+   * once (#486). Symmetric to the HTTP-401 path in getCollabTokenWithReauth: the
+   * REST interceptor and login() already drop the cached collab token on a 401/
+   * 403, but a rejected WEBSOCKET handshake left the stale token in the cache, so
+   * every subsequent mutation kept re-presenting the same bad token for up to the
+   * collab-token TTL (minutes) with no self-heal. Here, when the write rejects
+   * with the tagged collab-auth error, we invalidate the cached token and retry
+   * the write EXACTLY once with a force-refreshed token. Not a loop: a second
+   * failure (or any non-auth error) propagates unchanged.
+   *
+   * `write` receives the token to use, so the retry can hand it a genuinely fresh
+   * one rather than re-running with the same stale string.
+   */
+  protected async writeWithCollabAuthRetry<T>(
+    collabToken: string,
+    write: (token: string) => Promise<T>,
+  ): Promise<T> {
+    try {
+      return await write(collabToken);
+    } catch (e) {
+      if (!isCollabAuthFailedError(e)) throw e;
+      // The WS handshake rejected our token: drop it from the cache so it can't
+      // be reused for the rest of the TTL, mint a fresh one (forceRefresh bypasses
+      // the cache and re-invokes the provider/login), and retry the write once.
+      this.collabTokenCache = null;
+      const fresh = await this.getCollabTokenWithReauth(true);
+      return await write(fresh);
+    }
+  }
+
   /**
    * Connect to the collaboration websocket, read the live doc, apply
    * `transform`, write the result, and wait for the server to persist it —
@@ -518,19 +552,24 @@ export abstract class DocmostClientContext {
     // unsyncedChanges/connectionLost ack logic live in CollabSession.mutate,
     // preserved verbatim from the old inline machine (incl. the #152 structural
     // diff that keeps a live editor's cursor anchored).
-    const session = await acquireCollabSession(pageId, collabToken, this.apiUrl, {
-      // Only the actual 25s collab connect timeout emits this — the connect-vs-
-      // unload signal; the other failure paths must NOT emit it.
-      onConnectTimeout: () =>
-        this.onMetricFn?.("collab_connect_timeouts_total", 1),
+    // Wrap in the collab-auth self-heal (#486): a rejected WS handshake drops the
+    // cached collab token and retries once with a fresh one (the retry passes the
+    // refreshed token down to acquireCollabSession via `token`).
+    return this.writeWithCollabAuthRetry(collabToken, async (token) => {
+      const session = await acquireCollabSession(pageId, token, this.apiUrl, {
+        // Only the actual 25s collab connect timeout emits this — the connect-vs-
+        // unload signal; the other failure paths must NOT emit it.
+        onConnectTimeout: () =>
+          this.onMetricFn?.("collab_connect_timeouts_total", 1),
+      });
+      try {
+        return await session.mutate(transform);
+      } catch (e) {
+        // Drop the session on any failure so the next call reconnects fresh.
+        session.destroy("mutate failed");
+        throw e;
+      }
     });
-    try {
-      return await session.mutate(transform);
-    } catch (e) {
-      // Drop the session on any failure so the next call reconnects fresh.
-      session.destroy("mutate failed");
-      throw e;
-    }
   }
 
   /**
@@ -659,7 +698,11 @@ export abstract class DocmostClientContext {
     transform: (doc: any) => any,
   ): Promise<{ doc?: any; verify?: any }> {
     const pageUuid = await this.resolvePageId(pageId);
-    return mutatePageContent(pageUuid, collabToken, apiUrl, transform);
+    // #486: on a rejected collab-WS handshake, invalidate + refresh the token and
+    // retry the write once (symmetric to the HTTP-401 reauth path).
+    return this.writeWithCollabAuthRetry(collabToken, (token) =>
+      mutatePageContent(pageUuid, token, apiUrl, transform),
+    );
   }
 
   /**
@@ -679,7 +722,11 @@ export abstract class DocmostClientContext {
     apiUrl: string,
   ): Promise<{ doc?: any; verify?: any }> {
     const pageUuid = await this.resolvePageId(pageId);
-    return replacePageContent(pageUuid, doc, collabToken, apiUrl);
+    // #486: on a rejected collab-WS handshake, invalidate + refresh the token and
+    // retry the write once (symmetric to the HTTP-401 reauth path).
+    return this.writeWithCollabAuthRetry(collabToken, (token) =>
+      replacePageContent(pageUuid, doc, token, apiUrl),
+    );
   }
 
   /**

packages/mcp/src/lib/collab-session.ts

@@ -37,6 +37,25 @@ const CONNECT_TIMEOUT_MS = 25000;
 /** Time we wait for the server to acknowledge our write before giving up. */
 const PERSIST_TIMEOUT_MS = 20000;
 
+/**
+ * Marker property set on the Error thrown when the Hocuspocus handshake REJECTS
+ * our collab token (onAuthenticationFailed). The client wraps content writes so
+ * that on this specific failure it invalidates its cached collab token and
+ * retries once with a fresh one — symmetric to the HTTP-401 reauth path (#486).
+ * A plain message-match would be brittle; a tagged property is unambiguous and
+ * survives teardown (which rejects pending ops with this SAME error object).
+ */
+const COLLAB_AUTH_FAILED_MARKER = "collabAuthFailed";
+
+/** True when `e` is the tagged collab-WS auth-failure error (see marker above). */
+export function isCollabAuthFailedError(e: unknown): boolean {
+  return !!(
+    e &&
+    typeof e === "object" &&
+    (e as Record<string, unknown>)[COLLAB_AUTH_FAILED_MARKER] === true
+  );
+}
+
 /**
  * Tunables, read fresh from the environment on every acquire so tests (and a
  * live rollback) can change them without reloading the module. Mirrors how
@@ -302,10 +321,13 @@ export class CollabSession {
           this.openResolve?.();
         },
         onAuthenticationFailed: () => {
-          this.teardown(
-            new Error("Authentication failed for collaboration connection"),
-            true,
-          );
+          // Tag the error so the client can tell a REJECTED collab token apart
+          // from a generic disconnect and invalidate + refresh it (#486).
+          const err = new Error(
+            "Authentication failed for collaboration connection",
+          ) as Error & { [COLLAB_AUTH_FAILED_MARKER]?: boolean };
+          err[COLLAB_AUTH_FAILED_MARKER] = true;
+          this.teardown(err, true);
         },
       });
     });

packages/mcp/test/mock/collab-auth-failure-reset.test.mjs

@@ -0,0 +1,137 @@
+// Unit tests for the collab-token reset on a Hocuspocus WS auth failure (#486).
+//
+// Before this fix the cached collab token (#435) was dropped ONLY on an HTTP
+// 401/403 (the REST interceptor + login()); a rejected collab-WEBSOCKET handshake
+// left the stale token in the cache, so every subsequent mutation re-presented
+// the SAME bad token for up to the collab-token TTL (minutes) with no self-heal.
+//
+// The fix wraps collab writes in `writeWithCollabAuthRetry`: when the write
+// rejects with the tagged collab-auth error (collab-session.ts's
+// onAuthenticationFailed), it invalidates the cached token and retries the write
+// ONCE with a force-refreshed token — symmetric to the HTTP-401 path.
+//
+// writeWithCollabAuthRetry / getCollabTokenWithReauth are protected in TS but
+// plain methods on the compiled build, so the tests call them directly (same
+// convention as collab-token-cache.test.mjs).
+import { test, afterEach } from "node:test";
+import assert from "node:assert/strict";
+import { DocmostClient } from "../../build/client.js";
+
+const ENV_KEY = "MCP_COLLAB_TOKEN_TTL_MS";
+afterEach(() => {
+  delete process.env[ENV_KEY];
+});
+
+// A counting provider that returns a distinct token each call so a cached
+// (reused) token is visibly the SAME string while a fresh mint is different.
+function countingProvider() {
+  let n = 0;
+  const fn = async () => {
+    n++;
+    return `provider-token-${n}`;
+  };
+  return {
+    fn,
+    get calls() {
+      return n;
+    },
+  };
+}
+
+// The tagged error collab-session.ts throws on a rejected WS handshake.
+function collabAuthError() {
+  const err = new Error("Authentication failed for collaboration connection");
+  err.collabAuthFailed = true;
+  return err;
+}
+
+test("a WS auth failure clears the cached token and retries the write with a FRESH one (#486)", async () => {
+  process.env[ENV_KEY] = "300000"; // 5 min: the cache is warm across the burst.
+  const p = countingProvider();
+  const client = new DocmostClient({
+    apiUrl: "http://127.0.0.1:1/api",
+    getToken: async () => "access",
+    getCollabToken: p.fn,
+  });
+
+  // Warm the cache the way a real write would (mints provider-token-1).
+  const initial = await client.getCollabTokenWithReauth();
+  assert.equal(initial, "provider-token-1");
+  assert.equal(p.calls, 1);
+
+  const tokensSeen = [];
+  const write = async (token) => {
+    tokensSeen.push(token);
+    // The FIRST attempt (with the stale cached token) fails the WS handshake;
+    // the retry (with a fresh token) succeeds.
+    if (tokensSeen.length === 1) throw collabAuthError();
+    return `written-with:${token}`;
+  };
+
+  const result = await client.writeWithCollabAuthRetry(initial, write);
+
+  assert.equal(tokensSeen.length, 2, "write attempted exactly twice (one retry)");
+  assert.equal(tokensSeen[0], "provider-token-1", "first attempt used the stale token");
+  assert.equal(
+    tokensSeen[1],
+    "provider-token-2",
+    "retry used a FRESH force-refreshed token, not the stale cached one",
+  );
+  assert.equal(result, "written-with:provider-token-2", "the retry's result wins");
+  assert.equal(p.calls, 2, "exactly one extra mint for the retry — no loop");
+
+  // The cache now holds the fresh token, so a subsequent op reuses it (proving
+  // the stale token was evicted and the fresh one cached, not re-minted).
+  const next = await client.getCollabTokenWithReauth();
+  assert.equal(next, "provider-token-2", "the fresh token replaced the stale cache");
+  assert.equal(p.calls, 2, "served from cache — provider not re-invoked");
+});
+
+test("a successful write is NOT retried and mints nothing extra", async () => {
+  process.env[ENV_KEY] = "300000";
+  const p = countingProvider();
+  const client = new DocmostClient({
+    apiUrl: "http://127.0.0.1:1/api",
+    getToken: async () => "access",
+    getCollabToken: p.fn,
+  });
+
+  const initial = await client.getCollabTokenWithReauth(); // provider-token-1
+  let attempts = 0;
+  const result = await client.writeWithCollabAuthRetry(initial, async (token) => {
+    attempts++;
+    return `ok:${token}`;
+  });
+
+  assert.equal(attempts, 1, "no retry on success");
+  assert.equal(result, "ok:provider-token-1");
+  assert.equal(p.calls, 1, "no extra mint");
+});
+
+test("a NON-auth write error propagates unchanged (no reset, no retry)", async () => {
+  process.env[ENV_KEY] = "300000";
+  const p = countingProvider();
+  const client = new DocmostClient({
+    apiUrl: "http://127.0.0.1:1/api",
+    getToken: async () => "access",
+    getCollabToken: p.fn,
+  });
+
+  const initial = await client.getCollabTokenWithReauth(); // provider-token-1
+  let attempts = 0;
+  await assert.rejects(
+    client.writeWithCollabAuthRetry(initial, async () => {
+      attempts++;
+      throw new Error("collab connection closed before persist"); // NOT tagged.
+    }),
+    /closed before persist/,
+  );
+
+  assert.equal(attempts, 1, "a non-auth error is not retried");
+  assert.equal(p.calls, 1, "the cache is untouched -> no fresh mint");
+
+  // Cache still holds the original token (was never invalidated).
+  const still = await client.getCollabTokenWithReauth();
+  assert.equal(still, "provider-token-1");
+  assert.equal(p.calls, 1);
+});