Assistant: migrate to v2 runtime handler with Postgres-backed AgentRunner

Replace the deprecated copilotRuntimeNextJSAppRouterEndpoint wrapper
(which was already the v2 single-route handler underneath) with
createCopilotRuntimeHandler from @copilotkit/runtime/v2, built once at
module scope, and plug in a custom PostgresAgentRunner:

- run() proxies the agent's event stream untouched — MAF persists every
  turn in chatthreadsnapshot, so the BFF records nothing
- connect() forwards to MAF's snapshot hydration (empty-messages run →
  RUN_STARTED → MESSAGES_SNAPSHOT → RUN_FINISHED, no LLM call), making
  the DB the only conversation store — correct across clears, restarts
  and future instances
- stop() aborts via a process-local live-run map (same pattern as the
  official sqlite-runner); isRunning() has no caller in the v2 SSE path

This deletes the whole workaround layer the in-memory runner forced:
the connect intercepts (URL + envelope forms) and Asistente's
client-side hydration run. The ask-box flow now awaits connectAgent
instead. Auth moves to a single Request rewrite (ws_token cookie →
Authorization Bearer) before the handler — the v2 path forwards
authorization + x-* headers to both run clones and runner.connect.
Stays in single-route mode: same envelope protocol the client already
auto-detected, no exposure to CopilotKit#4953, /threads* REST not
needed. Telemetry disabled via COPILOTKIT_TELEMETRY_DISABLED.

Verified full matrix in dev: fresh ask, reload replay via runner,
3 cleared convos + double navigation (only last survives), card renders
once and survives follow-up + reload, Inicio ask-box with history,
stale-tab persists only its new turn. 126 backend tests green.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

frontend/server.ts

@@ -1,12 +1,12 @@
 import { serve } from "@hono/node-server";
 import { serveStatic } from "@hono/node-server/serve-static";
 import {
+  AgentRunner,
   CopilotRuntime,
-  ExperimentalEmptyAdapter,
-  copilotRuntimeNextJSAppRouterEndpoint,
-} from "@copilotkit/runtime";
+  createCopilotRuntimeHandler,
+} from "@copilotkit/runtime/v2";
 import { HttpAgent, Middleware, EventType } from "@ag-ui/client";
-import { Observable } from "rxjs";
+import { Observable, ReplaySubject } from "rxjs";
 import { Hono } from "hono";
 
 const BACKEND_URL =
@@ -383,52 +383,21 @@ app.use("*", async (c, next) => {
   });
 });
 
-app.all("/api/copilotkit/*", async (c) => {
-  // CopilotChat fires "connect" on every mount with an explicit threadId,
-  // and the runtime's in-memory runner answers it by replaying THIS
-  // PROCESS's event history — every run since the server started, across
-  // "Nueva conversación" clears (the DB delete can't touch process memory).
-  // That resurrected cleared conversations on navigation. The
-  // empty-messages hydration run against MAF's snapshot store is our single
-  // restore path, so connect gets an immediately-completed stream instead.
-  //
-  // Two transports must be caught: multi-route (POST …/agent/<id>/connect)
-  // and single-route (POST /api/copilotkit with {method:"agent/connect"} in
-  // the body — the one CopilotKit actually uses here; the URL-only check
-  // silently missed it).
-  const emptyStream = () =>
-    new Response("", {
-      status: 200,
-      headers: { "Content-Type": "text/event-stream" },
-    });
-  if (new URL(c.req.url).pathname.endsWith("/connect")) {
-    return emptyStream();
-  }
-  if (
-    c.req.method === "POST" &&
-    (c.req.header("content-type") ?? "").includes("application/json")
-  ) {
-    try {
-      const envelope = (await c.req.raw.clone().json()) as { method?: string };
-      if (envelope?.method === "agent/connect") {
-        return emptyStream();
-      }
-    } catch {
-      // not JSON — fall through to the runtime
-    }
-  }
+// ── CopilotKit v2 runtime (module scope, built once) ─────────────────────────
+// Migrated 2026-07-04 off the deprecated copilotRuntimeNextJSAppRouterEndpoint
+// wrapper (which was already the v2 single-route handler underneath) onto
+// createCopilotRuntimeHandler directly, with a Postgres-backed AgentRunner:
+// run() is a pure proxy to the MAF backend (which persists every turn in
+// chatthreadsnapshot), and connect() forwards to MAF's snapshot hydration —
+// so the ONLY conversation store is the DB. This deletes the in-memory
+// runner (whose process-local replay resurrected cleared conversations) and
+// the client-side hydration hack that compensated for it.
 
-  const cookieHeader = c.req.header("cookie") ?? "";
-  const match = cookieHeader.match(/(?:^|;\s*)ws_token=([^;]+)/);
-  const token = match?.[1];
-  const agentHeaders: Record<string, string> = token
-    ? { Authorization: `Bearer ${token}` }
-    : {};
-  // Note: the browser's X-Client-Timezone header (set in App.tsx) reaches
-  // the backend without help — CopilotKit's runtime forwards authorization
-  // and all x-* headers to the agent (extractForwardableHeaders).
+// The v2 handler nags about anonymous telemetry unless disabled.
+process.env.COPILOTKIT_TELEMETRY_DISABLED ??= "true";
 
-  const agent = new HttpAgent({ url: AGENT_URL, headers: agentHeaders });
+function makeWealthysmartAgent(headers: Record<string, string> = {}): HttpAgent {
+  const agent = new HttpAgent({ url: AGENT_URL, headers });
   // CK_MIDDLEWARES=off runs the stack bare — used to audit which of these
   // workarounds are still needed after CopilotKit/MAF upgrades.
   /* eslint-disable @typescript-eslint/no-explicit-any */
@@ -442,9 +411,83 @@ app.all("/api/copilotkit/*", async (c) => {
     agent.use(new DebugLogMiddleware() as any);
   }
   /* eslint-enable @typescript-eslint/no-explicit-any */
+  return agent;
+}
+
+// ── PostgresAgentRunner ───────────────────────────────────────────────────────
+// The conversation store is Postgres (chatthreadsnapshot), written by MAF at
+// every run end. So the runner records NOTHING:
+// - run() proxies the agent's event stream (the per-request clone the v2
+//   handler prepared, auth headers already forwarded onto it).
+// - connect() asks MAF for its snapshot hydration — an empty-messages run
+//   returns RUN_STARTED → [STATE_SNAPSHOT] → MESSAGES_SNAPSHOT → RUN_FINISHED
+//   with no LLM call (unknown thread: RUN_STARTED → RUN_FINISHED). The same
+//   stream shape the in-memory runner's replay approximated, but sourced
+//   from the DB, so it is correct across clears, restarts and instances.
+// - Live runs are tracked in-process only for stop(); the official
+//   sqlite-runner does the same (single-instance limitation acknowledged).
+// isRunning() has no caller in the v2 SSE path (verified at 1.62.2).
+
+// eslint-disable-next-line @typescript-eslint/no-explicit-any
+const liveRuns = new Map<string, any>();
+
+// eslint-disable-next-line @typescript-eslint/no-explicit-any
+function proxyAgentRun(agent: any, input: any, threadId: string): Observable<any> {
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  const subject = new ReplaySubject<any>(Infinity);
+  liveRuns.set(threadId, agent);
+  agent
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    .runAgent(input, { onEvent: ({ event }: any) => subject.next(event) })
+    .then(() => subject.complete())
+    // eslint-disable-next-line @typescript-eslint/no-explicit-any
+    .catch((err: any) => subject.error(err))
+    .finally(() => {
+      if (liveRuns.get(threadId) === agent) liveRuns.delete(threadId);
+    });
+  return subject.asObservable();
+}
+
+// eslint-disable-next-line @typescript-eslint/no-explicit-any
+class PostgresAgentRunner extends (AgentRunner as any) {
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  run(request: any): Observable<any> {
+    return proxyAgentRun(request.agent, request.input, request.threadId);
+  }
+
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  connect(request: any): Observable<any> {
+    // request.headers = authorization + x-* from the incoming browser
+    // request (extractForwardableHeaders) — exactly what MAF needs.
+    const agent = makeWealthysmartAgent(request.headers ?? {});
+    agent.threadId = request.threadId;
+    // No messages + known threadId = MAF's hydration trigger.
+    return proxyAgentRun(agent, {}, `connect:${request.threadId}`);
+  }
+
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  isRunning(request: any): Promise<boolean> {
+    return Promise.resolve(liveRuns.has(request.threadId));
+  }
+
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  async stop(request: any): Promise<boolean | undefined> {
+    const agent = liveRuns.get(request.threadId);
+    if (!agent) return false;
+    try {
+      agent.abortRun();
+      liveRuns.delete(request.threadId);
+      return true;
+    } catch {
+      return false;
+    }
+  }
+}
 
 const runtime = new CopilotRuntime({
-    agents: { wealthysmart: agent },
+  agents: { wealthysmart: makeWealthysmartAgent() },
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  runner: new PostgresAgentRunner() as any,
   // a2ui disabled 2026-07-04: CK 1.60+ validates generated ops against a
   // catalog and our agent's ops fail validation (surface never paints).
   // Markdown tables cover the use case until the pipeline matures.
@@ -501,14 +544,32 @@ app.all("/api/copilotkit/*", async (c) => {
   },
 });
 
-  const { handleRequest } = copilotRuntimeNextJSAppRouterEndpoint({
+const ckHandler = createCopilotRuntimeHandler({
   runtime,
-    serviceAdapter: new ExperimentalEmptyAdapter(),
-    endpoint: "/api/copilotkit",
+  basePath: "/api/copilotkit",
+  // Single-route mode: same envelope protocol the client already resolved
+  // via auto-detect (its GET /info probe 405s here, so it stays "single").
+  // Multi-route would only add /threads* REST endpoints we don't use and is
+  // exposed to CopilotKit#4953 (frontend tools under multi-route).
+  mode: "single-route",
+  cors: false,
 });
 
-  return handleRequest(c.req.raw as Parameters<typeof handleRequest>[0]);
-});
+// The v2 handler forwards only `authorization` and `x-*` headers to agents
+// and to runner.connect — cookies never pass. Translate the auth cookie into
+// a Bearer header before the handler sees the request.
+function withBearerFromCookie(req: Request): Request {
+  if (req.headers.get("authorization")) return req;
+  const cookie = req.headers.get("cookie") ?? "";
+  const match = cookie.match(/(?:^|;\s*)ws_token=([^;]+)/);
+  if (!match) return req;
+  const headers = new Headers(req.headers);
+  headers.set("Authorization", `Bearer ${match[1]}`);
+  return new Request(req, { headers });
+}
+
+app.all("/api/copilotkit/*", (c) => ckHandler(withBearerFromCookie(c.req.raw)));
+app.all("/api/copilotkit", (c) => ckHandler(withBearerFromCookie(c.req.raw)));
 
 app.get("/api/health", (c) => c.json({ ok: true }));
 

frontend/src/pages/Asistente.tsx

@@ -39,39 +39,34 @@ export default function Asistente() {
   const [confirmClear, setConfirmClear] = useState(false);
   const [clearing, setClearing] = useState(false);
 
-  // Boot sequence, once per page load: hydrate the persisted thread, then
-  // send any question that arrived from the Inicio ask-box via router state.
-  // Order matters — hydration first keeps the invariant that every normal
-  // run's input carries the full client-known history (the BFF's snapshot
-  // reconciliation relies on it).
+  // Ask-box flow: a question typed on Inicio arrives via router state.
+  // History hydration is no longer done here — CopilotChat's mount connect
+  // replays the persisted thread through the BFF's PostgresAgentRunner. We
+  // still await our own connect before sending so the run's input carries
+  // the full client-known history (idempotent with CopilotChat's connect:
+  // the MESSAGES_SNAPSHOT merge is id-based).
   const bootRef = useRef(false);
   useEffect(() => {
-    if (!agent || bootRef.current) return;
-    bootRef.current = true;
     const ask = (location.state as { ask?: string } | null)?.ask;
-    if (ask) {
+    if (!ask || !agent || bootRef.current) return;
+    bootRef.current = true;
     // Clear the state so back/refresh doesn't re-send the question.
     navigate(location.pathname, { replace: true, state: null });
-    }
     void (async () => {
       agent.threadId = CHAT_THREAD_ID;
       if (agent.messages.length === 0) {
-        // Empty-messages run = MAF's hydration trigger: replays the stored
-        // snapshot as MESSAGES_SNAPSHOT without invoking the LLM.
         try {
-          await copilotkit.runAgent({ agent });
+          await copilotkit.connectAgent({ agent });
         } catch (err) {
-          console.error("[asistente] thread hydration failed:", err);
+          console.error("[asistente] connect before ask failed:", err);
         }
       }
-      if (ask) {
       agent.addMessage({
         id: crypto.randomUUID(),
         role: "user",
         content: ask,
       });
       void copilotkit.runAgent({ agent });
-      }
     })();
     // eslint-disable-next-line react-hooks/exhaustive-deps
   }, [agent]);