fix(whatsapp): retry opening-phase 428 closes

Co-authored-by: dataCenter430 <titan032000@gmail.com>

CHANGELOG.md

@@ -66,6 +66,7 @@ Docs: https://docs.openclaw.ai
 - Gateway: scope `sessions.resolve` sessionId and label store loads to the requested agent so large unrelated agent stores are not parsed for scoped lookups. Fixes #51264. (#79474) Thanks @samzong.
 - Gateway: share serialized streaming event envelopes across eligible WebSocket and node subscribers while preserving per-client sequence numbers. (#80299) Thanks @samzong.
 - Browser: report Chrome MCP existing-session page readiness in browser status without letting status probes exceed the client timeout. Fixes #80268. (#80280) Thanks @ai-hpc.
+- WhatsApp: route opening-phase Baileys 428 connectionClosed through the WhatsApp reconnect policy and keep post-open 428 closes retryable, so transient setup socket closes retry with WhatsApp diagnostics instead of escaping as a bare `channel exited` error. Fixes #75736; mitigates #77443. Thanks @dataCenter430.
 - Providers/self-hosted: read model-scoped llama.cpp runtime context from `/props.default_generation_settings.n_ctx` while keeping top-level `n_ctx` as a fallback, so session budgeting reflects the loaded context window. Fixes #73664. (#74057) Thanks @brokemac79.
 - Memory: reject symlinked directory components in configured extra memory paths before reading Markdown files. (#80331) Thanks @samzong.
 - Sessions/transcripts: replace whole-file `readFile` scans with shared streaming helpers (`streamSessionTranscriptLines` and `streamSessionTranscriptLinesReverse`) for idempotency lookup, latest/tail assistant text reads, delivery-mirror dedupe, and compaction fork loading, so long-running sessions no longer materialize the full transcript in memory. Forward scans use `readline` over a bounded `createReadStream`; reverse scans read bounded chunks from the file end and decode complete JSONL lines newest-first without a fixed tail cap. Synthetic 200 MiB transcript: peak RSS delta drops from +252 MiB to +27 MiB while preserving malformed-line tolerance and idempotency-key return semantics. Fixes #54296. Thanks @jack-stormentswe.

extensions/whatsapp/src/auto-reply.web-auto-reply.connection-and-logging.e2e.test.ts

@@ -169,6 +169,75 @@ describe("web auto-reply connection", () => {
     }
   });
 
+  it("retries opening-phase Boom 428 through the reconnect policy", async () => {
+    const boom428 = {
+      output: {
+        statusCode: 428,
+        payload: { error: "Precondition Required", message: "Connection Terminated" },
+      },
+    };
+    const listenerFactory = vi.fn(async () => {
+      throw boom428;
+    });
+
+    const sleep = vi.fn(async () => {});
+    const { runtime, run } = startWebAutoReplyMonitor({
+      monitorWebChannelFn: monitorWebChannel as never,
+      listenerFactory,
+      sleep,
+      reconnect: { initialMs: 10, maxMs: 10, maxAttempts: 2, factor: 1.1 },
+    });
+
+    await run;
+
+    expect(listenerFactory).toHaveBeenCalledTimes(2);
+    expect(sleep).toHaveBeenCalled();
+    expectErrorContaining(runtime.error, "status 428");
+    expectErrorContaining(runtime.error, "Retry 1/2");
+    expectErrorContaining(runtime.error, "2/2 attempts");
+  });
+
+  it("keeps post-open Baileys 428 on the reconnect path", async () => {
+    const sleep = vi.fn(async () => {});
+    const scripted = createScriptedWebListenerFactory();
+    const { controller, run } = startWebAutoReplyMonitor({
+      monitorWebChannelFn: monitorWebChannel as never,
+      listenerFactory: scripted.listenerFactory,
+      sleep,
+      reconnect: { initialMs: 10, maxMs: 10, maxAttempts: 3, factor: 1.1 },
+    });
+
+    await vi.waitFor(
+      () => {
+        expect(scripted.getListenerCount()).toBe(1);
+      },
+      { timeout: 250, interval: 2 },
+    );
+    scripted.resolveClose(0, {
+      status: 428,
+      isLoggedOut: false,
+      error: "Connection Terminated",
+    });
+
+    await vi.waitFor(
+      () => {
+        expect(scripted.getListenerCount()).toBeGreaterThanOrEqual(2);
+      },
+      { timeout: 250, interval: 2 },
+    );
+
+    controller.abort();
+    scripted.resolveClose(scripted.getListenerCount() - 1, {
+      status: 499,
+      isLoggedOut: false,
+      error: "aborted",
+    });
+    await run;
+
+    expect(scripted.getListenerCount()).toBeGreaterThanOrEqual(2);
+    expect(sleep).toHaveBeenCalled();
+  });
+
   it("treats status 440 as non-retryable and stops without retrying", async () => {
     const sleep = vi.fn(async () => {});
     const scripted = createScriptedWebListenerFactory();

extensions/whatsapp/src/auto-reply/monitor.ts

@@ -29,7 +29,13 @@ import {
   resolveReconnectPolicy,
   sleepWithAbort,
 } from "../reconnect.js";
-import { formatError, getWebAuthAgeMs, logoutWeb, readWebSelfId } from "../session.js";
+import {
+  formatError,
+  getStatusCode,
+  getWebAuthAgeMs,
+  logoutWeb,
+  readWebSelfId,
+} from "../session.js";
 import { resolveWhatsAppSocketTiming } from "../socket-timing.js";
 import { getRuntimeConfig, getRuntimeConfigSourceSnapshot } from "./config.runtime.js";
 import { whatsappHeartbeatLog, whatsappLog } from "./loggers.js";
@@ -43,6 +49,8 @@ import { isLikelyWhatsAppCryptoError } from "./util.js";
 function isNonRetryableWebCloseStatus(statusCode: unknown): boolean {
   // WhatsApp 440 = session conflict ("Unknown Stream Errored (conflict)").
   // This is persistent until the operator resolves the conflicting session.
+  // Baileys 428 = DisconnectReason.connectionClosed, a generic WebSocket close
+  // that is often transient and must stay on the reconnect path.
   return statusCode === 440;
 }
 
@@ -395,6 +403,50 @@ export async function monitorWebChannel(
           },
         });
       } catch (error) {
+        if (getStatusCode(error) === 428) {
+          const retryDecision = controller.consumeReconnectAttempt();
+          statusController.noteReconnectAttempts(retryDecision.reconnectAttempts);
+          statusController.noteClose({
+            statusCode: 428,
+            error: formatError(error),
+            reconnectAttempts: retryDecision.reconnectAttempts,
+            healthState: retryDecision.healthState,
+          });
+          if (retryDecision.action === "stop") {
+            reconnectLogger.warn(
+              {
+                connectionId,
+                status: 428,
+                reconnectAttempts: retryDecision.reconnectAttempts,
+                maxAttempts: reconnectPolicy.maxAttempts,
+              },
+              "web reconnect: 428 during opening; max attempts reached",
+            );
+            runtime.error(
+              `WhatsApp Web connection closed during setup (status 428) after ${retryDecision.reconnectAttempts}/${reconnectPolicy.maxAttempts} attempts. Relink with \`${formatCliCommand("openclaw channels login --channel whatsapp")}\` if the issue persists.`,
+            );
+            await controller.shutdown();
+            break;
+          }
+          reconnectLogger.info(
+            {
+              connectionId,
+              status: 428,
+              reconnectAttempts: retryDecision.reconnectAttempts,
+              delayMs: retryDecision.delayMs,
+            },
+            "web reconnect: 428 during opening; retrying",
+          );
+          runtime.error(
+            `WhatsApp Web connection closed during setup (status 428). Retry ${retryDecision.reconnectAttempts}/${reconnectPolicy.maxAttempts || "∞"} in ${formatDurationPrecise(retryDecision.delayMs ?? 0)}.`,
+          );
+          try {
+            await controller.waitBeforeRetry(retryDecision.delayMs ?? 0);
+          } catch {
+            break;
+          }
+          continue;
+        }
         if (!isRetryableAuthUnstableError(error)) {
           throw error;
         }