fix(model-fallback): add HTTP statusCode check for GLM rate limit fallback

isRetryableModelError() now checks the HTTP status code (429/503/529)
in addition to existing message pattern matching. This ensures rate
limit errors trigger model fallback regardless of error message format
or language (e.g., Chinese GLM errors).

Changes:
- ErrorInfo interface extended with statusCode?: number
- isRetryableModelError() checks statusCode after STOP patterns, before
  message pattern fallback
- extractErrorStatusCode() added to error-classifier.ts (supports
  statusCode, status, code, response.status fields)
- GLM-specific STOP patterns added: daily call limit, in arrears,
  fair use policy, recharge and try — these prevent quota/billing 429s
  from being treated as transient rate limits
- statusCode propagated through tryFallbackRetry and manager.ts

400 intentionally excluded from statusCode check (permanent client error).

src/features/background-agent/manager.ts

@@ -46,6 +46,7 @@ import {
   isAbortedSessionError,
   extractErrorName,
   extractErrorMessage,
+  extractErrorStatusCode,
   getSessionErrorMessage,
   isRecord,
 } from "./error-classifier"
@@ -749,6 +750,7 @@ The fallback retry session is now created and can be inspected directly.
         const errorInfo = {
           name: extractErrorName(error),
           message: extractErrorMessage(error),
+          statusCode: extractErrorStatusCode(error),
         }
         if (await this.tryFallbackRetry(existingTask, errorInfo, "promptAsync.launch")) {
           return
@@ -1079,6 +1081,7 @@ The fallback retry session is now created and can be inspected directly.
       const errorInfo = {
         name: extractErrorName(error),
         message: extractErrorMessage(error),
+        statusCode: extractErrorStatusCode(error),
       }
       if (await this.tryFallbackRetry(existingTask, errorInfo, "promptAsync.resume")) {
         return
@@ -1199,6 +1202,7 @@ The fallback retry session is now created and can be inspected directly.
       const errorInfo = {
         name: extractErrorName(assistantError),
         message: extractErrorMessage(assistantError),
+        statusCode: extractErrorStatusCode(assistantError),
       }
       void this.tryFallbackRetry(task, errorInfo, "message.updated").catch((error) => {
         log("[background-agent] Error handling message.updated fallback retry:", {
@@ -1444,7 +1448,7 @@ The fallback retry session is now created and can be inspected directly.
 
   private async handleSessionErrorEvent(args: {
     task: BackgroundTask
-    errorInfo: { name?: string; message?: string }
+    errorInfo: { name?: string; message?: string; statusCode?: number }
     errorName: string | undefined
     errorMessage: string | undefined
   }): Promise<void> {
@@ -1532,7 +1536,7 @@ The fallback retry session is now created and can be inspected directly.
 
   private tryFallbackRetry(
     task: BackgroundTask,
-    errorInfo: { name?: string; message?: string },
+    errorInfo: { name?: string; message?: string; statusCode?: number },
     source: string,
   ): Promise<boolean> {
     const previousSessionID = task.sessionId