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/shared/model-error-classifier.test.ts

@@ -3,7 +3,7 @@ const { describe, expect, test, beforeEach, afterEach, mock, spyOn } = require("
 import * as connectedProvidersCache from "./connected-providers-cache"
 
 let readConnectedProvidersCacheSpy: ReturnType<typeof spyOn> | undefined
-const { shouldRetryError, selectFallbackProvider } = await import("./model-error-classifier")
+const { shouldRetryError, selectFallbackProvider, isRetryableModelError } = await import("./model-error-classifier")
 
 describe("model-error-classifier", () => {
   beforeEach(() => {
@@ -270,6 +270,139 @@ describe("model-error-classifier", () => {
     //#then
     expect(result).toBe(false)
   })
+
+  test("GLM 429 rate limit with statusCode and Chinese message triggers fallback (statusCode check)", () => {
+    //#given
+    const error = { statusCode: 429, message: "请求频率过高" }
+
+    //#when
+    const result = isRetryableModelError(error)
+
+    //#then
+    expect(result).toBe(true)
+  })
+
+  test("GLM 429 rate limit with statusCode and no message at all triggers fallback", () => {
+    //#given
+    const error = { statusCode: 429 }
+
+    //#when
+    const result = isRetryableModelError(error)
+
+    //#then
+    expect(result).toBe(true)
+  })
+
+  test("GLM 503 service unavailable with statusCode triggers fallback", () => {
+    //#given
+    const error = { statusCode: 503, message: "Service Unavailable" }
+
+    //#when
+    const result = isRetryableModelError(error)
+
+    //#then
+    expect(result).toBe(true)
+  })
+
+  test("GLM 529 overloaded with statusCode triggers fallback", () => {
+    //#given
+    const error = { statusCode: 529 }
+
+    //#when
+    const result = isRetryableModelError(error)
+
+    //#then
+    expect(result).toBe(true)
+  })
+
+  test("HTTP 400 with statusCode does NOT trigger fallback via statusCode alone (400 excluded)", () => {
+    //#given — message does NOT match any retryable pattern
+    const error = { statusCode: 400, message: "Invalid parameter: model_name" }
+
+    //#when
+    const result = isRetryableModelError(error)
+
+    //#then
+    expect(result).toBe(false)
+  })
+
+  test("HTTP 401 with statusCode does NOT trigger fallback (not a rate limit)", () => {
+    //#given
+    const error = { statusCode: 401, message: "Unauthorized" }
+
+    //#when
+    const result = isRetryableModelError(error)
+
+    //#then
+    expect(result).toBe(false)
+  })
+
+  test("GLM code 1304 daily quota 429 does NOT trigger fallback (STOP pattern wins)", () => {
+    //#given
+    const error = {
+      statusCode: 429,
+      message: "Daily call limit for this API key has been reached. Limit will reset at midnight UTC.",
+    }
+
+    //#when
+    const result = isRetryableModelError(error)
+
+    //#then
+    expect(result).toBe(false)
+  })
+
+  test("GLM account in arrears 429 does NOT trigger fallback (STOP pattern wins)", () => {
+    //#given
+    const error = {
+      statusCode: 429,
+      message: "Your account is in arrears, please recharge and try again.",
+    }
+
+    //#when
+    const result = isRetryableModelError(error)
+
+    //#then
+    expect(result).toBe(false)
+  })
+
+  test("GLM fair use policy violation 429 does NOT trigger fallback (STOP pattern wins)", () => {
+    //#given
+    const error = {
+      statusCode: 429,
+      message: "Request blocked under Fair Use Policy. Your request rate has been restricted.",
+    }
+
+    //#when
+    const result = isRetryableModelError(error)
+
+    //#then
+    expect(result).toBe(false)
+  })
+
+  test("STOP message pattern takes precedence over 429 statusCode", () => {
+    //#given
+    const error = {
+      statusCode: 429,
+      message: "quota exceeded for this account, usage limit has been reached",
+    }
+
+    //#when
+    const result = isRetryableModelError(error)
+
+    //#then
+    expect(result).toBe(false)
+  })
+
+  test("rate limit message without statusCode still works (backward compat)", () => {
+    //#given
+    const error = { message: "rate limit reached for requests" }
+
+    //#when
+    const result = isRetryableModelError(error)
+
+    //#then
+    expect(result).toBe(true)
+  })
 })
 
 export {}