fix(llm): classify zai token limit overflow (#35671)

Author: fengjikui

packages/llm/src/provider-error.ts

@@ -6,6 +6,7 @@ const patterns = [
   /input is too long for requested model/i,
   /exceeds the context window/i,
   /input token count.*exceeds the maximum/i,
+  /tokens in request more than max tokens allowed/i,
   /maximum prompt length is \d+/i,
   /reduce the length of the messages/i,
   /maximum context length is \d+ tokens/i,

packages/llm/test/provider-error.test.ts

@@ -0,0 +1,8 @@
+import { describe, expect, test } from "bun:test"
+import { isContextOverflow } from "../src"
+
+describe("provider error classification", () => {
+  test("classifies Z.AI GLM token limit messages as context overflow", () => {
+    expect(isContextOverflow("tokens in request more than max tokens allowed")).toBe(true)
+  })
+})

packages/opencode/test/session/message-v2.test.ts

@@ -1448,6 +1448,7 @@ describe("session.message-v2.fromError", () => {
       "prompt is too long: 213462 tokens > 200000 maximum",
       "Your input exceeds the context window of this model",
       "The input token count (1196265) exceeds the maximum number of tokens allowed (1048575)",
+      "tokens in request more than max tokens allowed",
       "Please reduce the length of the messages or completion",
       "400 status code (no body)",
       "413 status code (no body)",