From adf178a6b95c61506ddaadaf4dd062badb4a8fda Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=86=AF=E5=9F=BA=E9=AD=81?=
 <56265583+fengjikui@users.noreply.github.com>
Date: Tue, 7 Jul 2026 22:46:27 +0800
Subject: [PATCH] fix(llm): classify zai token limit overflow (#35671)

---
 packages/llm/src/provider-error.ts                | 1 +
 packages/llm/test/provider-error.test.ts          | 8 ++++++++
 packages/opencode/test/session/message-v2.test.ts | 1 +
 3 files changed, 10 insertions(+)
 create mode 100644 packages/llm/test/provider-error.test.ts

diff --git a/packages/llm/src/provider-error.ts b/packages/llm/src/provider-error.ts
index 8d3f2a8f63a..321bd7927ef 100644
--- a/packages/llm/src/provider-error.ts
+++ b/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,
diff --git a/packages/llm/test/provider-error.test.ts b/packages/llm/test/provider-error.test.ts
new file mode 100644
index 00000000000..3622c894541
--- /dev/null
+++ b/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)
+  })
+})
diff --git a/packages/opencode/test/session/message-v2.test.ts b/packages/opencode/test/session/message-v2.test.ts
index 1de84c9dd95..9bb688aeddb 100644
--- a/packages/opencode/test/session/message-v2.test.ts
+++ b/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)",