feat(glm): max_tokens 可选透传（site-import 前置）

max_tokens 探针结论: 8192 可用（glm-4-flash 实测 max_tokens=8192 调用成功返回，finish_reason=stop；Task 5 可按 8192 取值）

Co-Authored-By: Claude Code <noreply@anthropic.com>

tests/test_glm_provider.py

@@ -0,0 +1,34 @@
+"""GLMProvider max_tokens 透传（site-import spec §3.2）。"""
+from unittest.mock import MagicMock, patch
+
+from app.engine.providers.glm import GLMProvider
+
+
+def _provider(**kw):
+    with patch("app.engine.providers.glm.ZhipuAI"):
+        return GLMProvider(api_key="k", **kw)
+
+
+def _ok(cli):
+    cli.chat.completions.create.return_value.choices = [
+        MagicMock(message=MagicMock(content="ok"))]
+
+
+class TestMaxTokensPassthrough:
+    def test_默认不传_调用无max_tokens参数(self):
+        import asyncio
+        p = _provider()
+        with patch.object(p, "client") as cli:
+            _ok(cli)
+            asyncio.run(p.chat([{"role": "user", "content": "hi"}], "sys"))
+            _, kwargs = cli.chat.completions.create.call_args
+            assert "max_tokens" not in kwargs
+
+    def test_传入max_tokens_透传到create(self):
+        import asyncio
+        p = _provider(max_tokens=4096)
+        with patch.object(p, "client") as cli:
+            _ok(cli)
+            asyncio.run(p.chat([{"role": "user", "content": "hi"}], "sys"))
+            _, kwargs = cli.chat.completions.create.call_args
+            assert kwargs.get("max_tokens") == 4096