test: 清理 backlog——chat_structured 超限检测 + client 上下文管理器

tests/test_inference_engine.py

@@ -1,14 +1,10 @@
 from __future__ import annotations
 
-import json
-
-import pytest
-
 from genesis.inference.engine import InferenceEngine
 from genesis.inference.exceptions import LLMError
 from genesis.inference.prompt_registry import PromptRegistry
 from genesis.inference.token import approximate_token_count
-from genesis.inference.types import ChatMessage, Prompt
+from genesis.inference.types import Prompt
 from tests.inference_helpers import FakeLLMClient
 
 
@@ -161,6 +157,32 @@ def test_chat_structured_failed_on_network():
     assert r.status == "failed"
 
 
+def test_chat_structured_truncation_callback_triggered():
+    # chat_structured 超限时同样触发 truncate_cb（与 chat 流程一致）
+    seen = {}
+
+    def truncate_cb(prompt_text, variables):
+        seen["called"] = True
+        return {**variables, "chapter": "裁剪版"}
+
+    eng = InferenceEngine(
+        client=FakeLLMClient([("ok", '{"a": 1}')]),
+        models=Models(),
+        registry=PromptRegistry(),
+        estimator=approximate_token_count,
+        truncate_cb=truncate_cb,
+    )
+    eng._max_context_tokens = 2  # 强制超限（渲染约 3 token > 2）
+    r = eng.chat_structured(
+        session_id="s1",
+        prompt=Prompt(name="p", version="v1", template="abcd{{ chapter }}"),
+        variables={"chapter": "很长很长的标题"},
+        schema={"type": "object", "properties": {"a": {"type": "number"}}},
+    )
+    assert seen["called"] is True
+    assert r.status == "ok"
+
+
 # ---------- 补充分支覆盖（defensive / 缺失配置） ----------
 
 def test_chat_fallback_all_failed_when_only_primary():