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

src/genesis/inference/client.py

@@ -48,6 +48,13 @@ class HttpLLMClient:
         self._retry_backoff = retry_backoff
         self._client = httpx.Client(timeout=timeout_sec, transport=transport)
 
+    def __enter__(self) -> HttpLLMClient:
+        """支持 with 块：退出时自动关闭底层连接。"""
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb) -> None:
+        self._client.close()
+
     def chat(
         self,
         *,

src/genesis/inference/engine.py

@@ -133,6 +133,9 @@ class InferenceEngine:
         retry_count: int = 2,
     ) -> StructuredResult:
         rendered = self._render_prompt(prompt, variables)
+        if self._estimator(rendered) > self._max_context_tokens:
+            variables = self._apply_truncation(rendered, variables)
+            rendered = self._render_prompt(prompt, variables)
         # 追加 schema 约束说明（不强制模板支持）
         schema_hint = json.dumps(schema, ensure_ascii=False) if schema else ""
         base_rendered = rendered + (f'\n\n请输出符合以下 JSON Schema 的 JSON：{schema_hint}' if schema_hint else "")