feat(inference): chat_structured 接入 jsonschema 真校验（T1 架构审查整改）

- pyproject.toml 新增 jsonschema>=4.23 依赖
- engine.py: json.loads 后 jsonschema.validate，校验失败按解析失败重试（带错误信息）
- 新增 3 用例：违规重试成功/耗尽 parse_error 含详情/合法一次通过
- 全量 163 passed / 100.00% 覆盖（936 stmts/238 br），fail_under=99 达标

tests/test_inference_engine.py

@@ -318,6 +318,49 @@ def test_chat_structured_empty_schema_no_hint():
     assert r.status == "ok" and r.data == {"v": True}
 
 
+# ---------- T1: chat_structured 真 schema 校验（jsonschema） ----------
+
+def test_chat_structured_schema_violation_retries():
+    """返回不合 schema 的 JSON 时带错误信息重试；第二次合法 → ok。"""
+    client = FakeLLMClient([("ok", '{"a": "not_a_number"}'), ("ok", '{"a": 2}')])
+    eng = make_engine(client)
+    r = eng.chat_structured(
+        session_id="s1", prompt=Prompt(name="p", version="v1", template="提取"),
+        variables={},
+        schema={"type": "object", "properties": {"a": {"type": "number"}}, "required": ["a"]},
+    )
+    assert r.status == "ok" and r.data == {"a": 2} and r.parse_attempts == 2
+    # 第二次调用带上次校验错误信息（重试提示）
+    assert "校验失败" in client.calls[1]["messages"][0]
+
+
+def test_chat_structured_schema_violation_parse_error():
+    """全部返回不合 schema 的 JSON → parse_error，error 含校验详情。"""
+    client = FakeLLMClient([("ok", '{"a": "bad"}'), ("ok", '{"a": "bad"}')])
+    eng = make_engine(client)
+    r = eng.chat_structured(
+        session_id="s1", prompt=Prompt(name="p", version="v1", template="提取"),
+        variables={},
+        schema={"type": "object", "properties": {"a": {"type": "number"}}, "required": ["a"]},
+        retry_count=1,
+    )
+    assert r.status == "parse_error"
+    assert "校验失败" in (r.error or "")
+    assert r.parse_attempts == 2
+
+
+def test_chat_structured_schema_valid_passes_without_retry():
+    """返回合法 JSON 时一次通过，不触发重试。"""
+    client = FakeLLMClient([("ok", '{"a": 1}')])
+    eng = make_engine(client)
+    r = eng.chat_structured(
+        session_id="s1", prompt=Prompt(name="p", version="v1", template="提取"),
+        variables={},
+        schema={"type": "object", "properties": {"a": {"type": "number"}}, "required": ["a"]},
+    )
+    assert r.status == "ok" and r.data == {"a": 1} and r.parse_attempts == 1
+
+
 def test_chat_truncation_callback_returns_none_keeps_variables():
     """truncate_cb 返回 None 时回退原 variables（覆盖 new_vars is None 分支）。"""
     def truncate_cb(prompt_text, variables):