feat(core): 添加 LLMResponse frozen dataclass

含 content/thinking/ttft_ms/max_inter_token_ms/call_id 等 11 个字段。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

core/types.py

@@ -1 +1,24 @@
 """跨模块共享类型。"""
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+
+@dataclass(frozen=True)
+class LLMResponse:
+    """LLM/VLM 调用的统一返回值。
+
+    由 adapters 层生成，core 层消费。frozen=True 确保响应不可变。
+    """
+
+    content: str
+    thinking: str
+    model: str
+    provider: str
+    prompt_tokens: int
+    completion_tokens: int
+    latency_ms: int
+    ttft_ms: float | None
+    max_inter_token_ms: float | None
+    cache_hit: bool
+    call_id: str

tests/unit/test_core_types.py

@@ -0,0 +1,51 @@
+"""core/types.py 单元测试。"""
+from __future__ import annotations
+
+import pytest
+
+from core.types import LLMResponse
+
+
+class TestLLMResponse:
+    @pytest.fixture()
+    def sample_response(self) -> LLMResponse:
+        return LLMResponse(
+            content="回答内容",
+            thinking="思考过程",
+            model="deepseek-v4-pro",
+            provider="deepseek",
+            prompt_tokens=100,
+            completion_tokens=50,
+            latency_ms=1200,
+            ttft_ms=350.0,
+            max_inter_token_ms=45.0,
+            cache_hit=False,
+            call_id="test-uuid-001",
+        )
+
+    def test_frozen_prevents_mutation(self, sample_response: LLMResponse) -> None:
+        with pytest.raises(AttributeError):
+            sample_response.content = "篡改"
+
+    def test_all_fields_accessible(self, sample_response: LLMResponse) -> None:
+        assert sample_response.content == "回答内容"
+        assert sample_response.thinking == "思考过程"
+        assert sample_response.model == "deepseek-v4-pro"
+        assert sample_response.provider == "deepseek"
+        assert sample_response.prompt_tokens == 100
+        assert sample_response.completion_tokens == 50
+        assert sample_response.latency_ms == 1200
+        assert sample_response.ttft_ms == 350.0
+        assert sample_response.max_inter_token_ms == 45.0
+        assert sample_response.cache_hit is False
+        assert sample_response.call_id == "test-uuid-001"
+
+    def test_cache_hit_response_has_none_ttft(self) -> None:
+        resp = LLMResponse(
+            content="cached", thinking="", model="m", provider="p",
+            prompt_tokens=0, completion_tokens=0, latency_ms=1,
+            ttft_ms=None, max_inter_token_ms=None, cache_hit=True, call_id="c",
+        )
+        assert resp.ttft_ms is None
+        assert resp.max_inter_token_ms is None
+        assert resp.cache_hit is True