feat: inject run_id as cache_salt for per-epoch resampling (algo #10)

tests/unit/test_agent_loop.py

@@ -94,6 +94,17 @@ def _invalid_tool_json() -> str:
 class TestAgentLoop:
     """AgentLoop 推理循环引擎测试。"""
 
+    @pytest.mark.asyncio
+    async def test_forwards_cache_salt(self) -> None:
+        """AgentLoop.run(cache_salt=...) 透传到 llm.chat（算法 #10 跨 epoch 重采样）。"""
+        llm = AsyncMock()
+        llm.chat.return_value = _make_response(_submit_json())
+
+        loop = AgentLoop(llm=llm, max_steps=10)
+        await loop.run("system", "user", _StubDispatcher(), cache_salt="run:e2")
+
+        assert llm.chat.call_args.kwargs["cache_salt"] == "run:e2"
+
     @pytest.mark.asyncio
     async def test_submit_answer_terminates_loop(self) -> None:
         """submit_answer 终止循环 → finished, result=args, steps_used=1。"""

tests/unit/test_harness_inference.py

@@ -698,6 +698,7 @@ class TestConcurrencyControl:
             *,
             session_id: str | None = None,
             parent_call_id: str | None = None,
+            cache_salt: str | None = None,
         ) -> LLMResponse:
             nonlocal current_concurrent, max_concurrent
             current_concurrent += 1