feat(engine): allow replay tool executor injection

app-instance/backend/tests/unit/test_agent_loop_replay_executor.py

@@ -0,0 +1,71 @@
+from __future__ import annotations
+
+from pathlib import Path
+from types import SimpleNamespace
+
+import pytest
+
+from beaver.engine.loader import EngineLoader
+from beaver.engine.loop import AgentLoop
+from beaver.engine.providers.base import LLMProvider, LLMResponse, ToolCallRequest
+from beaver.engine.providers.factory import ProviderBundle
+from beaver.skills.learning.replay import ReplayToolExecutor, ReplayToolPolicy
+
+
+class ToolCallingProvider(LLMProvider):
+    def __init__(self) -> None:
+        super().__init__()
+        self.calls = 0
+
+    async def chat(
+        self,
+        messages: list[dict],
+        tools: list[dict] | None = None,
+        model: str | None = None,
+        max_tokens: int | None = None,
+        temperature: float = 0.7,
+        thinking_enabled: bool | None = None,
+    ) -> LLMResponse:
+        self.calls += 1
+        if self.calls == 1:
+            return LLMResponse(
+                content="",
+                tool_calls=[
+                    ToolCallRequest(
+                        id="call-1",
+                        name="read_file",
+                        arguments={"path": "README.md"},
+                    )
+                ],
+            )
+        return LLMResponse(content="done")
+
+    def get_default_model(self) -> str:
+        return "stub"
+
+
+@pytest.mark.asyncio
+async def test_process_direct_uses_replay_tool_executor(tmp_path: Path) -> None:
+    loop = AgentLoop(loader=EngineLoader(workspace=tmp_path))
+    loaded = loop.boot()
+    provider = ToolCallingProvider()
+    runtime = SimpleNamespace(model="stub", provider_name="stub")
+    replay_executor = ReplayToolExecutor(
+        loaded.tool_executor,
+        registry=loaded.tool_registry,
+        policy=ReplayToolPolicy(),
+    )
+
+    result = await loop.process_direct(
+        "Read the README.",
+        provider_bundle=ProviderBundle(main_runtime=runtime, main_provider=provider),  # type: ignore[arg-type]
+        include_skill_assembly=False,
+        pinned_skill_names=[],
+        tool_executor_override=replay_executor,
+        max_tool_iterations=2,
+        source="skill_replay_eval",
+    )
+
+    assert result.output_text == "done"
+    assert replay_executor.traces
+    assert replay_executor.traces[0]["tool_name"] == "read_file"