feat(skill-learning): run replay arms through agent loop

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

@@ -0,0 +1,36 @@
+from __future__ import annotations
+
+import asyncio
+from types import SimpleNamespace
+
+from beaver.skills.learning.replay import ReplayArmRequest, ReplayRunner
+
+
+class FakeAgentLoop:
+    def boot(self):
+        return SimpleNamespace(tool_executor=SimpleNamespace(), tool_registry=SimpleNamespace(get=lambda name: None))
+
+    async def process_direct(self, task: str, **kwargs):
+        executor = kwargs["tool_executor_override"]
+        await executor.execute("mcp_outlook_send_email", {"to": "ada@example.com"})
+        return SimpleNamespace(session_id="session-replay", run_id="run-replay", output_text="done", finish_reason="stop")
+
+
+def test_replay_runner_returns_arm_report_with_tool_trace() -> None:
+    runner = ReplayRunner(agent_loop=FakeAgentLoop())
+    request = ReplayArmRequest(
+        case_id="case-1",
+        arm="candidate",
+        task_text="Send a status email to Ada.",
+        pinned_skill_names=[],
+        pinned_skill_contexts=[],
+        provider_bundle=object(),
+        model_settings={"max_tool_iterations": 2},
+    )
+
+    report = asyncio.run(runner.run_arm(request))
+
+    assert report["case_id"] == "case-1"
+    assert report["arm"] == "candidate"
+    assert report["finish_reason"] == "stop"
+    assert report["tool_calls"][0]["tool_name"] == "mcp_outlook_send_email"