feat: harden agent runtime for long-running tasks

tests/agent/test_task_cancel.py

@@ -8,6 +8,10 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
+from nanobot.config.schema import AgentDefaults
+
+_MAX_TOOL_RESULT_CHARS = AgentDefaults().max_tool_result_chars
+
 
 def _make_loop(*, exec_config=None):
     """Create a minimal AgentLoop with mocked dependencies."""
@@ -186,7 +190,12 @@ class TestSubagentCancellation:
         bus = MessageBus()
         provider = MagicMock()
         provider.get_default_model.return_value = "test-model"
-        mgr = SubagentManager(provider=provider, workspace=MagicMock(), bus=bus)
+        mgr = SubagentManager(
+            provider=provider,
+            workspace=MagicMock(),
+            bus=bus,
+            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        )
 
         cancelled = asyncio.Event()
 
@@ -214,7 +223,12 @@ class TestSubagentCancellation:
         bus = MessageBus()
         provider = MagicMock()
         provider.get_default_model.return_value = "test-model"
-        mgr = SubagentManager(provider=provider, workspace=MagicMock(), bus=bus)
+        mgr = SubagentManager(
+            provider=provider,
+            workspace=MagicMock(),
+            bus=bus,
+            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        )
         assert await mgr.cancel_by_session("nonexistent") == 0
 
     @pytest.mark.asyncio
@@ -236,19 +250,24 @@ class TestSubagentCancellation:
             if call_count["n"] == 1:
                 return LLMResponse(
                     content="thinking",
-                    tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={})],
+                    tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={"path": "."})],
                     reasoning_content="hidden reasoning",
                     thinking_blocks=[{"type": "thinking", "thinking": "step"}],
                 )
             captured_second_call[:] = messages
             return LLMResponse(content="done", tool_calls=[])
         provider.chat_with_retry = scripted_chat_with_retry
-        mgr = SubagentManager(provider=provider, workspace=tmp_path, bus=bus)
+        mgr = SubagentManager(
+            provider=provider,
+            workspace=tmp_path,
+            bus=bus,
+            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        )
 
-        async def fake_execute(self, name, arguments):
+        async def fake_execute(self, **kwargs):
             return "tool result"
 
-        monkeypatch.setattr("nanobot.agent.tools.registry.ToolRegistry.execute", fake_execute)
+        monkeypatch.setattr("nanobot.agent.tools.filesystem.ListDirTool.execute", fake_execute)
 
         await mgr._run_subagent("sub-1", "do task", "label", {"channel": "test", "chat_id": "c1"})
 
@@ -273,6 +292,7 @@ class TestSubagentCancellation:
             provider=provider,
             workspace=tmp_path,
             bus=bus,
+            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
             exec_config=ExecToolConfig(enable=False),
         )
         mgr._announce_result = AsyncMock()
@@ -304,20 +324,25 @@ class TestSubagentCancellation:
         provider.get_default_model.return_value = "test-model"
         provider.chat_with_retry = AsyncMock(return_value=LLMResponse(
             content="thinking",
-            tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={})],
+            tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={"path": "."})],
         ))
-        mgr = SubagentManager(provider=provider, workspace=tmp_path, bus=bus)
+        mgr = SubagentManager(
+            provider=provider,
+            workspace=tmp_path,
+            bus=bus,
+            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        )
         mgr._announce_result = AsyncMock()
 
         calls = {"n": 0}
 
-        async def fake_execute(self, name, arguments):
+        async def fake_execute(self, **kwargs):
             calls["n"] += 1
             if calls["n"] == 1:
                 return "first result"
             raise RuntimeError("boom")
 
-        monkeypatch.setattr("nanobot.agent.tools.registry.ToolRegistry.execute", fake_execute)
+        monkeypatch.setattr("nanobot.agent.tools.filesystem.ListDirTool.execute", fake_execute)
 
         await mgr._run_subagent("sub-1", "do task", "label", {"channel": "test", "chat_id": "c1"})
 
@@ -340,15 +365,20 @@ class TestSubagentCancellation:
         provider.get_default_model.return_value = "test-model"
         provider.chat_with_retry = AsyncMock(return_value=LLMResponse(
             content="thinking",
-            tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={})],
+            tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={"path": "."})],
         ))
-        mgr = SubagentManager(provider=provider, workspace=tmp_path, bus=bus)
+        mgr = SubagentManager(
+            provider=provider,
+            workspace=tmp_path,
+            bus=bus,
+            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        )
         mgr._announce_result = AsyncMock()
 
         started = asyncio.Event()
         cancelled = asyncio.Event()
 
-        async def fake_execute(self, name, arguments):
+        async def fake_execute(self, **kwargs):
             started.set()
             try:
                 await asyncio.sleep(60)
@@ -356,7 +386,7 @@ class TestSubagentCancellation:
                 cancelled.set()
                 raise
 
-        monkeypatch.setattr("nanobot.agent.tools.registry.ToolRegistry.execute", fake_execute)
+        monkeypatch.setattr("nanobot.agent.tools.filesystem.ListDirTool.execute", fake_execute)
 
         task = asyncio.create_task(
             mgr._run_subagent("sub-1", "do task", "label", {"channel": "test", "chat_id": "c1"})
@@ -364,7 +394,7 @@ class TestSubagentCancellation:
         mgr._running_tasks["sub-1"] = task
         mgr._session_tasks["test:c1"] = {"sub-1"}
 
-        await started.wait()
+        await asyncio.wait_for(started.wait(), timeout=1.0)
 
         count = await mgr.cancel_by_session("test:c1")