fix(agent): let subagents recover from tool errors

tests/agent/test_runner_errors.py

@@ -9,6 +9,7 @@ from unittest.mock import AsyncMock, MagicMock
 import pytest
 
 from agent.runner_helpers import make_run_spec
+from nanobot.agent.tools import ToolResult
 from nanobot.config.schema import AgentDefaults
 from nanobot.providers.base import LLMProvider, LLMResponse, ToolCallRequest
 
@@ -16,14 +17,17 @@ _MAX_TOOL_RESULT_CHARS = AgentDefaults().max_tool_result_chars
 
 
 @pytest.mark.asyncio
-async def test_runner_returns_structured_tool_error():
+async def test_runner_returns_tool_exception_to_model_for_recovery():
     from nanobot.agent.runner import AgentRunner
 
     provider = MagicMock(spec=LLMProvider)
-    provider.chat_with_retry = AsyncMock(return_value=LLMResponse(
-        content="working",
-        tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={})],
-    ))
+    provider.chat_with_retry = AsyncMock(side_effect=[
+        LLMResponse(
+            content="working",
+            tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={})],
+        ),
+        LLMResponse(content="recovered", tool_calls=[]),
+    ])
     tools = MagicMock()
     tools.get_definitions.return_value = []
     tools.execute = AsyncMock(side_effect=RuntimeError("boom"))
@@ -36,14 +40,17 @@ async def test_runner_returns_structured_tool_error():
         model="test-model",
         max_iterations=2,
         max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-        fail_on_tool_error=True,
     ))
 
-    assert result.stop_reason == "tool_error"
-    assert result.error == "Error: RuntimeError: boom"
+    assert provider.chat_with_retry.await_count == 2
+    assert result.stop_reason == "completed"
+    assert result.error is None
+    assert result.final_content == "recovered"
     assert result.tool_events == [
         {"name": "list_dir", "status": "error", "detail": "boom"}
     ]
+    tool_message = next(message for message in result.messages if message.get("role") == "tool")
+    assert "Error: RuntimeError: boom" in tool_message["content"]
 
 
 @pytest.mark.asyncio
@@ -180,35 +187,38 @@ async def test_runner_ignores_tool_calls_when_finish_reason_blocks_execution(
 
 
 @pytest.mark.asyncio
-async def test_runner_tool_error_sets_final_content():
+async def test_runner_returns_structured_tool_error_to_model_for_recovery():
     from nanobot.agent.runner import AgentRunner
 
     provider = MagicMock(spec=LLMProvider)
 
-    async def chat_with_retry(*, messages, **kwargs):
-        return LLMResponse(
+    provider.chat_with_retry = AsyncMock(side_effect=[
+        LLMResponse(
             content="working",
             tool_calls=[ToolCallRequest(id="call_1", name="read_file", arguments={"path": "x"})],
             usage=None,
-        )
-
-    provider.chat_with_retry = chat_with_retry
+        ),
+        LLMResponse(content="used another path", tool_calls=[], usage=None),
+    ])
     tools = MagicMock()
     tools.get_definitions.return_value = []
-    tools.execute = AsyncMock(side_effect=RuntimeError("boom"))
+    tools.execute = AsyncMock(return_value=ToolResult.error("Error: File not found: x"))
 
     runner = AgentRunner()
     result = await runner.run(make_run_spec(provider,
         initial_messages=[{"role": "user", "content": "do task"}],
         tools=tools,
         model="test-model",
-        max_iterations=1,
+        max_iterations=2,
         max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-        fail_on_tool_error=True,
     ))
 
-    assert result.final_content == "Error: RuntimeError: boom"
-    assert result.stop_reason == "tool_error"
+    assert provider.chat_with_retry.await_count == 2
+    assert result.final_content == "used another path"
+    assert result.stop_reason == "completed"
+    assert result.tool_events == [
+        {"name": "read_file", "status": "error", "detail": "Error: File not found: x"}
+    ]
 
 
 @pytest.mark.asyncio
@@ -241,7 +251,6 @@ async def test_runner_preserves_successful_exec_output_that_starts_with_error():
         model="test-model",
         max_iterations=2,
         max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-        fail_on_tool_error=True,
     ))
 
     assert result.final_content == "done"
@@ -252,9 +261,8 @@ async def test_runner_preserves_successful_exec_output_that_starts_with_error():
 
 
 @pytest.mark.asyncio
-async def test_runner_tool_error_preserves_tool_results_in_messages():
-    """When a tool raises a fatal error, its results must still be appended
-    to messages so the session never contains orphan tool_calls (#2943)."""
+async def test_runner_preserves_tool_error_results_in_messages():
+    """Tool errors stay paired with their calls so the model can recover (#2943)."""
     from nanobot.agent.runner import AgentRunner
 
     provider = MagicMock(spec=LLMProvider)
@@ -292,11 +300,10 @@ async def test_runner_tool_error_preserves_tool_results_in_messages():
         model="test-model",
         max_iterations=1,
         max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
-        fail_on_tool_error=True,
     ))
 
-    assert result.stop_reason == "tool_error"
-    # Both tool results must be in messages even though tc2 had a fatal error.
+    assert result.stop_reason == "max_iterations"
+    # Both tool results must be in messages even though tc2 returned an error.
     tool_msgs = [m for m in result.messages if m.get("role") == "tool"]
     assert len(tool_msgs) == 2
     assert tool_msgs[0]["tool_call_id"] == "tc1"