test(agent-runner): strengthen local agent e2e gate

tests/unit_tests/provider/conftest.py

@@ -8,6 +8,8 @@ without calling real LLM APIs or network requests.
 from __future__ import annotations
 
 import json
+import inspect
+from typing import Any
 
 import pytest
 from unittest.mock import AsyncMock, Mock
@@ -32,7 +34,11 @@ class FakeProviderAPIRequester(requester.ProviderAPIRequester):
         self._invoke_count = 0
         self._last_messages = None
         self._last_model = None
+        self._last_funcs = None
+        self._invoke_payloads = []
         self._last_count_tokens_payload = None
+        self._count_tokens_payloads = []
+        self._scripted_llm_responses = []
 
     @staticmethod
     def _content_to_text(content) -> str:
@@ -52,6 +58,44 @@ class FakeProviderAPIRequester(requester.ProviderAPIRequester):
             return ''.join(parts)
         return str(content)
 
+    def queue_llm_responses(self, *responses: Any) -> None:
+        """Queue deterministic LLM responses for multi-turn tests."""
+        self._scripted_llm_responses.extend(responses)
+
+    async def _coerce_llm_response(
+        self,
+        response: Any,
+        *,
+        query: Any,
+        model: requester.RuntimeLLMModel,
+        messages: list,
+        funcs: list | None,
+        extra_args: dict,
+        remove_think: bool,
+    ):
+        """Convert scripted response values into provider Message objects."""
+        import langbot_plugin.api.entities.builtin.provider.message as provider_message
+
+        if callable(response):
+            response = response(
+                query=query,
+                model=model,
+                messages=messages,
+                funcs=funcs,
+                extra_args=extra_args,
+                remove_think=remove_think,
+            )
+            if inspect.isawaitable(response):
+                response = await response
+
+        if isinstance(response, provider_message.Message):
+            return response
+        if isinstance(response, dict):
+            return provider_message.Message.model_validate(response)
+        if isinstance(response, str):
+            return provider_message.Message(role='assistant', content=response)
+        return response
+
     async def invoke_llm(
         self,
         query,
@@ -65,10 +109,30 @@ class FakeProviderAPIRequester(requester.ProviderAPIRequester):
         self._invoke_count += 1
         self._last_messages = messages
         self._last_model = model
+        self._last_funcs = funcs or []
+        self._invoke_payloads.append(
+            {
+                'messages': messages,
+                'funcs': funcs or [],
+                'extra_args': dict(extra_args or {}),
+                'remove_think': remove_think,
+            }
+        )
 
         # Import the message entity for response
         import langbot_plugin.api.entities.builtin.provider.message as provider_message
 
+        if self._scripted_llm_responses:
+            return await self._coerce_llm_response(
+                self._scripted_llm_responses.pop(0),
+                query=query,
+                model=model,
+                messages=messages,
+                funcs=funcs,
+                extra_args=extra_args,
+                remove_think=remove_think,
+            )
+
         return provider_message.Message(
             role='assistant',
             content=[provider_message.ContentElement(type='text', text='Fake LLM response')],
@@ -106,6 +170,7 @@ class FakeProviderAPIRequester(requester.ProviderAPIRequester):
                     'role': getattr(message, 'role', ''),
                     'content': self._content_to_text(getattr(message, 'content', None)),
                     'tool_calls': getattr(message, 'tool_calls', None),
+                    'tool_call_id': getattr(message, 'tool_call_id', None),
                 }
             )
 
@@ -119,6 +184,7 @@ class FakeProviderAPIRequester(requester.ProviderAPIRequester):
             )
 
         self._last_count_tokens_payload = payload
+        self._count_tokens_payloads.append(payload)
         text = json.dumps(payload, ensure_ascii=False, sort_keys=True, default=str)
         return max(1, (len(text) + 3) // 4)
 

tests/unit_tests/test_skill_service.py

@@ -2,6 +2,7 @@ from types import SimpleNamespace
 from unittest.mock import AsyncMock
 
 import pytest
+from langbot_plugin.entities.io.errors import ActionCallTimeoutError
 
 from langbot.pkg.api.http.service.skill import SkillService
 
@@ -82,6 +83,17 @@ class TestRequireBoxForWrite:
         service = SkillService(self._ap_with_disabled_box())
         assert await service.list_skills() == []
 
+    @pytest.mark.asyncio
+    async def test_list_skills_returns_empty_when_box_action_times_out(self):
+        """A transient Box list failure should not break unrelated extension surfaces."""
+        box_service = SimpleNamespace(
+            available=True,
+            list_skills=AsyncMock(side_effect=ActionCallTimeoutError('Action box_list_skills call timed out')),
+        )
+        service = SkillService(SimpleNamespace(skill_mgr=SimpleNamespace(reload_skills=AsyncMock()), box_service=box_service))
+
+        assert await service.list_skills() == []
+
     @pytest.mark.asyncio
     async def test_read_skill_file_refused_when_box_unavailable(self):
         service = SkillService(self._ap_with_disabled_box())