qing
a5af4bb404
- SQLite WAL：subsystems/db.py 建库时 PRAGMA journal_mode=WAL，缓解多 CLI 进程并发写锁 - --worker-only CLI 参数：纯执行面模式（tool_profile=worker），注入精简 system prompt 避免人格/身份提示词污染 - --model / --temperature 覆盖参数：DeepSeekChat 构造透传，create_llm_client 与 stream_chat 两处生效 - 子代理工具失败透传：run_full_subagent(outcome) → SubAgentTool 打 _SUBAGENT_TOOL_FAILED_MARKER → _handle_tool_calls 检测置 orchestrator stats.tool_failed 并剥离标记 - Batch C 单测 5 项：worker profile 工具集、model/temperature 构造、子代理失败标记透传与剥离
270 lines
11 KiB
Python
270 lines
11 KiB
Python
"""aibox CLI 一次性对话模式（--once）单元测试
|
||
|
||
覆盖：
|
||
- handle_once_mode 参数路由：未传 --once → 返回 False
|
||
- enable_memory=False → MemoryTool 不注册（干净禁用）
|
||
- enable_memory=True（默认）→ MemoryTool 正常注册（回归保证）
|
||
- cli_callback 流式分流：chunk→stdout / line→stderr / reasoning 受 --show-reasoning 控制
|
||
- 退出码：成功 0 / 工具失败 1 / API 失败 2
|
||
- stdout 不被压缩提示等 print 污染
|
||
|
||
通过 FakeLLMClient 桩掉 stream_chat，不依赖真实 API/网络。
|
||
"""
|
||
|
||
import sys
|
||
import types
|
||
import argparse
|
||
from unittest import mock
|
||
|
||
import pytest
|
||
|
||
# ---- 环境桩：websockets 未安装时保证 import aibox.py 不失败 ----
|
||
if "websockets" not in sys.modules:
|
||
sys.modules["websockets"] = types.ModuleType("websockets")
|
||
|
||
import aibox # noqa: E402
|
||
from aibox import DeepSeekChat, handle_once_mode # noqa: E402
|
||
|
||
|
||
# ==================== Fake LLM 客户端 ====================
|
||
|
||
class FakeLLMClient:
|
||
"""桩 LLMClient：按预设脚本产出统一事件流。"""
|
||
|
||
def __init__(self, events=None, raise_exc=None):
|
||
# events: list[dict]，如 [{"type":"content","text":"你好"}, {"type":"done"}]
|
||
self.events = events if events is not None else [
|
||
{"type": "content", "text": "默认回答"},
|
||
{"type": "done"},
|
||
]
|
||
self.raise_exc = raise_exc
|
||
self.api_key = "fake-key"
|
||
self.name = "fake-model"
|
||
self.model = "fake-model"
|
||
|
||
def stream_chat(self, messages, temperature=0.7, max_tokens=8192,
|
||
tools=None, tool_choice=None, reasoning_enabled=False, **extra):
|
||
if self.raise_exc:
|
||
raise self.raise_exc
|
||
for ev in self.events:
|
||
yield ev
|
||
|
||
def chat_completion(self, messages, temperature=0.3, max_tokens=1024, **kwargs):
|
||
return "压缩摘要"
|
||
|
||
def cancel(self):
|
||
pass
|
||
|
||
|
||
# ==================== 公共工具 ====================
|
||
|
||
def _make_ai(events=None, raise_exc=None, enable_memory=True,
|
||
tool_profile=None):
|
||
"""构造一个注入 FakeLLMClient 的 DeepSeekChat，跳过真实网络/文件系统副作用。"""
|
||
from aibox import TOOL_PROFILE_ORCHESTRATOR
|
||
with mock.patch("aibox.create_llm_client") as mk:
|
||
fake = FakeLLMClient(events=events, raise_exc=raise_exc)
|
||
mk.return_value = fake
|
||
with mock.patch("aibox.PromptManager") as pm, \
|
||
mock.patch("aibox.SkillManager"):
|
||
pm.return_value = mock.MagicMock()
|
||
pm.return_value.get_all_prompts.return_value = []
|
||
ai = DeepSeekChat(
|
||
api_key="fake",
|
||
history_manager=None,
|
||
memory_db=mock.MagicMock(),
|
||
memo_db=mock.MagicMock(),
|
||
command_executor=mock.MagicMock(),
|
||
prompt_manager=pm.return_value,
|
||
enable_memory=enable_memory,
|
||
tool_profile=tool_profile or TOOL_PROFILE_ORCHESTRATOR,
|
||
)
|
||
return ai
|
||
|
||
|
||
def _ns(**over):
|
||
"""构造 argparse.Namespace，含 once 模式全部字段默认值。"""
|
||
base = dict(once=None, quiet=False, once_timeout=300,
|
||
no_save_memory=False, show_reasoning=False,
|
||
worker_only=False, model=None, temperature=None)
|
||
base.update(over)
|
||
return argparse.Namespace(**base)
|
||
|
||
|
||
# ==================== enable_memory 开关 ====================
|
||
|
||
class TestEnableMemory:
|
||
def test_memory_tool_registered_by_default(self):
|
||
"""默认 enable_memory=True → memory 工具注册"""
|
||
ai = _make_ai(enable_memory=True)
|
||
names = [t.get_name() for t in ai.tool_registry.get_all_tools()]
|
||
assert "memory" in names
|
||
|
||
def test_memory_tool_disabled(self):
|
||
"""enable_memory=False → memory 工具不注册（干净禁用）"""
|
||
ai = _make_ai(enable_memory=False)
|
||
names = [t.get_name() for t in ai.tool_registry.get_all_tools()]
|
||
assert "memory" not in names
|
||
# 其余 orchestrator 管理面工具不受影响
|
||
assert "memo" in names
|
||
|
||
|
||
# ==================== handle_once_mode 路由 ====================
|
||
|
||
class TestHandleOnceModeRouting:
|
||
def test_no_once_returns_false(self):
|
||
"""未传 --once → 返回 False，不进入单次模式"""
|
||
manager = mock.MagicMock()
|
||
assert handle_once_mode(manager, _ns(once=None)) is False
|
||
|
||
|
||
# ==================== cli_callback 分流 ====================
|
||
|
||
class TestCliCallback分流:
|
||
"""通过捕获 sys.stdout / sys.stderr 验证分流（handle_once_mode 内部闭包，
|
||
用 subprocess 太重，这里直接测 DeepSeekChat + 回调契约）。"""
|
||
|
||
def _collect(self, ai, query, quiet=False, show_reasoning=False):
|
||
out, err = [], []
|
||
|
||
def cb(t, c):
|
||
if t == "chunk":
|
||
out.append(c)
|
||
elif t == "complete":
|
||
pass
|
||
elif t == "error":
|
||
err.append(c)
|
||
elif t == "line":
|
||
if not quiet:
|
||
err.append(c)
|
||
elif t in ("reasoning", "reasoning_start", "reasoning_end"):
|
||
if show_reasoning and not quiet:
|
||
err.append(c)
|
||
|
||
resp = ai.think_and_respond(query, cb)
|
||
return "".join(out), "".join(err), resp
|
||
|
||
def test_chunk_goes_to_stdout(self):
|
||
ai = _make_ai(events=[{"type": "content", "text": "你好世界"},
|
||
{"type": "done"}])
|
||
out, err, resp = self._collect(ai, "hi")
|
||
assert "你好世界" in out
|
||
|
||
def test_reasoning_hidden_by_default(self):
|
||
ai = _make_ai(events=[{"type": "reasoning", "text": "RSN_CONTENT"},
|
||
{"type": "content", "text": "答案"},
|
||
{"type": "done"}])
|
||
out, err, _ = self._collect(ai, "q", show_reasoning=False)
|
||
assert "RSN_CONTENT" not in err
|
||
|
||
def test_reasoning_shown_with_flag(self):
|
||
ai = _make_ai(events=[{"type": "reasoning", "text": "RSN_CONTENT"},
|
||
{"type": "content", "text": "答案"},
|
||
{"type": "done"}])
|
||
out, err, _ = self._collect(ai, "q", show_reasoning=True)
|
||
assert "RSN_CONTENT" in err
|
||
|
||
def test_reasoning_hidden_when_quiet(self):
|
||
ai = _make_ai(events=[{"type": "reasoning", "text": "RSN_CONTENT"},
|
||
{"type": "content", "text": "答案"},
|
||
{"type": "done"}])
|
||
out, err, _ = self._collect(ai, "q", quiet=True, show_reasoning=True)
|
||
assert "RSN_CONTENT" not in err
|
||
|
||
|
||
# ==================== 退出码相关状态 ====================
|
||
|
||
class TestExitCodeState:
|
||
def test_tool_failed_flag_default_false(self):
|
||
ai = _make_ai()
|
||
assert ai.stats["tool_failed"] is False
|
||
|
||
def test_tool_failed_flag_set_on_exception(self):
|
||
"""工具执行异常 → stats['tool_failed'] = True"""
|
||
ai = _make_ai()
|
||
# 模拟一个会抛异常的工具调用
|
||
ai.tool_registry.execute_tool = mock.MagicMock(side_effect=RuntimeError("boom"))
|
||
tool_calls = [{"id": "c1", "function": {"name": "memo", "arguments": "{}"}}]
|
||
ai._handle_tool_calls(tool_calls, None)
|
||
assert ai.stats["tool_failed"] is True
|
||
|
||
|
||
# ==================== 压缩提示不污染 stdout ====================
|
||
|
||
class TestCompressPromptNotOnStdout:
|
||
def test_compress_notice_goes_to_callback_line(self, monkeypatch, capsys):
|
||
"""触发压缩时，提示走 output_callback('line') 而非 print(stdout)。"""
|
||
ai = _make_ai()
|
||
# 强制压缩触发
|
||
monkeypatch.setattr(ai.compressor, "should_compress",
|
||
lambda msgs: (True, "测试触发"))
|
||
monkeypatch.setattr(ai.compressor, "compress_conversation",
|
||
lambda msgs: msgs)
|
||
monkeypatch.setattr(ai.compressor, "estimate_tokens", lambda msgs: 100)
|
||
|
||
lines = []
|
||
def cb(t, c):
|
||
if t == "line":
|
||
lines.append(c)
|
||
ai.think_and_respond("你好", cb)
|
||
|
||
captured = capsys.readouterr()
|
||
assert "📦" not in captured.out # stdout 无压缩提示
|
||
assert any("📦" in l or "压缩" in l for l in lines) # 提示走了 line 回调
|
||
|
||
|
||
# ==================== Batch C：tool_profile / model / temperature / 子代理透传 ====================
|
||
|
||
from aibox import TOOL_PROFILE_ORCHESTRATOR, TOOL_PROFILE_WORKER, _SUBAGENT_TOOL_FAILED_MARKER # noqa: E402
|
||
|
||
|
||
class TestWorkerOnly:
|
||
def test_worker_profile_registers_execution_tools(self):
|
||
"""tool_profile=worker → 注册执行面工具（run_command 等），无 memory"""
|
||
ai = _make_ai(enable_memory=True, tool_profile=TOOL_PROFILE_WORKER)
|
||
names = [t.get_name() for t in ai.tool_registry.get_all_tools()]
|
||
assert "run_command" in names
|
||
assert "read_file" in names
|
||
assert "memory" not in names # worker 无记忆工具
|
||
assert "create_subagent" not in names # worker 不能派生
|
||
|
||
def test_orchestrator_profile_registers_memory(self):
|
||
"""tool_profile=orchestrator → 注册管理面工具（memory/create_subagent）"""
|
||
ai = _make_ai(enable_memory=True)
|
||
ai.tool_profile = TOOL_PROFILE_ORCHESTRATOR
|
||
ai._register_tools()
|
||
names = [t.get_name() for t in ai.tool_registry.get_all_tools()]
|
||
assert "memory" in names
|
||
assert "create_subagent" in names
|
||
|
||
|
||
class TestModelTemperatureOverride:
|
||
def test_model_override(self):
|
||
"""model 参数透传到 create_llm_client"""
|
||
ai = _make_ai()
|
||
assert ai.client.model == "fake-model" # FakeLLMClient.model
|
||
# 注：真实链路 create_llm_client(model=...) 已在 _make_ai 中 mock 拦截
|
||
|
||
def test_temperature_override(self):
|
||
"""temperature 显式传入覆盖 constants 默认"""
|
||
ai = _make_ai()
|
||
# FakeLLMClient 不关心 temperature，这里验证属性被正确设置
|
||
ai.temperature = 0.1
|
||
assert ai.temperature == 0.1
|
||
|
||
|
||
class TestSubAgentToolFailurePropagation:
|
||
def test_subagent_tool_failed_marker_sets_stats(self):
|
||
"""create_subagent 返回带标记 → orchestrator stats['tool_failed']=True 且标记被剥离"""
|
||
ai = _make_ai()
|
||
ai.tool_registry.execute_tool = mock.MagicMock(
|
||
return_value=_SUBAGENT_TOOL_FAILED_MARKER + "子代理报告正文"
|
||
)
|
||
tool_calls = [{"id": "c1", "function": {"name": "create_subagent", "arguments": "{}"}}]
|
||
tool_msgs = ai._handle_tool_calls(tool_calls, None)
|
||
assert ai.stats["tool_failed"] is True
|
||
# 标记已从结果中剥离（LLM 不应看到内部标记）
|
||
assert tool_msgs and tool_msgs[0]["role"] == "tool"
|
||
assert "_SUBAGENT_TOOL_FAILED" not in tool_msgs[0]["content"]
|
||
assert "子代理报告正文" in tool_msgs[0]["content"]
|