fix(aibox): batch I audit fixes - prompt write cap, light-subagent cancel propagation, atomic history writes

Remaining-item sweep (audit report §12): - N9: cap prompt file writes (identity/soul/status, 10k chars) to bound persistent-injection surface - F5: run_light_subagent switches to stream_chat + parent cancel_event (mid-stream interrupt); ExpressEmotionTool injects parent event - Q4: busy_timeout=10s on mark_as_triggered (multi-process DB contention) - Q5: malformed reminder_time tasks returned as due (were silently dropped by SQL-level string filter, which is now Python-side authoritative check) - Q7b: load_conversation realpath prefix check (../ traversal defense) - Q8: atomic JSON writes (tmp+os.replace) for index/current/archive - F6: dedicated ws command executor for /new, /reload_prompts - F9: --once hard-exit backstop after soft timeout - PromptManager singleton lock; limit=0 semantics (None = no LIMIT)
2026-08-18 03:09:05 +00:00
1 parent 9fee9a1478
commit db54921066
@@ -0,0 +1,227 @@
+"""aibox 第四轮审计 Batch I 修复回归测试（2026-08-18，审计报告 §十二）
+
+覆盖：
+  - N9：prompt 写入内容长度上限（持久化注入面约束）
+  - Q7b：load_conversation 越界路径拒绝（realpath 前缀校验）
+  - F5：run_light_subagent 取消传播（流式可中断 + 父已取消早退）
+  - Q5：提醒时间格式异常的任务按到期返回（不再静默丢弃）
+  - Q8：对话文件原子写（无 .tmp 残留、JSON 完整）
+  - F6：WebSocketHandler 命令专用线程池存在且可释放
+  - limit=0 语义修正（None 才不加 LIMIT）
+
+Q4（busy_timeout 10s）为时序性行为（默认 5s 等待已能通过短竞争），
+不做慢速单测；F9（--once 硬超时）为进程级行为，由 CLI 集成面覆盖。
+"""
+
+import os
+import queue
+import sqlite3
+import sys
+import threading
+import time
+import types
+from pathlib import Path
+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 run_light_subagent  # noqa: E402
+
+from subsystems.db import MemoryDatabase, MemoDatabase  # noqa: E402
+from subsystems.prompt_manager import PromptManager  # noqa: E402
+from subsystems.conversation_history import ConversationHistory  # noqa: E402
+from tools.prompt_tools import (  # noqa: E402
+    UpdateIdentityTool,
+    UpdateSoulTool,
+    SaveMemoryAndEndConversationTool,
+)
+
+
+# ==================== N9：prompt 写入长度上限 ====================
+
+class TestN9PromptContentCap:
+    def test_update_identity_oversized_rejected(self, tmp_path, monkeypatch):
+        """manager 层兜底：超长身份内容拒绝写入"""
+        pm = PromptManager()
+        with mock.patch.object(pm, "_prompts_dir", str(tmp_path)):
+            assert pm.update_identity("x" * (PromptManager.MAX_CONTENT_LENGTH + 1)) is False
+            assert not (tmp_path / pm.IDENTITY_FILE).exists()
+
+    def test_update_identity_tool_friendly_error(self, tmp_path):
+        """工具层：超长内容返回明确提示而非写入"""
+        pm = PromptManager()
+        with mock.patch.object(pm, "_prompts_dir", str(tmp_path)):
+            tool = UpdateIdentityTool(pm, None)
+            r = tool.execute(content="x" * (PromptManager.MAX_CONTENT_LENGTH + 1))
+        assert "内容过长" in r
+
+    def test_update_soul_tool_friendly_error(self, tmp_path):
+        pm = PromptManager()
+        with mock.patch.object(pm, "_prompts_dir", str(tmp_path)):
+            tool = UpdateSoulTool(pm, None)
+            r = tool.execute(content="y" * (PromptManager.MAX_CONTENT_LENGTH + 1))
+        assert "内容过长" in r
+
+    def test_save_memory_status_oversized_rejected(self, tmp_path):
+        """save_memory_and_end_conversation：状态内容超长拒绝"""
+        pm = PromptManager()
+        with mock.patch.object(pm, "_prompts_dir", str(tmp_path)):
+            tool = SaveMemoryAndEndConversationTool(
+                exit_callback=lambda *a: None,
+                memory_db=None, prompt_manager=pm, logger=None)
+            r = tool.execute(summary="这是一段足够长的对话总结" * 20,
+                             current_status="x" * PromptManager.MAX_CONTENT_LENGTH)
+        assert "状态内容过长" in r
+
+    def test_normal_content_still_written(self, tmp_path):
+        pm = PromptManager()
+        with mock.patch.object(pm, "_prompts_dir", str(tmp_path)):
+            assert pm.update_identity("正常身份内容") is True
+            assert "正常身份内容" in (tmp_path / pm.IDENTITY_FILE).read_text(encoding="utf-8")
+
+
+# ==================== Q7b：load_conversation 路径校验 ====================
+
+class TestQ7bLoadConversationBoundary:
+    def test_traversal_rejected(self, tmp_path):
+        h = ConversationHistory(save_dir=str(tmp_path / "save"), load_history=False)
+        secret = tmp_path / "secret.json"
+        secret.write_text('{"leak": true}', encoding="utf-8")
+        assert h.load_conversation("../secret.json") is None
+
+    def test_normal_file_still_loads(self, tmp_path):
+        h = ConversationHistory(save_dir=str(tmp_path / "save"), load_history=False)
+        h.current_conversation = {
+            "id": "1", "start_time": "2026-08-18 00:00:00", "end_time": None,
+            "topic": "t", "messages": [{"role": "user", "content": "hi"}],
+            "tool_calls": [], "stats": {},
+        }
+        h.save_current_conversation()
+        h.archive_current_conversation()
+        archives = list(h.archive_dir.glob("conversation_*.json"))
+        assert archives
+        loaded = h.load_conversation(archives[0].name)
+        assert loaded is not None and loaded["id"] == "1"
+
+
+# ==================== F5：run_light_subagent 取消传播 ====================
+
+class _BlockingLightClient:
+    """流式产出首段后卡住，直到 cancel() 才中断的伪 LLM 客户端"""
+
+    model = "fake-model"
+    default_temperature = None
+
+    def __init__(self):
+        self.cancelled = threading.Event()
+
+    def cancel(self):
+        self.cancelled.set()
+
+    def stream_chat(self, messages, **kwargs):
+        yield {"type": "content", "text": "开头"}
+        while not self.cancelled.wait(timeout=0.1):
+            pass
+        raise RuntimeError("连接已中断（cancel）")
+
+
+class TestF5LightSubagentCancel:
+    def test_cancelled_before_start_returns_early(self):
+        """父事件已置位 → 直接返回取消提示，不创建客户端"""
+        parent = threading.Event()
+        parent.set()
+        with mock.patch("aibox.create_llm_client") as mk:
+            r = run_light_subagent("r", "t", None, cancel_event=parent)
+        assert "取消" in r
+        mk.assert_not_called()
+
+    def test_cancel_during_stream_aborts(self):
+        """流式中父级取消 → 观察者线程 cancel 客户端 → 立即中断返回"""
+        parent = threading.Event()
+        fake = _BlockingLightClient()
+        with mock.patch("aibox.create_llm_client", return_value=fake):
+            result_holder = {}
+
+            def _run():
+                result_holder["r"] = run_light_subagent(
+                    "r", "t", None, cancel_event=parent)
+
+            th = threading.Thread(target=_run, daemon=True)
+            th.start()
+            time.sleep(0.5)  # 等待首段产出、观察者就绪
+            parent.set()
+            th.join(timeout=5)
+        assert not th.is_alive()  # 未挂死
+        assert "失败" in result_holder.get("r", "")
+
+    def test_express_emotion_registered_with_parent_event(self):
+        """DeepSeekChat 注册 ExpressEmotionTool 时注入自身取消事件"""
+        from test_once_mode import _make_ai
+        ai = _make_ai()
+        tool = next((t for t in ai.tool_registry.get_all_tools()
+                     if t.get_name() == "express_emotion"), None)
+        assert tool is not None
+        assert tool.cancel_event is ai._cancel_event
+
+
+# ==================== Q5：格式异常任务不丢弃 ====================
+
+class TestQ5MalformedReminderTime:
+    def test_malformed_time_task_returned_as_due(self, tmp_path):
+        db = MemoDatabase(db_path=str(tmp_path / "m.db"))
+        mid = db.add_memo(title="格式异常", content="c", reminder_time="不是时间")
+        pending = db.get_pending_memos(before_time="2026-08-18 00:00:00")
+        assert any(m["id"] == mid for m in pending)
+
+    def test_normal_pending_still_filtered(self, tmp_path):
+        db = MemoDatabase(db_path=str(tmp_path / "m.db"))
+        db.add_memo(title="未来任务", content="c", reminder_time="2099-01-01 00:00:00")
+        pending = db.get_pending_memos(before_time="2026-08-18 00:00:00")
+        assert pending == []
+
+
+# ==================== Q8：对话文件原子写 ====================
+
+class TestQ8AtomicWrites:
+    def test_no_tmp_leftover_and_valid_json(self, tmp_path):
+        h = ConversationHistory(save_dir=str(tmp_path / "save"), load_history=False)
+        h.current_conversation = {
+            "id": "1", "start_time": "2026-08-18 00:00:00", "end_time": None,
+            "topic": "t", "messages": [], "tool_calls": [], "stats": {},
+        }
+        h.save_current_conversation()
+        assert h.current_file.exists()  # 文件名可能被用户配置覆盖，用实例属性
+        import json
+        json.loads(h.current_file.read_text(encoding="utf-8"))  # 不抛即合法 JSON
+        h.archive_current_conversation()  # 归档后 current 文件按设计移除
+        assert list(Path(tmp_path).rglob("*.tmp")) == []
+
+
+# ==================== F6：WS 命令专用线程池 ====================
+
+class TestF6CmdExecutor:
+    def test_handler_has_dedicated_executor(self):
+        from aibox import WebSocketHandler
+        h = WebSocketHandler(ai_manager=None)
+        assert h._cmd_executor is not None
+        h.shutdown()
+        assert h._cmd_executor is None
+
+
+# ==================== limit=0 语义 ====================
+
+class TestLimitZeroSemantics:
+    def test_pending_memos_limit_zero_returns_none(self, tmp_path):
+        db = MemoDatabase(db_path=str(tmp_path / "m.db"))
+        db.add_memo(title="t", content="c", reminder_time="2026-01-01 00:00:00")
+        assert db.get_pending_memos(limit=0, before_time="2026-08-18 00:00:00") == []
+
+    def test_immediate_memos_limit_zero_returns_none(self, tmp_path):
+        db = MemoDatabase(db_path=str(tmp_path / "m.db"))
+        db.add_memo(title="t", content="c", is_immediate=True)
+        assert db.get_immediate_memos(limit=0) == []