ai-companion/app/tests/test_flows_runtime.py

#!/usr/bin/env python3
"""Phase 3 Flows 运行时装配测试。

**不依赖网络、不启动 WebRTC**。验证的是装配正确性：

  - 节点配置形态（只用 task_messages、不自动开口）
  - 工具 schema 随身份变化
  - handler 桥接到工具层，且身份由服务端注入
  - 运行时开关默认是 legacy

真正跑起来的行为（RTVI 消息、TTS、延迟）由现场测试和真人网页验收覆盖。

用法：
    ~/venvs/ai_assistant/bin/python app/tests/test_flows_runtime.py
"""

from __future__ import annotations

import asyncio
import os
import sys
from pathlib import Path

ROOT = Path(__file__).resolve().parent.parent.parent
sys.path.insert(0, str(ROOT))

from app.agent import flows_runtime as FR  # noqa: E402
from app.agent.tools import ToolContext  # noqa: E402
from app.config import AgentConfig, AppConfig  # noqa: E402
from app.identity import ManualIdentityProvider  # noqa: E402
from app.memory.base import ConfirmStatus, Memory, MemoryKind  # noqa: E402

OK, FAIL = [], []


def check(name: str, cond: bool, detail: str = "") -> None:
    (OK if cond else FAIL).append(name)
    print(f"  [{'PASS' if cond else 'FAIL'}] {name}" + (f" — {detail}" if detail else ""))


class FakeStore:
    """最小实现，只够装配与 handler 调用。"""
    def __init__(self):
        self.rows: list[Memory] = []
        self._n = 1

    async def retrieve(self, owner_user_id, query, **kw):
        return [r for r in self.rows if r.owner_user_id == owner_user_id][:5]

    async def remember(self, mem: Memory) -> int:
        m = Memory(**{**mem.__dict__, "memory_id": self._n})
        self._n += 1
        self.rows.append(m)
        return m.memory_id

    async def forget(self, owner_user_id, memory_id):
        before = len(self.rows)
        self.rows = [r for r in self.rows
                     if not (r.memory_id == memory_id
                             and r.owner_user_id == owner_user_id)]
        return len(self.rows) < before


class FakeTTS:
    sample_rate = 24000
    def synthesize(self, text):
        import numpy as np
        return np.zeros(2400, dtype=np.float32)


class FakeRTVI:
    def __init__(self): self.msgs = []
    async def push_transport_message(self, m): self.msgs.append(type(m).__name__)


# ---------------------------------------------------------------- 配置开关

def test_runtime_switch():
    print("\n=== 1. 运行时开关 ===")
    check("默认是 legacy", AgentConfig(runtime="legacy").use_flows is False)
    check("显式 flows 才启用", AgentConfig(runtime="flows").use_flows is True)
    check("大小写不敏感", AgentConfig(runtime="FLOWS").use_flows is True)
    check("未知值当 legacy", AgentConfig(runtime="xyz").use_flows is False)

    saved = os.environ.pop("AI_AGENT_RUNTIME", None)
    try:
        from app.config import load_env
        import importlib
        import app.config as C
        C._loaded = False          # 重新读一次环境
        check("未设环境变量时默认 legacy",
              AppConfig.load().agent.runtime == "legacy")
    finally:
        if saved is not None:
            os.environ["AI_AGENT_RUNTIME"] = saved


# ---------------------------------------------------------------- 节点形态

def test_node_shape():
    print("\n=== 2. 节点配置形态 ===")
    identity = ManualIdentityProvider("u_a")
    store = FakeStore()
    bridge = FR.FlowsBridge(rtvi=FakeRTVI(), tts=FakeTTS(),
                            cfg=AppConfig.load())

    def ctx_factory():
        d = identity.current()
        return ToolContext(owner_user_id=d.user_id, session_id="s1",
                           turn_id="t1", identity_confirmed=d.confirmed,
                           store=store)

    schemas = [
        {"type": "function", "function": {
            "name": "memory_search", "description": "x",
            "parameters": {"type": "object",
                           "properties": {"query": {"type": "string"}},
                           "required": ["query"]}}},
    ]
    node = FR._conversation_node(display_name="林", tool_schemas=schemas,
                                 ctx_factory=ctx_factory)

    check("节点名是 conversation", node["name"] == "conversation")
    check("**不用 role_message**", "role_message" not in node,
          "避免两条 system 消息")
    check("用 task_messages 承载人格",
          len(node["task_messages"]) == 1
          and node["task_messages"][0]["role"] == "system")
    check("人格里含称呼", "林" in node["task_messages"][0]["content"])
    check("respond_immediately=False（不自动开口）",
          node["respond_immediately"] is False)
    check("工具已注册", len(node["functions"]) == 1)


# ---------------------------------------------------------------- handler 桥接

async def test_handler_bridge():
    print("\n=== 3. handler 桥接到工具层 ===")
    identity = ManualIdentityProvider("u_a")
    store = FakeStore()
    FR.set_last_user_text("记住我不吃香菜")

    def ctx_factory():
        d = identity.current()
        return ToolContext(owner_user_id=d.user_id, session_id="s1",
                           turn_id="t1", identity_confirmed=d.confirmed,
                           user_text=FR._LAST_USER_TEXT[0], store=store)

    handler = FR._make_handler("memory_remember", ctx_factory)
    out = await handler({"kind": "preference", "key": "饮食偏好",
                         "value": "不吃香菜"})
    check("handler 返回文本", isinstance(out, str) and "已记住" in out, out[:40])
    check("写入的 owner 来自服务端",
          store.rows and store.rows[0].owner_user_id == "u_a")

    # 身份未确认时，handler 应拒绝（策略层兜底）
    identity.reset()
    out2 = await handler({"kind": "preference", "value": "x"})
    # 策略层给模型的话是"现在还不能记录私人信息。请先确认身份。"，
    # 断言要匹配实际措辞（早先写死"身份未确认"导致误判成 FAIL）。
    check("身份未确认时 handler 拒绝",
          "不能记录" in out2 or "确认身份" in out2, out2[:40])

    # 越权参数应被工具层拦下
    identity.switch("u_a")
    out3 = await handler({"kind": "fact", "value": "x", "owner_user_id": "u_b"})
    check("越权参数被拦", "不合法" in out3, out3[:40])


# ---------------------------------------------------------------- 零件装配

async def test_build_parts():
    print("\n=== 4. build_flows_parts 装配 ===")
    cfg = AppConfig.load()
    # 强制用 deepseek 配置（本地 env 可能没设 AI_LLM_PRIMARY）
    from app.config import deepseek_config
    cfg.llm = deepseek_config()

    if not cfg.llm.api_key:
        check("跳过（无 DeepSeek 密钥）", True)
        return

    llm, aggregator, bridge, ctx_factory, schemas = await FR.build_flows_parts(
        cfg=cfg, memory=FakeStore(), identity=ManualIdentityProvider("u_a"),
        session_id="s1", tts=FakeTTS(), rtvi=FakeRTVI())

    check("返回 LLM service", llm is not None and type(llm).__name__ == "DeepSeekLLMService")
    check("模型名被覆盖为 deepseek-flash",
          llm._settings.model == cfg.llm.model, llm._settings.model)
    check("thinking 关闭",
          getattr(llm._settings.thinking, "type", None) == "disabled")
    check("aggregator 有 user/assistant",
          aggregator.user() is not None and aggregator.assistant() is not None)
    check("工具 schema 随身份给出（含记忆工具）",
          any(s["function"]["name"].startswith("memory_") for s in schemas),
          str([s["function"]["name"] for s in schemas]))
    check("Phase 3 不含 web_search",
          not any(s["function"]["name"] == "web_search" for s in schemas),
          "搜索仍走 legacy 路径")

    # 身份未确认时不暴露记忆工具
    _, _, _, _, schemas2 = await FR.build_flows_parts(
        cfg=cfg, memory=FakeStore(), identity=ManualIdentityProvider(),
        session_id="s1", tts=FakeTTS(), rtvi=FakeRTVI())
    check("身份未确认时不给记忆工具",
          not any(s["function"]["name"].startswith("memory_") for s in schemas2))


def main() -> int:
    test_runtime_switch()
    test_node_shape()
    asyncio.run(test_handler_bridge())
    asyncio.run(test_build_parts())

    print("\n" + "=" * 62)
    print(f"通过 {len(OK)} / {len(OK) + len(FAIL)}")
    for n in FAIL:
        print(f"  未通过: {n}")
    return 0 if not FAIL else 1


if __name__ == "__main__":
    sys.exit(main())