修复网页对话并接入 SearXNG 搜索

app/tests/test_search.py

@@ -0,0 +1,147 @@
+#!/usr/bin/env python3
+"""联网搜索客户端与 LLM 工具闭环的无外部依赖测试。"""
+
+from __future__ import annotations
+
+import asyncio
+import sys
+from pathlib import Path
+
+import numpy as np
+from aiohttp import web
+
+ROOT = Path(__file__).resolve().parent.parent.parent
+sys.path.insert(0, str(ROOT))
+
+from app.config import AppConfig, SearchConfig  # noqa: E402
+from app.engine import ConversationEngine, EventKind  # noqa: E402
+from app.identity import ManualIdentityProvider  # noqa: E402
+from app.llm.base import Chunk, ChunkKind  # noqa: E402
+from app.search import SearchResult, SearXNGSearchClient  # noqa: E402
+from app.voice.tts import text_for_speech  # noqa: E402
+
+
+class FakeLLM:
+    name = "fake"
+    last_backend = "fake"
+
+    def __init__(self):
+        self.calls = []
+
+    async def stream(self, messages, *, tools=None, max_tokens=None):
+        self.calls.append((list(messages), tools))
+        if len(self.calls) == 1:
+            # 模拟 OpenAI SSE 中参数逐块累计后的两个中间状态。
+            yield Chunk(
+                kind=ChunkKind.TOOL_CALL, tool_index=0, tool_id="call_search",
+                tool_name="web_search", tool_arguments='{"query":"Deep',
+            )
+            yield Chunk(
+                kind=ChunkKind.TOOL_CALL, tool_index=0, tool_id="call_search",
+                tool_name="web_search", tool_arguments='{"query":"DeepSeek 最新"}',
+            )
+            yield Chunk(kind=ChunkKind.DONE, finish_reason="tool_calls")
+        else:
+            yield Chunk(kind=ChunkKind.CONTENT, text="根据最新资料，测试成功。")
+            yield Chunk(
+                kind=ChunkKind.CONTENT,
+                text="\n来源：DeepSeek 文档 https://example.com/deepseek",
+            )
+            yield Chunk(kind=ChunkKind.DONE, finish_reason="stop")
+
+
+class FakeSearch(SearXNGSearchClient):
+    def __init__(self):
+        self.queries = []
+
+    async def search(self, query):
+        self.queries.append(query)
+        return [SearchResult("DeepSeek 文档", "https://example.com/deepseek", "最新说明")]
+
+
+class FakeMemory:
+    async def start_session(self, *_args): pass
+    async def end_session(self, *_args): pass
+    async def retrieve(self, *_args, **_kwargs): return []
+    async def add_turn(self, *_args): pass
+
+
+class FakeTTS:
+    sample_rate = 16000
+
+    def __init__(self):
+        self.texts = []
+
+    def synthesize(self, text):
+        self.texts.append(text)
+        return np.ones(160, dtype=np.float32) * 0.1
+
+
+async def test_searxng_client() -> None:
+    async def search(request):
+        assert request.query["format"] == "json"
+        assert request.query["q"] == "测试 搜索"
+        return web.json_response({"results": [
+            {"title": "  结果 一  ", "url": "https://example.com/a",
+             "content": " 摘要  内容 ", "engines": ["duckduckgo"]},
+            {"title": "坏链接", "url": "javascript:alert(1)"},
+        ]})
+
+    app = web.Application()
+    app.router.add_get("/search", search)
+    runner = web.AppRunner(app)
+    await runner.setup()
+    site = web.TCPSite(runner, "127.0.0.1", 0)
+    await site.start()
+    port = site._server.sockets[0].getsockname()[1]
+    try:
+        client = SearXNGSearchClient(SearchConfig(
+            enabled=True, base_url=f"http://127.0.0.1:{port}",
+            timeout_s=2, max_results=5,
+        ))
+        results = await client.search("  测试   搜索  ")
+        assert len(results) == 1
+        assert results[0].title == "结果 一"
+        assert results[0].snippet == "摘要 内容"
+    finally:
+        await runner.cleanup()
+
+
+async def test_engine_tool_loop() -> None:
+    cfg = AppConfig()
+    cfg.search.enabled = True
+    cfg.memory.auto_extract_enabled = False
+    llm, search, tts = FakeLLM(), FakeSearch(), FakeTTS()
+    engine = ConversationEngine(
+        cfg, llm, FakeMemory(), ManualIdentityProvider(), tts, search=search,
+    )
+    await engine.start_session("search_test", user_id="u_test")
+
+    events = [event async for event in engine.respond_to_text("DeepSeek 最近更新了什么？")]
+    reply = "".join(e.text for e in events if e.kind == EventKind.RESPONSE_DELTA)
+    calls = [e.tool_call for e in events if e.kind == EventKind.TOOL_CALL]
+    metrics = [e.metrics for e in events if e.kind == EventKind.METRICS][-1]
+
+    assert search.queries == ["DeepSeek 最新"]
+    assert len(calls) == 1 and calls[0].id == "call_search"
+    assert len(llm.calls) == 2
+    second_messages = llm.calls[1][0]
+    assert second_messages[-2]["role"] == "assistant"
+    assert second_messages[-1]["role"] == "tool"
+    assert "https://example.com/deepseek" in second_messages[-1]["content"]
+    assert "https://example.com/deepseek" in reply
+    assert metrics.searches == 1
+    assert tts.texts == ["根据最新资料，测试成功。"]
+
+
+async def main() -> int:
+    await test_searxng_client()
+    await test_engine_tool_loop()
+    assert text_for_speech("回答。\n来源：文档 https://example.com") == "回答。"
+    assert text_for_speech("查看[官方文档](https://example.com)。") == "查看官方文档。"
+    print("联网搜索回归测试：12/12 PASS")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(asyncio.run(main()))