fix: searxng搜索引擎支持

2026-03-12 12:38:01 +08:00
parent fc4f7cca21
commit 7f1e42c3fd
8 changed files with 340 additions and 20 deletions
--- a/README.md
+++ b/README.md
@@ -169,7 +169,7 @@ nanobot channels login

 > [!TIP]
 > Set your API key in `~/.nanobot/config.json`.
-> Get API keys: [OpenRouter](https://openrouter.ai/keys) (Global) · [Brave Search](https://brave.com/search/api/) (optional, for web search)
+> Get API keys: [OpenRouter](https://openrouter.ai/keys) (Global) · [Brave Search](https://brave.com/search/api/) or a self-hosted SearXNG instance (optional, for web search)

 **1. Initialize**

@@ -212,6 +212,42 @@ nanobot agent

 That's it! You have a working AI assistant in 2 minutes.

+### Optional: Web Search
+
+`web_search` supports both Brave Search and SearXNG.
+
+**Brave Search**
+
+```json
+{
+  "tools": {
+    "web": {
+      "search": {
+        "provider": "brave",
+        "apiKey": "your-brave-api-key"
+      }
+    }
+  }
+}
+```
+
+**SearXNG**
+
+```json
+{
+  "tools": {
+    "web": {
+      "search": {
+        "provider": "searxng",
+        "baseUrl": "http://localhost:8080"
+      }
+    }
+  }
+}
+```
+
+`baseUrl` can point either to the SearXNG root (for example `http://localhost:8080`) or directly to `/search`.
+
 ## 💬 Chat Apps

 Connect nanobot to your favorite chat platform.
--- a/nanobot/agent/loop.py
+++ b/nanobot/agent/loop.py
@@ -55,6 +55,9 @@ class AgentLoop:
        context_window_tokens: int = 65_536,
        brave_api_key: str | None = None,
        web_proxy: str | None = None,
+        web_search_provider: str = "brave",
+        web_search_base_url: str | None = None,
+        web_search_max_results: int = 5,
        exec_config: ExecToolConfig | None = None,
        cron_service: CronService | None = None,
        restrict_to_workspace: bool = False,
@@ -72,6 +75,9 @@ class AgentLoop:
        self.context_window_tokens = context_window_tokens
        self.brave_api_key = brave_api_key
        self.web_proxy = web_proxy
+        self.web_search_provider = web_search_provider
+        self.web_search_base_url = web_search_base_url
+        self.web_search_max_results = web_search_max_results
        self.exec_config = exec_config or ExecToolConfig()
        self.cron_service = cron_service
        self.restrict_to_workspace = restrict_to_workspace
@@ -86,6 +92,9 @@ class AgentLoop:
            model=self.model,
            brave_api_key=brave_api_key,
            web_proxy=web_proxy,
+            web_search_provider=web_search_provider,
+            web_search_base_url=web_search_base_url,
+            web_search_max_results=web_search_max_results,
            exec_config=self.exec_config,
            restrict_to_workspace=restrict_to_workspace,
        )
@@ -119,7 +128,15 @@ class AgentLoop:
            restrict_to_workspace=self.restrict_to_workspace,
            path_append=self.exec_config.path_append,
        ))
-        self.tools.register(WebSearchTool(api_key=self.brave_api_key, proxy=self.web_proxy))
+        self.tools.register(
+            WebSearchTool(
+                provider=self.web_search_provider,
+                api_key=self.brave_api_key,
+                base_url=self.web_search_base_url,
+                max_results=self.web_search_max_results,
+                proxy=self.web_proxy,
+            )
+        )
        self.tools.register(WebFetchTool(proxy=self.web_proxy))
        self.tools.register(MessageTool(send_callback=self.bus.publish_outbound))
        self.tools.register(SpawnTool(manager=self.subagents))
--- a/nanobot/agent/subagent.py
+++ b/nanobot/agent/subagent.py
@@ -30,6 +30,9 @@ class SubagentManager:
        model: str | None = None,
        brave_api_key: str | None = None,
        web_proxy: str | None = None,
+        web_search_provider: str = "brave",
+        web_search_base_url: str | None = None,
+        web_search_max_results: int = 5,
        exec_config: "ExecToolConfig | None" = None,
        restrict_to_workspace: bool = False,
    ):
@@ -40,6 +43,9 @@ class SubagentManager:
        self.model = model or provider.get_default_model()
        self.brave_api_key = brave_api_key
        self.web_proxy = web_proxy
+        self.web_search_provider = web_search_provider
+        self.web_search_base_url = web_search_base_url
+        self.web_search_max_results = web_search_max_results
        self.exec_config = exec_config or ExecToolConfig()
        self.restrict_to_workspace = restrict_to_workspace
        self._running_tasks: dict[str, asyncio.Task[None]] = {}
@@ -101,9 +107,17 @@ class SubagentManager:
                restrict_to_workspace=self.restrict_to_workspace,
                path_append=self.exec_config.path_append,
            ))
-            tools.register(WebSearchTool(api_key=self.brave_api_key, proxy=self.web_proxy))
+            tools.register(
+                WebSearchTool(
+                    provider=self.web_search_provider,
+                    api_key=self.brave_api_key,
+                    base_url=self.web_search_base_url,
+                    max_results=self.web_search_max_results,
+                    proxy=self.web_proxy,
+                )
+            )
            tools.register(WebFetchTool(proxy=self.web_proxy))
-            
+
            system_prompt = self._build_subagent_prompt()
            messages: list[dict[str, Any]] = [
                {"role": "system", "content": system_prompt},
--- a/nanobot/agent/tools/web.py
+++ b/nanobot/agent/tools/web.py
@@ -45,7 +45,7 @@ def _validate_url(url: str) -> tuple[bool, str]:


 class WebSearchTool(Tool):
-    """Search the web using Brave Search API."""
+    """Search the web using Brave Search or SearXNG."""

    name = "web_search"
    description = "Search the web. Returns titles, URLs, and snippets."
@@ -58,8 +58,17 @@ class WebSearchTool(Tool):
        "required": ["query"]
    }

-    def __init__(self, api_key: str | None = None, max_results: int = 5, proxy: str | None = None):
+    def __init__(
+        self,
+        provider: str = "brave",
+        api_key: str | None = None,
+        base_url: str | None = None,
+        max_results: int = 5,
+        proxy: str | None = None,
+    ):
+        self._init_provider = provider
        self._init_api_key = api_key
+        self._init_base_url = base_url
        self.max_results = max_results
        self.proxy = proxy

@@ -68,7 +77,32 @@ class WebSearchTool(Tool):
        """Resolve API key at call time so env/config changes are picked up."""
        return self._init_api_key or os.environ.get("BRAVE_API_KEY", "")

+    @property
+    def provider(self) -> str:
+        """Resolve search provider at call time so env/config changes are picked up."""
+        return (
+            self._init_provider or os.environ.get("WEB_SEARCH_PROVIDER", "brave")
+        ).strip().lower()
+
+    @property
+    def base_url(self) -> str:
+        """Resolve SearXNG base URL at call time so env/config changes are picked up."""
+        return (self._init_base_url or os.environ.get("SEARXNG_BASE_URL", "")).strip()
+
    async def execute(self, query: str, count: int | None = None, **kwargs: Any) -> str:
+        provider = self.provider
+        n = min(max(count or self.max_results, 1), 10)
+
+        if provider == "brave":
+            return await self._search_brave(query=query, count=n)
+        if provider == "searxng":
+            return await self._search_searxng(query=query, count=n)
+        return (
+            f"Error: Unsupported web search provider '{provider}'. "
+            "Supported values: brave, searxng."
+        )
+
+    async def _search_brave(self, query: str, count: int) -> str:
        if not self.api_key:
            return (
                "Error: Brave Search API key not configured. Set it in "
@@ -77,27 +111,18 @@ class WebSearchTool(Tool):
            )

        try:
-            n = min(max(count or self.max_results, 1), 10)
            logger.debug("WebSearch: {}", "proxy enabled" if self.proxy else "direct connection")
            async with httpx.AsyncClient(proxy=self.proxy) as client:
                r = await client.get(
                    "https://api.search.brave.com/res/v1/web/search",
-                    params={"q": query, "count": n},
+                    params={"q": query, "count": count},
                    headers={"Accept": "application/json", "X-Subscription-Token": self.api_key},
-                    timeout=10.0
+                    timeout=10.0,
                )
                r.raise_for_status()

-            results = r.json().get("web", {}).get("results", [])[:n]
-            if not results:
-                return f"No results for: {query}"
-
-            lines = [f"Results for: {query}\n"]
-            for i, item in enumerate(results, 1):
-                lines.append(f"{i}. {item.get('title', '')}\n   {item.get('url', '')}")
-                if desc := item.get("description"):
-                    lines.append(f"   {desc}")
-            return "\n".join(lines)
+            results = r.json().get("web", {}).get("results", [])[:count]
+            return self._format_results(query, results, snippet_keys=("description",))
        except httpx.ProxyError as e:
            logger.error("WebSearch proxy error: {}", e)
            return f"Proxy error: {e}"
@@ -105,6 +130,62 @@ class WebSearchTool(Tool):
            logger.error("WebSearch error: {}", e)
            return f"Error: {e}"

+    async def _search_searxng(self, query: str, count: int) -> str:
+        if not self.base_url:
+            return (
+                "Error: SearXNG base URL not configured. Set tools.web.search.baseUrl "
+                'in ~/.nanobot/config.json (or export SEARXNG_BASE_URL), e.g. "http://localhost:8080".'
+            )
+
+        is_valid, error_msg = _validate_url(self.base_url)
+        if not is_valid:
+            return f"Error: Invalid SearXNG base URL: {error_msg}"
+
+        try:
+            logger.debug("WebSearch: {}", "proxy enabled" if self.proxy else "direct connection")
+            async with httpx.AsyncClient(proxy=self.proxy) as client:
+                r = await client.get(
+                    self._build_searxng_search_url(),
+                    params={"q": query, "format": "json"},
+                    headers={"Accept": "application/json"},
+                    timeout=10.0,
+                )
+                r.raise_for_status()
+
+            results = r.json().get("results", [])[:count]
+            return self._format_results(
+                query,
+                results,
+                snippet_keys=("content", "snippet", "description"),
+            )
+        except httpx.ProxyError as e:
+            logger.error("WebSearch proxy error: {}", e)
+            return f"Proxy error: {e}"
+        except Exception as e:
+            logger.error("WebSearch error: {}", e)
+            return f"Error: {e}"
+
+    def _build_searxng_search_url(self) -> str:
+        base_url = self.base_url.rstrip("/")
+        return base_url if base_url.endswith("/search") else f"{base_url}/search"
+
+    @staticmethod
+    def _format_results(
+        query: str,
+        results: list[dict[str, Any]],
+        snippet_keys: tuple[str, ...],
+    ) -> str:
+        if not results:
+            return f"No results for: {query}"
+
+        lines = [f"Results for: {query}\n"]
+        for i, item in enumerate(results, 1):
+            lines.append(f"{i}. {item.get('title', '')}\n   {item.get('url', '')}")
+            snippet = next((item.get(key) for key in snippet_keys if item.get(key)), None)
+            if snippet:
+                lines.append(f"   {snippet}")
+        return "\n".join(lines)
+

 class WebFetchTool(Tool):
    """Fetch and extract content from a URL using Readability."""
--- a/nanobot/cli/commands.py
+++ b/nanobot/cli/commands.py
@@ -350,6 +350,9 @@ def gateway(
        context_window_tokens=config.agents.defaults.context_window_tokens,
        brave_api_key=config.tools.web.search.api_key or None,
        web_proxy=config.tools.web.proxy or None,
+        web_search_provider=config.tools.web.search.provider,
+        web_search_base_url=config.tools.web.search.base_url or None,
+        web_search_max_results=config.tools.web.search.max_results,
        exec_config=config.tools.exec,
        cron_service=cron,
        restrict_to_workspace=config.tools.restrict_to_workspace,
@@ -533,6 +536,9 @@ def agent(
        context_window_tokens=config.agents.defaults.context_window_tokens,
        brave_api_key=config.tools.web.search.api_key or None,
        web_proxy=config.tools.web.proxy or None,
+        web_search_provider=config.tools.web.search.provider,
+        web_search_base_url=config.tools.web.search.base_url or None,
+        web_search_max_results=config.tools.web.search.max_results,
        exec_config=config.tools.exec,
        cron_service=cron,
        restrict_to_workspace=config.tools.restrict_to_workspace,
--- a/nanobot/config/schema.py
+++ b/nanobot/config/schema.py
@@ -306,7 +306,9 @@ class GatewayConfig(Base):
 class WebSearchConfig(Base):
    """Web search tool configuration."""

-    api_key: str = ""  # Brave Search API key
+    provider: Literal["brave", "searxng"] = "brave"
+    api_key: str = ""  # Brave Search API key (ignored by SearXNG)
+    base_url: str = ""  # Required for SearXNG, e.g. "http://localhost:8080"
    max_results: int = 5


--- a/tests/test_commands.py
+++ b/tests/test_commands.py
@@ -306,6 +306,20 @@ def test_agent_warns_about_deprecated_memory_window(mock_agent_runtime):
    assert "contextWindowTokens" in result.stdout


+def test_agent_passes_web_search_config_to_agent_loop(mock_agent_runtime) -> None:
+    mock_agent_runtime["config"].tools.web.search.provider = "searxng"
+    mock_agent_runtime["config"].tools.web.search.base_url = "http://localhost:8080"
+    mock_agent_runtime["config"].tools.web.search.max_results = 7
+
+    result = runner.invoke(app, ["agent", "-m", "hello"])
+
+    assert result.exit_code == 0
+    kwargs = mock_agent_runtime["agent_loop_cls"].call_args.kwargs
+    assert kwargs["web_search_provider"] == "searxng"
+    assert kwargs["web_search_base_url"] == "http://localhost:8080"
+    assert kwargs["web_search_max_results"] == 7
+
+
 def test_gateway_uses_workspace_from_config_by_default(monkeypatch, tmp_path: Path) -> None:
    config_file = tmp_path / "instance" / "config.json"
    config_file.parent.mkdir(parents=True)
--- a/tests/test_web_tools.py
+++ b/tests/test_web_tools.py
@@ -0,0 +1,150 @@
+from typing import Any
+
+import pytest
+
+from nanobot.agent.tools import web as web_module
+from nanobot.agent.tools.web import WebSearchTool
+from nanobot.config.schema import Config
+
+
+class _FakeResponse:
+    def __init__(self, payload: dict[str, Any]) -> None:
+        self._payload = payload
+
+    def raise_for_status(self) -> None:
+        return None
+
+    def json(self) -> dict[str, Any]:
+        return self._payload
+
+
+@pytest.mark.asyncio
+async def test_web_search_tool_brave_formats_results(monkeypatch: pytest.MonkeyPatch) -> None:
+    calls: list[dict[str, Any]] = []
+    payload = {
+        "web": {
+            "results": [
+                {
+                    "title": "Nanobot",
+                    "url": "https://example.com/nanobot",
+                    "description": "A lightweight personal AI assistant.",
+                }
+            ]
+        }
+    }
+
+    class _FakeAsyncClient:
+        def __init__(self, *args: Any, **kwargs: Any) -> None:
+            self.proxy = kwargs.get("proxy")
+
+        async def __aenter__(self) -> "_FakeAsyncClient":
+            return self
+
+        async def __aexit__(self, exc_type, exc, tb) -> None:
+            return None
+
+        async def get(
+            self,
+            url: str,
+            *,
+            params: dict[str, Any] | None = None,
+            headers: dict[str, str] | None = None,
+            timeout: float | None = None,
+        ) -> _FakeResponse:
+            calls.append({"url": url, "params": params, "headers": headers, "timeout": timeout})
+            return _FakeResponse(payload)
+
+    monkeypatch.setattr(web_module.httpx, "AsyncClient", _FakeAsyncClient)
+
+    tool = WebSearchTool(provider="brave", api_key="test-key")
+    result = await tool.execute(query="nanobot", count=3)
+
+    assert "Nanobot" in result
+    assert "https://example.com/nanobot" in result
+    assert "A lightweight personal AI assistant." in result
+    assert calls == [
+        {
+            "url": "https://api.search.brave.com/res/v1/web/search",
+            "params": {"q": "nanobot", "count": 3},
+            "headers": {"Accept": "application/json", "X-Subscription-Token": "test-key"},
+            "timeout": 10.0,
+        }
+    ]
+
+
+@pytest.mark.asyncio
+async def test_web_search_tool_searxng_formats_results(monkeypatch: pytest.MonkeyPatch) -> None:
+    calls: list[dict[str, Any]] = []
+    payload = {
+        "results": [
+            {
+                "title": "Nanobot Docs",
+                "url": "https://example.com/docs",
+                "content": "Self-hosted search works.",
+            }
+        ]
+    }
+
+    class _FakeAsyncClient:
+        def __init__(self, *args: Any, **kwargs: Any) -> None:
+            self.proxy = kwargs.get("proxy")
+
+        async def __aenter__(self) -> "_FakeAsyncClient":
+            return self
+
+        async def __aexit__(self, exc_type, exc, tb) -> None:
+            return None
+
+        async def get(
+            self,
+            url: str,
+            *,
+            params: dict[str, Any] | None = None,
+            headers: dict[str, str] | None = None,
+            timeout: float | None = None,
+        ) -> _FakeResponse:
+            calls.append({"url": url, "params": params, "headers": headers, "timeout": timeout})
+            return _FakeResponse(payload)
+
+    monkeypatch.setattr(web_module.httpx, "AsyncClient", _FakeAsyncClient)
+
+    tool = WebSearchTool(provider="searxng", base_url="http://localhost:8080")
+    result = await tool.execute(query="nanobot", count=4)
+
+    assert "Nanobot Docs" in result
+    assert "https://example.com/docs" in result
+    assert "Self-hosted search works." in result
+    assert calls == [
+        {
+            "url": "http://localhost:8080/search",
+            "params": {"q": "nanobot", "format": "json"},
+            "headers": {"Accept": "application/json"},
+            "timeout": 10.0,
+        }
+    ]
+
+
+def test_web_search_tool_searxng_keeps_explicit_search_path() -> None:
+    tool = WebSearchTool(provider="searxng", base_url="https://search.example.com/search/")
+
+    assert tool._build_searxng_search_url() == "https://search.example.com/search"
+
+
+def test_web_search_config_accepts_searxng_fields() -> None:
+    config = Config.model_validate(
+        {
+            "tools": {
+                "web": {
+                    "search": {
+                        "provider": "searxng",
+                        "baseUrl": "http://localhost:8080",
+                        "maxResults": 7,
+                    }
+                }
+            }
+        }
+    )
+
+    assert config.tools.web.search.provider == "searxng"
+    assert config.tools.web.search.base_url == "http://localhost:8080"
+    assert config.tools.web.search.max_results == 7