fix(firecrawl): pass tool base_url to FirecrawlApp as api_url (#5392)

_get_firecrawl_client only read api_key from the tool config and ignored
base_url, so self-hosted Firecrawl deployments were unreachable: the SDK
defaulted to https://api.firecrawl.dev and raised 'No API key provided'.
Now base_url is forwarded as api_url; api_url is omitted when unset so
cloud behavior is unchanged.

Also document the optional self-hosted base_url on both Firecrawl entries
in config.example.yaml and reconcile their headers to the fastCRW house
style (Cloud requires FIRECRAWL_API_KEY; self-host may need no key.).

backend/packages/harness/deerflow/community/firecrawl/tools.py

@@ -9,9 +9,16 @@ from deerflow.config import get_app_config
 def _get_firecrawl_client(tool_name: str = "web_search") -> FirecrawlApp:
     config = get_app_config().get_tool_config(tool_name)
     api_key = None
-    if config is not None and "api_key" in config.model_extra:
-        api_key = config.model_extra.get("api_key")
-    return FirecrawlApp(api_key=api_key)  # type: ignore[arg-type]
+    api_url = None
+    if config is not None:
+        if "api_key" in config.model_extra:
+            api_key = config.model_extra.get("api_key")
+        if "base_url" in config.model_extra:
+            api_url = config.model_extra.get("base_url")
+    kwargs = {"api_key": api_key}
+    if api_url:
+        kwargs["api_url"] = api_url
+    return FirecrawlApp(**kwargs)  # type: ignore[arg-type]
 
 
 @tool("web_search", parse_docstring=True)

backend/tests/test_firecrawl_tools.py

@@ -64,3 +64,51 @@ class TestWebFetchTool:
             "https://example.com",
             formats=["markdown"],
         )
+
+
+class TestFirecrawlBaseUrl:
+    @patch("deerflow.community.firecrawl.tools.FirecrawlApp")
+    @patch("deerflow.community.firecrawl.tools.get_app_config")
+    def test_fetch_passes_base_url_as_api_url(self, mock_get_app_config, mock_firecrawl_cls):
+        fetch_config = MagicMock()
+        fetch_config.model_extra = {"base_url": "http://192.168.0.47:3002"}
+
+        def get_tool_config(name):
+            if name == "web_fetch":
+                return fetch_config
+            return None
+
+        mock_get_app_config.return_value.get_tool_config.side_effect = get_tool_config
+
+        mock_scrape_result = MagicMock()
+        mock_scrape_result.markdown = "Fetched markdown"
+        mock_scrape_result.metadata = MagicMock(title="Fetched Page")
+        mock_firecrawl_cls.return_value.scrape.return_value = mock_scrape_result
+
+        from deerflow.community.firecrawl.tools import web_fetch_tool
+
+        result = web_fetch_tool.invoke({"url": "https://example.com"})
+
+        assert result == "# Fetched Page\n\nFetched markdown"
+        mock_firecrawl_cls.assert_called_once_with(api_key=None, api_url="http://192.168.0.47:3002")
+
+    @patch("deerflow.community.firecrawl.tools.FirecrawlApp")
+    @patch("deerflow.community.firecrawl.tools.get_app_config")
+    def test_search_passes_base_url_and_api_key(self, mock_get_app_config, mock_firecrawl_cls):
+        search_config = MagicMock()
+        search_config.model_extra = {
+            "api_key": "firecrawl-key",
+            "base_url": "http://192.168.0.47:3002",
+            "max_results": 5,
+        }
+        mock_get_app_config.return_value.get_tool_config.return_value = search_config
+
+        mock_result = MagicMock()
+        mock_result.web = []
+        mock_firecrawl_cls.return_value.search.return_value = mock_result
+
+        from deerflow.community.firecrawl.tools import web_search_tool
+
+        web_search_tool.invoke({"query": "test query"})
+
+        mock_firecrawl_cls.assert_called_once_with(api_key="firecrawl-key", api_url="http://192.168.0.47:3002")

config.example.yaml

@@ -868,12 +868,13 @@ tools:
   #   contents_max_characters: 1000
   #   # api_key: $EXA_API_KEY
 
-  # Web search tool (uses Firecrawl, requires FIRECRAWL_API_KEY)
+  # Web search tool (uses Firecrawl. Cloud requires FIRECRAWL_API_KEY; self-host may need no key.)
   # - name: web_search
   #   group: web
   #   use: deerflow.community.firecrawl.tools:web_search_tool
   #   max_results: 5
   #   # api_key: $FIRECRAWL_API_KEY
+  #   # base_url: http://<host>:3002  # optional: self-hosted Firecrawl; no cloud API key needed
 
   # Web search tool (uses GroundRoute, requires GROUNDROUTE_API_KEY)
   # GroundRoute is a meta search layer: one API in front of six engines (Serper,
@@ -1059,11 +1060,12 @@ tools:
   #   # Timeout for navigating to the page (in seconds). Set to positive value to enable, -1 to disable
   #   navigation_timeout: 30
 
-  # Web fetch tool (uses Firecrawl, requires FIRECRAWL_API_KEY)
+  # Web fetch tool (uses Firecrawl. Cloud requires FIRECRAWL_API_KEY; self-host may need no key.)
   # - name: web_fetch
   #   group: web
   #   use: deerflow.community.firecrawl.tools:web_fetch_tool
   #   # api_key: $FIRECRAWL_API_KEY
+  #   # base_url: http://<host>:3002  # optional: self-hosted Firecrawl; no cloud API key needed
 
   # Web fetch tool (uses GroundRoute, requires GROUNDROUTE_API_KEY)
   # Fetches a page's extracted text via GroundRoute mode=page.