refactor: replace sync requests with async httpx in Jina AI client (#1603)

* refactor: replace sync requests with async httpx in Jina AI client

Replace synchronous `requests.post()` with `httpx.AsyncClient` in
JinaClient.crawl() and make web_fetch_tool async. This is part of the
planned async concurrency optimization for the agent hot path
(see docs/TODO.md).

* fix: address Copilot review feedback on async Jina client

- Short-circuit error strings in web_fetch_tool before passing to
  ReadabilityExtractor, preventing misleading extraction results
- Log missing JINA_API_KEY warning only once per process to reduce
  noise under concurrent async fetching
- Use logger.exception instead of logger.error in crawl exception
  handler to preserve stack traces for debugging
- Add async web_fetch_tool tests and warn-once coverage

* fix: mock get_app_config in web_fetch_tool tests for CI

The web_fetch_tool tests failed in CI because get_app_config requires
a config.yaml file that isn't present in the test environment. Mock
the config loader to remove the filesystem dependency.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

backend/packages/harness/deerflow/community/jina_ai/jina_client.py

@@ -1,13 +1,16 @@
 import logging
 import os
 
-import requests
+import httpx
 
 logger = logging.getLogger(__name__)
 
+_api_key_warned = False
+
 
 class JinaClient:
-    def crawl(self, url: str, return_format: str = "html", timeout: int = 10) -> str:
+    async def crawl(self, url: str, return_format: str = "html", timeout: int = 10) -> str:
+        global _api_key_warned
         headers = {
             "Content-Type": "application/json",
             "X-Return-Format": return_format,
@@ -15,11 +18,13 @@ class JinaClient:
         }
         if os.getenv("JINA_API_KEY"):
             headers["Authorization"] = f"Bearer {os.getenv('JINA_API_KEY')}"
-        else:
+        elif not _api_key_warned:
+            _api_key_warned = True
             logger.warning("Jina API key is not set. Provide your own key to access a higher rate limit. See https://jina.ai/reader for more information.")
         data = {"url": url}
         try:
-            response = requests.post("https://r.jina.ai/", headers=headers, json=data)
+            async with httpx.AsyncClient() as client:
+                response = await client.post("https://r.jina.ai/", headers=headers, json=data, timeout=timeout)
 
             if response.status_code != 200:
                 error_message = f"Jina API returned status {response.status_code}: {response.text}"
@@ -34,5 +39,5 @@ class JinaClient:
             return response.text
         except Exception as e:
             error_message = f"Request to Jina API failed: {str(e)}"
-            logger.error(error_message)
+            logger.exception(error_message)
             return f"Error: {error_message}"

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

@@ -8,7 +8,7 @@ readability_extractor = ReadabilityExtractor()
 
 
 @tool("web_fetch", parse_docstring=True)
-def web_fetch_tool(url: str) -> str:
+async def web_fetch_tool(url: str) -> str:
     """Fetch the contents of a web page at a given URL.
     Only fetch EXACT URLs that have been provided directly by the user or have been returned in results from the web_search and web_fetch tools.
     This tool can NOT access content that requires authentication, such as private Google Docs or pages behind login walls.
@@ -23,6 +23,8 @@ def web_fetch_tool(url: str) -> str:
     config = get_app_config().get_tool_config("web_fetch")
     if config is not None and "timeout" in config.model_extra:
         timeout = config.model_extra.get("timeout")
-    html_content = jina_client.crawl(url, return_format="html", timeout=timeout)
+    html_content = await jina_client.crawl(url, return_format="html", timeout=timeout)
+    if isinstance(html_content, str) and html_content.startswith("Error:"):
+        return html_content
     article = readability_extractor.extract_article(html_content)
     return article.to_markdown()[:4096]