feat(search): Add robust fallback system with configurable retries and enhanced error handling

- Implement multi-engine failover system with configurable fallback order
    - Add retry logic with exponential backoff and rate limit detection
    - Introduce search configuration options:
      * fallback_engines: Ordered list of backup search providers
      * retry_delay: Seconds between retry batches (default: 60)
      * max_retries: Maximum system-wide retry attempts (default: 3)
    - Improve error resilience with:
      - Automatic engine switching on 429/Too Many Requests
      - Full system retries after configurable cooldown periods
      - Detailed logging for diagnostics and monitoring
    - Enhance engine prioritization logic:
      1. Primary configured engine
      2. Configured fallback engines
      3. Remaining available engines

    Example configuration:
    [search]
    engine = "Google"
    fallback_engines = ["DuckDuckGo", "Baidu"]  # Cascading fallback order
    retry_delay = 60                            # 1 minute between retry batches
    max_retries = 3                             # Attempt 3 full system retries

    This addresses critical reliability issues by:
    - Preventing search failures due to single-engine rate limits
    - Enabling recovery from transient network errors
    - Providing operational flexibility through configurable parameters
    - Improving visibility through granular logging (INFO/WARN/ERROR)

app/config.py

@@ -37,6 +37,18 @@ class ProxySettings(BaseModel):
 
 class SearchSettings(BaseModel):
     engine: str = Field(default="Google", description="Search engine the llm to use")
+    fallback_engines: List[str] = Field(
+        default_factory=lambda: ["DuckDuckGo", "Baidu"],
+        description="Fallback search engines to try if the primary engine fails",
+    )
+    retry_delay: int = Field(
+        default=60,
+        description="Seconds to wait before retrying all engines again after they all fail",
+    )
+    max_retries: int = Field(
+        default=3,
+        description="Maximum number of times to retry all engines when all fail",
+    )
 
 
 class BrowserSettings(BaseModel):

app/tool/web_search.py

@@ -2,6 +2,7 @@ import asyncio
 from typing import List
 
 from tenacity import retry, stop_after_attempt, wait_exponential
+from app.logger import logger
 
 from app.config import config
 from app.tool.base import BaseTool
@@ -42,6 +43,8 @@ class WebSearch(BaseTool):
     async def execute(self, query: str, num_results: int = 10) -> List[str]:
         """
         Execute a Web search and return a list of URLs.
+        Tries engines in order based on configuration, falling back if an engine fails with errors.
+        If all engines fail, it will wait and retry up to the configured number of times.
 
         Args:
             query (str): The search query to submit to the search engine.
@@ -50,37 +53,100 @@ class WebSearch(BaseTool):
         Returns:
             List[str]: A list of URLs matching the search query.
         """
+        # Get retry settings from config
+        retry_delay = 60  # Default to 60 seconds
+        max_retries = 3   # Default to 3 retries
+
+        if config.search_config:
+            retry_delay = getattr(config.search_config, "retry_delay", 60)
+            max_retries = getattr(config.search_config, "max_retries", 3)
+
+        # Try searching with retries when all engines fail
+        for retry_count in range(max_retries + 1):  # +1 because first try is not a retry
+            links = await self._try_all_engines(query, num_results)
+            if links:
+                return links
+
+            if retry_count < max_retries:
+                # All engines failed, wait and retry
+                logger.warning(f"All search engines failed. Waiting {retry_delay} seconds before retry {retry_count + 1}/{max_retries}...")
+                await asyncio.sleep(retry_delay)
+            else:
+                logger.error(f"All search engines failed after {max_retries} retries. Giving up.")
+
+        return []
+
+    async def _try_all_engines(self, query: str, num_results: int) -> List[str]:
+        """
+        Try all search engines in the configured order.
+
+        Args:
+            query (str): The search query to submit to the search engine.
+            num_results (int): The number of search results to return.
+
+        Returns:
+            List[str]: A list of URLs matching the search query, or empty list if all engines fail.
+        """
         engine_order = self._get_engine_order()
+        failed_engines = []
+
         for engine_name in engine_order:
             engine = self._search_engine[engine_name]
             try:
+                logger.info(f"🔎 Attempting search with {engine_name.capitalize()}...")
                 links = await self._perform_search_with_engine(
                     engine, query, num_results
                 )
                 if links:
+                    if failed_engines:
+                        logger.info(f"Search successful with {engine_name.capitalize()} after trying: {', '.join(failed_engines)}")
                     return links
             except Exception as e:
-                print(f"Search engine '{engine_name}' failed with error: {e}")
+                failed_engines.append(engine_name.capitalize())
+                is_rate_limit = "429" in str(e) or "Too Many Requests" in str(e)
+
+                if is_rate_limit:
+                    logger.warning(f"⚠️ {engine_name.capitalize()} search engine rate limit exceeded, trying next engine...")
+                else:
+                    logger.warning(f"⚠️ {engine_name.capitalize()} search failed with error: {e}")
+
+        if failed_engines:
+            logger.error(f"All search engines failed: {', '.join(failed_engines)}")
         return []
 
     def _get_engine_order(self) -> List[str]:
         """
         Determines the order in which to try search engines.
-        Preferred engine is first (based on configuration), followed by the remaining engines.
+        Preferred engine is first (based on configuration), followed by fallback engines,
+        and then the remaining engines.
 
         Returns:
             List[str]: Ordered list of search engine names.
         """
         preferred = "google"
-        if config.search_config and config.search_config.engine:
+        fallbacks = []
-            preferred = config.search_config.engine.lower()
+
+        if config.search_config:
+            if config.search_config.engine:
+                preferred = config.search_config.engine.lower()
+            if config.search_config.fallback_engines:
+                fallbacks = [engine.lower() for engine in config.search_config.fallback_engines]
 
         engine_order = []
+        # Add preferred engine first
         if preferred in self._search_engine:
             engine_order.append(preferred)
+
+        # Add configured fallback engines in order
+        for fallback in fallbacks:
+            if fallback in self._search_engine and fallback not in engine_order:
+                engine_order.append(fallback)
+
+        # Add any remaining engines
         for key in self._search_engine:
             if key not in engine_order:
                 engine_order.append(key)
+
         return engine_order
 
     @retry(

config/config.example.toml

@@ -65,3 +65,9 @@ temperature = 0.0                           # Controls randomness for vision mod
 # [search]
 # Search engine for agent to use. Default is "Google", can be set to "Baidu" or "DuckDuckGo".
 #engine = "Google"
+# Fallback engine order. Default is ["DuckDuckGo", "Baidu"] - will try in this order after primary engine fails.
+#fallback_engines = ["DuckDuckGo", "Baidu"]
+# Seconds to wait before retrying all engines again when they all fail due to rate limits. Default is 60.
+#retry_delay = 60
+# Maximum number of times to retry all engines when all fail. Default is 3.
+#max_retries = 3