Implement performance improvements for memory caching, HTTP client reuse, and regex optimization

Co-authored-by: Kenearos <86194771+Kenearos@users.noreply.github.com>

ai_provider.py

@@ -30,12 +30,27 @@ class PerplexityProvider:
         self.base_url = "https://api.perplexity.ai"
         self.logger = logger or logging.getLogger(__name__)
 
+        # Reusable HTTP client (created lazily)
+        self._client: Optional[httpx.AsyncClient] = None
+
         # Statistics
         self.total_requests = 0
         self.total_tokens = 0
         self.total_errors = 0
         self.last_response_time = 0
 
+    async def _get_client(self) -> httpx.AsyncClient:
+        """Get or create the HTTP client (lazy initialization)"""
+        if self._client is None or self._client.is_closed:
+            self._client = httpx.AsyncClient(timeout=30.0)
+        return self._client
+
+    async def close(self):
+        """Close the HTTP client"""
+        if self._client is not None and not self._client.is_closed:
+            await self._client.aclose()
+            self._client = None
+
     async def get_response(self, messages):
         """
         Send messages to Perplexity API and get response
@@ -66,30 +81,30 @@ class PerplexityProvider:
         start_time = time.time()
 
         try:
-            async with httpx.AsyncClient(timeout=30.0) as client:
-                response = await client.post(
-                    f"{self.base_url}/chat/completions",
-                    json=payload,
-                    headers=headers
-                )
+            client = await self._get_client()
+            response = await client.post(
+                f"{self.base_url}/chat/completions",
+                json=payload,
+                headers=headers
+            )
 
-                self.last_response_time = time.time() - start_time
+            self.last_response_time = time.time() - start_time
 
-                if response.status_code == 200:
-                    data = response.json()
-                    content = data['choices'][0]['message']['content']
-                    tokens_used = data.get('usage', {}).get('total_tokens', 0)
+            if response.status_code == 200:
+                data = response.json()
+                content = data['choices'][0]['message']['content']
+                tokens_used = data.get('usage', {}).get('total_tokens', 0)
 
-                    # Update statistics
-                    self.total_requests += 1
-                    self.total_tokens += tokens_used
+                # Update statistics
+                self.total_requests += 1
+                self.total_tokens += tokens_used
 
-                    return content
-                else:
-                    self.total_errors += 1
-                    error_msg = f"API Error {response.status_code}: {response.text}"
-                    self.logger.error(error_msg)
-                    return None
+                return content
+            else:
+                self.total_errors += 1
+                error_msg = f"API Error {response.status_code}: {response.text}"
+                self.logger.error(error_msg)
+                return None
 
         except httpx.TimeoutException:
             self.total_errors += 1