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

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

tests/test_integration.py

@@ -22,48 +22,51 @@ class TestFullWorkflow:
         detector = MentionDetector(config.bot_name)
         ai = PerplexityProvider(api_key=config.perplexity_key, model=config.model)
 
-        # Mock API response
-        with patch('httpx.AsyncClient') as mock_client:
-            mock_response = Mock()
-            mock_response.status_code = 200
-            mock_response.json.return_value = mock_perplexity_response
+        # Mock API client for lazy initialization
+        mock_client = Mock()
+        mock_client.is_closed = False
+        mock_response = Mock()
+        mock_response.status_code = 200
+        mock_response.json.return_value = mock_perplexity_response
 
-            mock_post = AsyncMock(return_value=mock_response)
-            mock_client.return_value.__aenter__.return_value.post = mock_post
+        mock_client.post = AsyncMock(return_value=mock_response)
 
-            # Simulate user message
-            username = "testuser"
-            user_message = "@TestBot what's the weather?"
+        # Inject the mock client
+        ai._client = mock_client
 
-            # 1. Detect mention
-            assert detector.is_mentioned(user_message)
+        # Simulate user message
+        username = "testuser"
+        user_message = "@TestBot what's the weather?"
 
-            # 2. Extract content
-            content = detector.extract_content(user_message)
-            assert content == "what's the weather?"
+        # 1. Detect mention
+        assert detector.is_mentioned(user_message)
 
-            # 3. Load history
-            history = memory.get_user_history(username, limit=5)
-            assert len(history) == 0  # First message
+        # 2. Extract content
+        content = detector.extract_content(user_message)
+        assert content == "what's the weather?"
 
-            # 4. Build messages for API
-            messages = [{"role": "system", "content": config.get_system_prompt()}]
-            messages.extend(memory.format_for_prompt(history))
-            messages.append({"role": "user", "content": content})
+        # 3. Load history
+        history = memory.get_user_history(username, limit=5)
+        assert len(history) == 0  # First message
 
-            # 5. Get AI response
-            response = await ai.get_response(messages)
-            assert response == "This is a test response from the AI."
+        # 4. Build messages for API
+        messages = [{"role": "system", "content": config.get_system_prompt()}]
+        messages.extend(memory.format_for_prompt(history))
+        messages.append({"role": "user", "content": content})
 
-            # 6. Save to memory
-            memory.add_message(username, "user", content)
-            memory.add_message(username, "assistant", response)
+        # 5. Get AI response
+        response = await ai.get_response(messages)
+        assert response == "This is a test response from the AI."
 
-            # 7. Verify history was saved
-            saved_history = memory.get_user_history(username)
-            assert len(saved_history) == 2
-            assert saved_history[0]["content"] == content
-            assert saved_history[1]["content"] == response
+        # 6. Save to memory
+        memory.add_message(username, "user", content)
+        memory.add_message(username, "assistant", response)
+
+        # 7. Verify history was saved
+        saved_history = memory.get_user_history(username)
+        assert len(saved_history) == 2
+        assert saved_history[0]["content"] == content
+        assert saved_history[1]["content"] == response
 
     @pytest.mark.asyncio
     async def test_conversation_context_preserved(self, temp_dir, mock_env_file):