Refactor Google and OpenAI provider response handling and tool utilities

- Improved error handling and logging in Google response processing.
- Simplified streaming content extraction and error detection in Google provider.
- Enhanced content extraction logic in OpenAI provider to handle edge cases.
- Streamlined tool conversion functions for both Google and OpenAI providers.
- Removed redundant comments and improved code readability across multiple files.
- Updated context window retrieval and message truncation logic for better performance.
- Ensured consistent handling of tool calls and arguments in OpenAI responses.

config/sample_config.ini

@@ -8,18 +8,21 @@ api_key = YOUR_API_KEY
 base_url = https://openrouter.ai/api/v1
 model = openai/gpt-4o-2024-11-20
 context_window = 128000
+temperature = 0.6
 
 [anthropic]
 api_key = YOUR_API_KEY
 base_url = https://api.anthropic.com/v1/messages
 model = claude-3-7-sonnet-20250219
 context_window = 128000
+temperature = 0.6
 
 [google]
 api_key = YOUR_API_KEY
 base_url = https://generativelanguage.googleapis.com/v1beta/generateContent
 model = gemini-2.0-flash
 context_window = 1000000
+temperature = 0.6
 
 
 [openai]
@@ -27,6 +30,7 @@ api_key = YOUR_API_KEY
 base_url = https://api.openai.com/v1
 model = openai/gpt-4o
 context_window = 128000
+temperature = 0.6
 
 [mcp]
 servers_json = config/mcp_config.json