Support for different LLM hosts (remote or local, compatible with OpenAI API interface)

[P4o1o]

added two flags for the scan command:

• --url <llm_host_url> / -u <llm_host_url> gives you the possibility to specify the url of the LLM backend (if not specified the program will use OpenAI url: https://api.openai.com)
• --model <model_name> / -m <model_name> gives you the possibility to choose the model you prefer (if not specified the program will use gpt-4.1-nano)

Example:

 # example with ollama at local host with default ollama port
 vibesafe scan --url http://127.0.0.1:11434 --model gemma3:27b-it-q8_0
# or
 vibesafe scan -u http://127.0.0.1:11434 -m gemma3:27b-it-q8_0 

# or if you prefer Deepseek
vibesafe scan -u https://api.deepseek.com -m deepseek-chat

[slowcoder360]

Thank you for doing this, I really appreciate it!

[slowcoder360]

Thank you so much for your work! This is a great addition to the project, you are a legend.