feat: add Docker Model Runner as local LLM provider (#58)

[ishitatiwari1517]

Pull Request

Description

This PR adds support for Docker Model Runner as a local LLM provider. Docker Model Runner (introduced in Docker Desktop 4.40) exposes an OpenAI-compatible API on localhost, allowing users to run DockSec with local models fully air-gapped without needing any third-party API keys or external calls.

Changes included:

• Added docker-model-runner to the LLM configurations in utils.py and config_manager.py (bypasses API key requirements by passing no-key-required).
• Updated docksec.py argparse choices to include docker-model-runner.
• Added a check_docker_model_runner() verification method in setup_external_tools.py.
• Updated README.md to document the setup and usage of Docker Model Runner.
• Added comprehensive unit tests in test_utils.py to ensure correct get_llm() initialization for the new provider.

Closes #58

Type of Change

• Bug fix
• New feature
• Breaking change
• Documentation update
• Code style update (formatting, renaming)
• Code refactoring (no functional changes)
• Performance improvement
• Test update
• Build / CI configuration
• Security fix

How Has This Been Tested?

Describe the tests run to verify the changes:

• Unit tests
• Manual testing

Test Configuration:

• Python version: 3.12+
• Operating System: macOS
• DockSec version: latest

Checklist

• Code follows the style guidelines of this project
• Self-review completed
• Hard-to-understand areas are commented
• Documentation updated where needed
• No new warnings or errors introduced
• Tests added that prove the fix or feature works
• All existing tests pass
• Dependent changes have been merged and published
• Spelling checked

Screenshots (if applicable)

Related Issues / PRs

• Relates to [FEATURE] Add Docker Model Runner as a local LLM provider #58
• Depends on # (None)

---

By submitting this pull request, I confirm that my contribution is made under the terms of the MIT license.