Fix API key loading logic to read directly from config file

[DavidLee528]

Summary:
This PR fixes a configuration issue where the agent attempted to read the API key as an environment variable name from config.json, causing initialization failures. The code now correctly loads the API key value directly from the configuration file and improves the error message for missing keys.

Changes:

• Removed environment variable lookup via os.getenv(config['api_key']).
• Added direct assignment from config['api_key'].
• Updated error message to clearly indicate missing configuration.

Impact:
Ensures consistent API key loading from config.json and prevents false “environment variable not set” errors during agent initialization.

[gemini-code-assist]

Summary of Changes

Hello @DavidLee528, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses a critical configuration flaw that caused agent initialization failures due to misinterpreting the API key's source. By directly loading the API key from config.json and refining the error message, the change ensures robust and consistent API key handling, preventing misleading errors and improving the agent's startup reliability.

Highlights

• API Key Loading Logic: The pull request fixes an issue where the agent incorrectly attempted to load the API key by treating its value from config.json as an environment variable name. It now correctly reads the API key value directly from the configuration file.
• Error Messaging: The error message for a missing API key has been improved to clearly indicate that the 'api_key' configuration itself is not set, rather than implying an environment variable is missing.
• Environment Variable Removal: The reliance on os.getenv() for API key retrieval based on a config value has been removed, simplifying the configuration process.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request correctly fixes the API key loading logic to read the key directly from config.json instead of treating it as an environment variable name. The change is straightforward and addresses the bug described. I've added a couple of suggestions to further improve the robustness of the configuration handling: one to add validation for the placeholder API key value, and another to consider using environment variables for secrets as a security best practice. Overall, good fix!

[gemini-code-assist]

The validation for api_key only checks for an empty value. The default config.json uses "API_KEY" as a placeholder. It would be more robust to also check for this placeholder value to prevent runtime errors and provide a clearer message to the user if they haven't configured their key.

Suggested change

	if not config['api_key']:
	print('api_key configuration not set.')
	sys.exit(1)
	api_key = os.getenv(config['api_key'])
	api_key = config['api_key']
	api_key = config['api_key']
	if not api_key or api_key == 'API_KEY':
	print('Error: The "api_key" in config.json is missing or is a placeholder. Please provide a valid API key.')
	sys.exit(1)

[gemini-code-assist]

For enhanced security, it's a best practice to avoid storing secrets like API keys in plaintext configuration files, as they can be accidentally committed to version control. Consider loading the key directly from an environment variable instead (e.g., api_key = os.getenv('OPENAI_API_KEY')). This is a suggestion for future improvement and doesn't block this PR.