feat(openai): respect OPENAI_BASE_URL and OPENAI_API_BASE env vars

[dschrengost]

This PR updates the OpenAI provider to respect OPENAI_BASE_URL (and legacy OPENAI_API_BASE)
environment variables.

• Allows easier routing through proxies, gateways, or test endpoints
• Matches behavior of other OpenAI SDKs
• Adds debug logging when environment overrides are applied

[gemini-code-assist]

Summary of Changes

Hello @dschrengost, 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 introduces a significant enhancement to the OpenAI provider by enabling it to respect OPENAI_BASE_URL and OPENAI_API_BASE environment variables for configuring the API endpoint. This change provides greater flexibility for routing API traffic, such as through proxies or custom test environments, and aligns the provider's behavior with other official OpenAI SDKs. Additionally, it incorporates comprehensive logging to aid in debugging and understanding the flow of API configurations and requests.

Highlights

• Environment Variable Support for Base URL: The OpenAI provider now respects OPENAI_BASE_URL and OPENAI_API_BASE environment variables, allowing users to easily route API calls through proxies, gateways, or test endpoints. These environment variables take precedence over any base_url argument provided directly.
• Environment Variable Support for Organization: The organization parameter for OpenAI API calls can now also be configured via the OPENAI_ORG environment variable, aligning with standard OpenAI SDK behavior.
• Enhanced Debugging and Observability: Extensive debug and warning logging has been added throughout the OpenAI provider's initialization and request lifecycle. This includes logging when environment variables override explicit settings, details of client initialization, and information about each API call attempt, significantly improving observability.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 introduces a valuable feature by allowing OPENAI_BASE_URL and related environment variables to configure the OpenAI provider, which greatly improves flexibility for using proxies or custom endpoints. The addition of debug logging is also helpful for troubleshooting.

My review focuses on two main points:

1. There's an inconsistency in the precedence of configuration sources (environment variables vs. arguments) between base_url and organization.
2. The log levels for the newly added debug messages are inconsistent, with some informational logs being emitted as warnings.

Addressing these points will improve the consistency and usability of the new functionality. Please see the detailed comments for specific suggestions.

[gemini-code-assist]

There's an inconsistency in how configuration precedence is handled. For base_url, environment variables take precedence over arguments, but for organization, it's the other way around. This is also contrary to the PR's goal of matching other OpenAI SDKs, which prioritize arguments over environment variables.

For consistency within this provider and to align with the goal of allowing environment overrides, I recommend prioritizing environment variables for organization as well. You might also want to add a warning log when an override occurs, similar to base_url.

Also, consider supporting the standard OPENAI_ORGANIZATION environment variable in addition to OPENAI_ORG for better compatibility.

Suggested change

	# Organization can also be provided via env for official API usage
	self.organization = kwargs.get("organization") or os.getenv("OPENAI_ORG")
	# Organization can also be provided via env for official API usage
	env_org = os.getenv("OPENAI_ORGANIZATION") or os.getenv("OPENAI_ORG")
	kw_org = kwargs.get("organization")
	if env_org and kw_org and env_org != kw_org:
	logger.warning("[ZEN DEBUG] Overriding provided organization=%r with env=%r", kw_org, env_org)
	self.organization = env_org or kw_org

[gemini-code-assist]

The new logging messages prefixed with [ZEN DEBUG] use inconsistent log levels. Some informational messages are logged as WARNING, which could add unnecessary noise to the logs for users who have set their log level to WARNING.

For example, this log message is purely informational and would be better suited for the INFO or DEBUG level.

I recommend reviewing all new [ZEN DEBUG] logs and changing the ones that are informational from logger.warning to logger.info or logger.debug. This applies to other places in this file as well, such as lines 52-56, 282-287, and 605-611.

Suggested change

	logger.warning(
	"[ZEN DEBUG] OPENAI_BASE_URL env=%r effective=%r",
	env_base_url,
	self.base_url,
	)
	logger.info(
	"[ZEN DEBUG] OPENAI_BASE_URL env=%r effective=%r",
	env_base_url,
	self.base_url,
	)