chore: Add gcp resouce name span attribute

[surbhigarg92]

Adding a new span attribute called gcp.resource.name which contains an identifier to a particular spanner instance and database in the following format:

//spanner.googleapis.com/projects/{project}/instances/{instance_id}/databases/{database_id}
Example:

//spanner.googleapis.com/projects/my_project/instances/my_instance/databases/my_database

[gemini-code-assist]

Summary of Changes

Hello @surbhigarg92, 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 enhances observability by adding a new gcp.resource.name span attribute. This attribute provides a standardized, unique identifier for Google Cloud Spanner instances and databases within tracing spans, allowing for more precise correlation and analysis of distributed traces related to Spanner operations.

Highlights

• New Span Attribute: Introduces a new span attribute named gcp.resource.name to provide a unique identifier for Google Cloud Spanner instances and databases within tracing spans.
• Resource Name Format: The gcp.resource.name attribute will store the Spanner resource identifier in the format //spanner.googleapis.com/projects/{project}/instances/{instance_id}/databases/{database_id}.
• Implementation Logic: The attribute is set in src/instrument.ts within the startTrace function, constructing the full resource name by prepending //spanner.googleapis.com/ to the provided dbName.
• Test Coverage: Updated observability-test/observability.ts to include a test case that asserts the correct population and value of the new gcp.resource.name attribute.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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 adds a new gcp.resource.name span attribute, which is a good enhancement for observability. The implementation is mostly correct, but I've found a couple of issues. The db.name attribute is incorrectly being set to the full resource path, which doesn't align with OpenTelemetry semantic conventions. I've provided a suggestion to parse the database name correctly. Additionally, a unit test needs to be updated to assert the correct value for db.name after the changes.