refactor: clean up duplicate api structs

[ilblackdragon]

Builds on top of #375 - merge it first and refresh this

[gemini-code-assist]

Summary of Changes

Hello @ilblackdragon, 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 undertakes a significant refactoring effort to streamline the API's data model definitions. By centralizing core structs and enums related to responses and conversations within the services crate, it eliminates redundancy and enhances maintainability. The changes also introduce robust support for optional metadata on response messages, complete with validation to prevent oversized data, and consolidate request validation logic for improved consistency.

Highlights

• API Model Centralization: Many API-related structs and enums, such as CreateResponseRequest, ResponseObject, ConversationObject, and various tool-related types, have been moved from crates/api/src/models.rs to services::responses::models. They are now re-exported in the API crate, establishing a single source of truth and reducing code duplication.
• Metadata Support for Response Messages: The ResponseOutputItem::Message struct now includes an optional metadata field, allowing arbitrary JSON data to be associated with response messages. This metadata is handled during conversion between API and service layers.
• Metadata Size Validation: A new constant, MAX_METADATA_SIZE_BYTES, has been introduced in crates/services/src/common.rs to enforce a size limit on serialized metadata blobs. Validation logic for this limit has been added to CreateResponseRequest, CreateConversationRequest, and UpdateConversationRequest.
• Consolidated Validation Logic: Validation implementations for CreateResponseRequest, CreateConversationRequest, and UpdateConversationRequest have been relocated from crates/api/src/models.rs to crates/services/src/responses/models.rs, centralizing request validation within the services layer.

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 effectively centralizes API data structures in the services crate, reducing duplication and improving maintainability, and moves validation logic to reside with the data structures. However, a critical security oversight has been identified in the create_conversation_items route: the metadata field for individual conversation messages is processed without size validation, which could lead to resource exhaustion attacks. This needs to be addressed. On a positive note, the addition of annotations to MCP tools and new tests for backward compatibility and validation are valuable improvements. I also have one minor suggestion for simplification.

[gemini-code-assist]

The metadata field in ConversationInputItem::Message is now being extracted and processed, but it lacks size validation. Other similar metadata fields in the API (e.g., in CreateConversationRequest and UpdateConversationRequest) are validated against MAX_METADATA_SIZE_BYTES (16KB) to prevent database abuse and resource exhaustion. Since a single create_conversation_items request can contain up to 20 items, each with its own metadata, failing to validate the size could lead to significant database bloat or memory issues.