feat: add internal thinking field to capture model's reasoning output

[ilopezluna]

updated the Ollama HTTP handler to include thinking support for streaming chat responses

[gemini-code-assist]

Summary of Changes

Hello @ilopezluna, 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 the Ollama HTTP handler by integrating a new Thinking field into chat responses. This field is designed to expose the internal reasoning or thought process of the model, providing deeper insights into its output for both streaming and non-streaming interactions.

Highlights

• New Thinking Field: Introduced a Thinking string field in the Message struct within pkg/ollama/api.go. This field is designed to capture and expose the internal reasoning output of the model, marked with json:"thinking,omitempty" for efficient JSON serialization.
• Streaming Chat Responses: Modified the streamingChatResponseWriter in pkg/ollama/http_handler.go to extract ReasoningContent from incoming chat chunks. This content is now used to populate the new Thinking field in the outgoing streaming ChatResponse messages, providing real-time insight into the model's thought process.
• Non-Streaming Chat Responses: Updated the convertChatResponse function in pkg/ollama/http_handler.go to include the ReasoningContent from the model's response. This ensures that the Thinking field is also populated for non-streaming chat responses, maintaining consistency across response types.

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. ↩

[sourcery-ai]

Hey there - I've reviewed your changes - here's some feedback:

• The Message.Thinking field is tagged for JSON output but described as an internal field; if this content is meant to remain internal (e.g., for logging or debugging only), consider removing the JSON tag or using a separate non-serialized field to avoid unintentionally exposing reasoning to clients.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- The `Message.Thinking` field is tagged for JSON output but described as an internal field; if this content is meant to remain internal (e.g., for logging or debugging only), consider removing the JSON tag or using a separate non-serialized field to avoid unintentionally exposing reasoning to clients.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[gemini-code-assist]

Code Review

This pull request adds support for capturing the model's reasoning output (thinking) in chat responses. The changes are well-implemented, adding a Thinking field to the Message struct and updating the HTTP handler to populate this field for both streaming and non-streaming chat responses. The implementation is consistent with existing patterns for generate responses and includes necessary checks for safety. The code is clear and effectively achieves the goal of the pull request.