refactor: update profile constants and enhance recommendation logic

[TimilsinaBimal]

No description provided.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Review	Updated (UTC)
watchly	Ready	Preview, Comment	Jan 3, 2026 10:26am

[gemini-code-assist]

Summary of Changes

Hello @TimilsinaBimal, 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 refactors the recommendation system by updating various profile constants and enhancing the core recommendation logic. The changes aim to improve the quality, diversity, and performance of "Top Picks" recommendations by refining how items are sampled, scored, and filtered, leading to a more relevant and balanced user experience.

Highlights

• Recommendation Logic Refinement: The core get_top_picks strategy has been significantly overhauled, introducing new steps for candidate generation, scoring, and diversity capping to achieve more balanced and performant recommendations.
• Profile Constant Adjustments: Several constants governing recency decay, diversity caps (genre, creator, era), minimum vote counts, and ratings have been fine-tuned to modify the recommendation algorithm's behavior and output.
• Simplified Quality Adjustments: The apply_quality_adjustments function has been simplified to primarily boost high-confidence items, moving away from complex multiplicative penalties and placing more reliance on the base weighted rating.
• Expanded Profile Feature Utilization: The system now considers a greater number of top genres, keywords, directors, cast, eras, and countries when generating discover recommendations, and includes support for excluding specific genres.
• Improved Recency Handling: The logic for applying recency caps has been enhanced to directly evaluate item release dates against a defined threshold, rather than relying on source tags, and the recency half-life has been shortened for faster decay.

🧠 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 refactors the recommendation logic by updating various constants and enhancing the scoring and candidate generation process. The changes simplify the quality adjustment scoring and introduce a more sophisticated candidate sourcing strategy. Overall, the direction is positive, but there are several issues to address. These include a bug in the sampling logic, a potential logic error in sorting by popularity, and the final recommendation list not being trimmed to the requested limit. Additionally, there are opportunities to improve code quality by removing unused parameters, moving imports to the top level, and cleaning up some inconsistencies in comments and docstrings.

[TimilsinaBimal]

/gemini review

[gemini-code-assist]

Code Review

This pull request introduces new catalog configuration options, display_at_home and shuffle, allowing users to control whether a catalog appears on the Stremio home screen and if its items should be randomized. The API endpoint for catalogs is updated to support an optional extra parameter for filtering. Several recommendation constants are adjusted, including RECENCY_HALF_LIFE_DAYS (from 90 to 15 days) and diversity caps for genres, creators, and eras, alongside changes to minimum vote counts and ratings for quality filtering. The scoring logic for recommendations is simplified by removing is_ranked and is_fresh parameters, and apply_quality_adjustments is refactored to use a simpler boost. The get_catalog service now shuffles items if configured, and get_top_picks has been optimized with pre-enrichment limiting and updated diversity cap logic, while removing the fetching of trending/popular candidates. The frontend is updated to support these new display_at_home and shuffle settings with new UI controls and improved styling for catalog management. Additionally, the frontend now includes persistent login functionality using local storage for both Stremio auth keys and email/password, along with a new user profile dropdown and logout buttons.