fix(skill): update skill to reflect feedback from testing with gemini

[xjacka]

Summary

Linked Issues

Documentation

• No Docs Needed:

If this PR adds new feature or changes existing. Make sure documentation is adjusted accordingly. If the docs is not needed, please explain why.

[gemini-code-assist]

Summary of Changes

Hello, 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 primarily focuses on enhancing the development environment's compatibility by updating Python dependency lock files to include support for Python 3.13. Concurrently, it refines several key documentation sections to improve clarity and address feedback from recent testing, ensuring developers have more precise guidance on agent classification, file handling, and advanced features like trajectory implementation.

Highlights

• Python Version Support: The Python version requirement in uv.lock has been updated to support a broader range, specifically '>=3.13, <3.15', and corresponding Python 3.13 wheels have been added for several dependencies.
• Documentation Clarity: Multiple documentation files have been updated to provide clearer guidelines, including agent classification for interaction_mode, emphasizing MIME types for file identification, and refining trajectory implementation instructions.
• Trajectory Implementation Guidance: The trajectory.md file now includes more explicit instructions on how to import, inject, and use the TrajectoryExtensionServer, including the use of group_id for updating existing steps and handling trajectory emission from nested functions.
• New Anti-Pattern Added: A new anti-pattern has been added to SKILL.md advising against using context.session_id and instead recommending context.context_id for session identification.

🧠 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.

Changelog

• apps/agentstack-cli/uv.lock
  • Updated the requires-python range from ==3.14.* to '>=3.13, <3.15'
  • Added Python 3.13 compatible wheels for cffi, charset_normalizer, gnureadline, jiter, psutil, pydantic_core, pywin32, pyyaml, rpds_py, and wrapt
• skills/agentstack-wrapper/SKILL.md
  • Clarified the table header for agent classification to explicitly state interaction_mode
  • Added a new anti-pattern warning against using context.session_id and advising context.context_id instead
• skills/agentstack-wrapper/references/files.md
  • Updated guidance for file identification to explicitly state 'Always use the MIME type for identification; do not rely on file extensions.'
• skills/agentstack-wrapper/references/platform-extensions.md
  • Updated the description for the 'Trajectory' extension from 'Emits' to 'Yields' multi-step reasoning
• skills/agentstack-wrapper/references/trajectory.md
  • Changed 'emit trajectory' to 'yield trajectory' in decision rules for consistency
  • Added detailed instructions for trajectory implementation, including import statements, injection as an agent function parameter, and using group_id for updates
  • Clarified how to emit trajectory entries from nested functions by passing the trajectory object
  • Updated anti-pattern to reflect the new yield trajectory.trajectory_metadata(...) syntax
• skills/agentstack-wrapper/references/wrapper-entrypoint.md
  • Clarified that interaction_mode must be either 'multi-turn' or 'single-turn' when populating AgentDetail
  • Updated the emit trajectory output entry in the 'Key Operations' table to yield trajectory.trajectory_metadata(...)
  • Changed 'Emit trajectory' to 'Yield trajectory' in the conditional workflows for single-turn and multi-turn agents

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 introduces several documentation improvements for the agentstack-wrapper skill, based on feedback from testing. Key changes include clarifying the values for interaction_mode, correcting the session identifier to context.context_id, and emphasizing the use of MIME types for file identification. The guide for implementing trajectory updates has been significantly improved for accuracy, now correctly instructing to yield trajectory metadata. Additionally, the dependency lock file has been updated to support a wider range of Python versions. Overall, these changes enhance the clarity and correctness of the documentation.

_{Note: Security Review has been skipped due to the limited scope of the PR.}