Refine Jules system prompt in triage_agent.py

[milhy545]

Updated src/mycoder/triage_agent.py to refine the system prompt for the Jules triage agent.

Changes:

• Updated JULES_SYSTEM_PROMPT to align with user-provided text.
• Changed output specification to "Write a JSON array to the output file."
• Adapted shell-style variables (!{echo $VAR}) to Python format ({var}).
• Escaped JSON braces for str.format() compatibility.
• Stripped conflicting "Final Command Construction" instructions to ensure strict JSON output and prevent parsing failures.
• Updated AGENTS.md with changelog entry.

Tests passed:

• tests/unit/test_triage_agent.py verified prompt construction and JSON parsing.

---

PR created automatically by Jules for task 1692529356453814078 started by @milhy545

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.

[github-actions]

🤖 Hi @milhy545, I've received your request, and I'm working on it now! You can track my progress in the logs for more details.

[gemini-code-assist]

Summary of Changes

Hello @milhy545, 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 focuses on enhancing the reliability and clarity of the Jules triage agent's system prompt. The changes ensure that the agent consistently produces strict JSON output by refining instructions, adapting variable formats, and removing ambiguous guidance, ultimately improving the agent's interaction and parsing success.

Highlights

• System Prompt Refinement: The JULES_SYSTEM_PROMPT in src/mycoder/triage_agent.py has been updated to align with user-provided text, ensuring clearer and stricter JSON output.
• Output Specification Clarification: The output specification within the system prompt was updated to explicitly state "Write a JSON array to the output file," providing better guidance for the agent.
• Variable Format Adaptation: Shell-style variables (!{echo $VAR}) within the prompt were adapted to Python's str.format() compatible format ({var}).
• JSON Brace Escaping: JSON braces within the prompt were escaped to ensure compatibility with Python's str.format() method.
• Instruction Streamlining: Conflicting "Final Command Construction" instructions were removed from the prompt to enforce strict JSON output and prevent parsing failures.
• Changelog Update: An entry was added to AGENTS.md documenting the refinement of the triage_agent.py system prompt.

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 updates the system prompt for the Jules triage agent and adds a corresponding changelog entry. While the changelog update is fine, the modification to the system prompt in src/mycoder/triage_agent.py introduces an inconsistency. The prompt now directs the LLM to write to an "output file," but the script's implementation writes the result to standard output. This discrepancy can be confusing and I've recommended reverting that specific text to be more general and accurate.

[gemini-code-assist]

The prompt now instructs the LLM to "Write a JSON array to the output file." However, the script's main function processes the LLM's response and prints it to standard output (stdout), not a file. This creates a contradiction between the instruction and the actual behavior, which could confuse the LLM. The previous wording, "Write a JSON array to the output.", was more accurate as "output" can generally refer to the generation result.

Suggested change

	Write a JSON array to the output file. Format:
	Write a JSON array to the output. Format: