Skip to content

fix: update stale Plan+ and AI-DevOps agent refs to Build+ in command generator#244

Merged
marcusquinn merged 1 commit intomainfrom
bugfix/fix-stale-agent-refs-in-commands
Jan 27, 2026
Merged

fix: update stale Plan+ and AI-DevOps agent refs to Build+ in command generator#244
marcusquinn merged 1 commit intomainfrom
bugfix/fix-stale-agent-refs-in-commands

Conversation

@marcusquinn
Copy link
Owner

@marcusquinn marcusquinn commented Jan 27, 2026

Summary

  • 7 slash commands were broken with "agent not found" because they referenced disabled agents Plan+ and AI-DevOps
  • Updated all 6 hardcoded agent references in generate-opencode-commands.sh to Build+

Affected Commands

Command Old Agent New Agent
/list-todo Plan+ (disabled) Build+
/save-todo Plan+ (disabled) Build+
/create-prd Plan+ (disabled) Build+
/generate-tasks Plan+ (disabled) Build+
/plan-status Plan+ (disabled) Build+
/show-plan Plan+ (disabled) Build+
/onboarding AI-DevOps (disabled) Build+

Root Cause

PR #226 consolidated Plan+ and AI-DevOps into Build+ and disabled the old agents, but the hardcoded heredoc templates in generate-opencode-commands.sh were not updated to match.

Summary by CodeRabbit

  • Chores
    • Updated agent assignments for command processing workflows.

✏️ Tip: You can customize this high-level summary in your review settings.

… generator

7 slash commands (/list-todo, /save-todo, /create-prd,
/generate-tasks, /plan-status, /show-plan, /onboarding) were
referencing disabled agents Plan+ and AI-DevOps. Updated all
6 hardcoded refs in generate-opencode-commands.sh to Build+.
@gemini-code-assist
Copy link

Summary of Changes

Hello @marcusquinn, 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 fixes several broken slash commands by updating their underlying agent references. Previously, these commands were attempting to use disabled agents (Plan+ and AI-DevOps), resulting in 'agent not found' errors. The changes ensure that all affected commands now correctly reference the active Build+ agent, restoring their intended functionality and improving the overall reliability of the command system.

Highlights

  • Agent Reference Updates: Updated hardcoded agent references from Plan+ and AI-DevOps to Build+ within the generate-opencode-commands.sh script. This change affects the generation of several slash commands.
  • Command Functionality Restoration: Resolved 'agent not found' errors for 7 slash commands, including /list-todo, /save-todo, /create-prd, /generate-tasks, /plan-status, /show-plan, and /onboarding, by pointing them to the correct active agent.
  • Root Cause Resolution: Addressed the issue where an earlier consolidation of Plan+ and AI-DevOps agents into Build+ (in PR refactor: consolidate Plan+ and AI-DevOps into Build+ #226) was not reflected in the command generation script, leading to broken commands.
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.

@coderabbitai
Copy link
Contributor

coderabbitai bot commented Jan 27, 2026

Walkthrough

Updated agent metadata in generated OpenCode command files, changing references from Plan+ to Build+ for multiple commands and AI-DevOps to Build+ for onboarding. No functional changes to command content, workflows, or error handling—only frontmatter updates.

Changes

Cohort / File(s) Summary
Agent Metadata Updates
.agent/scripts/generate-opencode-commands.sh (generator script affecting: create-prd.md, generate-tasks.md, list-todo.md, save-todo.md, plan-status.md, onboarding.md)
Updated agent field in generated command frontmatter: Plan+ → Build+ (5 commands), AI-DevOps → Build+ (onboarding). No changes to command aliases, content, or workflows.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Possibly related PRs

Poem

🚀 From Plan+ to Build+ we ascend,
The agents evolve, their metadata bend,
Onboarding joins the Build+ cohort crew,
Six commands unified—zero debt shines through! ✨

🚥 Pre-merge checks | ✅ 3
✅ Passed checks (3 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title clearly and specifically identifies the main change: updating stale agent references from Plan+ and AI-DevOps to Build+ in the command generator script.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing touches
  • 📝 Generate docstrings

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@sonarqubecloud
Copy link

Copy link

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request correctly updates hardcoded agent references for several slash commands, fixing them. One point of concern is that the PR description lists /show-plan as an affected command, but there's no corresponding update for it in the diff. Please ensure this isn't an accidental omission. For maintainability, I've also added a suggestion to replace the hardcoded agent strings with a shell variable. This would centralize the agent name and make future updates less error-prone.

Comment on lines 541 to 545
cat > "$OPENCODE_COMMAND_DIR/create-prd.md" << 'EOF'
---
description: Generate a Product Requirements Document for a feature
agent: Plan+
agent: Build+
---

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

To improve maintainability and prevent hardcoded values from becoming stale in the future, consider defining the agent name as a variable (e.g., BUILD_AGENT=\"Build+\") at the top of the script. You can then reference this variable in all the command generation blocks. This makes future updates much easier and less error-prone.

This pattern should be applied to all commands being updated in this PR.

Note that you'll need to change << 'EOF' to << EOF in each block to enable variable expansion.

Suggested change
cat > "$OPENCODE_COMMAND_DIR/create-prd.md" << 'EOF'
---
description: Generate a Product Requirements Document for a feature
agent: Plan+
agent: Build+
---
cat > "$OPENCODE_COMMAND_DIR/create-prd.md" << EOF
---
description: Generate a Product Requirements Document for a feature
agent: ${BUILD_AGENT}
---

@github-actions
Copy link

🔍 Code Quality Report

�[0;35m[MONITOR]�[0m Code Review Monitoring Report

�[0;34m[INFO]�[0m Latest Quality Status:
SonarCloud: 0 bugs, 0 vulnerabilities, 457 code smells

�[0;34m[INFO]�[0m Recent monitoring activity:
Tue Jan 27 23:06:03 UTC 2026: Code review monitoring started
Tue Jan 27 23:06:04 UTC 2026: SonarCloud - Bugs: 0, Vulnerabilities: 0, Code Smells: 457
Tue Jan 27 23:06:04 UTC 2026: Qlty - 0 issues found, auto-formatting applied
Tue Jan 27 23:06:06 UTC 2026: Codacy analysis completed with auto-fixes

📈 Current Quality Metrics

  • BUGS: 0
  • CODE SMELLS: 457
  • VULNERABILITIES: 0

Generated on: Tue Jan 27 23:07:19 UTC 2026


Generated by AI DevOps Framework Code Review Monitoring

@marcusquinn marcusquinn merged commit 591c6ed into main Jan 27, 2026
13 checks passed
@augmentcode
Copy link

augmentcode bot commented Jan 27, 2026

🤖 Augment PR Summary

Summary: Fixes broken OpenCode slash commands by updating references to disabled agents.

Changes: Replaces agent: Plan+ and agent: AI-DevOps with agent: Build+ in the heredoc command templates generated by generate-opencode-commands.sh.

🤖 Was this summary useful? React with 👍 or 👎

Copy link

@augmentcode augmentcode bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Review completed. No suggestions at this time.

Comment augment review to trigger a new review at any time.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant