chore: implement agent-review improvements#37
Conversation
1. Add auto-discovery for commands in scripts/commands/*.md - Prevents needing to manually add new commands to generator - Skips SKILL.md and already-defined commands 2. Document multi-worktree awareness in ralph-loop.md - status --all to check all worktrees - Parallel loop warnings - Integration with worktree-sessions.sh 3. Add /code-simplifier to AGENTS.md slash commands list
|
Caution Review failedThe pull request is closed. WalkthroughThis PR extends the AI DevOps framework by introducing a new "/code-simplifier" slash command, implementing auto-discovery logic to automatically detect and copy command markdowns from a dedicated directory, and documenting multi-worktree awareness patterns for Ralph loops. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Possibly related PRs
Poem
✨ Finishing touches
📜 Recent review detailsConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro 📒 Files selected for processing (3)
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. Comment |
Summary of ChangesHello @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 refines the agent's operational efficiency and documentation based on a previous agent review. It introduces an automated mechanism for registering new OpenCode commands, significantly improves the clarity and scope of multi-worktree documentation for Ralph loops, and updates the list of available slash commands. Highlights
Using Gemini Code AssistThe 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
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 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
|
|
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Sun Jan 11 03:51:00 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces some nice improvements for command auto-discovery and multi-worktree support. The changes are well-described and address the goals outlined. I've provided a few suggestions to enhance the robustness, maintainability, and consistency of the code and documentation. My main points focus on making hardcoded paths configurable, improving a file-processing loop in the shell script, and ensuring documentation is clear and consistent. Since no specific style guide was provided, my feedback is based on general best practices for shell scripting and markdown.
| | `todo/tasks/tasks-*.md` | Implementation task lists | | ||
|
|
||
| **Slash commands:** `/save-todo`, `/plan-status`, `/create-prd`, `/generate-tasks`, `/log-time-spent`, `/ready`, `/sync-beads`, `/remember`, `/recall`, `/session-review`, `/full-loop` | ||
| **Slash commands:** `/save-todo`, `/plan-status`, `/create-prd`, `/generate-tasks`, `/log-time-spent`, `/ready`, `/sync-beads`, `/remember`, `/recall`, `/session-review`, `/full-loop`, `/code-simplifier` |
There was a problem hiding this comment.
The list of slash commands is growing. To improve readability and make it easier to find a specific command in the future, it's good practice to keep such lists sorted alphabetically.
| **Slash commands:** `/save-todo`, `/plan-status`, `/create-prd`, `/generate-tasks`, `/log-time-spent`, `/ready`, `/sync-beads`, `/remember`, `/recall`, `/session-review`, `/full-loop`, `/code-simplifier` | |
| **Slash commands:** /code-simplifier, /create-prd, /full-loop, /generate-tasks, /log-time-spent, /plan-status, /ready, /recall, /remember, /save-todo, /session-review, /sync-beads |
| # Each file should have frontmatter with description and agent | ||
| # This prevents needing to manually add new commands to this script | ||
|
|
||
| COMMANDS_DIR="$HOME/.aidevops/agents/scripts/commands" |
There was a problem hiding this comment.
The path to the commands directory is hardcoded using $HOME. This creates a tight coupling with a specific user's directory structure and makes the script less portable. A more flexible approach is to use an environment variable (e.g., AIDEVOPS_HOME) for the base path, with a fallback to the current default. This allows users or CI/CD systems to easily override the path if needed.
| COMMANDS_DIR="$HOME/.aidevops/agents/scripts/commands" | |
| AIDEVOPS_HOME="${AIDEVOPS_HOME:-$HOME/.aidevops}" | |
| COMMANDS_DIR="$AIDEVOPS_HOME/agents/scripts/commands" |
| for cmd_file in "$COMMANDS_DIR"/*.md; do | ||
| [[ -f "$cmd_file" ]] || continue | ||
|
|
||
| cmd_name=$(basename "$cmd_file" .md) | ||
|
|
||
| # Skip SKILL.md (not a command) | ||
| [[ "$cmd_name" == "SKILL" ]] && continue | ||
|
|
||
| # Skip if already manually defined (avoid duplicates) | ||
| if [[ -f "$OPENCODE_COMMAND_DIR/$cmd_name.md" ]]; then | ||
| continue | ||
| fi | ||
|
|
||
| # Copy command file directly (it already has proper frontmatter) | ||
| cp "$cmd_file" "$OPENCODE_COMMAND_DIR/$cmd_name.md" | ||
| ((command_count++)) | ||
| echo -e " ${GREEN}✓${NC} Auto-discovered /$cmd_name command" | ||
| done |
There was a problem hiding this comment.
This loop for auto-discovering commands can be made more robust and readable:
- Use
nullglob: Instead of checking[[ -f "$cmd_file" ]]to handle cases where no files match the glob, you can setshopt -s nullglob. This causes the glob to expand to an empty string if there are no matches, preventing the loop from executing unnecessarily. It's a cleaner pattern for iterating over files. - Add Error Handling: The
cpcommand might fail (e.g., due to file permissions). Currently, this failure would be silent. It's important to check the command's exit status and log an error to make debugging easier.
Here's a revised version of the loop that incorporates these improvements:
shopt -s nullglob
for cmd_file in "$COMMANDS_DIR"/*.md; do
cmd_name=$(basename "$cmd_file" .md)
# Skip SKILL.md (not a command)
[[ "$cmd_name" == "SKILL" ]] && continue
# Skip if already manually defined (avoid duplicates)
if [[ -f "$OPENCODE_COMMAND_DIR/$cmd_name.md" ]]; then
continue
fi
# Copy command file directly, with error handling
if cp "$cmd_file" "$OPENCODE_COMMAND_DIR/$cmd_name.md"; then
((command_count++))
echo -e " ${GREEN}✓${NC} Auto-discovered /$cmd_name command"
else
echo -e " ${RED}✗${NC} Failed to copy /$cmd_name command" >&2
fi
done
shopt -u nullglob|
|
||
| ```bash | ||
| # Show loops across all worktrees | ||
| ~/.aidevops/agents/scripts/ralph-loop-helper.sh status --all |
There was a problem hiding this comment.
The command examples use a hardcoded path with ~. To improve clarity and maintain consistency with the scripts (especially if they are made configurable), it's better to use a placeholder variable like $AIDEVOPS_HOME. This signals to the user that the path is based on a configurable root directory. This suggestion also applies to the command on line 310.
| ~/.aidevops/agents/scripts/ralph-loop-helper.sh status --all | |
| ~/$AIDEVOPS_HOME/agents/scripts/ralph-loop-helper.sh status --all |
🤖 Augment PR SummarySummary: This PR incorporates improvements from a prior Changes:
Technical Notes: Auto-discovery copies command markdown files that already contain frontmatter, while avoiding duplicates with manually generated command stubs. 🤖 Was this summary useful? React with 👍 or 👎 |
![augmentcode[bot]](https://avatars.githubusercontent.com/in/1027498?s=60&v=4){kind=small}
| [[ "$cmd_name" == "SKILL" ]] && continue | ||
|
|
||
| # Skip if already manually defined (avoid duplicates) | ||
| if [[ -f "$OPENCODE_COMMAND_DIR/$cmd_name.md" ]]; then |
There was a problem hiding this comment.
Because this check skips when the destination file already exists, auto-discovered commands will not get refreshed on subsequent runs (so edits to the source scripts/commands/*.md may never propagate). Consider distinguishing “manually defined earlier in this script” vs “previously auto-copied” so auto-discovered commands can stay in sync.
🤖 Was this useful? React with 👍 or 👎
1 participant
Summary
Implements improvements identified by
/agent-reviewfrom the previous session.Changes
1. Auto-Discovery for OpenCode Commands (High Priority)
Commands in
.agent/scripts/commands/*.mdare now auto-discovered by the generator script. This prevents needing to manually add new commands.2. Multi-Worktree Documentation (Medium Priority)
Added documentation to
ralph-loop.mdfor:status --all- Check loops across all worktreesworktree-sessions.sh3. Slash Commands List (Low Priority)
Added
/code-simplifierto the slash commands list in AGENTS.md.Files Changed
generate-opencode-commands.shscripts/commands/*.mdworkflows/ralph-loop.mdAGENTS.md/code-simplifierto slash commandsSummary by CodeRabbit
New Features
Documentation
✏️ Tip: You can customize this high-level summary in your review settings.