t1418: Deduplicate claim-task-id.sh guidance (3x → 1x canonical)#3925
t1418: Deduplicate claim-task-id.sh guidance (3x → 1x canonical)#3925marcusquinn merged 3 commits intomarcusquinn:mainfrom
Conversation
Replace duplicated claim-task-id.sh + gh-issue-create dedup logic in Self-Improvement (AGENTS.md:60) and Self-improvement repo routing (build.txt:248) with back-references to the canonical Cross-repo task creation workflow. Closes marcusquinn#3913
|
@coderabbitai review |
Summary of ChangesHello, 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 documentation related to creating self-improvement tasks and routing them to the correct repository. By replacing redundant, verbose instructions with concise back-references to a canonical workflow, it significantly improves the clarity, consistency, and maintainability of the guidance. The change ensures that all relevant documentation points to a single source of truth for the task creation process, reducing the likelihood of outdated or conflicting information. Highlights
Changelog
Activity
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
|
|
Important Review skippedAuto reviews are limited based on label configuration. 🚫 Review skipped — only excluded labels are configured. (1)
Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
WalkthroughConsolidated agent guidance: replaced duplicated, detailed self-improvement and routing instructions with a short reference to the "Cross-repo task creation" workflow (claim ID → commit → issue) in framework docs and build prompts. No code or public API signatures changed. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Possibly related PRs
Suggested labels
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
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 |
✅ Actions performedReview triggered.
|
![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 effectively deduplicates the guidance for claim-task-id.sh by consolidating the instructions into a canonical location and using references in other places. The changes in .agents/AGENTS.md and .agents/prompts/build.txt improve maintainability by establishing a single source of truth. I have one suggestion for the change in .agents/AGENTS.md to improve clarity and consistency with the change in build.txt, specifically regarding the formatting of operational details for better agent understanding.
Note: Security Review has been skipped due to the limited scope of the PR.
.agents/AGENTS.md
Outdated
| **Route to the correct repo.** Not every improvement belongs in the current project. Before creating a self-improvement task, determine whether the problem is project-specific or framework-level: | ||
|
|
||
| - **Framework-level** — route to the aidevops repo. Indicators: the observation references files under `~/.aidevops/`, framework scripts (`ai-actions.sh`, `ai-lifecycle.sh`, `supervisor/`, `dispatch.sh`, `pre-edit-check.sh`, helper scripts), agent prompt behaviour, supervisor/pulse logic, or cross-repo orchestration. Use `claim-task-id.sh --repo-path <aidevops-repo-path> --title "description"` (resolve the slug from `~/.config/aidevops/repos.json`). Only run `gh issue create --repo <aidevops-slug>` if `claim-task-id.sh` was invoked with `--no-issue` or its output did not include a `ref=GH#` (or `ref=GL#` for GitLab) token — otherwise the issue already exists and a second `gh issue create` would produce a duplicate. The fix belongs in the framework, not in the project that happened to trigger it. | ||
| - **Framework-level** — route to the aidevops repo. Indicators: the observation references files under `~/.aidevops/`, framework scripts (`ai-actions.sh`, `ai-lifecycle.sh`, `supervisor/`, `dispatch.sh`, `pre-edit-check.sh`, helper scripts), agent prompt behaviour, supervisor/pulse logic, or cross-repo orchestration. Follow the "Cross-repo task creation" workflow below (claim ID → commit → issue). The fix belongs in the framework, not in the project that happened to trigger it. |
There was a problem hiding this comment.
This instruction clarifies the 'Cross-repo task creation' workflow for the agent. Formatting this important operational detail as a bullet point, as suggested, significantly improves clarity and readability, ensuring the agent understands the context and proper routing. This aligns with the guideline to present critical operational information in an explicit and easily digestible format.
| - **Framework-level** — route to the aidevops repo. Indicators: the observation references files under `~/.aidevops/`, framework scripts (`ai-actions.sh`, `ai-lifecycle.sh`, `supervisor/`, `dispatch.sh`, `pre-edit-check.sh`, helper scripts), agent prompt behaviour, supervisor/pulse logic, or cross-repo orchestration. Follow the "Cross-repo task creation" workflow below (claim ID → commit → issue). The fix belongs in the framework, not in the project that happened to trigger it. | |
| - **Framework-level** — route to the aidevops repo. Indicators: the observation references files under `~/.aidevops/`, framework scripts (`ai-actions.sh`, `ai-lifecycle.sh`, `supervisor/`, `dispatch.sh`, `pre-edit-check.sh`, helper scripts), agent prompt behaviour, supervisor/pulse logic, or cross-repo orchestration. Follow the "Cross-repo task creation" workflow below (claim ID → commit → issue), targeting the aidevops repo path. The fix belongs in the framework, not in the project that happened to trigger it. |
References
- For important operational details like task claiming, format them as bullet points for clarity and readability.
There was a problem hiding this comment.
Applied in 7f390ee. Added ", targeting the aidevops repo path" to make the routing target explicit. Good catch.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
🧹 Nitpick comments (1)
.agents/prompts/build.txt (1)
248-248: Avoid keeping a second canonical workflow inbuild.txt.This back-reference now depends on an in-file copy of the same workflow that already exists in
.agents/AGENTS.md:162-167, so the two docs can still drift. Ifbuild.txtmust stay self-contained, consider generating this block fromAGENTS.md; otherwise, point toAGENTS.mddirectly.Based on learnings: All instructions, documentation, and operational guidance should be maintained in AGENTS.md as the single source of truth
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In @.agents/prompts/build.txt at line 248, The "Self-improvement repo routing" block in .agents/prompts/build.txt duplicates guidance already maintained in .agents/AGENTS.md (around the "Self-Improvement" section) and risks drift; remove the duplicate block from build.txt and either replace it with a single-line pointer to .agents/AGENTS.md ("See AGENTS.md 'Self-Improvement'") or make build.txt generate that section programmatically from AGENTS.md so AGENTS.md remains the single source of truth; update any references to the "Self-improvement repo routing" paragraph in build.txt to point to AGENTS.md and ensure the cross-repo task creation heuristic (claim ID → commit → issue targeting aidevops repo) is described only in AGENTS.md.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In @.agents/prompts/build.txt:
- Line 248: The "Self-improvement repo routing" block in
.agents/prompts/build.txt duplicates guidance already maintained in
.agents/AGENTS.md (around the "Self-Improvement" section) and risks drift;
remove the duplicate block from build.txt and either replace it with a
single-line pointer to .agents/AGENTS.md ("See AGENTS.md 'Self-Improvement'") or
make build.txt generate that section programmatically from AGENTS.md so
AGENTS.md remains the single source of truth; update any references to the
"Self-improvement repo routing" paragraph in build.txt to point to AGENTS.md and
ensure the cross-repo task creation heuristic (claim ID → commit → issue
targeting aidevops repo) is described only in AGENTS.md.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 4dabc329-e925-4c43-8ef0-39d9517dbdf7
📒 Files selected for processing (2)
.agents/AGENTS.md.agents/prompts/build.txt
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
✨ Finishing Touches🧪 Generate unit tests (beta)
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 |
|
Dispatching fix worker to address 1 unresolved bot review suggestion.
|
…d pointer Address CodeRabbit review: build.txt line 248 duplicated the full framework-vs-project routing indicator list from AGENTS.md, risking drift. Replace with a cross-reference to AGENTS.md 'Route to the correct repo' while keeping the core principle and procedural back-reference in-context.
|
CodeRabbit nitpick addressed (build.txt line 248): Replaced the duplicated routing heuristic (framework-vs-project indicator list) with a cross-reference to AGENTS.md "Route to the correct repo". The core principle and procedural back-reference remain in-context since What changed: The full indicator list ( What was kept: The routing principle ("route to the correct repo"), the procedural reference ("use Cross-repo task creation workflow above"), and the warning about framework tasks in project repos — these are needed in-context for the system prompt to function. Commit: f66f95b |
|
This PR is from an external contributor (@johnwaldo). Auto-merge is disabled for external PRs — a maintainer must review and merge manually. |
marcusquinn
added
the
external-contributor
|
CodeRabbit nitpick (build.txt line 248) — dismissed, by design.
The previous commit ( Generating |
2 participants
Summary
claim-task-id.sh+gh issue creatededup logic in two locations with back-references to the single canonical "Cross-repo task creation" workflowBefore
The same
claim-task-id.shusage pattern withgh issue creatededup guard was written out in full 3 times:.agents/AGENTS.mdline 60 (Self-Improvement section).agents/AGENTS.mdlines 162-167 (Cross-repo task creation — canonical).agents/prompts/build.txtline 248 (Self-improvement repo routing)Plus
prompts/build.txtline 242 has its own canonical copy.After
Verification
rg "Cross-repo task creation"confirms all back-references resolve to existing headingsCloses #3913
Summary by CodeRabbit
Documentation
Chores