Repository navigation
docs: add tracer and capability search guidance - #12
Conversation
|
Warning Rate limit exceeded
To keep reviews running without waiting, you can enable usage-based add-on for your organization. This allows additional reviews beyond the hourly cap. Account admins can enable it under billing. ⌛ 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: Organization UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughAdds an explicit "Existing capability search" step to the Anchor phase in codebase navigation with AST-aware and grep-based search examples; and introduces a "Depth, Risk, and Slice Gate" in task framing to classify tasks and route work (exploration, spec-driven, tracer bullet, spike) before edits. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
🚥 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. Review rate limit: 0/1 reviews remaining, refill in 52 minutes and 58 seconds.Comment |
There was a problem hiding this comment.
Pull request overview
Updates the repo’s agent directives to better guide task scoping/routing for higher-risk work and to encourage reuse-first navigation by searching for existing capabilities before implementing new ones.
Changes:
- Added a compact “Depth, Risk, and Slice Gate” to
task-framingto route complex/high-uncertainty work to exploration/spec/spike/tracer approaches before full implementation. - Added “existing capability search” as an explicit Anchor step in
codebase-navigation, recommending AST-aware search tools with a grep fallback.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| directives/task-framing.md | Adds a depth/risk classification and routing table plus tracer-bullet vs full-feature guidance. |
| directives/codebase-navigation.md | Adds capability reuse search guidance in the Anchor phase with example AST-aware and grep-based search commands. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| | Unknown / risk | Route first | | ||
| | --- | --- | | ||
| | Need to understand existing code, runtime, or dependency behavior | Exploration Path | | ||
| | Behavior, API, or acceptance criteria unclear | Specification-Driven Development | | ||
| | Feasibility unknown and throwaway validation is acceptable | Spike | | ||
| | Multi-layer integration or user feedback may change the shape | Tracer bullet | |
| ast-grep --pattern 'export const $NAME = $$$VALUE' src | ||
|
|
||
| # Portable fallback when ast-grep is unavailable | ||
| grep -R "function .*<domain-term>\|const .*<domain-term>\|export .*<domain-term>" src tests --exclude-dir=node_modules | head -30 |
| ast-grep --pattern 'export function $NAME($$$ARGS) { $$$BODY }' src | ||
| ast-grep --pattern 'export const $NAME = $$$VALUE' src | ||
|
|
||
| # Portable fallback when ast-grep is unavailable | ||
| grep -R "function .*<domain-term>\|const .*<domain-term>\|export .*<domain-term>" src tests --exclude-dir=node_modules | head -30 |
Copilot review follow-upAddressed all three Copilot comments:
Verification:
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@directives/task-framing.md`:
- Around line 108-113: The table currently defines "Exploration Path" with two
conflicting constraints (no code edits vs. run a disposable spike); update the
directive by splitting "Exploration Path" into two distinct modes—"Exploration
Path (Read-only)" with Output constraint "No code edits until the unknown is
resolved" and "Exploration Path (Spike)" with Output constraint "Run a
disposable spike; do not ship spike code without a normal implementation
pass"—or alternatively replace the single "Exploration Path" entry with one row
that adds a clarifying sentence in the Output constraint explaining when edits
are allowed (e.g., "Edits permitted only in throwaway spike branches; changes
must be discarded or replaced by production implementation after validation").
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: ca350ab1-c265-40ae-a2cd-873c1556037a
📒 Files selected for processing (2)
directives/codebase-navigation.mddirectives/task-framing.md
✅ Files skipped from review due to trivial changes (1)
- directives/codebase-navigation.md
CodeRabbit follow-upAddressed the remaining CodeRabbit comment by splitting the
Verification:
|
Summary
Self-Audit
Self-audit completed; no routed findings.
Jenga note: the weakest assumption is that the task-framing gate is worth its added context. This PR keeps it compact and decision-oriented, and avoids adding architecture coupling thresholds or a new directive.
Verification
git diff --checkpassed.directives/task-framing.mdanddirectives/codebase-navigation.md.Summary by CodeRabbit