feat(elicitation): halt with clear error on missing/malformed registry#2517
Conversation
🤖 Augment PR SummarySummary: Adds a Step 1 registry guard to 🤖 Was this summary useful? React with 👍 or 👎 |
| **Action:** Load `./methods.csv` for elicitation methods. If party-mode may participate, resolve the agent roster via: | ||
| **Action:** Load `./methods.csv` for elicitation methods. | ||
|
|
||
| **HALT — registry guard:** If `./methods.csv` cannot be read, is empty, is missing the header `num,category,method_name,description,output_pattern`, or contains no method rows, STOP immediately and report to the user: "Advanced Elicitation cannot run — the method registry `methods.csv` is missing or malformed." Do NOT invent methods or proceed from memory. |
There was a problem hiding this comment.
This instructs the agent to report an exact quoted (English) message, which may conflict with the earlier requirement to always speak output in {communication_language} and lead to inconsistent behavior in non-English runs.
Severity: medium
🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughStep 1 now requires ChangesAdvanced Elicitation Registry Guard
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ 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 |
What
Add a registry load guard to
bmad-advanced-elicitationStep 1: HALT with a clear error ifmethods.csvis missing, empty, or malformed.Why
Step 1 loaded
methods.csvwith no failure path, so a missing/corrupted registry made the agent silently invent methods from memory. This fails fast with an explicit message instead.Fixes #2516
How
Testing
npm run validate:refs,npm run validate:skills, andmarkdownlinton the file: no new findings vsmain(verified by diffing counts with/without the change).