vellum-ai Vellum Change Review
Review Stance
Prioritize bugs, behavioral regressions, security risks, migration gaps, broken package boundaries, and missing tests. Findings come before summaries. Avoid cosmetic feedback unless it affects correctness, maintainability, or user experience.
Required Checks
- Inspect the actual diff before judging the change.
- Identify which packages are affected:
assistant,gateway,clients,cli,skills,packages, ormeta. - Check package boundaries:
assistantmust not import fromgatewayby relative path.gatewaymust not import fromassistantby relative path.assistantandskillsmust not import each other directly.- Runtime code must not import from
meta.
- Check persistence changes:
- DB schema or data changes need append-only DB migrations.
- Workspace path, format, or file changes need append-only workspace migrations.
- Migrations must be idempotent and registered.
- Check feature flags:
- New assistant flags must be declared in
meta/feature-flags/feature-flag-registry.json. - Default-disabled or rollout-only features must not ship user-facing release notes.
- New flags may require a companion platform PR.
- New assistant flags must be declared in
- Check user-facing text:
- User-facing copy should say "assistant", not "daemon".
- Examples must use generic names, emails, phone numbers, and IDs.
- Check LLM/provider usage:
- LLM calls must go through the provider abstraction.
- Comments and logs should use provider-agnostic wording.
- Check tests and verification:
- Look for focused tests covering changed behavior.
- Prefer scoped
bun test path/to/test.ts; never suggest broadbun test. - Suggest
bunx tsc --noEmitwhen type-level risk is broad.
Review Output
Use this structure:
## Findings
- [severity] `path`: issue, impact, and concrete fix.
## Open Questions
- Any uncertainty that affects correctness or review confidence.
## Verification Gaps
- Tests or checks that still need to run.
If no issues are found, say that clearly and still mention residual risk or unrun checks.