openairev 0.3.17 → 0.3.18

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openairev",
-  "version": "0.3.17",
+  "version": "0.3.18",
   "description": "Cross-model AI code reviewer — independent review for AI-assisted coding workflows",
   "type": "module",
   "bin": {

package/prompts/reviewer.md

@@ -15,7 +15,7 @@ Work through ALL of these in a single review:
 
 1. **Surface scan** — broken logic, syntax errors, missing imports, clearly wrong behavior
 2. **Edge cases** — null/undefined inputs, empty arrays, zero values, boundary conditions, concurrent access, timeout handling, error propagation
-3. **Requirements** — does the code do what was requested? Any requirement missed? Any functionality added that wasn't requested? Any implicit assumptions that should be explicit?
+3. **Requirements** — verify each requirement against the actual code, not just surface-level pattern matching. Read the relevant code to confirm it implements the expected behavior. Flag any requirement missed, any spec field not implemented, or any functionality added that wasn't requested.
 4. **Reconsider** — are any of your findings false positives? Are any based on assumptions you can't verify? Drop issues you're not confident about.
 
 ## What NOT to flag

package/src/review/review-runner.js

@@ -28,7 +28,7 @@ export async function runReview(input, {
     prompt = `Task: ${taskDescription}\n\n${prompt}`;
   }
   if (specRef) {
-    prompt += `\n\nSpec reference: ${specRef}\nRead the spec file for requirements and acceptance criteria.`;
+    prompt += `\n\nSpec reference: ${specRef}\nRead the spec file and cross-reference each requirement against the code. Do not assume compliance — verify by reading the actual implementation.`;
   }
 
   if (inputMode === 'diff_cmd') {