@wix/evalforge-evaluator 0.76.0 → 0.78.0

package/build/index.mjs

@@ -280,9 +280,12 @@ async function fetchEvaluationData(api, projectId2, evalRunId2) {
   if (evalRun.skillsGroupId) {
     skillsGroup = await api.getSkillsGroup(projectId2, evalRun.skillsGroupId);
     if (skillsGroup.skillIds.length > 0) {
-      skills = await Promise.all(
+      const fetchResults = await Promise.allSettled(
         skillsGroup.skillIds.map((id) => api.getSkill(projectId2, id))
       );
+      skills = fetchResults.filter(
+        (r) => r.status === "fulfilled"
+      ).map((r) => r.value).filter((s) => !s.deleted);
     }
     if (evalRun.skillVersions && Object.keys(evalRun.skillVersions).length > 0) {
       skills = await Promise.all(
@@ -1128,7 +1131,8 @@ IMPORTANT: This is an automated evaluation run. Follow these guidelines:
 4. Keep your approach simple and direct - avoid excessive planning.
 5. Make targeted edits using Read and Edit tools rather than exploring the entire codebase.
 6. If you encounter an error, fix it directly rather than starting over.
-7. Your project root is the current working directory. Always create and modify source code files relative to the project root, NOT inside .claude/skills/ directories.`;
+7. Your project root is the current working directory. Always create and modify source code files relative to the project root, NOT inside .claude/skills/ directories.
+8. Before finishing, run the project's package manager install command (e.g. \`npm install\`, \`yarn install\`, or \`pnpm install\` depending on the lockfile present) to ensure all dependencies are installed and the project is ready to build.`;
       const fullPrompt = scenario.triggerPrompt + evaluatorPromptSuffix;
       for await (const message of query({
         prompt: fullPrompt,