[autoresearch] baseline: system prompt quality tests (5/5 passing)

autoresearch.toml

@@ -0,0 +1,14 @@
+# Autoresearch Configuration for Response Quality Optimization
+# Target: Improve model response quality and accuracy
+
+target_file = "tauri-app/src/prompts/system.ts"
+eval_command = "cd tauri-app && npm test -- --testPathPattern='system-prompt' --json --outputFile=test-results.json && node -e \"const fs=require('fs');const r=JSON.parse(fs.readFileSync('test-results.json'));console.log('Score:', r.success?r.numPassedTests/(r.numPassedTests+r.numFailedTests)*100:0)\""
+metric_name = "test_pass_rate"
+metric_direction = "higher"
+time_budget = "2m"
+branch = "autoresearch-quality"
+
+# Alternative eval using benchmark questions
+# eval_command = "cd tauri-app && node scripts/benchmark-quality.js"
+# metric_name = "quality_score"
+# metric_direction = "higher"