test: add LLM retrieval accuracy tests

benchmarks/package.json

@@ -0,0 +1,26 @@
+{
+  "name": "@toon/benchmarks",
+  "type": "module",
+  "private": true,
+  "scripts": {
+    "benchmark:token-efficiency": "tsx scripts/token-efficiency-benchmark.ts",
+    "benchmark:accuracy": "tsx --env-file=.env scripts/accuracy-benchmark.ts",
+    "fetch-github-data": "tsx scripts/fetch-github-data.ts",
+    "test": "vitest"
+  },
+  "devDependencies": {
+    "@ai-sdk/anthropic": "^2.0.37",
+    "@ai-sdk/google": "^2.0.23",
+    "@ai-sdk/openai": "^2.0.53",
+    "@ai-sdk/provider": "^2.0.0",
+    "@antfu/eslint-config": "^6.1.0",
+    "@faker-js/faker": "^10.1.0",
+    "ai": "^5.0.80",
+    "consola": "^3.4.2",
+    "csv-stringify": "^6.6.0",
+    "gpt-tokenizer": "^3.2.0",
+    "ofetch": "^1.4.1",
+    "p-map": "^7.0.3",
+    "yaml": "^2.8.1"
+  }
+}