convex-evals/package.json at main · get-convex/convex-evals · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
{
  "name": "evals-convex",
  "version": "1.0.0",
  "private": true,
  "engines": {
    "bun": ">=1.3"
  },
  "devDependencies": {
    "@eslint/eslintrc": "^3.2.0",
    "@eslint/js": "^9.19.0",
    "@types/markdown-it": "^14.1.2",
    "@typescript-eslint/eslint-plugin": "^8.19.1",
    "@typescript-eslint/parser": "^8.19.1",
    "@vitejs/plugin-react": "^6.0.0",
    "eslint": "^9.19.0",
    "eslint-plugin-react-hooks": "^7.0.0",
    "eslint-plugin-react-refresh": "^0.5.0",
    "typescript": "^5.7.3"
  },
  "dependencies": {
    "@ai-sdk/anthropic": "^3.0.37",
    "@ai-sdk/google": "^3.0.21",
    "@ai-sdk/openai": "^3.0.25",
    "@ai-sdk/openai-compatible": "^2.0.27",
    "@ai-sdk/togetherai": "^2.0.30",
    "@ai-sdk/xai": "^3.0.47",
    "@cursor/sdk": "1.0.13",
    "@inquirer/prompts": "^8.0.0",
    "@types/bun": "^1.3.8",
    "@types/jszip": "^3.4.1",
    "@types/node": "^25.0.0",
    "ai": "^6.0.73",
    "chalk": "^5.6.2",
    "commander": "^14.0.0",
    "convex": "^1.31.2",
    "dotenv": "^17.2.1",
    "get-port": "^7.1.0",
    "gpt-tokenizer": "^3.4.0",
    "jszip": "^3.10.1",
    "markdown-it": "^14.1.0",
    "openai": "^6.18.0",
    "prettier": "^3.4.2",
    "typescript-eslint": "^8.23.0",
    "vitest": "^4.0.0",
    "zod": "^4.3.6"
  },
  "scripts": {
    "dev": "bun run scripts/dev.ts",
    "format:guidelines": "prettier -w runner/models/guidelines.md",
    "format-check:guidelines": "prettier -c runner/models/guidelines.md",
    "typecheck": "tsc --noEmit && cd evalScores && bunx tsc -p convex/tsconfig.json && cd ../visualizer && bunx tsc",
    "lint": "eslint runner/ evalScores/convex/",
    "test": "bun test runner scripts && cd evalScores && bun run test:once",
    "test:runner": "bun test runner scripts",
    "evals": "bun run scripts/runEvals.ts",
    "evalScores": "cd evalScores && bun run",
    "evals:list": "bun run scripts/runEvals.ts list",
    "local:run:fundamentals": "MODELS=gpt-5 TEST_FILTER=000-fundamentals bun run runner/index.ts",
    "local:run:one": "MODELS=gpt-5 TEST_FILTER=000-fundamentals/000 bun run runner/index.ts",
    "local:run": "bun run runner/index.ts",
    "list:models": "bun run scripts/listModels.ts",
    "build:release": "bun run buildRelease.ts",
    "ablation:generate": "bun run scripts/ablateGuidelines.ts",
    "ablation:run": "bun run scripts/runAblation.ts",
    "evalscores:sync-from-prod": "bun run scripts/syncEvalScoresFromProd.ts",
    "validate:guidelines": "bun run scripts/validateGuidelines.ts",
    "validate:answers": "bun run scripts/validateAnswers.ts",
    "generate:answer-types": "bun run scripts/generateAnswerTypes.ts",
    "generate:evalscores-types": "cd evalScores && bun run codegen",
    "visualizer:dev": "cd visualizer && bun run dev",
    "visualizer:build": "cd visualizer && bun run build"
  }
}