feat: Docker-isolated Claude CLI hello world

- evals/main.ts: run claude -p Hello in container, capture output - evals/Dockerfile: node:24-slim + @anthropic-ai/claude-code@2.1.63 - evals:build: build image (run after Dockerfile changes) - evals:run: run evals (requires image built first) - ANTHROPIC_API_KEY from .env via --env-file-if-exists
2026-03-27 10:09:26 +08:00 · 2026-03-03 11:14:44 -05:00
parent 760460c221
commit dce4600c08
7 changed files with 214 additions and 104 deletions
--- a/.env.example
+++ b/.env.example
@@ -0,0 +1 @@
+ANTHROPIC_API_KEY=sk-ant-...
--- a/evals/Dockerfile
+++ b/evals/Dockerfile
@@ -0,0 +1,2 @@
+FROM node:24-slim
+RUN npm install -g @anthropic-ai/claude-code@2.1.63
--- a/evals/main.ts
+++ b/evals/main.ts
@@ -0,0 +1,31 @@
+import { execSync, spawnSync } from "node:child_process";
+
+const apiKey = process.env.ANTHROPIC_API_KEY;
+if (!apiKey) throw new Error("ANTHROPIC_API_KEY required");
+
+try {
+	execSync("docker image inspect evals-claude", { stdio: "ignore" });
+} catch {
+	console.error("Docker image 'evals-claude' not found. Build it first with:\n  npm run evals:build");
+	process.exit(1);
+}
+
+const result = spawnSync(
+	"docker",
+	[
+		"run",
+		"--rm",
+		"-e",
+		`ANTHROPIC_API_KEY=${apiKey}`,
+		"evals-claude",
+		"claude",
+		"-p",
+		"Hello",
+	],
+	{ encoding: "utf-8" },
+);
+
+if (result.status !== 0) {
+	throw new Error(result.stderr || `Exit code ${result.status}`);
+}
+console.log(result.stdout);
--- a/mise.lock
+++ b/mise.lock
@@ -1,3 +1,8 @@
+[[tools.claude]]
+version = "2.1.63"
+backend = "aqua:anthropics/claude-code"
+"platforms.macos-arm64" = { checksum = "blake3:8719d16f09e5368fbbde5352fe1882fa3e70d6e984d77d513bf2230f22e2ddbe", url = "https://storage.googleapis.com/claude-code-dist-86c565f3-f756-42ad-8dfa-d59b1c096819/claude-code-releases/2.1.63/darwin-arm64/claude"}
+
 [[tools.node]]
 version = "24.13.0"
 backend = "core:node"
--- a/mise.toml
+++ b/mise.toml
@@ -3,6 +3,7 @@ experimental = true
 lockfile = true

 [tools]
+claude = "2.1.63"
 node = "lts"

 [env]
--- a/package-lock.json
+++ b/package-lock.json
@@ -10,6 +10,8 @@
 			"license": "MIT",
 			"devDependencies": {
 				"@biomejs/biome": "2.3.11",
+				"@types/node": "^24.0.0",
+				"tsx": "^4.21.0",
 				"vitest": "^3.0.0"
 			}
 		},
@@ -626,9 +628,9 @@
 			"license": "MIT"
 		},
 		"node_modules/@rollup/rollup-android-arm-eabi": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm-eabi/-/rollup-android-arm-eabi-4.57.0.tgz",
-			"integrity": "sha512-tPgXB6cDTndIe1ah7u6amCI1T0SsnlOuKgg10Xh3uizJk4e5M1JGaUMk7J4ciuAUcFpbOiNhm2XIjP9ON0dUqA==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm-eabi/-/rollup-android-arm-eabi-4.59.0.tgz",
+			"integrity": "sha512-upnNBkA6ZH2VKGcBj9Fyl9IGNPULcjXRlg0LLeaioQWueH30p6IXtJEbKAgvyv+mJaMxSm1l6xwDXYjpEMiLMg==",
 			"cpu": [
 				"arm"
 			],
@@ -640,9 +642,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-android-arm64": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm64/-/rollup-android-arm64-4.57.0.tgz",
-			"integrity": "sha512-sa4LyseLLXr1onr97StkU1Nb7fWcg6niokTwEVNOO7awaKaoRObQ54+V/hrF/BP1noMEaaAW6Fg2d/CfLiq3Mg==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm64/-/rollup-android-arm64-4.59.0.tgz",
+			"integrity": "sha512-hZ+Zxj3SySm4A/DylsDKZAeVg0mvi++0PYVceVyX7hemkw7OreKdCvW2oQ3T1FMZvCaQXqOTHb8qmBShoqk69Q==",
 			"cpu": [
 				"arm64"
 			],
@@ -654,9 +656,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-darwin-arm64": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-arm64/-/rollup-darwin-arm64-4.57.0.tgz",
-			"integrity": "sha512-/NNIj9A7yLjKdmkx5dC2XQ9DmjIECpGpwHoGmA5E1AhU0fuICSqSWScPhN1yLCkEdkCwJIDu2xIeLPs60MNIVg==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-arm64/-/rollup-darwin-arm64-4.59.0.tgz",
+			"integrity": "sha512-W2Psnbh1J8ZJw0xKAd8zdNgF9HRLkdWwwdWqubSVk0pUuQkoHnv7rx4GiF9rT4t5DIZGAsConRE3AxCdJ4m8rg==",
 			"cpu": [
 				"arm64"
 			],
@@ -668,9 +670,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-darwin-x64": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-x64/-/rollup-darwin-x64-4.57.0.tgz",
-			"integrity": "sha512-xoh8abqgPrPYPr7pTYipqnUi1V3em56JzE/HgDgitTqZBZ3yKCWI+7KUkceM6tNweyUKYru1UMi7FC060RyKwA==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-x64/-/rollup-darwin-x64-4.59.0.tgz",
+			"integrity": "sha512-ZW2KkwlS4lwTv7ZVsYDiARfFCnSGhzYPdiOU4IM2fDbL+QGlyAbjgSFuqNRbSthybLbIJ915UtZBtmuLrQAT/w==",
 			"cpu": [
 				"x64"
 			],
@@ -682,9 +684,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-freebsd-arm64": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-arm64/-/rollup-freebsd-arm64-4.57.0.tgz",
-			"integrity": "sha512-PCkMh7fNahWSbA0OTUQ2OpYHpjZZr0hPr8lId8twD7a7SeWrvT3xJVyza+dQwXSSq4yEQTMoXgNOfMCsn8584g==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-arm64/-/rollup-freebsd-arm64-4.59.0.tgz",
+			"integrity": "sha512-EsKaJ5ytAu9jI3lonzn3BgG8iRBjV4LxZexygcQbpiU0wU0ATxhNVEpXKfUa0pS05gTcSDMKpn3Sx+QB9RlTTA==",
 			"cpu": [
 				"arm64"
 			],
@@ -696,9 +698,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-freebsd-x64": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-x64/-/rollup-freebsd-x64-4.57.0.tgz",
-			"integrity": "sha512-1j3stGx+qbhXql4OCDZhnK7b01s6rBKNybfsX+TNrEe9JNq4DLi1yGiR1xW+nL+FNVvI4D02PUnl6gJ/2y6WJA==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-x64/-/rollup-freebsd-x64-4.59.0.tgz",
+			"integrity": "sha512-d3DuZi2KzTMjImrxoHIAODUZYoUUMsuUiY4SRRcJy6NJoZ6iIqWnJu9IScV9jXysyGMVuW+KNzZvBLOcpdl3Vg==",
 			"cpu": [
 				"x64"
 			],
@@ -710,9 +712,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-linux-arm-gnueabihf": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-gnueabihf/-/rollup-linux-arm-gnueabihf-4.57.0.tgz",
-			"integrity": "sha512-eyrr5W08Ms9uM0mLcKfM/Uzx7hjhz2bcjv8P2uynfj0yU8GGPdz8iYrBPhiLOZqahoAMB8ZiolRZPbbU2MAi6Q==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-gnueabihf/-/rollup-linux-arm-gnueabihf-4.59.0.tgz",
+			"integrity": "sha512-t4ONHboXi/3E0rT6OZl1pKbl2Vgxf9vJfWgmUoCEVQVxhW6Cw/c8I6hbbu7DAvgp82RKiH7TpLwxnJeKv2pbsw==",
 			"cpu": [
 				"arm"
 			],
@@ -724,9 +726,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-linux-arm-musleabihf": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-musleabihf/-/rollup-linux-arm-musleabihf-4.57.0.tgz",
-			"integrity": "sha512-Xds90ITXJCNyX9pDhqf85MKWUI4lqjiPAipJ8OLp8xqI2Ehk+TCVhF9rvOoN8xTbcafow3QOThkNnrM33uCFQA==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-musleabihf/-/rollup-linux-arm-musleabihf-4.59.0.tgz",
+			"integrity": "sha512-CikFT7aYPA2ufMD086cVORBYGHffBo4K8MQ4uPS/ZnY54GKj36i196u8U+aDVT2LX4eSMbyHtyOh7D7Zvk2VvA==",
 			"cpu": [
 				"arm"
 			],
@@ -738,9 +740,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-linux-arm64-gnu": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-gnu/-/rollup-linux-arm64-gnu-4.57.0.tgz",
-			"integrity": "sha512-Xws2KA4CLvZmXjy46SQaXSejuKPhwVdaNinldoYfqruZBaJHqVo6hnRa8SDo9z7PBW5x84SH64+izmldCgbezw==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-gnu/-/rollup-linux-arm64-gnu-4.59.0.tgz",
+			"integrity": "sha512-jYgUGk5aLd1nUb1CtQ8E+t5JhLc9x5WdBKew9ZgAXg7DBk0ZHErLHdXM24rfX+bKrFe+Xp5YuJo54I5HFjGDAA==",
 			"cpu": [
 				"arm64"
 			],
@@ -752,9 +754,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-linux-arm64-musl": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-musl/-/rollup-linux-arm64-musl-4.57.0.tgz",
-			"integrity": "sha512-hrKXKbX5FdaRJj7lTMusmvKbhMJSGWJ+w++4KmjiDhpTgNlhYobMvKfDoIWecy4O60K6yA4SnztGuNTQF+Lplw==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-musl/-/rollup-linux-arm64-musl-4.59.0.tgz",
+			"integrity": "sha512-peZRVEdnFWZ5Bh2KeumKG9ty7aCXzzEsHShOZEFiCQlDEepP1dpUl/SrUNXNg13UmZl+gzVDPsiCwnV1uI0RUA==",
 			"cpu": [
 				"arm64"
 			],
@@ -766,9 +768,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-linux-loong64-gnu": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-loong64-gnu/-/rollup-linux-loong64-gnu-4.57.0.tgz",
-			"integrity": "sha512-6A+nccfSDGKsPm00d3xKcrsBcbqzCTAukjwWK6rbuAnB2bHaL3r9720HBVZ/no7+FhZLz/U3GwwZZEh6tOSI8Q==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-loong64-gnu/-/rollup-linux-loong64-gnu-4.59.0.tgz",
+			"integrity": "sha512-gbUSW/97f7+r4gHy3Jlup8zDG190AuodsWnNiXErp9mT90iCy9NKKU0Xwx5k8VlRAIV2uU9CsMnEFg/xXaOfXg==",
 			"cpu": [
 				"loong64"
 			],
@@ -780,9 +782,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-linux-loong64-musl": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-loong64-musl/-/rollup-linux-loong64-musl-4.57.0.tgz",
-			"integrity": "sha512-4P1VyYUe6XAJtQH1Hh99THxr0GKMMwIXsRNOceLrJnaHTDgk1FTcTimDgneRJPvB3LqDQxUmroBclQ1S0cIJwQ==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-loong64-musl/-/rollup-linux-loong64-musl-4.59.0.tgz",
+			"integrity": "sha512-yTRONe79E+o0FWFijasoTjtzG9EBedFXJMl888NBEDCDV9I2wGbFFfJQQe63OijbFCUZqxpHz1GzpbtSFikJ4Q==",
 			"cpu": [
 				"loong64"
 			],
@@ -794,9 +796,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-linux-ppc64-gnu": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-ppc64-gnu/-/rollup-linux-ppc64-gnu-4.57.0.tgz",
-			"integrity": "sha512-8Vv6pLuIZCMcgXre6c3nOPhE0gjz1+nZP6T+hwWjr7sVH8k0jRkH+XnfjjOTglyMBdSKBPPz54/y1gToSKwrSQ==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-ppc64-gnu/-/rollup-linux-ppc64-gnu-4.59.0.tgz",
+			"integrity": "sha512-sw1o3tfyk12k3OEpRddF68a1unZ5VCN7zoTNtSn2KndUE+ea3m3ROOKRCZxEpmT9nsGnogpFP9x6mnLTCaoLkA==",
 			"cpu": [
 				"ppc64"
 			],
@@ -808,9 +810,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-linux-ppc64-musl": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-ppc64-musl/-/rollup-linux-ppc64-musl-4.57.0.tgz",
-			"integrity": "sha512-r1te1M0Sm2TBVD/RxBPC6RZVwNqUTwJTA7w+C/IW5v9Ssu6xmxWEi+iJQlpBhtUiT1raJ5b48pI8tBvEjEFnFA==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-ppc64-musl/-/rollup-linux-ppc64-musl-4.59.0.tgz",
+			"integrity": "sha512-+2kLtQ4xT3AiIxkzFVFXfsmlZiG5FXYW7ZyIIvGA7Bdeuh9Z0aN4hVyXS/G1E9bTP/vqszNIN/pUKCk/BTHsKA==",
 			"cpu": [
 				"ppc64"
 			],
@@ -822,9 +824,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-linux-riscv64-gnu": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-riscv64-gnu/-/rollup-linux-riscv64-gnu-4.57.0.tgz",
-			"integrity": "sha512-say0uMU/RaPm3CDQLxUUTF2oNWL8ysvHkAjcCzV2znxBr23kFfaxocS9qJm+NdkRhF8wtdEEAJuYcLPhSPbjuQ==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-riscv64-gnu/-/rollup-linux-riscv64-gnu-4.59.0.tgz",
+			"integrity": "sha512-NDYMpsXYJJaj+I7UdwIuHHNxXZ/b/N2hR15NyH3m2qAtb/hHPA4g4SuuvrdxetTdndfj9b1WOmy73kcPRoERUg==",
 			"cpu": [
 				"riscv64"
 			],
@@ -836,9 +838,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-linux-riscv64-musl": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-riscv64-musl/-/rollup-linux-riscv64-musl-4.57.0.tgz",
-			"integrity": "sha512-/MU7/HizQGsnBREtRpcSbSV1zfkoxSTR7wLsRmBPQ8FwUj5sykrP1MyJTvsxP5KBq9SyE6kH8UQQQwa0ASeoQQ==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-riscv64-musl/-/rollup-linux-riscv64-musl-4.59.0.tgz",
+			"integrity": "sha512-nLckB8WOqHIf1bhymk+oHxvM9D3tyPndZH8i8+35p/1YiVoVswPid2yLzgX7ZJP0KQvnkhM4H6QZ5m0LzbyIAg==",
 			"cpu": [
 				"riscv64"
 			],
@@ -850,9 +852,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-linux-s390x-gnu": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-s390x-gnu/-/rollup-linux-s390x-gnu-4.57.0.tgz",
-			"integrity": "sha512-Q9eh+gUGILIHEaJf66aF6a414jQbDnn29zeu0eX3dHMuysnhTvsUvZTCAyZ6tJhUjnvzBKE4FtuaYxutxRZpOg==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-s390x-gnu/-/rollup-linux-s390x-gnu-4.59.0.tgz",
+			"integrity": "sha512-oF87Ie3uAIvORFBpwnCvUzdeYUqi2wY6jRFWJAy1qus/udHFYIkplYRW+wo+GRUP4sKzYdmE1Y3+rY5Gc4ZO+w==",
 			"cpu": [
 				"s390x"
 			],
@@ -864,9 +866,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-linux-x64-gnu": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-gnu/-/rollup-linux-x64-gnu-4.57.0.tgz",
-			"integrity": "sha512-OR5p5yG5OKSxHReWmwvM0P+VTPMwoBS45PXTMYaskKQqybkS3Kmugq1W+YbNWArF8/s7jQScgzXUhArzEQ7x0A==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-gnu/-/rollup-linux-x64-gnu-4.59.0.tgz",
+			"integrity": "sha512-3AHmtQq/ppNuUspKAlvA8HtLybkDflkMuLK4DPo77DfthRb71V84/c4MlWJXixZz4uruIH4uaa07IqoAkG64fg==",
 			"cpu": [
 				"x64"
 			],
@@ -878,9 +880,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-linux-x64-musl": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-musl/-/rollup-linux-x64-musl-4.57.0.tgz",
-			"integrity": "sha512-XeatKzo4lHDsVEbm1XDHZlhYZZSQYym6dg2X/Ko0kSFgio+KXLsxwJQprnR48GvdIKDOpqWqssC3iBCjoMcMpw==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-musl/-/rollup-linux-x64-musl-4.59.0.tgz",
+			"integrity": "sha512-2UdiwS/9cTAx7qIUZB/fWtToJwvt0Vbo0zmnYt7ED35KPg13Q0ym1g442THLC7VyI6JfYTP4PiSOWyoMdV2/xg==",
 			"cpu": [
 				"x64"
 			],
@@ -892,9 +894,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-openbsd-x64": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-openbsd-x64/-/rollup-openbsd-x64-4.57.0.tgz",
-			"integrity": "sha512-Lu71y78F5qOfYmubYLHPcJm74GZLU6UJ4THkf/a1K7Tz2ycwC2VUbsqbJAXaR6Bx70SRdlVrt2+n5l7F0agTUw==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-openbsd-x64/-/rollup-openbsd-x64-4.59.0.tgz",
+			"integrity": "sha512-M3bLRAVk6GOwFlPTIxVBSYKUaqfLrn8l0psKinkCFxl4lQvOSz8ZrKDz2gxcBwHFpci0B6rttydI4IpS4IS/jQ==",
 			"cpu": [
 				"x64"
 			],
@@ -906,9 +908,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-openharmony-arm64": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-openharmony-arm64/-/rollup-openharmony-arm64-4.57.0.tgz",
-			"integrity": "sha512-v5xwKDWcu7qhAEcsUubiav7r+48Uk/ENWdr82MBZZRIm7zThSxCIVDfb3ZeRRq9yqk+oIzMdDo6fCcA5DHfMyA==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-openharmony-arm64/-/rollup-openharmony-arm64-4.59.0.tgz",
+			"integrity": "sha512-tt9KBJqaqp5i5HUZzoafHZX8b5Q2Fe7UjYERADll83O4fGqJ49O1FsL6LpdzVFQcpwvnyd0i+K/VSwu/o/nWlA==",
 			"cpu": [
 				"arm64"
 			],
@@ -920,9 +922,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-win32-arm64-msvc": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-win32-arm64-msvc/-/rollup-win32-arm64-msvc-4.57.0.tgz",
-			"integrity": "sha512-XnaaaSMGSI6Wk8F4KK3QP7GfuuhjGchElsVerCplUuxRIzdvZ7hRBpLR0omCmw+kI2RFJB80nenhOoGXlJ5TfQ==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-win32-arm64-msvc/-/rollup-win32-arm64-msvc-4.59.0.tgz",
+			"integrity": "sha512-V5B6mG7OrGTwnxaNUzZTDTjDS7F75PO1ae6MJYdiMu60sq0CqN5CVeVsbhPxalupvTX8gXVSU9gq+Rx1/hvu6A==",
 			"cpu": [
 				"arm64"
 			],
@@ -934,9 +936,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-win32-ia32-msvc": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-win32-ia32-msvc/-/rollup-win32-ia32-msvc-4.57.0.tgz",
-			"integrity": "sha512-3K1lP+3BXY4t4VihLw5MEg6IZD3ojSYzqzBG571W3kNQe4G4CcFpSUQVgurYgib5d+YaCjeFow8QivWp8vuSvA==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-win32-ia32-msvc/-/rollup-win32-ia32-msvc-4.59.0.tgz",
+			"integrity": "sha512-UKFMHPuM9R0iBegwzKF4y0C4J9u8C6MEJgFuXTBerMk7EJ92GFVFYBfOZaSGLu6COf7FxpQNqhNS4c4icUPqxA==",
 			"cpu": [
 				"ia32"
 			],
@@ -948,9 +950,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-win32-x64-gnu": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-win32-x64-gnu/-/rollup-win32-x64-gnu-4.57.0.tgz",
-			"integrity": "sha512-MDk610P/vJGc5L5ImE4k5s+GZT3en0KoK1MKPXCRgzmksAMk79j4h3k1IerxTNqwDLxsGxStEZVBqG0gIqZqoA==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-win32-x64-gnu/-/rollup-win32-x64-gnu-4.59.0.tgz",
+			"integrity": "sha512-laBkYlSS1n2L8fSo1thDNGrCTQMmxjYY5G0WFWjFFYZkKPjsMBsgJfGf4TLxXrF6RyhI60L8TMOjBMvXiTcxeA==",
 			"cpu": [
 				"x64"
 			],
@@ -962,9 +964,9 @@
 			]
 		},
 		"node_modules/@rollup/rollup-win32-x64-msvc": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/@rollup/rollup-win32-x64-msvc/-/rollup-win32-x64-msvc-4.57.0.tgz",
-			"integrity": "sha512-Zv7v6q6aV+VslnpwzqKAmrk5JdVkLUzok2208ZXGipjb+msxBr/fJPZyeEXiFgH7k62Ak0SLIfxQRZQvTuf7rQ==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/@rollup/rollup-win32-x64-msvc/-/rollup-win32-x64-msvc-4.59.0.tgz",
+			"integrity": "sha512-2HRCml6OztYXyJXAvdDXPKcawukWY2GpR5/nxKp4iBgiO3wcoEGkAaqctIbZcNB6KlUQBIqt8VYkNSj2397EfA==",
 			"cpu": [
 				"x64"
 			],
@@ -1000,6 +1002,17 @@
 			"dev": true,
 			"license": "MIT"
 		},
+		"node_modules/@types/node": {
+			"version": "24.11.0",
+			"resolved": "https://registry.npmjs.org/@types/node/-/node-24.11.0.tgz",
+			"integrity": "sha512-fPxQqz4VTgPI/IQ+lj9r0h+fDR66bzoeMGHp8ASee+32OSGIkeASsoZuJixsQoVef1QJbeubcPBxKk22QVoWdw==",
+			"dev": true,
+			"license": "MIT",
+			"peer": true,
+			"dependencies": {
+				"undici-types": "~7.16.0"
+			}
+		},
 		"node_modules/@vitest/expect": {
 			"version": "3.2.4",
 			"resolved": "https://registry.npmjs.org/@vitest/expect/-/expect-3.2.4.tgz",
@@ -1292,6 +1305,19 @@
 				"node": "^8.16.0 || ^10.6.0 || >=11.0.0"
 			}
 		},
+		"node_modules/get-tsconfig": {
+			"version": "4.13.6",
+			"resolved": "https://registry.npmjs.org/get-tsconfig/-/get-tsconfig-4.13.6.tgz",
+			"integrity": "sha512-shZT/QMiSHc/YBLxxOkMtgSid5HFoauqCE3/exfsEcwg1WkeqjG+V40yBbBrsD+jW2HDXcs28xOfcbm2jI8Ddw==",
+			"dev": true,
+			"license": "MIT",
+			"dependencies": {
+				"resolve-pkg-maps": "^1.0.0"
+			},
+			"funding": {
+				"url": "https://github.com/privatenumber/get-tsconfig?sponsor=1"
+			}
+		},
 		"node_modules/js-tokens": {
 			"version": "9.0.1",
 			"resolved": "https://registry.npmjs.org/js-tokens/-/js-tokens-9.0.1.tgz",
@@ -1372,6 +1398,7 @@
 			"integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"engines": {
 				"node": ">=12"
 			},
@@ -1408,10 +1435,20 @@
 				"node": "^10 || ^12 || >=14"
 			}
 		},
+		"node_modules/resolve-pkg-maps": {
+			"version": "1.0.0",
+			"resolved": "https://registry.npmjs.org/resolve-pkg-maps/-/resolve-pkg-maps-1.0.0.tgz",
+			"integrity": "sha512-seS2Tj26TBVOC2NIc2rOe2y2ZO7efxITtLZcGSOnHHNOQ7CkiUBfw0Iw2ck6xkIhPwLhKNLS8BO+hEpngQlqzw==",
+			"dev": true,
+			"license": "MIT",
+			"funding": {
+				"url": "https://github.com/privatenumber/resolve-pkg-maps?sponsor=1"
+			}
+		},
 		"node_modules/rollup": {
-			"version": "4.57.0",
-			"resolved": "https://registry.npmjs.org/rollup/-/rollup-4.57.0.tgz",
-			"integrity": "sha512-e5lPJi/aui4TO1LpAXIRLySmwXSE8k3b9zoGfd42p67wzxog4WHjiZF3M2uheQih4DGyc25QEV4yRBbpueNiUA==",
+			"version": "4.59.0",
+			"resolved": "https://registry.npmjs.org/rollup/-/rollup-4.59.0.tgz",
+			"integrity": "sha512-2oMpl67a3zCH9H79LeMcbDhXW/UmWG/y2zuqnF2jQq5uq9TbM9TVyXvA4+t+ne2IIkBdrLpAaRQAvo7YI/Yyeg==",
 			"dev": true,
 			"license": "MIT",
 			"dependencies": {
@@ -1425,31 +1462,31 @@
 				"npm": ">=8.0.0"
 			},
 			"optionalDependencies": {
-				"@rollup/rollup-android-arm-eabi": "4.57.0",
-				"@rollup/rollup-android-arm64": "4.57.0",
-				"@rollup/rollup-darwin-arm64": "4.57.0",
-				"@rollup/rollup-darwin-x64": "4.57.0",
-				"@rollup/rollup-freebsd-arm64": "4.57.0",
-				"@rollup/rollup-freebsd-x64": "4.57.0",
-				"@rollup/rollup-linux-arm-gnueabihf": "4.57.0",
-				"@rollup/rollup-linux-arm-musleabihf": "4.57.0",
-				"@rollup/rollup-linux-arm64-gnu": "4.57.0",
-				"@rollup/rollup-linux-arm64-musl": "4.57.0",
-				"@rollup/rollup-linux-loong64-gnu": "4.57.0",
-				"@rollup/rollup-linux-loong64-musl": "4.57.0",
-				"@rollup/rollup-linux-ppc64-gnu": "4.57.0",
-				"@rollup/rollup-linux-ppc64-musl": "4.57.0",
-				"@rollup/rollup-linux-riscv64-gnu": "4.57.0",
-				"@rollup/rollup-linux-riscv64-musl": "4.57.0",
-				"@rollup/rollup-linux-s390x-gnu": "4.57.0",
-				"@rollup/rollup-linux-x64-gnu": "4.57.0",
-				"@rollup/rollup-linux-x64-musl": "4.57.0",
-				"@rollup/rollup-openbsd-x64": "4.57.0",
-				"@rollup/rollup-openharmony-arm64": "4.57.0",
-				"@rollup/rollup-win32-arm64-msvc": "4.57.0",
-				"@rollup/rollup-win32-ia32-msvc": "4.57.0",
-				"@rollup/rollup-win32-x64-gnu": "4.57.0",
-				"@rollup/rollup-win32-x64-msvc": "4.57.0",
+				"@rollup/rollup-android-arm-eabi": "4.59.0",
+				"@rollup/rollup-android-arm64": "4.59.0",
+				"@rollup/rollup-darwin-arm64": "4.59.0",
+				"@rollup/rollup-darwin-x64": "4.59.0",
+				"@rollup/rollup-freebsd-arm64": "4.59.0",
+				"@rollup/rollup-freebsd-x64": "4.59.0",
+				"@rollup/rollup-linux-arm-gnueabihf": "4.59.0",
+				"@rollup/rollup-linux-arm-musleabihf": "4.59.0",
+				"@rollup/rollup-linux-arm64-gnu": "4.59.0",
+				"@rollup/rollup-linux-arm64-musl": "4.59.0",
+				"@rollup/rollup-linux-loong64-gnu": "4.59.0",
+				"@rollup/rollup-linux-loong64-musl": "4.59.0",
+				"@rollup/rollup-linux-ppc64-gnu": "4.59.0",
+				"@rollup/rollup-linux-ppc64-musl": "4.59.0",
+				"@rollup/rollup-linux-riscv64-gnu": "4.59.0",
+				"@rollup/rollup-linux-riscv64-musl": "4.59.0",
+				"@rollup/rollup-linux-s390x-gnu": "4.59.0",
+				"@rollup/rollup-linux-x64-gnu": "4.59.0",
+				"@rollup/rollup-linux-x64-musl": "4.59.0",
+				"@rollup/rollup-openbsd-x64": "4.59.0",
+				"@rollup/rollup-openharmony-arm64": "4.59.0",
+				"@rollup/rollup-win32-arm64-msvc": "4.59.0",
+				"@rollup/rollup-win32-ia32-msvc": "4.59.0",
+				"@rollup/rollup-win32-x64-gnu": "4.59.0",
+				"@rollup/rollup-win32-x64-msvc": "4.59.0",
 				"fsevents": "~2.3.2"
 			}
 		},
@@ -1558,12 +1595,41 @@
 				"node": ">=14.0.0"
 			}
 		},
+		"node_modules/tsx": {
+			"version": "4.21.0",
+			"resolved": "https://registry.npmjs.org/tsx/-/tsx-4.21.0.tgz",
+			"integrity": "sha512-5C1sg4USs1lfG0GFb2RLXsdpXqBSEhAaA/0kPL01wxzpMqLILNxIxIOKiILz+cdg/pLnOUxFYOR5yhHU666wbw==",
+			"dev": true,
+			"license": "MIT",
+			"peer": true,
+			"dependencies": {
+				"esbuild": "~0.27.0",
+				"get-tsconfig": "^4.7.5"
+			},
+			"bin": {
+				"tsx": "dist/cli.mjs"
+			},
+			"engines": {
+				"node": ">=18.0.0"
+			},
+			"optionalDependencies": {
+				"fsevents": "~2.3.3"
+			}
+		},
+		"node_modules/undici-types": {
+			"version": "7.16.0",
+			"resolved": "https://registry.npmjs.org/undici-types/-/undici-types-7.16.0.tgz",
+			"integrity": "sha512-Zz+aZWSj8LE6zoxD+xrjh4VfkIG8Ya6LvYkZqtUQGJPZjYl53ypCaUwWqo7eI0x66KBGeRo+mlBEkMSeSZ38Nw==",
+			"dev": true,
+			"license": "MIT"
+		},
 		"node_modules/vite": {
 			"version": "7.3.1",
 			"resolved": "https://registry.npmjs.org/vite/-/vite-7.3.1.tgz",
 			"integrity": "sha512-w+N7Hifpc3gRjZ63vYBXA56dvvRlNWRczTdmCBBa+CotUzAPf5b7YMdMR/8CQoeYE5LX3W4wj6RYTgonm1b9DA==",
 			"dev": true,
 			"license": "MIT",
+			"peer": true,
 			"dependencies": {
 				"esbuild": "^0.27.0",
 				"fdir": "^6.5.0",
--- a/package.json
+++ b/package.json
@@ -14,10 +14,14 @@
 		"check": "biome check --write .",
 		"ci:check": "biome ci .",
 		"test": "vitest run",
-		"test:sanity": "vitest run test/sanity.test.ts"
+		"test:sanity": "vitest run test/sanity.test.ts",
+		"evals:run": "tsx --env-file-if-exists=.env evals/main.ts",
+		"evals:build": "docker build -t evals-claude evals/"
 	},
 	"devDependencies": {
 		"@biomejs/biome": "2.3.11",
+		"@types/node": "^24.0.0",
+		"tsx": "^4.21.0",
 		"vitest": "^3.0.0"
 	}
 }