diff --git a/tests/evals/package-lock.json b/tests/evals/package-lock.json
index 3eeb688d0..de0ec1a80 100644
--- a/tests/evals/package-lock.json
+++ b/tests/evals/package-lock.json
@@ -7,7 +7,7 @@
       "name": "@skill-builder/evals",
       "dependencies": {
         "js-yaml": "^4.1.1",
-        "promptfoo": "0.121.11",
+        "promptfoo": "0.121.12",
         "smol-toml": "^1.6.1",
         "typescript": "~6.0.2"
       }
@@ -137,9 +137,6 @@
       "cpu": [
         "arm64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "SEE LICENSE IN LICENSE.md",
       "optional": true,
       "os": [
@@ -153,9 +150,6 @@
       "cpu": [
         "arm64"
       ],
-      "libc": [
-        "musl"
-      ],
       "license": "SEE LICENSE IN LICENSE.md",
       "optional": true,
       "os": [
@@ -169,9 +163,6 @@
       "cpu": [
         "x64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "SEE LICENSE IN LICENSE.md",
       "optional": true,
       "os": [
@@ -185,9 +176,6 @@
       "cpu": [
         "x64"
       ],
-      "libc": [
-        "musl"
-      ],
       "license": "SEE LICENSE IN LICENSE.md",
       "optional": true,
       "os": [
@@ -1989,9 +1977,6 @@
       "cpu": [
         "arm"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "LGPL-3.0-or-later",
       "optional": true,
       "os": [
@@ -2008,9 +1993,6 @@
       "cpu": [
         "arm64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "LGPL-3.0-or-later",
       "optional": true,
       "os": [
@@ -2027,9 +2009,6 @@
       "cpu": [
         "ppc64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "LGPL-3.0-or-later",
       "optional": true,
       "os": [
@@ -2046,9 +2025,6 @@
       "cpu": [
         "riscv64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "LGPL-3.0-or-later",
       "optional": true,
       "os": [
@@ -2065,9 +2041,6 @@
       "cpu": [
         "s390x"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "LGPL-3.0-or-later",
       "optional": true,
       "os": [
@@ -2084,9 +2057,6 @@
       "cpu": [
         "x64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "LGPL-3.0-or-later",
       "optional": true,
       "os": [
@@ -2103,9 +2073,6 @@
       "cpu": [
         "arm64"
       ],
-      "libc": [
-        "musl"
-      ],
       "license": "LGPL-3.0-or-later",
       "optional": true,
       "os": [
@@ -2122,9 +2089,6 @@
       "cpu": [
         "x64"
       ],
-      "libc": [
-        "musl"
-      ],
       "license": "LGPL-3.0-or-later",
       "optional": true,
       "os": [
@@ -2141,9 +2105,6 @@
       "cpu": [
         "arm"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "Apache-2.0",
       "optional": true,
       "os": [
@@ -2166,9 +2127,6 @@
       "cpu": [
         "arm64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "Apache-2.0",
       "optional": true,
       "os": [
@@ -2191,9 +2149,6 @@
       "cpu": [
         "ppc64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "Apache-2.0",
       "optional": true,
       "os": [
@@ -2216,9 +2171,6 @@
       "cpu": [
         "riscv64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "Apache-2.0",
       "optional": true,
       "os": [
@@ -2241,9 +2193,6 @@
       "cpu": [
         "s390x"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "Apache-2.0",
       "optional": true,
       "os": [
@@ -2266,9 +2215,6 @@
       "cpu": [
         "x64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "Apache-2.0",
       "optional": true,
       "os": [
@@ -2291,9 +2237,6 @@
       "cpu": [
         "arm64"
       ],
-      "libc": [
-        "musl"
-      ],
       "license": "Apache-2.0",
       "optional": true,
       "os": [
@@ -2316,9 +2259,6 @@
       "cpu": [
         "x64"
       ],
-      "libc": [
-        "musl"
-      ],
       "license": "Apache-2.0",
       "optional": true,
       "os": [
@@ -2562,6 +2502,28 @@
         }
       }
     },
+    "node_modules/@inquirer/search": {
+      "version": "4.1.9",
+      "resolved": "https://registry.npmjs.org/@inquirer/search/-/search-4.1.9.tgz",
+      "integrity": "sha512-ZlbM28Q9lmLkFPNAIv+ZuY530n5Km8U1WW48oYEvDhe9yc2uL3m3t+JSdRUkQlk5fuIuskgiIVjcb7czFzQpuA==",
+      "license": "MIT",
+      "dependencies": {
+        "@inquirer/core": "^11.1.10",
+        "@inquirer/figures": "^2.0.5",
+        "@inquirer/type": "^4.0.5"
+      },
+      "engines": {
+        "node": ">=23.5.0 || ^22.13.0 || ^21.7.0 || ^20.12.0"
+      },
+      "peerDependencies": {
+        "@types/node": ">=18"
+      },
+      "peerDependenciesMeta": {
+        "@types/node": {
+          "optional": true
+        }
+      }
+    },
     "node_modules/@inquirer/select": {
       "version": "5.1.5",
       "resolved": "https://registry.npmjs.org/@inquirer/select/-/select-5.1.5.tgz",
@@ -2788,9 +2750,6 @@
       "cpu": [
         "arm64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -2807,9 +2766,6 @@
       "cpu": [
         "arm64"
       ],
-      "libc": [
-        "musl"
-      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -2826,9 +2782,6 @@
       "cpu": [
         "riscv64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -2845,9 +2798,6 @@
       "cpu": [
         "x64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -2864,9 +2814,6 @@
       "cpu": [
         "x64"
       ],
-      "libc": [
-        "musl"
-      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -2905,29 +2852,29 @@
       "license": "MIT"
     },
     "node_modules/@openai/agents": {
-      "version": "0.8.5",
-      "resolved": "https://registry.npmjs.org/@openai/agents/-/agents-0.8.5.tgz",
-      "integrity": "sha512-OFA7XVV1qXE8lzatvQj080KdSArt8utBExFXRfD5B/R7KT0D+AVaKwg6nLoW3Gxb30vRkIUQf+MaW/Wz+gO3Yg==",
+      "version": "0.11.4",
+      "resolved": "https://registry.npmjs.org/@openai/agents/-/agents-0.11.4.tgz",
+      "integrity": "sha512-HEOnixfXyziXgYcuRWIx+oJRYLgTxX8VFeJPIAum7LSYxznO5orJsn4u+u3w+7xe1BupoB8eUaJ7dDvOSChKPA==",
       "license": "MIT",
       "dependencies": {
-        "@openai/agents-core": "0.8.5",
-        "@openai/agents-openai": "0.8.5",
-        "@openai/agents-realtime": "0.8.5",
+        "@openai/agents-core": "0.11.4",
+        "@openai/agents-openai": "0.11.4",
+        "@openai/agents-realtime": "0.11.4",
         "debug": "^4.4.0",
-        "openai": "^6.26.0"
+        "openai": "^6.35.0"
       },
       "peerDependencies": {
         "zod": "^4.0.0"
       }
     },
     "node_modules/@openai/agents-core": {
-      "version": "0.8.5",
-      "resolved": "https://registry.npmjs.org/@openai/agents-core/-/agents-core-0.8.5.tgz",
-      "integrity": "sha512-qs9mmN+D+UmqEZo3qrvhhIIXIOgSvJPic0v4a+ruq+eYgcQMk3PY8lLcsdQwJit6zf2Wyfv1q2cX5m3jzWZpKw==",
+      "version": "0.11.4",
+      "resolved": "https://registry.npmjs.org/@openai/agents-core/-/agents-core-0.11.4.tgz",
+      "integrity": "sha512-K529uAX9oZV8LUnsv0b+c+nWflIJc+LAJeEfZLN74q0J9UYvyt4pddt30e7OsGS1kPVK/lbChnPCOkPhnd1cpg==",
       "license": "MIT",
       "dependencies": {
         "debug": "^4.4.0",
-        "openai": "^6.26.0"
+        "openai": "^6.35.0"
       },
       "optionalDependencies": {
         "@modelcontextprotocol/sdk": "^1.26.0"
@@ -2942,26 +2889,26 @@
       }
     },
     "node_modules/@openai/agents-openai": {
-      "version": "0.8.5",
-      "resolved": "https://registry.npmjs.org/@openai/agents-openai/-/agents-openai-0.8.5.tgz",
-      "integrity": "sha512-cGYmyiVy8ecgf2Vch0L/ekeNo3xuZsuWnRsxyv+w9ai9dgxUifdEQ6G3dtsjMLtmXVHRVGoO7mVBr+tKcilntw==",
+      "version": "0.11.4",
+      "resolved": "https://registry.npmjs.org/@openai/agents-openai/-/agents-openai-0.11.4.tgz",
+      "integrity": "sha512-NAiiCsUsb+4twlaCIZ4OM8s9WoDNKjHfZBrw1jkE/oXH4sXO5OwRqi85ZM5xtfZNBqBF0IEY5hIuwWOhZntdKg==",
       "license": "MIT",
       "dependencies": {
-        "@openai/agents-core": "0.8.5",
+        "@openai/agents-core": "0.11.4",
         "debug": "^4.4.0",
-        "openai": "^6.26.0"
+        "openai": "^6.35.0"
       },
       "peerDependencies": {
         "zod": "^4.0.0"
       }
     },
     "node_modules/@openai/agents-realtime": {
-      "version": "0.8.5",
-      "resolved": "https://registry.npmjs.org/@openai/agents-realtime/-/agents-realtime-0.8.5.tgz",
-      "integrity": "sha512-JqKVsR33OvKtTxRp5Ylhw8WfNvJ49ZIhlhMZlSVKqwR2Ks6JuxqFJ0zM9p7JIbTQDSlAZnmnZJv1qlItaildiQ==",
+      "version": "0.11.4",
+      "resolved": "https://registry.npmjs.org/@openai/agents-realtime/-/agents-realtime-0.11.4.tgz",
+      "integrity": "sha512-SZS22YbsKilfPpsVJmHwigYbNX3W+ZHZFTm5+uDdV3OnziodCQu2P/cMag2dcpwmJq/fW0lANUzD+YC4l0qwoA==",
       "license": "MIT",
       "dependencies": {
-        "@openai/agents-core": "0.8.5",
+        "@openai/agents-core": "0.11.4",
         "@types/ws": "^8.18.1",
         "debug": "^4.4.0",
         "ws": "^8.18.1"
@@ -2971,9 +2918,9 @@
       }
     },
     "node_modules/@openai/codex": {
-      "version": "0.128.0",
-      "resolved": "https://registry.npmjs.org/@openai/codex/-/codex-0.128.0.tgz",
-      "integrity": "sha512-+xp6ODmFfBNnexIWRHApEaPXot2j6gyM8A5we/5IS/uY4eYHj4arETct4hQ5M4eO+MK7JY3ZU4xhuobhlysr0A==",
+      "version": "0.130.0",
+      "resolved": "https://registry.npmjs.org/@openai/codex/-/codex-0.130.0.tgz",
+      "integrity": "sha512-WGDj+RZ3TXWC/7MlwprgLWOqzpwatPIINPhP3IRzHA0ni+o3QZ4i4xrS2uWwGmHUJ395J5JHwoZAAZYyfJyz6w==",
       "license": "Apache-2.0",
       "optional": true,
       "bin": {
@@ -2983,19 +2930,19 @@
         "node": ">=16"
       },
       "optionalDependencies": {
-        "@openai/codex-darwin-arm64": "npm:@openai/codex@0.128.0-darwin-arm64",
-        "@openai/codex-darwin-x64": "npm:@openai/codex@0.128.0-darwin-x64",
-        "@openai/codex-linux-arm64": "npm:@openai/codex@0.128.0-linux-arm64",
-        "@openai/codex-linux-x64": "npm:@openai/codex@0.128.0-linux-x64",
-        "@openai/codex-win32-arm64": "npm:@openai/codex@0.128.0-win32-arm64",
-        "@openai/codex-win32-x64": "npm:@openai/codex@0.128.0-win32-x64"
+        "@openai/codex-darwin-arm64": "npm:@openai/codex@0.130.0-darwin-arm64",
+        "@openai/codex-darwin-x64": "npm:@openai/codex@0.130.0-darwin-x64",
+        "@openai/codex-linux-arm64": "npm:@openai/codex@0.130.0-linux-arm64",
+        "@openai/codex-linux-x64": "npm:@openai/codex@0.130.0-linux-x64",
+        "@openai/codex-win32-arm64": "npm:@openai/codex@0.130.0-win32-arm64",
+        "@openai/codex-win32-x64": "npm:@openai/codex@0.130.0-win32-x64"
       }
     },
     "node_modules/@openai/codex-darwin-arm64": {
       "name": "@openai/codex",
-      "version": "0.128.0-darwin-arm64",
-      "resolved": "https://registry.npmjs.org/@openai/codex/-/codex-0.128.0-darwin-arm64.tgz",
-      "integrity": "sha512-w+6zohfHx/kHBdles/CyFKaY57u9I3nK8QI9+NrdwMliKA0b7xn13yblRNkMpe09j6vL1oAWoxYsMOQ/vjBGug==",
+      "version": "0.130.0-darwin-arm64",
+      "resolved": "https://registry.npmjs.org/@openai/codex/-/codex-0.130.0-darwin-arm64.tgz",
+      "integrity": "sha512-R9pkGC7kwC8yQ8el5hvBlmugQlcsG/pHMEFgZluu03X9fD2TezGxdq3KqRDRCZuMYl07ILamVEoqknuJ0cq7MA==",
       "cpu": [
         "arm64"
       ],
@@ -3010,9 +2957,9 @@
     },
     "node_modules/@openai/codex-darwin-x64": {
       "name": "@openai/codex",
-      "version": "0.128.0-darwin-x64",
-      "resolved": "https://registry.npmjs.org/@openai/codex/-/codex-0.128.0-darwin-x64.tgz",
-      "integrity": "sha512-SDbn6fO22Puy8xmMIbZi4f2znMrUEPwABApke4mo+4ihaauwuVjeqzXvW5SPJz5ty/bG11/mSupQgReT7T8BBw==",
+      "version": "0.130.0-darwin-x64",
+      "resolved": "https://registry.npmjs.org/@openai/codex/-/codex-0.130.0-darwin-x64.tgz",
+      "integrity": "sha512-gJ+7J8djevgtdra+NgDAiQQPW+O3KTsgGfE3E5dpDfww3zS5OCeV0V2dhxqnJdlOjOSDw99o0P2LqBv19mhpRw==",
       "cpu": [
         "x64"
       ],
@@ -3027,9 +2974,9 @@
     },
     "node_modules/@openai/codex-linux-arm64": {
       "name": "@openai/codex",
-      "version": "0.128.0-linux-arm64",
-      "resolved": "https://registry.npmjs.org/@openai/codex/-/codex-0.128.0-linux-arm64.tgz",
-      "integrity": "sha512-+SvH73H60qvCXFuQGP/EsmR//s1hHMBR22PvJkXvM/hdnTIGucx+JqRUjAWdmmQ1IU6j3kgwVvdLW/6ICB+M6w==",
+      "version": "0.130.0-linux-arm64",
+      "resolved": "https://registry.npmjs.org/@openai/codex/-/codex-0.130.0-linux-arm64.tgz",
+      "integrity": "sha512-tFtH0V9/hEI3d9y7zP92BXI9FM4Z3+STNQaOR52Czv18TRtCFUp7CbIUYaToopuq6UBfnE1VKr8RLhwT5FcbmA==",
       "cpu": [
         "arm64"
       ],
@@ -3044,9 +2991,9 @@
     },
     "node_modules/@openai/codex-linux-x64": {
       "name": "@openai/codex",
-      "version": "0.128.0-linux-x64",
-      "resolved": "https://registry.npmjs.org/@openai/codex/-/codex-0.128.0-linux-x64.tgz",
-      "integrity": "sha512-2lnSPA05CRRuKAzFW8BCmmNCSieDcToLwfC2ALLbBYilGLgzhRibjlDglK9F1BkEzfohSSWJu4PBbRu/aG60lQ==",
+      "version": "0.130.0-linux-x64",
+      "resolved": "https://registry.npmjs.org/@openai/codex/-/codex-0.130.0-linux-x64.tgz",
+      "integrity": "sha512-3VcNlez99xdnEf+kB1IOpWv9fICYV9PiGj4sLCO4TCcShLnyxe+YBGa3poknkvXLnMG0qiN9SMnYS2FGrMxQcA==",
       "cpu": [
         "x64"
       ],
@@ -3060,13 +3007,13 @@
       }
     },
     "node_modules/@openai/codex-sdk": {
-      "version": "0.128.0",
-      "resolved": "https://registry.npmjs.org/@openai/codex-sdk/-/codex-sdk-0.128.0.tgz",
-      "integrity": "sha512-Eao0LLA5x90qwU6SXYd21h4KxdCef1WpCvHFgKdbqzWMJ79lUvguGDGvx1RheP+zTdKGxJfJ6dulI5wSXoUBhQ==",
+      "version": "0.130.0",
+      "resolved": "https://registry.npmjs.org/@openai/codex-sdk/-/codex-sdk-0.130.0.tgz",
+      "integrity": "sha512-ICKaZ5zrIDg71AiQcsUToVoe5Icmrc3LwSM5+2z7Cf8F1x6nOaY7/ucpFlr4aH8oDe7t3dangc+MsWZTkdvDFw==",
       "license": "Apache-2.0",
       "optional": true,
       "dependencies": {
-        "@openai/codex": "0.128.0"
+        "@openai/codex": "0.130.0"
       },
       "engines": {
         "node": ">=18"
@@ -3074,9 +3021,9 @@
     },
     "node_modules/@openai/codex-win32-arm64": {
       "name": "@openai/codex",
-      "version": "0.128.0-win32-arm64",
-      "resolved": "https://registry.npmjs.org/@openai/codex/-/codex-0.128.0-win32-arm64.tgz",
-      "integrity": "sha512-ECJvsqmYFdA9pn42xxK3Odp/G16AjmBW0BglX8L0PwPjqbstbmlew9bfHf7xvL+SNfNl4NmyotW0+RNo1phgaA==",
+      "version": "0.130.0-win32-arm64",
+      "resolved": "https://registry.npmjs.org/@openai/codex/-/codex-0.130.0-win32-arm64.tgz",
+      "integrity": "sha512-vdpmiNp57L/arZabltLXn8TyEtNa7W1meOEkr+3R6W/8ZyBt++wuqz1Orv134OT2grrcFJsIVCAIPiqUxCvBkA==",
       "cpu": [
         "arm64"
       ],
@@ -3091,9 +3038,9 @@
     },
     "node_modules/@openai/codex-win32-x64": {
       "name": "@openai/codex",
-      "version": "0.128.0-win32-x64",
-      "resolved": "https://registry.npmjs.org/@openai/codex/-/codex-0.128.0-win32-x64.tgz",
-      "integrity": "sha512-k3jmUAFrzkUtvjGTXvSKjQqJLLlzjxp/VoHJDYedgmXUn6j70HxK38IwapzmnYfiBiTuzETvGwjXHzZgzKjhoQ==",
+      "version": "0.130.0-win32-x64",
+      "resolved": "https://registry.npmjs.org/@openai/codex/-/codex-0.130.0-win32-x64.tgz",
+      "integrity": "sha512-FzMznm7fr5/nbjZgOujZ9Y9AbdGm7ji1FOoWiY3U+srqauvZaTgn6o6aCheSL7kuymu7nTLOO/cAyWV6NuesqQ==",
       "cpu": [
         "x64"
       ],
@@ -3125,9 +3072,9 @@
       }
     },
     "node_modules/@opentelemetry/api-logs": {
-      "version": "0.216.0",
-      "resolved": "https://registry.npmjs.org/@opentelemetry/api-logs/-/api-logs-0.216.0.tgz",
-      "integrity": "sha512-KmGTgvxTJ0J01d4mOeX1wMV5NUTNf9HebIuOOGDfIn0a/IrnXIQbOnlylDyl9tkDv4h0DUpdI/GqCdLzfTkUXg==",
+      "version": "0.218.0",
+      "resolved": "https://registry.npmjs.org/@opentelemetry/api-logs/-/api-logs-0.218.0.tgz",
+      "integrity": "sha512-fmEWp5kXlGEc3i/lR698Hz41DfGyN4Tbe4g7L1AxSc7fF8Xeh/FQ9Quqpa9dVA413Q1Ad43QOLzU4JoXgbFPWw==",
       "license": "Apache-2.0",
       "dependencies": {
         "@opentelemetry/api": "^1.3.0"
@@ -3164,14 +3111,14 @@
       }
     },
     "node_modules/@opentelemetry/exporter-trace-otlp-http": {
-      "version": "0.216.0",
-      "resolved": "https://registry.npmjs.org/@opentelemetry/exporter-trace-otlp-http/-/exporter-trace-otlp-http-0.216.0.tgz",
-      "integrity": "sha512-DhWjvj0PUPFwFnhOEivpum8sJzj6FTuyx88zff+oHVLUhfd6cLyw4AIai/F4j0PZqYZBFuMT/OTMUd9wdXnBEQ==",
+      "version": "0.218.0",
+      "resolved": "https://registry.npmjs.org/@opentelemetry/exporter-trace-otlp-http/-/exporter-trace-otlp-http-0.218.0.tgz",
+      "integrity": "sha512-8dqezsmPhtKitIK/eTipZhYl9EX2/gNQ5zUMhaz3uxEURwfkNf8IPvo6yNfrzbxdtpAOybS/+h7wmIWYqFSpiw==",
       "license": "Apache-2.0",
       "dependencies": {
         "@opentelemetry/core": "2.7.1",
-        "@opentelemetry/otlp-exporter-base": "0.216.0",
-        "@opentelemetry/otlp-transformer": "0.216.0",
+        "@opentelemetry/otlp-exporter-base": "0.218.0",
+        "@opentelemetry/otlp-transformer": "0.218.0",
         "@opentelemetry/resources": "2.7.1",
         "@opentelemetry/sdk-trace-base": "2.7.1"
       },
@@ -3183,13 +3130,13 @@
       }
     },
     "node_modules/@opentelemetry/otlp-exporter-base": {
-      "version": "0.216.0",
-      "resolved": "https://registry.npmjs.org/@opentelemetry/otlp-exporter-base/-/otlp-exporter-base-0.216.0.tgz",
-      "integrity": "sha512-sSnvb5f+FYa4mfYxj03rmmUh+aDwo3jok62dgIWUDw8ZCUPzEbgtv/YhZyKUSlKNNey7Uc5xmJgmtTLLIV6UDQ==",
+      "version": "0.218.0",
+      "resolved": "https://registry.npmjs.org/@opentelemetry/otlp-exporter-base/-/otlp-exporter-base-0.218.0.tgz",
+      "integrity": "sha512-ZwqpkNL5W7RyGJPDZ9g06DvKp8KFTWPJPN12anpMQYSKpTSU0z3EIZuPq9vPGpS8siFyOqDYDAuCwlNO9FqgbA==",
       "license": "Apache-2.0",
       "dependencies": {
         "@opentelemetry/core": "2.7.1",
-        "@opentelemetry/otlp-transformer": "0.216.0"
+        "@opentelemetry/otlp-transformer": "0.218.0"
       },
       "engines": {
         "node": "^18.19.0 || >=20.6.0"
@@ -3199,18 +3146,17 @@
       }
     },
     "node_modules/@opentelemetry/otlp-transformer": {
-      "version": "0.216.0",
-      "resolved": "https://registry.npmjs.org/@opentelemetry/otlp-transformer/-/otlp-transformer-0.216.0.tgz",
-      "integrity": "sha512-g4Rb6sAsxQAo11eDjixfKxelruBsQFdJ8Wo23FCj7D6OXbidgXMu2xaRSYs4RdlomzAXSJuc86RcS3xmE8A6uA==",
+      "version": "0.218.0",
+      "resolved": "https://registry.npmjs.org/@opentelemetry/otlp-transformer/-/otlp-transformer-0.218.0.tgz",
+      "integrity": "sha512-CFaKH87WAzjuJ4awowTTLzUvMfaRfiOFG5+qm5S5ncyalRtN4ecQ+YmuANJSCrVPuvZFEkUgKhBPBndxi3rHsQ==",
       "license": "Apache-2.0",
       "dependencies": {
-        "@opentelemetry/api-logs": "0.216.0",
+        "@opentelemetry/api-logs": "0.218.0",
         "@opentelemetry/core": "2.7.1",
         "@opentelemetry/resources": "2.7.1",
-        "@opentelemetry/sdk-logs": "0.216.0",
+        "@opentelemetry/sdk-logs": "0.218.0",
         "@opentelemetry/sdk-metrics": "2.7.1",
-        "@opentelemetry/sdk-trace-base": "2.7.1",
-        "protobufjs": "8.0.1"
+        "@opentelemetry/sdk-trace-base": "2.7.1"
       },
       "engines": {
         "node": "^18.19.0 || >=20.6.0"
@@ -3236,12 +3182,12 @@
       }
     },
     "node_modules/@opentelemetry/sdk-logs": {
-      "version": "0.216.0",
-      "resolved": "https://registry.npmjs.org/@opentelemetry/sdk-logs/-/sdk-logs-0.216.0.tgz",
-      "integrity": "sha512-KB3rcwQuitq0JbbsCcNdqMhRJX3kArAYz/ovb0jGRaBQAIrt2roik3xQXuhYxS37zx0jSkUZcJu1z3Y2UCxbDA==",
+      "version": "0.218.0",
+      "resolved": "https://registry.npmjs.org/@opentelemetry/sdk-logs/-/sdk-logs-0.218.0.tgz",
+      "integrity": "sha512-QvnNdugatFTVCJXH0Mcu7GOOJSylA9j127kIezOE4YwTI4YbowRons2K4WZTv5FMS8T4q9P0NdaRHdkSmeAIag==",
       "license": "Apache-2.0",
       "dependencies": {
-        "@opentelemetry/api-logs": "0.216.0",
+        "@opentelemetry/api-logs": "0.218.0",
         "@opentelemetry/core": "2.7.1",
         "@opentelemetry/resources": "2.7.1",
         "@opentelemetry/semantic-conventions": "^1.29.0"
@@ -3419,9 +3365,6 @@
       "cpu": [
         "x64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -3764,9 +3707,6 @@
       "cpu": [
         "arm64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "Apache-2.0 AND MIT",
       "optional": true,
       "os": [
@@ -3783,9 +3723,6 @@
       "cpu": [
         "arm64"
       ],
-      "libc": [
-        "musl"
-      ],
       "license": "Apache-2.0 AND MIT",
       "optional": true,
       "os": [
@@ -3802,9 +3739,6 @@
       "cpu": [
         "ppc64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "Apache-2.0 AND MIT",
       "optional": true,
       "os": [
@@ -3821,9 +3755,6 @@
       "cpu": [
         "s390x"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "Apache-2.0 AND MIT",
       "optional": true,
       "os": [
@@ -3840,9 +3771,6 @@
       "cpu": [
         "x64"
       ],
-      "libc": [
-        "glibc"
-      ],
       "license": "Apache-2.0 AND MIT",
       "optional": true,
       "os": [
@@ -3859,9 +3787,6 @@
       "cpu": [
         "x64"
       ],
-      "libc": [
-        "musl"
-      ],
       "license": "Apache-2.0 AND MIT",
       "optional": true,
       "os": [
@@ -8875,16 +8800,16 @@
       "optional": true
     },
     "node_modules/promptfoo": {
-      "version": "0.121.11",
-      "resolved": "https://registry.npmjs.org/promptfoo/-/promptfoo-0.121.11.tgz",
-      "integrity": "sha512-URdQxCgfKbXfA5jFYBkYdGNcz6z2mo/umnGUJ1irVYNNDV9X8qUNAt0sC5OixTUCEGgx1+H9frcbboTtZuJybQ==",
+      "version": "0.121.12",
+      "resolved": "https://registry.npmjs.org/promptfoo/-/promptfoo-0.121.12.tgz",
+      "integrity": "sha512-xP/RV+J05eZEsDDDnfU6nCdL0WLUVbo4FnmpwRFascgKLXIO+95NRV7T2iI2v1+Xa51I0Pb/VKIz/qRo41R69Q==",
       "license": "MIT",
       "workspaces": [
         "src/app",
         "site"
       ],
       "dependencies": {
-        "@anthropic-ai/sdk": "^0.92.0",
+        "@anthropic-ai/sdk": "^0.97.1",
         "@apidevtools/json-schema-ref-parser": "^15.3.1",
         "@googleapis/sheets": "^13.0.1",
         "@inquirer/checkbox": "^5.1.0",
@@ -8892,13 +8817,14 @@
         "@inquirer/core": "^11.1.5",
         "@inquirer/editor": "^5.0.8",
         "@inquirer/input": "^5.0.8",
+        "@inquirer/search": "^4.1.8",
         "@inquirer/select": "^5.1.0",
         "@modelcontextprotocol/sdk": "^1.29.0",
-        "@openai/agents": "^0.8.5",
+        "@openai/agents": "^0.11.3",
         "@opencode-ai/sdk": "^1.14.33",
         "@opentelemetry/api": "^1.9.0",
         "@opentelemetry/core": "^2.6.0",
-        "@opentelemetry/exporter-trace-otlp-http": "^0.216.0",
+        "@opentelemetry/exporter-trace-otlp-http": "^0.218.0",
         "@opentelemetry/resources": "^2.6.0",
         "@opentelemetry/sdk-trace-base": "^2.6.0",
         "@opentelemetry/sdk-trace-node": "^2.6.0",
@@ -8908,7 +8834,7 @@
         "ajv": "^8.18.0",
         "ajv-formats": "^3.0.1",
         "async": "^3.2.6",
-        "better-sqlite3": "^12.8.0",
+        "better-sqlite3": "^12.10.0",
         "binary-extensions": "^3.1.0",
         "cache-manager": "^7.2.8",
         "chalk": "^5.6.2",
@@ -8945,7 +8871,7 @@
         "mathjs": "^15.1.1",
         "minimatch": "^10.2.4",
         "nunjucks": "^3.2.4",
-        "openai": "^6.35.0",
+        "openai": "^6.37.0",
         "opener": "^1.5.2",
         "ora": "^9.3.0",
         "parse5": "^8.0.0",
@@ -8976,24 +8902,24 @@
         "node": "^20.20.0 || >=22.22.0"
       },
       "optionalDependencies": {
-        "@anthropic-ai/claude-agent-sdk": "^0.2.126",
-        "@aws-sdk/client-bedrock-agent-runtime": "^3.1040.0",
-        "@aws-sdk/client-bedrock-runtime": "^3.1040.0",
+        "@anthropic-ai/claude-agent-sdk": "^0.2.141",
+        "@aws-sdk/client-bedrock-agent-runtime": "^3.1045.0",
+        "@aws-sdk/client-bedrock-runtime": "^3.1045.0",
         "@aws-sdk/client-s3": "^3.1003.0",
-        "@aws-sdk/client-sagemaker-runtime": "^3.1040.0",
+        "@aws-sdk/client-sagemaker-runtime": "^3.1045.0",
         "@aws-sdk/credential-provider-sso": "^3.972.16",
-        "@azure/ai-projects": "^2.1.0",
+        "@azure/ai-projects": "^2.1.1",
         "@azure/identity": "^4.13.0",
-        "@azure/msal-node": "^5.1.0",
+        "@azure/msal-node": "^5.2.0",
         "@azure/openai-assistants": "^1.0.0-beta.6",
-        "@fal-ai/client": "~1.10.0",
+        "@fal-ai/client": "~1.10.1",
         "@huggingface/transformers": "^4.0.0",
-        "@ibm-cloud/watsonx-ai": "^1.7.11",
+        "@ibm-cloud/watsonx-ai": "^1.7.12",
         "@ibm-generative-ai/node-sdk": "^3.2.4",
-        "@openai/codex-sdk": "^0.128.0",
-        "@playwright/browser-chromium": "^1.59.1",
-        "@rollup/rollup-linux-x64-gnu": "^4.59.0",
-        "@slack/web-api": "^7.15.0",
+        "@openai/codex-sdk": "^0.130.0",
+        "@playwright/browser-chromium": "^1.60.0",
+        "@rollup/rollup-linux-x64-gnu": "^4.60.3",
+        "@slack/web-api": "^7.15.2",
         "@smithy/node-http-handler": "^4.4.14",
         "@swc/core": "^1.15.18",
         "@swc/core-darwin-arm64": "^1.15.18",
@@ -9008,7 +8934,7 @@
         "natural": "^8.1.1",
         "node-sql-parser": "^5.4.0",
         "pdf-parse": "^2.4.5",
-        "playwright": "^1.59.1",
+        "playwright": "^1.60.0",
         "playwright-extra": "^4.3.6",
         "read-excel-file": "^9.0.0",
         "sharp": "^0.34.5"
diff --git a/tests/evals/package.json b/tests/evals/package.json
index 03da00829..96951655a 100644
--- a/tests/evals/package.json
+++ b/tests/evals/package.json
@@ -28,7 +28,7 @@
   },
   "dependencies": {
     "js-yaml": "^4.1.1",
-    "promptfoo": "0.121.11",
+    "promptfoo": "0.121.12",
     "smol-toml": "^1.6.1",
     "typescript": "~6.0.2"
   },