feat(evals): add coding-task evaluation framework (#2084)

package.json

@@ -19,6 +19,8 @@
 		"solheim-smoke:check-types": "tsc -p scripts/solheim-smoke/tsconfig.json",
 		"test:agent-evals:unit": "node --import tsx --test scripts/agent-evals/*.test.ts",
 		"agent-evals:check-types": "tsc -p scripts/agent-evals/tsconfig.json",
+		"coding-evals:side": "node --import tsx scripts/agent-evals/coding-side.mts",
+		"coding-evals:compare": "node --import tsx scripts/agent-evals/coding-compare.mts",
 		"test:mutation-ci": "node --test scripts/stryker-diff.test.mjs",
 		"lifecycle:model-check": "tsx scripts/check-task-lifecycle.ts && tsx scripts/check-task-store-concurrency.ts && tsx scripts/check-provider-handoff-scheduler.ts && pnpm cleanup-protocol:model-check && pnpm parser-scope:model-check && tsx scripts/check-completion-persistence.ts && tsx scripts/check-delegated-mode-readers.ts && pnpm tool-turn:model-check",
 		"webview-recovery:model-check": "node --import tsx scripts/check-webview-recovery.ts",
@@ -52,6 +54,7 @@
 		"@stryker-mutator/core": "10.0.0",
 		"@stryker-mutator/vitest-runner": "10.0.0",
 		"@types/node": "catalog:",
+		"@types/proper-lockfile": "catalog:",
 		"@vscode/vsce": "3.9.2",
 		"esbuild": "0.28.2",
 		"eslint": "9.39.5",
@@ -60,6 +63,7 @@
 		"lint-staged": "16.4.0",
 		"ovsx": "0.10.12",
 		"prettier": "3.9.10",
+		"proper-lockfile": "catalog:",
 		"rimraf": "6.0.1",
 		"tsx": "4.23.15",
 		"turbo": "catalog:",

pnpm-workspace.yaml

@@ -6,9 +6,11 @@ packages:
 
 catalog:
     "@types/node": 22.20.5
+    "@types/proper-lockfile": 4.1.4
     "@vitest/coverage-v8": 4.1.12
     "@vitest/ui": 4.1.12
     eslint-plugin-turbo: 2.11.10
+    proper-lockfile: 4.1.2
     turbo: 2.11.10
     vite: 8.3.5
     vitest: 4.1.12