alexion
80a4fafa06
Add the maintainer-facing command that runs one chosen benchmark cell on demand, so only the token budget available at that moment is spent. runCells (bench/run-loop.ts) runs one (arm, task) cell for a batch of trials — defaulting to five with a reporting floor of three — by driving the existing single-cell runner and the append-only sample store rather than reimplementing orchestration. Re-running a cell deepens it: trial numbering continues past the highest trial the cell already holds and the new samples append, so a cell's sample size grows across sittings without overwriting prior runs. bench/run.ts is the command: parseRunArgs is the pure, unit-tested argument seam, and runBenchCommand is the live boundary that resolves host access, resolves the scored suite against the host's self-review support, selects the task, and drives the run loop. It is invoked via the new bench:run npm script, run under tsx (a new devDependency) because the harness's .js-specifier imports need a TypeScript-aware runner. The Claude Agent SDK is now declared as an optional peerDependency — documented but neither installed for package consumers nor pulled into CI. Every arm runs on the driver's single fixed model; the command exposes no per-cell model override that could break cross-arm comparability. The default store root bench/results/ is gitignored.
63 lines
1.6 KiB
JSON
63 lines
1.6 KiB
JSON
{
|
|
"name": "gitea-axi",
|
|
"version": "0.1.0",
|
|
"description": "Agent-ergonomic CLI for Gitea issues and pull requests",
|
|
"type": "module",
|
|
"license": "MIT",
|
|
"engines": {
|
|
"node": ">=20"
|
|
},
|
|
"bin": {
|
|
"gitea-axi": "dist/main.js"
|
|
},
|
|
"repository": {
|
|
"type": "git",
|
|
"url": "git+https://git.alexion.dev/alexion/gitea-axi.git"
|
|
},
|
|
"homepage": "https://git.alexion.dev/alexion/gitea-axi",
|
|
"bugs": {
|
|
"url": "https://git.alexion.dev/alexion/gitea-axi/issues"
|
|
},
|
|
"publishConfig": {
|
|
"access": "public",
|
|
"registry": "https://registry.npmjs.org/"
|
|
},
|
|
"files": [
|
|
"dist",
|
|
"skills"
|
|
],
|
|
"scripts": {
|
|
"build": "tsc -p tsconfig.build.json",
|
|
"prepack": "npm run build",
|
|
"typecheck": "tsc --noEmit",
|
|
"test": "vitest run",
|
|
"test:watch": "vitest",
|
|
"test:coverage": "vitest run --coverage",
|
|
"test:e2e": "vitest run --config vitest.e2e.config.ts",
|
|
"test:pack": "vitest run --config vitest.packaging.config.ts",
|
|
"test:bench": "vitest run --config vitest.bench.config.ts",
|
|
"test:bench:smoke": "vitest run --config vitest.bench-smoke.config.ts",
|
|
"bench:run": "tsx bench/run.ts"
|
|
},
|
|
"dependencies": {
|
|
"@toon-format/toon": "^2.3.0",
|
|
"axi-sdk-js": "^0.1.8",
|
|
"gitea-js": "^1.23.0"
|
|
},
|
|
"devDependencies": {
|
|
"@types/node": "^20.19.0",
|
|
"@vitest/coverage-v8": "^3.2.7",
|
|
"tsx": "^4.23.1",
|
|
"typescript": "^5.8.0",
|
|
"vitest": "^3.2.0"
|
|
},
|
|
"peerDependencies": {
|
|
"@anthropic-ai/claude-agent-sdk": ">=0.3.0"
|
|
},
|
|
"peerDependenciesMeta": {
|
|
"@anthropic-ai/claude-agent-sdk": {
|
|
"optional": true
|
|
}
|
|
}
|
|
}
|