mirror of
https://github.com/windmill-labs/windmill.git
synced 2026-10-03 16:02:12 +00:00
hugocasaandClaude Opus 5.5
e117871bec
* feat: run ai evals weekly on current models and post results to a dashboard Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * feat: add current flagship models, a reasoning flag and claude 5.5 defaults Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix: never send a reasoning disable claude 5.5 or gpt-6-astra reject, and treat gpt-6 as a reasoning model Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix: address review on gpt-6 support, chat completions tools and model metadata Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix: leave tiered gpt-6 unpriced and drop the off sentinel on gpt-5 and o-series Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * docs: point the ai_evals readme at the model registry instead of copying it Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * refactor: encode the reasoning rules as per-family maps with a shared parity fixture Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix: keep the chat completions tools rule open-ended past gpt-5.6 and scope the parity fixture Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
22 lines
587 B
JSON
22 lines
587 B
JSON
{
|
|
"name": "windmill-ai-evals",
|
|
"private": true,
|
|
"type": "module",
|
|
"scripts": {
|
|
"cli": "bun cli/index.ts",
|
|
"typecheck": "tsc -p tsconfig.json",
|
|
"test:frontend-graph": "cd ../frontend && node_modules/.bin/vitest run --project server --config ../ai_evals/adapters/frontend/vitest.unit.config.ts"
|
|
},
|
|
"dependencies": {
|
|
"@anthropic-ai/claude-agent-sdk": "^0.3.284",
|
|
"@anthropic-ai/sdk": "^0.129.0",
|
|
"commander": "^14.0.3",
|
|
"openai": "^6.9.1",
|
|
"yaml": "^2.8.3"
|
|
},
|
|
"devDependencies": {
|
|
"@types/bun": "latest",
|
|
"typescript": "^5.0.0"
|
|
}
|
|
}
|