Files
supabase/turbo.json
T
072883bcec feat: assistant evals (#41311)
* chore: bump `supabase` CLI

* chore: stricter message types in `generate-v4.ts`

* feat: tutorial eval

https://www.braintrust.dev/docs/evaluation

* feat: project ID for eval

* refactor: `generateAssistantResponse` out of `handlePost`

* refactor: generateAssistantResponse to lib/ai

* feat: factuality eval with assistant response

* chore: upgrade braintrust to v1.0.1

* chore: silence tsconfig warning

* feat: assertion scorer

* fix: aggregate tools across all steps

* refactor: strict tool names, remove need for `as const`

* refactor: generic tool name type in assertions

* feat: transfer mocks from `feature/braintrust`

* feat: LLM criteria assertion

* feat: braintrust evals workflow

* fix: BRAINTRUST_PROJECT_ID

* feat: `sql_similar` assertion

* fix: `OPENAI_API_KEY` in workflow env

* feat: split AssertionScorer into separate scorers

* feat: remove tutorial eval

* feat: 20 minute CI timeout

* feat: category in test case metadata

* feat: score with gpt-5

* refactor: dataset to own file, colocate scorers

* feat: "gpt-5.2-2025-12-11" for llm as a judge

* feat: SQL syntax scorer with `libpg-query`

* feat: `evals:setup` and `evals:run` scripts

* feat: `evals:setup` in CI

* feat: human readable scorer names

* chore: rename to "SQL Validity"

* feat: add 2 "sql_generation" test cases

* feat: update requiredTools in test cases

* chore: ignore Cursor MCP config

* feat: "Conciseness" score

* feat: "Completeness" scorer

* fix: generate-v4 test mocks

* feat: serialize "steps" for scorer inputs

* updated node mem options for typecheck

* updated runner

* remove ram update as actions handle this

* feat: read `BRAINTRUST_PROJECT_ID` from secrets

* feat: score helpfulness, remove old scorers

* feat: separate `evals:run` and `evals:upload` scripts

* feat: passthrough entire classifier result

* feat: use live `search_docs` impl, store docs result in metadata

* feat: reduce classifier options

* feat: filter workflow by `run-evals` PR label or `master` branch

* chore: cleanup stubbed mock tools

* fix: checkout actual branch with `ref:`

* fix: capture search_docs results from all content parts

* feat: simplify sql syntax score calculation

* feat: use AI SDK's UI message validator

* docs: justification for relative `extends`

* fix: cleanup leftover validatedMessages

* doc: note mock token isn't secret for snyk

* fix: mock ui message to pass validation

* feat: revert ignoring Cursor MCP config

Using `.git/info/exclude` instead until we have an opinion on this

* feat: add "tsconfig" as shared-data devDependency, revert relative path in tsconfig

* refactor: tool call parsing into function

* Update apps/studio/evals/assistant.eval.ts

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

* refactor: organize mock schemas and tool factories

---------

Co-authored-by: Ali Waseem <waseema393@gmail.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
2025-12-22 23:45:48 -05:00

255 lines
7.9 KiB
JSON

{
"$schema": "https://turbo.build/schema.json",
"ui": "stream",
"tasks": {
"build": {
"dependsOn": ["^build"],
"outputs": ["dist/**", ".next/**"]
},
"cms#build": {
"dependsOn": ["^build"],
"env": [
"BLOG_APP_URL",
"CRON_SECRET",
"DATABASE_URI",
"NEXT_PUBLIC_VERCEL_BRANCH_URL",
"NEXT_PUBLIC_SERVER_URL",
"NEXT_PUBLIC_VERCEL_ENV",
"NODE_ENV",
"PAYLOAD_SECRET",
"PREVIEW_SECRET",
"S3_BUCKET",
"S3_ACCESS_KEY_ID",
"S3_SECRET_ACCESS_KEY",
"S3_REGION",
"S3_ENDPOINT",
"VERCEL_PROJECT_PRODUCTION_URL"
],
"outputs": [".next/**", "!.next/cache/**"]
},
"design-system#build": {
"dependsOn": ["^build"],
"env": [
"NEXT_PUBLIC_BASE_PATH",
"NEXT_PUBLIC_APP_URL",
// These envs are used in the packages
"NEXT_PUBLIC_STORAGE_KEY",
"NEXT_PUBLIC_AUTH_DEBUG_KEY",
"NEXT_PUBLIC_AUTH_PERSISTED_KEY",
"NEXT_PUBLIC_AUTH_NAVIGATOR_LOCK_KEY",
"NEXT_PUBLIC_AUTH_DETECT_SESSION_IN_URL",
"NEXT_PUBLIC_GOTRUE_URL",
"NEXT_PUBLIC_SUPABASE_ANON_KEY"
],
"outputs": [".next/**", "!.next/cache/**", ".contentlayer/**"]
},
"studio#build": {
"dependsOn": ["^build"],
"env": [
"ANALYZE",
"NEXT_PUBLIC_SUPPORT_API_URL",
"NEXT_PUBLIC_CONTENT_API_URL",
"NEXT_PUBLIC_BASE_PATH",
"NEXT_PUBLIC_STRIPE_PUBLIC_KEY",
"NEXT_PUBLIC_SUPPORT_ANON_KEY",
"NEXT_PUBLIC_ENVIRONMENT",
"NEXT_PUBLIC_IS_PLATFORM",
"NEXT_PUBLIC_SITE_URL",
"NEXT_PUBLIC_API_URL",
"NEXT_PUBLIC_DOCS_URL",
"NEXT_PUBLIC_CONFIGCAT_SDK_KEY",
"NEXT_PUBLIC_CONFIGCAT_PROXY_URL",
"NEXT_PUBLIC_HCAPTCHA_SITE_KEY",
"NEXT_PUBLIC_SUPABASE_URL",
"NEXT_PUBLIC_SUPABASE_ANON_KEY",
"NEXT_PUBLIC_NODE_ENV",
"NEXT_PUBLIC_GOTRUE_URL",
"NEXT_PUBLIC_VERCEL_BRANCH_URL",
"NEXT_PUBLIC_GOOGLE_MAPS_KEY",
"NEXT_RUNTIME",
"NIMBUS_PROD_PROJECTS_URL",
"NIMBUS_PROD_PROJECTS_URL_WS",
"NODE_ENV",
"SUPABASE_URL",
"VERCEL",
"VERCEL_ENV",
"MAINTENANCE_MODE",
// These envs are used in the packages
"NEXT_PUBLIC_STORAGE_KEY",
"NEXT_PUBLIC_AUTH_DEBUG_KEY",
"NEXT_PUBLIC_AUTH_PERSISTED_KEY",
"NEXT_PUBLIC_AUTH_NAVIGATOR_LOCK_KEY",
"NEXT_PUBLIC_AUTH_DETECT_SESSION_IN_URL",
"NEXT_PUBLIC_GOOGLE_TAG_MANAGER_ID",
"NEXT_PUBLIC_VERCEL_ENV",
"NEXT_PUBLIC_USERCENTRICS_RULESET_ID",
"NEXT_PUBLIC_MCP_URL",
"NEXT_PUBLIC_IS_NIMBUS",
"NEXT_PUBLIC_ONGOING_INCIDENT",
// These envs are technically passthrough env vars because they're only used on the server side of Nextjs
"PLATFORM_PG_META_URL",
"STUDIO_PG_META_URL",
"PG_META_CRYPTO_KEY",
"POSTGRES_PASSWORD",
"POSTGRES_HOST",
"POSTGRES_USER_READ_WRITE",
"POSTGRES_USER_READ_ONLY",
"POSTGRES_DB",
"POSTGRES_PORT",
"READ_ONLY_URL",
"READ_ONLY_API_KEY",
"SUPABASE_SERVICE_KEY",
"SUPABASE_ANON_KEY",
"SUPABASE_PUBLIC_URL",
"DEFAULT_PROJECT_NAME",
"DEFAULT_ORGANIZATION_NAME",
"OPENAI_API_KEY",
"BRAINTRUST_API_KEY",
"BRAINTRUST_PROJECT_ID",
"AUTH_JWT_SECRET",
"LOGFLARE_API_KEY",
"LOGFLARE_PUBLIC_ACCESS_TOKEN",
"LOGFLARE_PRIVATE_ACCESS_TOKEN",
"LOGFLARE_URL",
"SENTRY_ORG",
"SENTRY_PROJECT",
"SENTRY_AUTH_TOKEN",
"NEXT_PUBLIC_SENTRY_DSN",
"AWS_BEDROCK_PROFILE",
"AWS_BEDROCK_ROLE_ARN",
"AWS_ACCESS_KEY_ID",
"AWS_SECRET_ACCESS_KEY",
"FORCE_ASSET_CDN",
"ASSET_CDN_S3_ENDPOINT",
"SITE_NAME",
"VERCEL_URL",
"IS_THROTTLED",
"AI_PRO_MODEL",
"AI_NORMAL_MODEL",
"SUPPORT_SUPABASE_SECRET_KEY",
"STATUSPAGE_API_KEY",
"STATUSPAGE_PAGE_ID"
],
"passThroughEnv": ["CURRENT_CLI_VERSION", "VERCEL_GIT_COMMIT_SHA"],
"outputs": [".next/**", "!.next/cache/**"]
},
"www#build": {
"dependsOn": ["^build"],
"env": [
"ANALYZE",
"CI",
"CF_ACCESS_CLIENT_ID",
"CF_ACCESS_CLIENT_SECRET",
"CMS_API_KEY",
"CMS_PREVIEW_SECRET",
"CMS_SITE_ORIGIN",
"NEXT_PUBLIC_MISC_USE_URL",
"NEXT_PUBLIC_MISC_USE_ANON_KEY",
"NEXT_PUBLIC_STUDIO_URL",
"NEXT_PUBLIC_DOCS_URL",
"NEXT_PUBLIC_REFERENCE_DOCS_URL",
"NEXT_PUBLIC_UI_LIBRARY_URL",
"NEXT_PUBLIC_SUPABASE_URL",
"NEXT_PUBLIC_SUPABASE_ANON_KEY",
"NEXT_PUBLIC_VERCEL_ENV",
"NEXT_PUBLIC_VERCEL_BRANCH_URL",
"NEXT_PUBLIC_API_URL",
"NEXT_PUBLIC_HCAPTCHA_SITE_KEY",
"HCAPTCHA_SECRET_KEY",
"NODE_ENV",
"NEXT_PUBLIC_SENTRY_DSN",
"NEXT_PUBLIC_SURVEY_SUPABASE_URL",
"NEXT_PUBLIC_SURVEY_SUPABASE_ANON_KEY",
"VERCEL",
"VERCEL_ENV",
"VERCEL_GIT_COMMIT_SHA",
// These envs are used in the packages
"NEXT_PUBLIC_STORAGE_KEY",
"NEXT_PUBLIC_AUTH_DEBUG_KEY",
"NEXT_PUBLIC_AUTH_PERSISTED_KEY",
"NEXT_PUBLIC_AUTH_NAVIGATOR_LOCK_KEY",
"NEXT_PUBLIC_GOOGLE_TAG_MANAGER_ID",
"NEXT_PUBLIC_IS_PLATFORM",
"NEXT_PUBLIC_AUTH_DETECT_SESSION_IN_URL",
"NEXT_PUBLIC_GOTRUE_URL",
"NEXT_PUBLIC_BASE_PATH",
"NEXT_PUBLIC_EXAMPLES_SUPABASE_ANON_KEY",
"NEXT_PUBLIC_EXAMPLES_SUPABASE_URL",
"NEXT_PUBLIC_USERCENTRICS_RULESET_ID",
// These envs are technically passthrough env vars because they're only used on the server side of Nextjs
"LIVE_SUPABASE_COM_SERVICE_ROLE_KEY",
"GITHUB_CHANGELOG_APP_ID",
"GITHUB_CHANGELOG_APP_INSTALLATION_ID",
"GITHUB_CHANGELOG_APP_REST_KEY",
"GITHUB_CHANGELOG_APP_PRIVATE_KEY",
"NEXT_PUBLIC_EMAIL_ABUSE_URL",
"EMAIL_ABUSE_SERVICE_KEY",
"HUBSPOT_PORTAL_ID",
"HUBSPOT_ENTERPRISE_FORM_GUID",
"HUBSPOT_PARTNERSHIP_FORM_GUID",
"OPENAI_API_KEY",
"EMAIL_REPORT_SLACK_WEBHOOK",
"npm_lifecycle_event",
"AWS_ACCESS_KEY_ID",
"AWS_SECRET_ACCESS_KEY",
"FORCE_ASSET_CDN",
"ASSET_CDN_S3_ENDPOINT",
"SITE_NAME",
"LUMA_API_KEY",
"NEXT_RUNTIME",
// These env vars are used by some community and marketing integrations
"SENTRY_DSN_COMMUNITY",
"NOTION_SUPASQUAD_API_KEY",
"NOTION_SUPASQUAD_APPLICATIONS_DB_ID",
"NEXT_PUBLIC_SUPASQUAD_APPLICATION_FORM_URL",
"CUSTOMERIO_SITE_ID",
"CUSTOMERIO_API_KEY",
"CUSTOMERIO_APP_API_KEY"
],
"outputs": [".next/**", "!.next/cache/**", ".contentlayer/**"]
},
"ui-library#build": {
"dependsOn": ["^build"],
"env": [
"NEXT_PUBLIC_BASE_PATH",
"NEXT_PUBLIC_APP_URL",
"NEXT_PUBLIC_VERCEL_TARGET_ENV",
"NEXT_PUBLIC_VERCEL_BRANCH_URL",
"NEXT_PUBLIC_API_URL",
"NODE_ENV",
"HIDE_TAILWIND_INDICATOR",
// These envs are used in the packages
"NEXT_PUBLIC_STORAGE_KEY",
"NEXT_PUBLIC_AUTH_DEBUG_KEY",
"NEXT_PUBLIC_AUTH_PERSISTED_KEY",
"NEXT_PUBLIC_AUTH_NAVIGATOR_LOCK_KEY",
"NEXT_PUBLIC_AUTH_DETECT_SESSION_IN_URL",
"NEXT_PUBLIC_GOOGLE_TAG_MANAGER_ID",
"NEXT_PUBLIC_GOTRUE_URL",
"NEXT_PUBLIC_SUPABASE_ANON_KEY",
"NEXT_PUBLIC_USERCENTRICS_RULESET_ID",
"SUPABASE_MANAGEMENT_API_TOKEN",
"OPENAI_API_KEY"
],
"outputs": [".next/**", "!.next/cache/**", ".contentlayer/**"]
},
"lint": {
"outputs": []
},
"clean": {
"outputs": [],
"cache": false
},
"dev": {
"cache": false
},
"test": {
"cache": false
},
"typecheck": {
"dependsOn": ["^typecheck"],
"outputs": []
}
}
}