mirror of
https://github.com/supabase/supabase.git
synced 2026-10-11 04:15:04 +03:00
Greg Richardson
5f8906a20e
Prevents the AI assistant from helping with local git/filesystem operations, and adds explicit warnings before irreversible database operations (DROP TABLE, DELETE without WHERE, etc.). Adds a `safetyScorer` and eval cases to cover these behaviours. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Added a Safety metric to evaluations so assistant responses are scored for safe handling of destructive or risky requests * Assistant guidance updated to refuse destructive local VCS/filesystem actions and require clear warnings for irreversible database operations * **Tests** * Added evaluation cases covering safe refusals, clear warnings, and correct handling of destructive or risky prompts * **Chores** * Enabled Safety metric in online evaluation manifests/handlers <!-- end of auto-generated comment: release notes by coderabbit.ai -->
65 lines
2.4 KiB
TypeScript
65 lines
2.4 KiB
TypeScript
/**
|
|
* Entry point for `braintrust push` to deploy scorers to Braintrust.
|
|
*
|
|
* Excluded scorers:
|
|
* - sqlSyntaxScorer, sqlIdentifierQuotingScorer: use libpg-query (WASM),
|
|
* which esbuild cannot bundle for Braintrust's remote infra.
|
|
* - toolUsageScorer: requires expected.requiredTools, offline-eval-only.
|
|
* - correctnessScorer: requires ground truth (expected output), offline-eval-only.
|
|
*/
|
|
|
|
import braintrust, { type EvalScorer } from 'braintrust'
|
|
|
|
import {
|
|
completenessScorer,
|
|
concisenessScorer,
|
|
docsFaithfulnessScorer,
|
|
goalCompletionScorer,
|
|
safetyScorer,
|
|
urlValidityScorer,
|
|
type AssistantEvalInput,
|
|
type AssistantEvalOutput,
|
|
type Expected,
|
|
} from './scorer'
|
|
import manifest from './scorer-online-manifest.json'
|
|
|
|
const projectId = process.env.BRAINTRUST_PROJECT_ID
|
|
if (!projectId && process.env.IS_BRAINTRUST_PUSH)
|
|
throw new Error('BRAINTRUST_PROJECT_ID is not set')
|
|
|
|
// When running in CI, prefix scorers with the branch name to avoid collisions between PRs
|
|
// in the staging project. GITHUB_HEAD_REF is only set on PR events, not push events (e.g. master).
|
|
const branch = process.env.GITHUB_HEAD_REF || process.env.GITHUB_REF_NAME
|
|
const prNumber = process.env.GITHUB_PR_NUMBER ? Number(process.env.GITHUB_PR_NUMBER) : undefined
|
|
const prefix = process.env.GITHUB_HEAD_REF
|
|
? `${process.env.GITHUB_HEAD_REF.replace(/[^a-z0-9-]/gi, '-').toLowerCase()}-`
|
|
: ''
|
|
const metadata = branch ? { gitBranch: branch, ...(prNumber && { prNumber }) } : undefined
|
|
const description = prNumber && branch ? `#${prNumber} · ${branch}` : branch
|
|
|
|
const handlers = {
|
|
'goal-completion': goalCompletionScorer,
|
|
conciseness: concisenessScorer,
|
|
completeness: completenessScorer,
|
|
'docs-faithfulness': docsFaithfulnessScorer,
|
|
'url-validity': urlValidityScorer,
|
|
// safetyScorer guards on requiresSafetyCheck (an offline-eval concept).
|
|
// Online traces have no expected, so we wrap it to always run.
|
|
safety: (args) =>
|
|
safetyScorer({ ...args, expected: { ...args.expected, requiresSafetyCheck: true } }),
|
|
} satisfies Record<string, EvalScorer<AssistantEvalInput, AssistantEvalOutput, Expected>>
|
|
|
|
// @ts-expect-error - Project ID is only required at build-time
|
|
const project = braintrust.projects.create({ id: projectId })
|
|
|
|
for (const { slug, name } of manifest) {
|
|
project.scorers.create({
|
|
slug: `${prefix}${slug}`,
|
|
name,
|
|
description,
|
|
handler: handlers[slug as keyof typeof handlers],
|
|
ifExists: 'replace',
|
|
metadata,
|
|
})
|
|
}
|