mirror of
https://github.com/supabase/supabase.git
synced 2026-10-10 20:05:06 +03:00
Lays groundwork for online evals on Assistant chat logs. https://www.braintrust.dev/docs/observe/score-online ### Changes - New workflows: - `braintrust-scorers-deploy.yml` keeps prod scorers in sync on push to `master` - `braintrust-preview-scorers-deploy.yml` deploys preview scorers to the staging project for PRs labeled `preview-scorers`, posting a comment with scorer links ([example](https://github.com/supabase/supabase/pull/43194#issuecomment-4000097222)) - `braintrust-preview-scorers-cleanup.yml` deletes preview scorers when the PR is closed ([example](https://github.com/supabase/supabase/pull/43194#issuecomment-4000749847)) - Adds `evals/scorer-online.ts` entry point invoked with `pnpm scorers:deploy`, registering scorers for online evals in the Braintrust "Assistant" project - Refactors scorer code to separate online-compatible scorers (`scorer-online.ts`) from WASM-dependent ones (`scorer-wasm.ts`) - "URL Validity" scorer now only checks Supabase domains to prevent requests to untrusted origins - Span `input` is now shaped `{ prompt: string }` instead of plain `string` for compatibility with offline eval scorers - Env vars `BRAINTRUST_STAGING_PROJECT_ID` and `BRAINTRUST_PROJECT_ID` configured in GitHub repo settings - `generateAssistantResponse` now uses `startSpan` + `withCurrent` instead of `traced()` to manually manage the root span lifecycle — this ensures `onFinish` logs output to the span _before_ `span.end()` is called, which is when Braintrust triggers scoring automations ### Online Scorers We share scoring logic across offline and online evals, but some of our scorers aren't transferrable to an "online" setting due to runtime challenges or ground truth requirements. **Supported** - Goal Completion - Conciseness - Completeness - Docs Faithfulness - URL Validity **Unsupported** - Correctness (requires ground truth output) - Tool Usage (requires ground truth requiredTools) - SQL Syntax (uses libpg-query WASM) - SQL Identifier Quoting (uses libpg-query WASM) ### How to use these scorers Going forward if you want to add/edit online eval scorers, add the `preview-scorers` label to a PR. This deploys scorers to the [Assistant (Staging Scorers)](https://www.braintrust.dev/app/supabase.io/p/Assistant%20(Staging%20Scorers)?v=Overview) project in Braintrust with branch-specific slugs, and comments on the PR ([example](https://github.com/supabase/supabase/pull/43194#issuecomment-4000097222)). From the Braintrust dashboard you can "Test" the scorer with traces from any project. <img width="1866" height="528" alt="CleanShot 2026-03-05 at 15 15 00@2x" src="https://github.com/user-attachments/assets/4f15cebc-3f2d-4e8a-9ee2-fe8ef7bf4199" /> Once merged, scorers are deployed to the primary [Assistant](https://www.braintrust.dev/app/supabase.io/p/Assistant) project, and preview scorers are deleted from the staging project. Down the road, scorers on the Assistant project will run automatically on a sample of production traces. Closes AI-437
124 lines
4.3 KiB
YAML
124 lines
4.3 KiB
YAML
name: Deploy Braintrust preview scorers
|
|
|
|
on:
|
|
pull_request:
|
|
types: [labeled, synchronize]
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
|
|
cancel-in-progress: true
|
|
|
|
permissions:
|
|
pull-requests: write
|
|
contents: read
|
|
|
|
jobs:
|
|
push-scorers:
|
|
name: Push preview scorers
|
|
if: contains(github.event.pull_request.labels.*.name, 'preview-scorers') && github.event.pull_request.head.repo.full_name == github.repository
|
|
runs-on: ubuntu-latest
|
|
timeout-minutes: 10
|
|
|
|
steps:
|
|
- name: Checkout
|
|
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
|
|
with:
|
|
fetch-depth: 0
|
|
ref: ${{ github.head_ref || github.ref_name }}
|
|
|
|
- name: Check for scorer file changes
|
|
id: changed
|
|
# On labeled events, always push. On synchronize, only push if scorer files changed.
|
|
run: |
|
|
if [[ "${{ github.event.action }}" == "synchronize" ]]; then
|
|
changed=$(git diff --name-only origin/${{ github.event.pull_request.base.ref }}...HEAD | grep -E 'evals/scorer' || true)
|
|
if [ -z "$changed" ]; then
|
|
echo "No scorer files changed, skipping push"
|
|
echo "skip=true" >> $GITHUB_OUTPUT
|
|
else
|
|
echo "skip=false" >> $GITHUB_OUTPUT
|
|
fi
|
|
else
|
|
echo "skip=false" >> $GITHUB_OUTPUT
|
|
fi
|
|
|
|
- name: Install pnpm
|
|
if: steps.changed.outputs.skip != 'true'
|
|
uses: pnpm/action-setup@41ff72655975bd51cab0327fa583b6e92b6d3061 # v4.2.0
|
|
with:
|
|
run_install: false
|
|
|
|
- name: Use Node.js
|
|
if: steps.changed.outputs.skip != 'true'
|
|
uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
|
|
with:
|
|
node-version-file: ".nvmrc"
|
|
cache: "pnpm"
|
|
|
|
- name: Install Dependencies
|
|
if: steps.changed.outputs.skip != 'true'
|
|
run: pnpm install --frozen-lockfile
|
|
|
|
- name: Push scorers to staging
|
|
if: steps.changed.outputs.skip != 'true'
|
|
id: push
|
|
run: |
|
|
cd apps/studio && pnpm scorers:deploy
|
|
slugs=$(jq -r '[.[].slug] | join(",")' evals/scorer-online-manifest.json)
|
|
echo "slugs=$slugs" >> $GITHUB_OUTPUT
|
|
env:
|
|
BRAINTRUST_API_KEY: ${{ secrets.BRAINTRUST_API_KEY }}
|
|
BRAINTRUST_PROJECT_ID: ${{ secrets.BRAINTRUST_STAGING_PROJECT_ID }}
|
|
GITHUB_PR_NUMBER: ${{ github.event.pull_request.number }}
|
|
|
|
- name: Post PR comment
|
|
if: steps.changed.outputs.skip != 'true'
|
|
uses: actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b # v7.1.0
|
|
env:
|
|
BRAINTRUST_STAGING_PROJECT_ID: ${{ secrets.BRAINTRUST_STAGING_PROJECT_ID }}
|
|
SCORER_SLUGS: ${{ steps.push.outputs.slugs }}
|
|
with:
|
|
script: |
|
|
const prNumber = context.payload.pull_request.number
|
|
const branch = process.env.GITHUB_HEAD_REF
|
|
const prefix = branch.replace(/[^a-z0-9-]/gi, '-').toLowerCase()
|
|
const stagingUrl = 'https://www.braintrust.dev/app/supabase.io/p/Assistant%20(Staging%20Scorers)/scorers'
|
|
|
|
const slugs = process.env.SCORER_SLUGS.split(',')
|
|
const slugList = slugs.map(s => `- \`${prefix}-${s}\``).join('\n')
|
|
|
|
const sha = context.sha.slice(0, 7)
|
|
const marker = '<!-- preview-scorers-bot -->'
|
|
const body = `${marker}
|
|
### Braintrust Preview Scorers
|
|
|
|
Deployed scorers to [Assistant (Staging Scorers)](${stagingUrl}):
|
|
|
|
${slugList}
|
|
|
|
Commit: ${sha}`
|
|
|
|
const { data: comments } = await github.rest.issues.listComments({
|
|
owner: context.repo.owner,
|
|
repo: context.repo.repo,
|
|
issue_number: prNumber,
|
|
})
|
|
|
|
const existing = comments.find(c => c.body?.includes(marker))
|
|
|
|
if (existing) {
|
|
await github.rest.issues.updateComment({
|
|
owner: context.repo.owner,
|
|
repo: context.repo.repo,
|
|
comment_id: existing.id,
|
|
body,
|
|
})
|
|
} else {
|
|
await github.rest.issues.createComment({
|
|
owner: context.repo.owner,
|
|
repo: context.repo.repo,
|
|
issue_number: prNumber,
|
|
body,
|
|
})
|
|
}
|