mirror of
https://github.com/supabase/supabase.git
synced 2026-10-10 03:45:06 +03:00
## Motivation When Assistant runs a potentially destructive tool like `execute_sql`, it stops the LLM request and prompts for client-side approval and execution of the tool. After approval, a second request kicks off under a separate trace. This has made scoring and [Topics](https://www.braintrust.dev/blog/topics) classification challenging, as the generated `output` is split across stateless requests. The [span-level scoring](https://www.braintrust.dev/docs/evaluate/custom-code#score-spans) approach we've used thusfar (after the LLM call, we massage the result into an `output` payload that's stuck onto the root span) has been cumbersome and led to invalid scores / topics where only part of the assistant response is considered. It's also inefficient, as we're duplicating potentially large info (like the `search_docs` output) that already exists within the trace. An alternative to scoring spans is to [score traces](https://www.braintrust.dev/docs/evaluate/custom-code#score-traces). Braintrust [best practices](https://www.braintrust.dev/docs/evaluate/score-online#best-practices) advise: > Use span scope for evaluating individual operations or outputs. Use trace scope for evaluating multi-turn conversations, overall workflow completion, or when your scorer needs access to the full execution context. We've also received [direct guidance](https://supabase.slack.com/archives/C05QYJBLX89/p1777925770927149?thread_ts=1777905716.911979&cid=C05QYJBLX89) from their team to use this approach. ## Changes Migrates eval scorers from custom `AssistantEvalOutput` shape to trace-level scoring via `trace.getThread()` / `trace.getSpans()`, with thread parsing that scores the full latest Assistant turn and passes prior conversation separately where relevant. Moves `execute_sql` and `deploy_edge_function` from client-side execution after approval to AI SDK `needsApproval` + server-side `execute()`. SQL results returned to the model are gated by AI opt-in level, so row data is only included with `schema_and_log_and_data`; otherwise the tool returns the no-data-permissions sentinel. Adds `metadata.isFinalStep` to disambiguate multiple LLM requests within an "assistant" turn due to tool call requests/responses. For online evals, this means we should configure automations to only score traces with `metadata.isFinalStep = true` to ensure we're judging the complete generated response. Other minor kaizen changes: - Renamed `promptProviderOptions` to `systemProviderOptions` to clarify that this is associated with the "system" message and disambiguate from the root `providerOptions` - Adds `evals/trace-utils.ts` to handle Zod validation of the `unknown` span shapes from Braintrust, to more easily access typed inputs/output on tool spans. - Bumps AI SDK floor version `^6.0.116` → `^6.0.174` - Tweaked the "Conciseness" scorer to not unfairly dock points for the new `[called tool_name]` labels in serialized assistant response ## Verification In the studio staging build, I asked Assistant to create a todos table with 3 sample todos. I manually approved the `execute_sql` call and saw Assistant generate text before & after the call. In Braintrust I verified two traces were produced (see [filtered logs](https://www.braintrust.dev/app/supabase.io/p/Assistant/logs?v=Staging&tvt=trace&search={%22filter%22:[{%22text%22:%22metadata.environment%2520%253D%2520%27staging%27%22,%22label%22:%22metadata.environment%2520%253D%2520%27staging%27%22,%22originType%22:%22btql%22},{%22text%22:%22%2560Chat%2520ID%2560%2520%253D%2520%25221cb2ac45-e5e7-458c-9da4-3bf6863b8842%2522%22,%22label%22:%22Chat%2520ID%2520equals%25201cb2ac45-e5e7-458c-9da4-3bf6863b8842%22,%22originType%22:%22form%22}]})), the first with `metadata.isFinalStep = false` and the second with `metadata.isFinalStep = true`. In the Braintrust staging scorers, I ran the preview Completeness scorer on the second trace and verified it sees the complete Assistant response including markers for tool calls ([link to trace](https://www.braintrust.dev/app/supabase.io/p/Assistant%20(Staging%20Scorers)/trace?object_type=project_logs&object_id=b5214b62-ad1e-4929-9d5b-40b1daebe948&r=0ed0a4f8-8aff-4a34-bb1d-1df1d88a5070&s=ff9015f8-6bf7-4ab3-83a9-ca4e69e27e82)) <img width="1193" height="960" alt="CleanShot 2026-05-07 at 11 27 10@2x" src="https://github.com/user-attachments/assets/509d4858-c3a1-4068-986d-3aa4d5617d1a" /> I also tested the `deploy_edge_function` workflow and verified it still prompts for permission and warns on deployment of existing functions. **References** - https://www.braintrust.dev/docs/evaluate/custom-code#score-traces - https://ai-sdk.dev/docs/ai-sdk-core/tools-and-tool-calling#tool-execution-approval Supercedes https://github.com/supabase/supabase/pull/45556 and https://github.com/supabase/supabase/pull/45339 Closes AI-473 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Tool actions (SQL execution, edge-function deploy) now require explicit user Approve/Deny before proceeding. * **Improvements** * Assistant pauses for approval responses before sending follow-ups, giving clearer control over risky actions. * Deploy/replace flows show confirmation and clearer replace warnings. * Evaluation/scoring updated to use richer trace data for more accurate assistant performance signals. <!-- end of auto-generated comment: release notes by coderabbit.ai -->
137 lines
3.9 KiB
TypeScript
137 lines
3.9 KiB
TypeScript
import { screen } from '@testing-library/react'
|
|
import userEvent from '@testing-library/user-event'
|
|
import { beforeEach, describe, expect, it, vi } from 'vitest'
|
|
|
|
import { EdgeFunctionRenderer } from './EdgeFunctionRenderer'
|
|
import { render } from '@/tests/helpers'
|
|
|
|
const {
|
|
mockSendEvent,
|
|
mockUseEdgeFunctionQuery,
|
|
mockUseParams,
|
|
mockUseProjectSettingsV2Query,
|
|
mockUseSelectedOrganizationQuery,
|
|
} = vi.hoisted(() => ({
|
|
mockSendEvent: vi.fn(),
|
|
mockUseEdgeFunctionQuery: vi.fn(),
|
|
mockUseParams: vi.fn(),
|
|
mockUseProjectSettingsV2Query: vi.fn(),
|
|
mockUseSelectedOrganizationQuery: vi.fn(),
|
|
}))
|
|
|
|
vi.mock('common', async () => {
|
|
const actual = await vi.importActual<typeof import('common')>('common')
|
|
|
|
return {
|
|
...actual,
|
|
useParams: mockUseParams,
|
|
}
|
|
})
|
|
|
|
vi.mock('@/data/config/project-settings-v2-query', () => ({
|
|
useProjectSettingsV2Query: mockUseProjectSettingsV2Query,
|
|
}))
|
|
|
|
vi.mock('@/data/edge-functions/edge-function-query', () => ({
|
|
useEdgeFunctionQuery: mockUseEdgeFunctionQuery,
|
|
}))
|
|
|
|
vi.mock('@/data/telemetry/send-event-mutation', () => ({
|
|
useSendEventMutation: () => ({ mutate: mockSendEvent }),
|
|
}))
|
|
|
|
vi.mock('@/hooks/misc/useSelectedOrganization', () => ({
|
|
useSelectedOrganizationQuery: mockUseSelectedOrganizationQuery,
|
|
}))
|
|
|
|
vi.mock('../EdgeFunctionBlock/EdgeFunctionBlock', () => ({
|
|
EdgeFunctionBlock: ({
|
|
showReplaceWarning,
|
|
onCancelReplace,
|
|
onConfirmReplace,
|
|
}: {
|
|
showReplaceWarning?: boolean
|
|
onCancelReplace?: () => void
|
|
onConfirmReplace?: () => void
|
|
}) => (
|
|
<div>
|
|
{showReplaceWarning && (
|
|
<div>
|
|
<p>An edge function with this name already exists.</p>
|
|
<button onClick={onCancelReplace}>Cancel</button>
|
|
<button onClick={onConfirmReplace}>Replace function</button>
|
|
</div>
|
|
)}
|
|
</div>
|
|
),
|
|
}))
|
|
|
|
vi.mock('./ConfirmFooter', () => ({
|
|
ConfirmFooter: ({
|
|
confirmLabel,
|
|
onConfirm,
|
|
}: {
|
|
confirmLabel?: string
|
|
onConfirm?: () => void
|
|
}) => <button onClick={onConfirm}>{confirmLabel ?? 'Confirm'}</button>,
|
|
}))
|
|
|
|
describe('EdgeFunctionRenderer', () => {
|
|
beforeEach(() => {
|
|
mockSendEvent.mockReset()
|
|
mockUseEdgeFunctionQuery.mockReset()
|
|
mockUseParams.mockReturnValue({ ref: 'project-ref' })
|
|
mockUseProjectSettingsV2Query.mockReturnValue({ data: undefined })
|
|
mockUseSelectedOrganizationQuery.mockReturnValue({ data: { slug: 'org-slug' } })
|
|
})
|
|
|
|
it('only deploys an existing function from the replace warning confirmation', async () => {
|
|
const user = userEvent.setup()
|
|
const onApprove = vi.fn()
|
|
|
|
mockUseEdgeFunctionQuery.mockReturnValue({ data: { slug: 'hello-world' } })
|
|
|
|
render(
|
|
<EdgeFunctionRenderer
|
|
label="Deploy Edge Function"
|
|
code="Deno.serve(() => new Response('ok'))"
|
|
functionName="hello-world"
|
|
onApprove={onApprove}
|
|
/>
|
|
)
|
|
|
|
await user.click(screen.getByRole('button', { name: 'Deploy' }))
|
|
expect(screen.getByText('An edge function with this name already exists.')).toBeInTheDocument()
|
|
expect(onApprove).not.toHaveBeenCalled()
|
|
|
|
await user.click(screen.getByRole('button', { name: 'Deploy' }))
|
|
expect(onApprove).not.toHaveBeenCalled()
|
|
expect(mockSendEvent).not.toHaveBeenCalled()
|
|
|
|
await user.click(screen.getByRole('button', { name: 'Replace function' }))
|
|
expect(onApprove).toHaveBeenCalledTimes(1)
|
|
expect(mockSendEvent).toHaveBeenCalledTimes(1)
|
|
})
|
|
|
|
it('deploys immediately when no existing function is found', async () => {
|
|
const user = userEvent.setup()
|
|
const onApprove = vi.fn()
|
|
|
|
mockUseEdgeFunctionQuery.mockReturnValue({ data: undefined })
|
|
|
|
render(
|
|
<EdgeFunctionRenderer
|
|
label="Deploy Edge Function"
|
|
code="Deno.serve(() => new Response('ok'))"
|
|
functionName="hello-world"
|
|
onApprove={onApprove}
|
|
/>
|
|
)
|
|
|
|
await user.click(screen.getByRole('button', { name: 'Deploy' }))
|
|
|
|
expect(onApprove).toHaveBeenCalledTimes(1)
|
|
expect(mockSendEvent).toHaveBeenCalledTimes(1)
|
|
})
|
|
})
|