Files
supabase/apps/studio/pages/api/ai/sql/generate-v4.ts
Saxon Fletcher 9b17ce8f2c chore(studio): default assistant to GPT-5.6 Luna (#49749)
## I have read the
[CONTRIBUTING.md](https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md)
file.

YES

## What kind of change does this PR introduce?

Feature / chore: hide assistant model selection in the UI and default
chats to GPT-5.6 Luna.

## What is the current behavior?

The assistant composer exposes a model picker. Paid orgs default to
`gpt-5.3-codex`; everyone else defaults to `gpt-5.4-nano`.

## What is the new behavior?

- The model picker is hidden in the assistant composer and Explorer
home.
- Chats default to `gpt-5.6-luna` with `reasoningEffort: medium`.
- Model selection plumbing is kept (registry, entitlements, `setModel`,
generate-v4 request body) so a requested model can still be honored when
provided.
- Other completion endpoints still use `gpt-5.4-nano`.

## Additional context

Model selector UI can be re-enabled by passing `selectedModel` /
`onSelectModel` to `AssistantChatForm`.


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

* **New Features**
* Added support for the GPT-5.6 Luna model with medium reasoning
capability.
  * Made GPT-5.6 Luna the default assistant model.
* **Improvements**
* Simplified assistant chat by removing model selection from the primary
chat experience.
  * Updated model fallback behavior to use the standard assistant model.
* Chat forms can now optionally display model selection when configured.
* **Tests**
* Updated model coverage and assistant chat tests for the new defaults
and behavior.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-02 10:24:37 +10:00

288 lines
8.4 KiB
TypeScript

import pgMeta from '@supabase/pg-meta'
import type { JwtPayload } from '@supabase/supabase-js'
import { pipeUIMessageStreamToResponse, safeValidateUIMessages, toUIMessageStream } from 'ai'
import { IS_PLATFORM } from 'common'
import type { NextApiRequest, NextApiResponse } from 'next'
import z from 'zod'
import { executeSql } from '@/data/sql/execute-sql-mutation'
import type { AiOptInLevel } from '@/hooks/misc/useOrgOptedIntoAi'
import { getAIDetails } from '@/lib/ai/ai-details'
import { NO_SCHEMA_ACCESS_MESSAGE } from '@/lib/ai/assistant-context'
import {
assistantMessageMetadataSchema,
messagesIncludeLogsSnippets,
} from '@/lib/ai/assistant-message-metadata'
import { isTracingAllowed } from '@/lib/ai/braintrust-logger'
import { generateAssistantResponse } from '@/lib/ai/generate-assistant-response'
import { isExplorerEnabled } from '@/lib/ai/is-explorer-enabled'
import { getModel } from '@/lib/ai/model'
import {
DEFAULT_ASSISTANT_BASE_MODEL_ID,
getAssistantModelEntry,
isAssistantBaseModelId,
isKnownAssistantModelId,
type AssistantModelId,
} from '@/lib/ai/model.utils'
import { getTools } from '@/lib/ai/tools'
import { encodeNotebookToolError } from '@/lib/ai/tools/notebook-tools'
import { apiWrapper } from '@/lib/api/apiWrapper'
import { executeQuery } from '@/lib/api/self-hosted/query'
import { getURL } from '@/lib/helpers'
import { trustedUserEmail } from '@/lib/server/configcat'
export const maxDuration = 120
export const config = {
api: {
bodyParser: {
sizeLimit: '5mb',
},
},
}
async function handler(req: NextApiRequest, res: NextApiResponse, claims?: JwtPayload) {
const { method } = req
switch (method) {
case 'POST':
return handlePost(req, res, claims)
default:
res.setHeader('Allow', ['POST'])
res.status(405).json({
data: null,
error: { message: `Method ${method} Not Allowed` },
})
}
}
const wrapper = (req: NextApiRequest, res: NextApiResponse) =>
apiWrapper(req, res, handler, { withAuth: true })
export default wrapper
const requestBodySchema = z.object({
messages: z.array(z.any()),
projectRef: z.string(),
connectionString: z.string(),
schema: z.string().optional(),
table: z.string().optional(),
chatId: z.string().optional(),
chatName: z.string().optional(),
supportMode: z.boolean().optional(),
orgSlug: z.string().optional(),
model: z.string().optional(),
})
async function handlePost(req: NextApiRequest, res: NextApiResponse, claims?: JwtPayload) {
const authorization = req.headers.authorization
const accessToken = authorization?.replace('Bearer ', '')
if (IS_PLATFORM && !accessToken) {
return res.status(401).json({ error: 'Authorization token is required' })
}
const userId = claims?.sub
const body = typeof req.body === 'string' ? JSON.parse(req.body) : req.body
const { data, error: parseError } = requestBodySchema.safeParse(body)
if (parseError) {
return res.status(400).json({ error: 'Invalid request body', issues: parseError.issues })
}
const {
messages: rawMessages,
projectRef,
connectionString,
orgSlug: rawOrgSlug,
chatId,
chatName,
model: rawRequestedModel,
supportMode,
} = data
const requestedModel: AssistantModelId | undefined =
rawRequestedModel && isKnownAssistantModelId(rawRequestedModel) ? rawRequestedModel : undefined
const messagesValidation = await safeValidateUIMessages({
messages: rawMessages,
metadataSchema: assistantMessageMetadataSchema,
})
if (!messagesValidation.success) {
return res.status(400).json({
error: 'Invalid request body',
message: messagesValidation.error.message,
})
}
const messages = messagesValidation.data
const includesLogsSnippets = messagesIncludeLogsSnippets(messages)
let aiOptInLevel: AiOptInLevel = 'disabled'
let hasAccessToAdvanceModel = false
let orgHasHipaaAddon: boolean | undefined
let projectIsSensitive: boolean | null | undefined
let projectRegion: string | undefined
let orgId: number | undefined
let orgSlug: string | undefined
let planId: string | undefined
if (!IS_PLATFORM) {
aiOptInLevel = 'schema'
hasAccessToAdvanceModel = true
}
if (IS_PLATFORM && rawOrgSlug && authorization && projectRef) {
try {
const aiDetails = await getAIDetails({ orgSlug: rawOrgSlug, projectRef, authorization })
aiOptInLevel = aiDetails.aiOptInLevel
hasAccessToAdvanceModel = aiDetails.hasAccessToAdvanceModel
orgHasHipaaAddon = aiDetails.hasHipaaAddon
orgId = aiDetails.orgId
orgSlug = aiDetails.orgSlug
planId = aiDetails.planId
projectIsSensitive = aiDetails.isSensitive
projectRegion = aiDetails.region
} catch (error) {
return res.status(400).json({
error: 'There was an error fetching your organization details',
})
}
}
const explorerEnabled = await isExplorerEnabled(trustedUserEmail(claims?.email))
const envThrottled = process.env.IS_THROTTLED !== 'false'
let effectiveModel: AssistantModelId = requestedModel ?? DEFAULT_ASSISTANT_BASE_MODEL_ID
if (!hasAccessToAdvanceModel || (envThrottled && !isAssistantBaseModelId(effectiveModel))) {
effectiveModel = DEFAULT_ASSISTANT_BASE_MODEL_ID
}
const {
modelParams,
error: modelError,
systemProviderOptions,
} = await getModel({
provider: 'openai',
modelEntry: getAssistantModelEntry(effectiveModel),
})
if (modelError) {
return res.status(500).json({ error: modelError.message })
}
try {
const abortController = new AbortController()
req.on('close', () => abortController.abort())
req.on('aborted', () => abortController.abort())
// Fires when the response finishes streaming or the connection drops, which
// is what tears down the remote MCP connection opened in getTools.
res.on('close', () => abortController.abort())
const tools = await getTools({
projectRef,
connectionString,
authorization,
aiOptInLevel,
accessToken,
baseUrl: getURL(),
supportMode,
isExplorerEnabled: explorerEnabled,
signal: abortController.signal,
})
// Get a list of all schemas to add to context
const getSchemas = async (): Promise<string> => {
const pgMetaSchemasList = pgMeta.schemas.list()
type Schemas = z.infer<(typeof pgMetaSchemasList)['zod']>
const { result: schemas } = await executeSql<Schemas>(
{
projectRef,
connectionString,
sql: pgMetaSchemasList.sql,
},
undefined,
{
'Content-Type': 'application/json',
...(authorization && { Authorization: authorization }),
},
IS_PLATFORM ? undefined : executeQuery
)
return schemas?.length > 0
? `The available database schema names are: ${JSON.stringify(schemas)}`
: NO_SCHEMA_ACCESS_MESSAGE
}
const result = await generateAssistantResponse({
messages,
...modelParams,
tools,
aiOptInLevel,
getSchemas: aiOptInLevel !== 'disabled' ? getSchemas : undefined,
projectRef,
chatId,
chatName,
allowTracing: isTracingAllowed({
orgHasHipaaAddon,
projectIsSensitive,
projectRegion,
}),
supportMode,
userId,
orgId,
orgSlug,
planId,
includesLogsSnippets,
isExplorerEnabled: explorerEnabled,
requestedModel,
systemProviderOptions,
abortSignal: abortController.signal,
onSpanCreated: (spanId) => {
res.setHeader('x-braintrust-span-id', spanId)
},
})
const stream = toUIMessageStream({
stream: result.stream,
sendReasoning: true,
onError: (error) => {
console.error('Assistant stream error:', error)
const encoded = encodeNotebookToolError(error)
if (encoded !== null) return encoded
if (error == null) {
return 'unknown error'
}
if (typeof error === 'string') {
return error
}
if (error instanceof Error) {
return error.message
}
return JSON.stringify(error)
},
})
pipeUIMessageStreamToResponse({
response: res,
stream,
headers: { 'Content-Encoding': 'none' },
})
} catch (error) {
console.error('Error in handlePost:', error)
if (error instanceof Error) {
return res.status(500).json({ message: error.message })
}
return res.status(500).json({ message: 'An unexpected error occurred.' })
}
}