Files
supabase/apps/studio/lib/ai/model.ts
T
Matt Rossman adf8b0c67c feat(assistant): per-endpoint reasoningEffort + model config cleanup (#43981)
We're exploring support for newer models like
[gpt-5.4-nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/)
in Assistant. This model doesn't support the `'minimal'` reasoning
effort level we use for gpt-5-mini which leads to vague errors.

<img width="595" height="263" alt="CleanShot 2026-03-18 at 17 13 05@2x"
src="https://github.com/user-attachments/assets/cf7c2370-322d-4a8a-be55-23e680db0aa0"
/>


Also, we've [previously
discussed](https://supabase.slack.com/archives/C0161K73J1J/p1771544464850199?thread_ts=1771493920.775699&cid=C0161K73J1J)
that reasoning adds unnecessary latency to otherwise simple AI
completion endpoints like `title-v2`. We want more control of reasoning
level independent of model/endpoint.

This PR aims to solve both problems by:
- making reasoning effort configurable on a per-request basis
- adding compile-time guardrails to prevent selecting an incompatible
reasoning level for models
- adding a `DEFAULT_COMPLETION_MODEL` with minimal reasoning that we can
update with newer models that support disabling reasoning (independent
of Assistant chat model reasoning)

Other improvements to our model config logic:
- Fixes bug in `onboarding/design.ts` and `assistant.eval.ts` where
`providerOptions` was being dropped
- `getModel()` now returns a bundled `modelParams` object (spread into
AI SDK calls) so `providerOptions` can't be accidentally omitted (this
[has happened
before](https://supabase.slack.com/archives/C0161K73J1J/p1771518443534309?thread_ts=1771493920.775699&cid=C0161K73J1J))
- Introduces an `ASSISTANT_MODELS` registry as a single source of truth
for assistant model config, eliminating hardcoded model IDs across the
codebase
- Aligns free/pro model conditional logic with `assistant.advance_model`
entitlement naming conventions instead of the `isLimited` pattern
- Adds `console.error` logging of Assistant stream errors so we can
interpret reasoning effort compatibility errors in the future (instead
of just opaque "Sorry, I'm having trouble responding right now" card)
- Removes unnecessary type casts and generally making the model config
logic stricter
- Removes pre-existing dead code: `anthropic` provider variant in
`GetModelParams` / `PROVIDERS` registry that was never implemented in
`getModel()`

Now if you try to select an unsupported reasoning level you get a type
error:

<img width="1306" height="320" alt="CleanShot 2026-03-20 at 14 37 24@2x"
src="https://github.com/user-attachments/assets/a6ac234b-5ea5-4d81-8e01-ac4be34a0800"
/>

And if for some reason an invalid reasoning level slips through, you now
get a server-side error surfacing the issue:

<img width="1268" height="204" alt="CleanShot 2026-03-20 at 14 58 14@2x"
src="https://github.com/user-attachments/assets/aadc1b7a-9495-475f-9741-39979bd27cd7"
/>

I've tested gpt-5 and gpt-5-mini are still working on the staging
preview and verified the models were selected properly in Braintrust
logs. Both models are available on my Pro test account, and my Free test
account shows the Pro upgrade CTA.


Closes AI-446
Closes AI-551
2026-03-25 11:29:23 -04:00

105 lines
3.6 KiB
TypeScript

import { openai } from '@ai-sdk/openai'
import { LanguageModel } from 'ai'
import { checkAwsCredentials, createRoutedBedrock } from './bedrock'
import {
BedrockModel,
getDefaultModelForProvider,
Model,
OpenAIModelEntry,
OpenAIModelId,
ProviderModelConfig,
PROVIDERS,
} from './model.utils'
type PromptProviderOptions = Record<string, any>
type ProviderOptions = Record<string, any>
type ModelSuccess = {
/** Spread directly into AI SDK calls: `streamText({ ...modelParams, ... })` */
modelParams: { model: LanguageModel; providerOptions?: ProviderOptions }
promptProviderOptions?: PromptProviderOptions
error?: never
}
export type ModelError = {
modelParams?: never
promptProviderOptions?: never
error: Error
}
type ModelResponse = ModelSuccess | ModelError
export type GetModelParams =
| {
provider: 'openai'
/**
* Specifies which OpenAI model to use and its reasoning effort.
* Create entries via `openaiModelEntry()` — reasoning effort is validated against the model
* at compile time. Use `DEFAULT_COMPLETION_MODEL` for simple endpoints (minimal reasoning).
* Callers are responsible for resolving the correct entry (including throttling/entitlement
* fallbacks) before calling getModel.
*/
modelEntry: OpenAIModelEntry
}
| {
provider: 'bedrock'
/** Used for consistent hashing across Bedrock regions. */
routingKey: string
}
/**
* Retrieves a LanguageModel from a specific provider and model entry.
* Callers are responsible for resolving the correct model entry (including throttling/entitlement
* fallbacks) before calling this function.
* Returns promptProviderOptions that callers can attach to the system message.
*/
export async function getModel(params: GetModelParams): Promise<ModelResponse> {
const { provider } = params
const providerRegistry = PROVIDERS[provider]
if (!providerRegistry) {
return { error: new Error(`Unknown provider: ${provider}`) }
}
const models = providerRegistry.models as Record<Model, ProviderModelConfig>
const modelEntry = params.provider === 'openai' ? params.modelEntry : undefined
const useDefault = !modelEntry?.id || !models[modelEntry.id]
const chosenModelId = useDefault ? getDefaultModelForProvider(provider) : modelEntry?.id
if (provider === 'bedrock') {
const hasAwsCredentials = await checkAwsCredentials()
const hasAwsBedrockRoleArn = !!process.env.AWS_BEDROCK_ROLE_ARN
if (!hasAwsBedrockRoleArn || !hasAwsCredentials) {
return { error: new Error('AWS Bedrock credentials not available') }
}
const bedrock = createRoutedBedrock(params.routingKey)
const model = await bedrock(chosenModelId as BedrockModel)
const promptProviderOptions = (
providerRegistry.models as Record<BedrockModel, ProviderModelConfig>
)[chosenModelId as BedrockModel]?.promptProviderOptions
return { modelParams: { model }, promptProviderOptions }
}
if (provider === 'openai') {
if (!process.env.OPENAI_API_KEY) {
return { error: new Error('OPENAI_API_KEY not available') }
}
const baseProviderOptions = providerRegistry.providerOptions?.openai ?? {}
const openaiProviderOptions = modelEntry?.reasoningEffort
? { ...baseProviderOptions, reasoningEffort: modelEntry.reasoningEffort }
: baseProviderOptions
return {
modelParams: {
model: openai(chosenModelId as OpenAIModelId),
providerOptions: { openai: openaiProviderOptions },
},
promptProviderOptions: models[chosenModelId as OpenAIModelId]?.promptProviderOptions,
}
}
return { error: new Error(`Unsupported provider: ${provider}`) }
}