jpscott84/drinktracker
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Route all AI features through the Switchboard gateway

Browse Source 
Replace the direct Anthropic and OpenAI integrations with a single
provider that talks to Switchboard, an OpenAI-compatible gateway that
routes each request to the best available model. The app no longer pins
a model id anywhere: it sends switchboard/auto and lets the gateway
choose, then logs which model answered and what it cost.

Routing levers are set per feature in src/lib/ai/routing.ts. Three of
those choices came from measuring against the live gateway:

- category and prefer_free are set explicitly on every request. An API
  key carries its own routing defaults, and anything left unset inherits
  them - drink prompts were being sent to a free coding model.
- Token budgets are generous because the router may pick a reasoning
  model, and reasoning tokens come out of the same max_tokens budget as
  the answer. At 512 tokens a request returned null content; at 4096 the
  same request returned correct JSON.
- No tier lever on text features. tier "cheap" pinned a slow reasoning
  model (42-180s, two timeouts and one truncated response in five
  trials) and tier "frontier" escalated as far as Opus at $0.02 a call,
  while unconstrained routing answered in about a second. Vision keeps
  "frontier", where the accuracy is worth a few tenths of a cent.

Gateway failures are mapped to actionable messages rather than passed
through: a 401 relayed as 401 would read as an expired session and
bounce the user to login, and a 429 would collide with the app's own
rate limiter.

Also collapses the key lookup that was duplicated across ten call sites
into getUserProvider(), which fixes a latent bug where a bare findFirst
with no ordering let different features pick different providers.

Existing claude/openai key rows are ignored at runtime and offered for
removal in Settings, so no migration is needed before deploying.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
JP
2026-08-08 16:41:00 +00:00
parent 7c41b15ecc
commit a0e1619072
31 changed files with 830 additions and 429 deletions
Download Patch File Download Diff File Expand all files Collapse all files

94
src/app/(app)/settings/page.tsx
View File

@@ -20,11 +20,16 @@ interface ApiKeyInfo {
isActive: boolean
}
interface ApiKeysResponse {
keys: ApiKeyInfo[]
gatewayUrl: string
}
export default function SettingsPage() {
const queryClient = useQueryClient()
// API Keys
const { data: apiKeys = [] } = useQuery<ApiKeyInfo[]>({
const { data: apiKeyData } = useQuery<ApiKeysResponse>({
queryKey: ["api-keys"],
queryFn: async () => {
const res = await fetch("/api/settings/api-keys")
@@ -33,6 +38,11 @@ export default function SettingsPage() {
},
})
const apiKeys = apiKeyData?.keys ?? []
const legacyKeys = apiKeys.filter(
(k) => k.provider === "claude" || k.provider === "openai"
)
// Preferences
const { data: preferences, isLoading: prefsLoading } = useQuery({
queryKey: ["preferences"],
@@ -74,16 +84,32 @@ export default function SettingsPage() {
<CardHeader>
<CardTitle className="flex items-center gap-2">
<Key className="h-5 w-5" />
AI Provider Keys
AI Gateway
</CardTitle>
<CardDescription>
Add your API keys for AI-powered menu scanning. Keys are encrypted and stored securely.
AI features route through Switchboard, which picks the best model for each
request. Add your gateway API key below — it is encrypted before storage.
{apiKeyData?.gatewayUrl && (
<>
{" "}
This app is pointed at{" "}
<code className="text-xs">{apiKeyData.gatewayUrl}</code>.
</>
)}
</CardDescription>
</CardHeader>
<CardContent className="space-y-4">
<ApiKeyForm provider="claude" label="Anthropic Claude" existingKey={apiKeys.find(k => k.provider === "claude")} />
<Separator />
<ApiKeyForm provider="openai" label="OpenAI GPT-4o" existingKey={apiKeys.find(k => k.provider === "openai")} />
<ApiKeyForm
provider="switchboard"
label="Switchboard Gateway"
existingKey={apiKeys.find((k) => k.provider === "switchboard")}
/>
{legacyKeys.length > 0 && (
<>
<Separator />
<LegacyKeyNotice keys={legacyKeys} />
</>
)}
</CardContent>
</Card>
@@ -115,6 +141,62 @@ export default function SettingsPage() {
)
}
const LEGACY_PROVIDER_LABELS: Record<string, string> = {
claude: "Anthropic Claude",
openai: "OpenAI",
}
/**
* Keys left over from when the app called Claude and OpenAI directly. They are
* already ignored when picking a provider, but they are shown here so a user who
* still has one can see it is inert and remove it.
*/
function LegacyKeyNotice({ keys }: { keys: ApiKeyInfo[] }) {
const queryClient = useQueryClient()
const deleteKey = useMutation({
mutationFn: async (provider: string) => {
const res = await fetch(`/api/settings/api-keys?provider=${provider}`, {
method: "DELETE",
})
if (!res.ok) throw new Error("Failed to delete API key")
},
onSuccess: () => {
queryClient.invalidateQueries({ queryKey: ["api-keys"] })
},
})
return (
<div className="rounded-md border border-dashed p-3 space-y-3">
<p className="text-sm text-muted-foreground">
These keys are from an earlier version that called each AI provider directly.
They are no longer used and can be removed.
</p>
{keys.map((key) => (
<div key={key.id} className="flex items-center justify-between gap-2">
<div>
<p className="text-sm font-medium">
{LEGACY_PROVIDER_LABELS[key.provider] ?? key.provider}
</p>
<code className="text-xs bg-muted px-2 py-0.5 rounded">
{key.maskedKey}
</code>
</div>
<Button
variant="outline"
size="sm"
onClick={() => deleteKey.mutate(key.provider)}
disabled={deleteKey.isPending}
>
<Trash2 className="h-4 w-4 mr-1 text-destructive" />
Remove
</Button>
</div>
))}
</div>
)
}
function ApiKeyForm({
provider,
label,

25
src/app/api/ai/identify/route.ts
View File

@@ -1,8 +1,7 @@
import { NextResponse } from "next/server"
import { auth } from "@/lib/auth"
import { prisma } from "@/lib/prisma"
import { decrypt } from "@/lib/encryption"
import { createProvider } from "@/lib/ai/provider-factory"
import { getUserProvider } from "@/lib/ai/provider-factory"
import { aiErrorResponse } from "@/lib/ai/errors"
import { rateLimit } from "@/lib/rate-limit"
import { z } from "zod"
@@ -73,19 +72,7 @@ export async function POST(request: Request) {
const { imageBase64, mimeType, context } = parsed.data
const apiKeyRecord = await prisma.userApiKey.findFirst({
where: { userId: session.user.id, isActive: true },
})
if (!apiKeyRecord) {
return NextResponse.json(
{ error: "No AI provider configured. Add an API key in Settings." },
{ status: 400 }
)
}
const apiKey = decrypt(apiKeyRecord.encryptedKey, apiKeyRecord.iv)
const provider = createProvider(apiKeyRecord.provider, apiKey)
const provider = await getUserProvider(session.user.id)
const result = await provider.extractLabel(imageBase64, mimeType)
@@ -107,10 +94,6 @@ export async function POST(request: Request) {
return NextResponse.json(response)
} catch (error) {
console.error("AI identify error:", error)
return NextResponse.json(
{ error: "Failed to identify product. Please try again." },
{ status: 500 }
)
return aiErrorResponse(error, "Failed to identify product. Please try again.")
}
}

31
src/app/api/ai/search/route.ts
View File

@@ -1,8 +1,8 @@
import { NextResponse } from "next/server"
import { auth } from "@/lib/auth"
import { prisma } from "@/lib/prisma"
import { decrypt } from "@/lib/encryption"
import { createProvider } from "@/lib/ai/provider-factory"
import { AI_PROVIDER, getUserProvider } from "@/lib/ai/provider-factory"
import { aiErrorResponse } from "@/lib/ai/errors"
import { rateLimit } from "@/lib/rate-limit"
import { z } from "zod"
import type { Prisma } from "@prisma/client"
@@ -33,18 +33,6 @@ export async function POST(request: Request) {
return NextResponse.json({ error: "Invalid query" }, { status: 400 })
}
// Get user's AI provider
const apiKeyRecord = await prisma.userApiKey.findFirst({
where: { userId: session.user.id, isActive: true },
})
if (!apiKeyRecord) {
return NextResponse.json(
{ error: "No AI provider configured. Add an API key in Settings." },
{ status: 400 }
)
}
// Check cache first (24hr TTL)
const queryHash = parsed.data.query.toLowerCase().trim()
const twentyFourHoursAgo = new Date(Date.now() - 24 * 60 * 60 * 1000)
@@ -54,7 +42,7 @@ export async function POST(request: Request) {
userId_queryHash_provider: {
userId: session.user.id,
queryHash,
provider: apiKeyRecord.provider,
provider: AI_PROVIDER,
},
},
})
@@ -63,8 +51,7 @@ export async function POST(request: Request) {
return NextResponse.json(cached.results)
}
const apiKey = decrypt(apiKeyRecord.encryptedKey, apiKeyRecord.iv)
const provider = createProvider(apiKeyRecord.provider, apiKey)
const provider = await getUserProvider(session.user.id)
const result = await provider.searchDrinks(parsed.data.query)
@@ -74,7 +61,7 @@ export async function POST(request: Request) {
userId_queryHash_provider: {
userId: session.user.id,
queryHash,
provider: apiKeyRecord.provider,
provider: AI_PROVIDER,
},
},
update: {
@@ -87,16 +74,12 @@ export async function POST(request: Request) {
queryHash,
query: parsed.data.query,
results: { drinks: result.drinks } as unknown as Prisma.InputJsonValue,
provider: apiKeyRecord.provider,
provider: AI_PROVIDER,
},
})
return NextResponse.json({ drinks: result.drinks })
} catch (error) {
console.error("AI search error:", error)
return NextResponse.json(
{ error: "Search failed. Please try again." },
{ status: 500 }
)
return aiErrorResponse(error, "Search failed. Please try again.")
}
}

20
src/app/api/bar/barcode-lookup/route.ts
View File

@@ -1,8 +1,8 @@
import { NextResponse } from "next/server"
import { auth } from "@/lib/auth"
import { prisma } from "@/lib/prisma"
import { decrypt } from "@/lib/encryption"
import { createProvider } from "@/lib/ai/provider-factory"
import { getUserProvider } from "@/lib/ai/provider-factory"
import { FEATURE_ROUTING } from "@/lib/ai/routing"
import { rateLimit } from "@/lib/rate-limit"
import { z } from "zod"
@@ -71,13 +71,7 @@ async function lookupOpenFoodFacts(barcode: string) {
async function lookupViaAI(barcode: string, userId: string) {
try {
const apiKeyRecord = await prisma.userApiKey.findFirst({
where: { userId, isActive: true },
})
if (!apiKeyRecord) return null
const apiKey = decrypt(apiKeyRecord.encryptedKey, apiKeyRecord.iv)
const provider = createProvider(apiKeyRecord.provider, apiKey)
const provider = await getUserProvider(userId)
const systemPrompt = `You are a product identification expert. Given a UPC/EAN barcode number, identify the product — especially alcoholic beverages, spirits, mixers, and bar supplies.
@@ -91,7 +85,8 @@ Do not include any text before or after the JSON.`
const response = await provider.sendTextRequest(
systemPrompt,
`Identify the product with UPC/EAN barcode: ${barcode}`
`Identify the product with UPC/EAN barcode: ${barcode}`,
FEATURE_ROUTING.barcodeLookup
)
const match = response.match(/\{[\s\S]*\}/)
@@ -104,7 +99,10 @@ Do not include any text before or after the JSON.`
brand: (parsed.brand as string) || null,
category: parsed.category || "SPIRITS",
}
} catch {
} catch (error) {
// Best-effort fallback after Open Food Facts, so a failure here is not fatal to
// the request. Logged so a gateway outage is not completely invisible.
console.warn("[switchboard] barcode AI fallback failed:", error)
return null
}
}

28
src/app/api/bartender/recreate/route.ts
View File

@@ -1,8 +1,9 @@
import { NextResponse } from "next/server"
import { auth } from "@/lib/auth"
import { prisma } from "@/lib/prisma"
import { decrypt } from "@/lib/encryption"
import { createProvider } from "@/lib/ai/provider-factory"
import { getUserProvider } from "@/lib/ai/provider-factory"
import { FEATURE_ROUTING } from "@/lib/ai/routing"
import { aiErrorResponse } from "@/lib/ai/errors"
import { rateLimit } from "@/lib/rate-limit"
import { COCKTAIL_RECIPE_PROMPT, buildBarInventoryString } from "@/lib/ai/prompts"
import { fuzzyMatchIngredients, recalculateMissingCount } from "@/lib/ingredient-matcher"
@@ -34,17 +35,6 @@ export async function POST(request: Request) {
return NextResponse.json({ error: "Invalid request" }, { status: 400 })
}
const apiKeyRecord = await prisma.userApiKey.findFirst({
where: { userId: session.user.id, isActive: true },
})
if (!apiKeyRecord) {
return NextResponse.json(
{ error: "No AI provider configured. Add an API key in Settings." },
{ status: 400 }
)
}
const barItems = await prisma.barItem.findMany({
where: {
userId: session.user.id,
@@ -56,12 +46,12 @@ export async function POST(request: Request) {
const inventoryString = buildBarInventoryString(barItems)
const prompt = COCKTAIL_RECIPE_PROMPT.replace("{barInventory}", inventoryString)
const apiKey = decrypt(apiKeyRecord.encryptedKey, apiKeyRecord.iv)
const provider = createProvider(apiKeyRecord.provider, apiKey)
const provider = await getUserProvider(session.user.id)
const rawResponse = await provider.sendTextRequest(
prompt,
`Generate a recipe for: ${parsed.data.cocktailName}`
`Generate a recipe for: ${parsed.data.cocktailName}`,
FEATURE_ROUTING.bartenderRecreate
)
// Parse JSON from response
@@ -91,10 +81,6 @@ export async function POST(request: Request) {
return NextResponse.json(recipe)
} catch (error) {
console.error("Bartender recreate error:", error)
return NextResponse.json(
{ error: "Failed to generate recipe. Please try again." },
{ status: 500 }
)
return aiErrorResponse(error, "Failed to generate recipe. Please try again.")
}
}

28
src/app/api/bartender/suggest/route.ts
View File

@@ -1,8 +1,9 @@
import { NextResponse } from "next/server"
import { auth } from "@/lib/auth"
import { prisma } from "@/lib/prisma"
import { decrypt } from "@/lib/encryption"
import { createProvider } from "@/lib/ai/provider-factory"
import { getUserProvider } from "@/lib/ai/provider-factory"
import { FEATURE_ROUTING } from "@/lib/ai/routing"
import { aiErrorResponse } from "@/lib/ai/errors"
import { rateLimit } from "@/lib/rate-limit"
import { WHAT_CAN_I_MAKE_PROMPT, buildBarInventoryString } from "@/lib/ai/prompts"
import { fuzzyMatchIngredients, recalculateMissingCount } from "@/lib/ingredient-matcher"
@@ -22,17 +23,6 @@ export async function POST() {
}
try {
const apiKeyRecord = await prisma.userApiKey.findFirst({
where: { userId: session.user.id, isActive: true },
})
if (!apiKeyRecord) {
return NextResponse.json(
{ error: "No AI provider configured. Add an API key in Settings." },
{ status: 400 }
)
}
const barItems = await prisma.barItem.findMany({
where: {
userId: session.user.id,
@@ -51,12 +41,12 @@ export async function POST() {
const inventoryString = buildBarInventoryString(barItems)
const prompt = WHAT_CAN_I_MAKE_PROMPT.replace("{barInventory}", inventoryString)
const apiKey = decrypt(apiKeyRecord.encryptedKey, apiKeyRecord.iv)
const provider = createProvider(apiKeyRecord.provider, apiKey)
const provider = await getUserProvider(session.user.id)
const rawResponse = await provider.sendTextRequest(
prompt,
"What cocktails can I make with my bar inventory?"
"What cocktails can I make with my bar inventory?",
FEATURE_ROUTING.bartenderSuggest
)
// Parse JSON from response
@@ -98,10 +88,6 @@ export async function POST() {
return NextResponse.json({ suggestions })
} catch (error) {
console.error("Bartender suggest error:", error)
return NextResponse.json(
{ error: "Failed to generate suggestions. Please try again." },
{ status: 500 }
)
return aiErrorResponse(error, "Failed to generate suggestions. Please try again.")
}
}

29
src/app/api/recommend/profile/route.ts
View File

@@ -1,8 +1,9 @@
import { NextResponse } from "next/server"
import { auth } from "@/lib/auth"
import { prisma } from "@/lib/prisma"
import { decrypt } from "@/lib/encryption"
import { createProvider } from "@/lib/ai/provider-factory"
import { getUserProvider } from "@/lib/ai/provider-factory"
import { FEATURE_ROUTING } from "@/lib/ai/routing"
import { aiErrorResponse } from "@/lib/ai/errors"
import { rateLimit } from "@/lib/rate-limit"
import { FLAVOR_PROFILE_PROMPT, buildDrinkHistoryString } from "@/lib/ai/prompts"
import type { Prisma } from "@prisma/client"
@@ -67,18 +68,6 @@ export async function POST() {
}
try {
// Get user's AI provider
const apiKeyRecord = await prisma.userApiKey.findFirst({
where: { userId: session.user.id, isActive: true },
})
if (!apiKeyRecord) {
return NextResponse.json(
{ error: "No AI provider configured. Add an API key in Settings." },
{ status: 400 }
)
}
// Fetch all drinks with ratings
const drinks = await prisma.drink.findMany({
where: { userId: session.user.id },
@@ -120,12 +109,12 @@ export async function POST() {
const drinkHistory = buildDrinkHistoryString(drinkSummaries)
const prompt = FLAVOR_PROFILE_PROMPT.replace("{drinkHistory}", drinkHistory)
const apiKey = decrypt(apiKeyRecord.encryptedKey, apiKeyRecord.iv)
const provider = createProvider(apiKeyRecord.provider, apiKey)
const provider = await getUserProvider(session.user.id)
const rawResponse = await provider.sendTextRequest(
prompt,
"Analyze my drink history and build my flavor profile."
"Analyze my drink history and build my flavor profile.",
FEATURE_ROUTING.flavorProfile
)
// Parse the JSON response
@@ -183,10 +172,6 @@ export async function POST() {
},
})
} catch (error) {
console.error("Flavor profile generation error:", error)
return NextResponse.json(
{ error: "Failed to generate flavor profile. Please try again." },
{ status: 500 }
)
return aiErrorResponse(error, "Failed to generate flavor profile. Please try again.")
}
}

29
src/app/api/recommend/similar/route.ts
View File

@@ -1,8 +1,9 @@
import { NextResponse } from "next/server"
import { auth } from "@/lib/auth"
import { prisma } from "@/lib/prisma"
import { decrypt } from "@/lib/encryption"
import { createProvider } from "@/lib/ai/provider-factory"
import { getUserProvider } from "@/lib/ai/provider-factory"
import { FEATURE_ROUTING } from "@/lib/ai/routing"
import { aiErrorResponse } from "@/lib/ai/errors"
import { rateLimit } from "@/lib/rate-limit"
import { SIMILAR_DRINK_PROMPT } from "@/lib/ai/prompts"
import { z } from "zod"
@@ -40,18 +41,6 @@ export async function POST(request: Request) {
)
}
// Get user's AI provider
const apiKeyRecord = await prisma.userApiKey.findFirst({
where: { userId: session.user.id, isActive: true },
})
if (!apiKeyRecord) {
return NextResponse.json(
{ error: "No AI provider configured. Add an API key in Settings." },
{ status: 400 }
)
}
// Fetch the source drink
const drink = await prisma.drink.findFirst({
where: { id: parsed.data.drinkId, userId: session.user.id },
@@ -99,12 +88,12 @@ export async function POST(request: Request) {
.replace("{sourceDrink}", sourceDrink)
.replace("{flavorProfile}", flavorProfile)
const apiKey = decrypt(apiKeyRecord.encryptedKey, apiKeyRecord.iv)
const provider = createProvider(apiKeyRecord.provider, apiKey)
const provider = await getUserProvider(session.user.id)
const rawResponse = await provider.sendTextRequest(
prompt,
`Find drinks similar to ${drink.name}.`
`Find drinks similar to ${drink.name}.`,
FEATURE_ROUTING.recommendSimilar
)
// Parse JSON response
@@ -131,10 +120,6 @@ export async function POST(request: Request) {
return NextResponse.json({ recommendations, sourceDrink: drink.name })
} catch (error) {
console.error("Similar drink error:", error)
return NextResponse.json(
{ error: "Failed to find similar drinks. Please try again." },
{ status: 500 }
)
return aiErrorResponse(error, "Failed to find similar drinks. Please try again.")
}
}

29
src/app/api/recommend/suggest/route.ts
View File

@@ -1,8 +1,9 @@
import { NextResponse } from "next/server"
import { auth } from "@/lib/auth"
import { prisma } from "@/lib/prisma"
import { decrypt } from "@/lib/encryption"
import { createProvider } from "@/lib/ai/provider-factory"
import { getUserProvider } from "@/lib/ai/provider-factory"
import { FEATURE_ROUTING } from "@/lib/ai/routing"
import { aiErrorResponse } from "@/lib/ai/errors"
import { rateLimit } from "@/lib/rate-limit"
import { RECOMMEND_DRINK_PROMPT } from "@/lib/ai/prompts"
import { z } from "zod"
@@ -38,18 +39,6 @@ export async function POST(request: Request) {
return NextResponse.json({ error: "Invalid request" }, { status: 400 })
}
// Get user's AI provider
const apiKeyRecord = await prisma.userApiKey.findFirst({
where: { userId: session.user.id, isActive: true },
})
if (!apiKeyRecord) {
return NextResponse.json(
{ error: "No AI provider configured. Add an API key in Settings." },
{ status: 400 }
)
}
// Fetch flavor profile
const profile = await prisma.flavorProfile.findUnique({
where: { userId: session.user.id },
@@ -82,12 +71,12 @@ export async function POST(request: Request) {
.replace("{flavorProfile}", profile.profileText)
.replace("{context}", context)
const apiKey = decrypt(apiKeyRecord.encryptedKey, apiKeyRecord.iv)
const provider = createProvider(apiKeyRecord.provider, apiKey)
const provider = await getUserProvider(session.user.id)
const rawResponse = await provider.sendTextRequest(
prompt,
"Recommend drinks for me based on my profile and the context provided."
"Recommend drinks for me based on my profile and the context provided.",
FEATURE_ROUTING.recommendSuggest
)
// Parse JSON response
@@ -114,10 +103,6 @@ export async function POST(request: Request) {
return NextResponse.json({ recommendations })
} catch (error) {
console.error("Drink suggestion error:", error)
return NextResponse.json(
{ error: "Failed to get suggestions. Please try again." },
{ status: 500 }
)
return aiErrorResponse(error, "Failed to get suggestions. Please try again.")
}
}

6
src/app/api/scan/route.ts
View File

@@ -166,12 +166,14 @@ async function processMenuScan(
])
} catch (error) {
console.error("Menu scan processing failed:", error)
// This runs detached from the request, so the stored message is all the user
// ever sees. Map gateway faults to something actionable rather than a raw error.
const { toAIGatewayError } = await import("@/lib/ai/errors")
await prisma.menuScan.update({
where: { id: scanId },
data: {
status: "FAILED",
errorMessage:
error instanceof Error ? error.message : "Unknown error",
errorMessage: toAIGatewayError(error).userMessage,
},
})
}

14
src/app/api/settings/api-keys/route.ts
View File

@@ -3,6 +3,7 @@ import { auth } from "@/lib/auth"
import { prisma } from "@/lib/prisma"
import { encrypt, decrypt, maskApiKey } from "@/lib/encryption"
import { apiKeySchema } from "@/lib/validators"
import { switchboardBaseUrl } from "@/lib/ai/switchboard-provider"
export async function GET() {
const session = await auth()
@@ -44,7 +45,9 @@ export async function GET() {
}
})
return NextResponse.json(maskedKeys)
// The gateway endpoint is server config, so surface it here rather than making the
// user guess which Switchboard instance this deployment points at.
return NextResponse.json({ keys: maskedKeys, gatewayUrl: switchboardBaseUrl() })
}
export async function POST(request: Request) {
@@ -90,6 +93,15 @@ export async function POST(request: Request) {
},
})
// Keys from the old direct Claude/OpenAI integration are already ignored when
// selecting a provider. Clear them now that a working replacement exists.
await prisma.userApiKey.deleteMany({
where: {
userId: session.user.id,
provider: { in: ["claude", "openai"] },
},
})
return NextResponse.json({
id: key.id,
provider: key.provider,