Route all AI features through the Switchboard gateway

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>

src/app/api/bar/barcode-lookup/route.ts

@@ -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
   }
 }