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>

prisma/schema.prisma

@@ -74,7 +74,7 @@ model VerificationToken {
 model UserApiKey {
   id            String   @id @default(cuid())
   userId        String
-  provider      String   // "claude" | "openai"
+  provider      String   // "switchboard" (legacy rows may be "claude" | "openai")
   encryptedKey  String   @db.Text
   iv            String   // initialization vector for decryption
   label         String?  // optional user-friendly label
@@ -94,7 +94,7 @@ model UserPreference {
   avoidedStyles   String[] // e.g., ["Sour", "Light Lager"]
   minAbv          Float?
   maxAbv          Float?
-  defaultProvider String?  // preferred AI provider
+  defaultProvider String?  // deprecated and unused; kept so old backups still restore
   createdAt       DateTime @default(now())
   updatedAt       DateTime @updatedAt
 
@@ -163,7 +163,7 @@ model MenuScan {
   userId         String
   imageUrl       String
   status         ScanStatus @default(UPLOADING)
-  aiProvider     String?    // which provider was used
+  aiProvider     String?    // "switchboard:<model_id>" — the model the gateway routed to
   aiRawResponse  Json?      // raw AI response for debugging
   errorMessage   String?    @db.Text
   processedAt    DateTime?
@@ -227,7 +227,7 @@ model SearchCache {
   queryHash String   // normalized (lowercase, trimmed)
   query     String   // original text
   results   Json     // { drinks: [...] }
-  provider  String   // "claude" | "openai"
+  provider  String   // "switchboard"
   createdAt DateTime @default(now())
 
   @@unique([userId, queryHash, provider])