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>
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

View File

@@ -24,7 +24,7 @@ export const ratingCreateSchema = z.object({
export const ratingUpdateSchema = ratingCreateSchema.omit({ drinkId: true }).partial()
export const apiKeySchema = z.object({
provider: z.enum(["claude", "openai"]),
provider: z.literal("switchboard"),
apiKey: z.string().min(1, "API key is required"),
label: z.string().max(100).optional(),
})
@@ -34,7 +34,8 @@ export const userPreferenceSchema = z.object({
avoidedStyles: z.array(z.string().max(50)).max(20).optional(),
minAbv: z.number().min(0).max(100).optional().nullable(),
maxAbv: z.number().min(0).max(100).optional().nullable(),
defaultProvider: z.enum(["claude", "openai"]).optional().nullable(),
// defaultProvider is intentionally absent: it was stored but never read, and there
// is only one provider now. The Prisma column stays so restoring an old backup works.
})
export const wishlistCreateSchema = z.object({