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/lib/ai/switchboard-log.ts

@@ -0,0 +1,35 @@
+import type { SwitchboardMeta } from "./switchboard-types"
+
+/**
+ * One line per gateway call so the cost and the model actually used are visible in
+ * the server log. Called from inside the provider, so every feature gets it for free.
+ */
+export function logSwitchboardMeta(
+  feature: string,
+  meta: SwitchboardMeta | null
+): void {
+  if (!meta) {
+    console.warn(`[switchboard] feature=${feature} no meta block in response`)
+    return
+  }
+
+  console.log(
+    `[switchboard] feature=${feature} model=${meta.model_id} ` +
+      `provider=${meta.provider} locality=${meta.locality} category=${meta.category} ` +
+      `cost=${meta.cost_usd ?? "?"} latency_ms=${meta.latency_ms} request_id=${meta.request_id}`
+  )
+
+  // Both of these silently degrade output quality, so they warn rather than log.
+  if (meta.failover) {
+    console.warn(
+      `[switchboard] feature=${feature} FAILOVER intended=${meta.intended_model} ` +
+        `actual=${meta.model_id} reason=${meta.reason}`
+    )
+  }
+  if (meta.context_overflow) {
+    console.warn(
+      `[switchboard] feature=${feature} CONTEXT OVERFLOW model=${meta.model_id} ` +
+        `- the provider may have truncated this request`
+    )
+  }
+}