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

@@ -245,6 +245,10 @@ if [[ "$SKIP_CONFIG" == "false" ]]; then
prompt_secret AUTH_SECRET "NextAuth secret" "$(openssl rand -base64 32)"
prompt_secret ENC_KEY "Encryption key" "$(openssl rand -hex 32)"
echo ""
echo -e "${BOLD}AI Gateway:${NC}"
prompt_value SWITCHBOARD_URL "Switchboard gateway URL" "http://192.168.2.11:8787/v1"
echo ""
echo -e "${BOLD}OAuth Providers (optional — press Enter to skip):${NC}"
prompt_value GOOGLE_CID "Google Client ID" ""
@@ -288,6 +292,9 @@ MINIO_USE_SSL="false"
# ─── Encryption (for API key storage) ────────────────────
ENCRYPTION_KEY="${ENC_KEY}"
# ─── AI Gateway (Switchboard) ────────────────────────────
SWITCHBOARD_BASE_URL="${SWITCHBOARD_URL}"
ENVEOF
chmod 600 "$ENV_FILE"
@@ -403,7 +410,7 @@ echo " Update: $DC_CMD pull && $DC_CMD up -d"
echo ""
echo -e " ${BOLD}${YELLOW}Next steps:${NC}"
echo " 1. Open ${APP_URL_CHECK} and create your account"
echo " 2. Add your Claude or OpenAI API key in Settings"
echo " 2. Add your Switchboard API key in Settings"
echo " 3. Set up a reverse proxy (nginx/Caddy) for HTTPS"
if [[ -z "${GOOGLE_CID:-}" ]] && [[ -z "${GITHUB_CID:-}" ]]; then
echo " 4. (Optional) Add OAuth providers in $ENV_FILE"