feat: multi-backend proxy with auto rate-limit jailing

Refactor from monolithic proxy to multi-backend architecture (Backend interface: OpenCode Zen + Kilo gateway). - Add auto rate-limit jailing: models returning HTTP 429 are hidden from /v1/models immediately and re-probed every 30 min - Backend interface supports model aliases, custom headers, and per-backend routing - Full Anthropic Messages API support with OpenAI format conversion - 9 free models across two backends with Claude name aliases
2026-06-26 19:08:01 +02:00
parent 0a4289cafc
commit 05a52d29e2
9 changed files with 652 additions and 245 deletions
@@ -0,0 +1,91 @@
+package proxy
+
+// KiloGatewayBase is the Kilo Code public gateway base URL.
+// Confirmed working without auth for free models (HTTP 200 on both
+// GET /api/gateway/models and POST /api/gateway/chat/completions).
+const KiloGatewayBase = "https://api.kilo.ai/api/gateway"
+
+// KiloBackend forwards to Kilo Code's free gateway models.
+//
+// Kilo is an opencode-based CLI whose gateway exposes a handful of free models
+// (suffixed ":free") reachable without authentication, in standard OpenAI
+// Chat Completions format.
+type KiloBackend struct{}
+
+// kiloFreeModels are the free models advertised by the Kilo gateway.
+// Sourced from GET /api/gateway/models filtering isFree:true.
+var kiloFreeModels = []ModelInfo{
+	{
+		ID:              "stepfun/step-3.7-flash:free",
+		Name:            "StepFun Step 3.7 Flash (Free)",
+		OwnedBy:         "stepfun",
+		ContextWindow:   256_000,
+		MaxOutputTokens: 32_000,
+		Description:     "StepFun. Flash rápido, tareas generales.",
+	},
+	{
+		ID:              "poolside/laguna-m.1:free",
+		Name:            "Poolside Laguna M.1 (Free)",
+		OwnedBy:         "poolside",
+		ContextWindow:   256_000,
+		MaxOutputTokens: 32_000,
+		Description:     "Poolside. Modelo orientado a código.",
+	},
+	{
+		ID:              "nvidia/nemotron-3-ultra-550b-a55b:free",
+		Name:            "Nemotron 3 Ultra 550B (Free)",
+		OwnedBy:         "nvidia",
+		ContextWindow:   1_000_000,
+		MaxOutputTokens: 16_384,
+		Description:     "NVIDIA Nemotron 3 Ultra (550B/55B MoE). 1M contexto, razonamiento.",
+	},
+	{
+		ID:              "openrouter/free",
+		Name:            "OpenRouter Best Free (Free)",
+		OwnedBy:         "openrouter",
+		ContextWindow:   256_000,
+		MaxOutputTokens: 32_000,
+		Description:     "OpenRouter selecciona automáticamente el mejor modelo free disponible.",
+	},
+}
+
+// kiloAliases lets clients use shorter names for Kilo free models.
+var kiloAliases = map[string]string{
+	"stepfun":       "stepfun/step-3.7-flash:free",
+	"stepfun-free":  "stepfun/step-3.7-flash:free",
+	"poolside":      "poolside/laguna-m.1:free",
+	"poolside-free": "poolside/laguna-m.1:free",
+	"laguna":        "poolside/laguna-m.1:free",
+	"openrouter":    "openrouter/free",
+}
+
+// Name returns the backend identifier.
+func (KiloBackend) Name() string { return "kilo" }
+
+// Models returns the Kilo free models.
+func (KiloBackend) Models() []ModelInfo { return kiloFreeModels }
+
+// Resolve maps a requested name to a Kilo free model ID.
+func (KiloBackend) Resolve(model string) (string, bool) {
+	if mapped, ok := kiloAliases[model]; ok {
+		return mapped, true
+	}
+	for _, m := range kiloFreeModels {
+		if m.ID == model {
+			return model, true
+		}
+	}
+	return "", false
+}
+
+// ChatURL is the Kilo gateway chat completions endpoint.
+func (KiloBackend) ChatURL() string { return KiloGatewayBase + "/chat/completions" }
+
+// Headers returns minimal headers for the Kilo gateway (no auth needed for free).
+func (KiloBackend) Headers(_, _ string) map[string]string {
+	return map[string]string{
+		"Content-Type": "application/json",
+		"Accept":       "text/event-stream, application/json",
+		"User-Agent":   "kilo/7.3.54",
+	}
+}