Merge pull request #410 from Regis-RCR/fix/local-404-cascade

fix(sse): model-only lockout for local provider 404

open-sse/config/constants.ts

@@ -135,6 +135,7 @@ export const COOLDOWN_MS = {
   unauthorized: 2 * 60 * 1000, // 401 → 2 min
   paymentRequired: 2 * 60 * 1000, // 402/403 → 2 min
   notFound: 2 * 60 * 1000, // 404 → 2 minutes
+  notFoundLocal: 5 * 1000, // 404 on local provider → 5s model-only lockout (connection stays active)
   transientInitial: 5 * 1000, // 408/500/502/503/504 first hit → 5s (backoff from here)
   transientMax: 60 * 1000, // 502/503/504 backoff ceiling → 60s
   transient: 5 * 1000, // Legacy alias → points to transientInitial
@@ -162,6 +163,16 @@ export const PROVIDER_PROFILES = {
     circuitBreakerThreshold: 5, // More tolerant (occasional 502 is normal)
     circuitBreakerReset: 30000, // 30s reset
   },
+  // Local providers (localhost inference backends like Ollama, LM Studio, oMLX).
+  // Not yet wired into getProviderProfile() — will be used when local provider_nodes
+  // are integrated into the resilience layer. Kept here to avoid a second constants change.
+  local: {
+    transientCooldown: 2000, // 2s (local — very fast recovery)
+    rateLimitCooldown: 5000, // 5s (local — no real rate limits)
+    maxBackoffLevel: 3, // Low ceiling (local either works or doesn't)
+    circuitBreakerThreshold: 2, // Opens fast (if local is down, it's down)
+    circuitBreakerReset: 15000, // 15s reset (check again quickly)
+  },
 };
 
 // Default rate limit values for API Key providers (auto-enabled safety net)

open-sse/config/providerRegistry.ts

@@ -1057,6 +1057,38 @@ export function generateAliasMap(): Record<string, string> {
   return map;
 }
 
+// ── Local Provider Detection ──────────────────────────────────────────────
+
+// Evaluated once at module load time — process restart required for env var changes.
+const LOCAL_HOSTNAMES = new Set([
+  "localhost",
+  "127.0.0.1",
+  "::1",
+  "[::1]",
+  ...(typeof process !== "undefined" && process.env.LOCAL_HOSTNAMES
+    ? process.env.LOCAL_HOSTNAMES.split(",")
+        .map((h) => h.trim())
+        .filter(Boolean)
+    : []),
+]);
+
+/**
+ * Detect if a base URL points to a local inference backend.
+ * Used for shorter 404 cooldowns (model-only, not connection) and health check targets.
+ *
+ * Operators can extend via LOCAL_HOSTNAMES env var (comma-separated) for Docker
+ * hostnames (e.g., LOCAL_HOSTNAMES=omlx,mlx-audio).
+ */
+export function isLocalProvider(baseUrl?: string | null): boolean {
+  if (!baseUrl) return false;
+  try {
+    const url = new URL(baseUrl);
+    return LOCAL_HOSTNAMES.has(url.hostname);
+  } catch {
+    return false;
+  }
+}
+
 // ── Registry Lookup Helpers ───────────────────────────────────────────────
 
 const _byAlias = new Map<string, RegistryEntry>();

src/sse/handlers/chat.ts

@@ -382,7 +382,8 @@ async function handleSingleModelChat(
       credentials.connectionId,
       result.status,
       result.error,
-      provider
+      provider,
+      model
     );
 
     if (shouldFallback) {

src/sse/services/auth.ts

@@ -14,6 +14,8 @@ import {
   isModelLocked,
   lockModel,
 } from "@omniroute/open-sse/services/accountFallback.ts";
+import { isLocalProvider } from "@omniroute/open-sse/config/providerRegistry.ts";
+import { COOLDOWN_MS } from "@omniroute/open-sse/config/constants.ts";
 import * as log from "../utils/logger";
 import { fisherYatesShuffle, getNextFromDeckSync } from "@/shared/utils/shuffleDeck";
 
@@ -563,6 +565,23 @@ export async function markAccountUnavailable(
     );
     if (!shouldFallback) return { shouldFallback: false, cooldownMs: 0 };
 
+    // ── Local provider 404: model-only lockout, connection stays active ──
+    // Detection: URL-based only (apiKey===null heuristic was too broad — could match
+    // cloud providers with non-standard auth stored in providerSpecificData).
+    const connBaseUrl = (conn?.providerSpecificData as Record<string, unknown>)?.baseUrl as
+      | string
+      | undefined;
+
+    if (isLocalProvider(connBaseUrl) && status === 404 && provider && model) {
+      const localCooldown = COOLDOWN_MS.notFoundLocal;
+      lockModel(provider, connectionId, model, "local_not_found", localCooldown);
+      log.info(
+        "AUTH",
+        `Local 404 for ${model} — model-only lockout ${localCooldown / 1000}s (connection stays active)`
+      );
+      return { shouldFallback: true, cooldownMs: localCooldown };
+    }
+
     const rateLimitedUntil = getUnavailableUntil(cooldownMs);
     const errorMsg = typeof errorText === "string" ? errorText.slice(0, 100) : "Provider error";