luulam
f0adfb205a
- Endpoint: per-API-key model allowlist (schema v3) enforced on chat (403) and /v1/models; Full-access toggle + multi-select picker in Keys UI. - Providers: honor x-connection-id in /v1/chat/completions — pinned requests no longer rotate to another account on failure. - Providers: strategy saves merge into stored enabled:false override; Test All groups match grid sections; 1-by-1 skips disabled connections. - Dashboard: provider-card toggle syncs from server on failure; grid toggles always visible; connection rows get clear-✕ for stale error banners. - Combo editor: on desktop (xl+) the Add-Model picker opens as a floating side panel beside the untouched combo popup instead of stacking on top; mobile keeps the full-screen overlay. - Long API-key overflow fixed in key rows + provider model sections.
97 lines
3.9 KiB
JavaScript
97 lines
3.9 KiB
JavaScript
// OpenAI-compatible error types mapping (client-facing)
|
|
export const ERROR_TYPES = {
|
|
400: { type: "invalid_request_error", code: "bad_request" },
|
|
401: { type: "authentication_error", code: "invalid_api_key" },
|
|
402: { type: "billing_error", code: "payment_required" },
|
|
403: { type: "permission_error", code: "insufficient_quota" },
|
|
404: { type: "invalid_request_error", code: "model_not_found" },
|
|
406: { type: "invalid_request_error", code: "model_not_supported" },
|
|
429: { type: "rate_limit_error", code: "rate_limit_exceeded" },
|
|
500: { type: "server_error", code: "internal_server_error" },
|
|
502: { type: "server_error", code: "bad_gateway" },
|
|
503: { type: "server_error", code: "service_unavailable" },
|
|
504: { type: "server_error", code: "gateway_timeout" }
|
|
};
|
|
|
|
// Default error messages per status code (client-facing)
|
|
export const DEFAULT_ERROR_MESSAGES = {
|
|
400: "Bad request",
|
|
401: "Invalid API key provided",
|
|
402: "Payment required",
|
|
403: "You exceeded your current quota",
|
|
404: "Model not found",
|
|
406: "Model not supported",
|
|
429: "Rate limit exceeded",
|
|
500: "Internal server error",
|
|
502: "Bad gateway - upstream provider error",
|
|
503: "Service temporarily unavailable",
|
|
504: "Gateway timeout"
|
|
};
|
|
|
|
// Exponential backoff config for rate limits
|
|
export const BACKOFF_CONFIG = {
|
|
base: 2000,
|
|
max: 5 * 60 * 1000,
|
|
maxLevel: 15
|
|
};
|
|
|
|
// Default cooldown for transient/unknown errors
|
|
export const TRANSIENT_COOLDOWN_MS = 30 * 1000;
|
|
|
|
// Hard cap for provider-reported rate limit cooldown (e.g. codex resets_at can be 5-6h)
|
|
export const MAX_RATE_LIMIT_COOLDOWN_MS = 30 * 60 * 1000;
|
|
|
|
// Cooldown durations (ms)
|
|
const COOLDOWN = {
|
|
long: 2 * 60 * 1000,
|
|
short: 5 * 1000,
|
|
};
|
|
|
|
/**
|
|
* Unified error classification rules.
|
|
* Checked top-to-bottom: text rules first (by order), then status rules.
|
|
* Each rule: { text?, status?, cooldownMs?, backoff? }
|
|
* - text: substring match (case-insensitive) on error message
|
|
* - status: HTTP status code match
|
|
* - cooldownMs: fixed cooldown duration
|
|
* - backoff: true = use exponential backoff (rate limit)
|
|
*/
|
|
export const ERROR_RULES = [
|
|
// --- Text-based rules (checked first, order = priority) ---
|
|
{ text: "no credentials", cooldownMs: COOLDOWN.long },
|
|
{ text: "request not allowed", cooldownMs: COOLDOWN.short },
|
|
{ text: "improperly formed request", cooldownMs: COOLDOWN.long },
|
|
{ text: "rate limit", backoff: true },
|
|
{ text: "too many requests", backoff: true },
|
|
{ text: "quota exceeded", backoff: true },
|
|
{ text: "capacity", backoff: true },
|
|
{ text: "overloaded", backoff: true },
|
|
|
|
// --- Status-based rules (fallback when text doesn't match) ---
|
|
{ status: 401, cooldownMs: COOLDOWN.long },
|
|
{ status: 402, cooldownMs: COOLDOWN.long },
|
|
{ status: 403, cooldownMs: COOLDOWN.long },
|
|
{ status: 404, cooldownMs: COOLDOWN.long },
|
|
{ status: 429, backoff: true },
|
|
// --- Request-scoped errors: the request itself is broken — retrying the same
|
|
// body on another account/model can never succeed, and locking the account
|
|
// would punish a healthy credential for our own bad request. Callers use this
|
|
// to fail fast (no account rotation, no model lock).
|
|
{ text: "context_length_exceeded", requestScoped: true },
|
|
{ text: "context window", requestScoped: true },
|
|
{ text: "maximum context length", requestScoped: true },
|
|
{ text: "prompt is too long", requestScoped: true },
|
|
{ text: "input is too long", requestScoped: true },
|
|
{ text: "max_tokens exceed", requestScoped: true },
|
|
{ text: "reduce the length", requestScoped: true },
|
|
];
|
|
|
|
// Backward compat: COOLDOWN_MS object (used by index.js re-export)
|
|
export const COOLDOWN_MS = {
|
|
unauthorized: COOLDOWN.long,
|
|
paymentRequired: COOLDOWN.long,
|
|
notFound: COOLDOWN.long,
|
|
transient: TRANSIENT_COOLDOWN_MS,
|
|
requestNotAllowed: COOLDOWN.short,
|
|
};
|