@bitkyc08/opencodex
Version:
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM with Codex CLI/App/SDK and Claude Code
175 lines (162 loc) • 7.49 kB
text/typescript
/**
* OpenCode Zen short-window rate-limit guidance (#1145 / OCX-56).
*
* OpenCode's keyed Zen chat endpoint uses `https://opencode.ai/zen/v1`.
* Free-model traffic can hit a short-window burst ceiling around 15–20 RPM
* (community-measured). Zen often answers with opaque `429 Rate limit exceeded`
* bodies and may omit `Retry-After` / `X-RateLimit-*`; when those headers are
* present they still take precedence.
*/
import { validateClientRetryAfterHeader } from "../lib/retry-after";
import { registryEntryForProviderDestination } from "./registry";
const OPENCODE_ZEN_PROVIDER_IDS = new Set(["opencode-zen"]);
/** Observed free-model burst ceiling on Zen (not an official OpenCode figure). */
export const OPENCODE_ZEN_OBSERVED_RPM_HINT = "roughly 15-20 requests per minute";
/**
* Synthetic client backoff when Zen omits Retry-After after a rate-limit 429.
* Longer than the generic 2s default so Codex-shaped clients do not immediately
* re-hammer a ~15-20 RPM window.
*/
export const OPENCODE_ZEN_SYNTHETIC_RETRY_AFTER_SEC = 15;
const ENRICHMENT_MARKER = "15-20 requests per minute";
export function isOpenCodeZenRateLimitProvider(opts: {
providerName?: string;
baseUrl?: string;
adapter?: string;
}): boolean {
const name = opts.providerName?.trim();
if (name && OPENCODE_ZEN_PROVIDER_IDS.has(name)) return true;
const baseUrl = opts.baseUrl?.trim();
if (!baseUrl) return false;
const entry = registryEntryForProviderDestination({
baseUrl,
adapter: opts.adapter?.trim() || "openai-chat",
authMode: "key",
});
return entry !== undefined && OPENCODE_ZEN_PROVIDER_IDS.has(entry.id);
}
/**
* Same-key `retryOn429` only applies on key-authenticated HTTP paths — not
* keyless traffic and not custom `runTurn` transports.
*/
export function supportsOpenCodeZenRetryOn429Guidance(opts: {
authMode?: string;
hasApiKey?: boolean;
supportsHttpSameKeyRetry?: boolean;
}): boolean {
if (opts.supportsHttpSameKeyRetry === false) return false;
if (opts.authMode !== undefined && opts.authMode !== "key") return false;
return opts.hasApiKey === true;
}
/**
* Append actionable Zen rate-limit context to a generic upstream 429 message and
* embed a parseable `try again in Ns` hint so {@link resolveClientRetryAfter}
* surfaces a useful Retry-After when the gateway sent none.
*/
export function enrichOpenCodeZenRateLimitMessage(
message: string,
opts: {
status: number;
/** Parsed upstream error type, when available. */
upstreamErrorType?: string | null;
upstreamErrorCode?: string | null;
providerName?: string;
baseUrl?: string;
adapter?: string;
authMode?: string;
hasApiKey?: boolean;
/** Upstream Retry-After header; when valid, skip the synthetic 15s text hint. */
upstreamRetryAfter?: string | null;
/** False for custom `runTurn` transports outside the HTTP retry loop. */
supportsHttpSameKeyRetry?: boolean;
now?: number;
},
): string {
if (opts.status !== 429) return message;
if (!isOpenCodeZenRateLimitProvider(opts)) return message;
const errorText = `${opts.upstreamErrorType ?? ""} ${opts.upstreamErrorCode ?? ""} ${message}`.replace(/[_-]/g, " ");
if (/\b(?:quota|billing)\b|\busage\s+limit\b|\binsufficient\s+(?:credits?|balance|funds)\b|\b(?:credits?|balance)\s+(?:exhausted|depleted)\b/i.test(errorText)) return message;
if (opts.upstreamErrorType !== "rate_limit_error" && !/rate\s*limit/i.test(message)) return message;
if (message.includes(ENRICHMENT_MARKER)) return message;
const upstreamRetry = validateClientRetryAfterHeader(
opts.upstreamRetryAfter,
opts.now ?? Date.now(),
);
const retryHint = upstreamRetry || /try again in \d/i.test(message)
? ""
: ` Try again in ${OPENCODE_ZEN_SYNTHETIC_RETRY_AFTER_SEC}s.`;
const paceHint = supportsOpenCodeZenRetryOn429Guidance(opts)
? " Slow the request pace, or set providers.opencode-zen.retryOn429 for same-key backoff."
: " Slow the request pace.";
return (
`${message}`
+ ` OpenCode Zen free-model traffic is often limited to ${OPENCODE_ZEN_OBSERVED_RPM_HINT}`
+ ` (observed; OpenCode does not publish this RPM, and may omit rate-limit headers).`
+ `${retryHint}`
+ paceHint
);
}
/**
* Zen upstream-error guidance on Responses and native Messages.
*/
export function enrichOpenCodeZenUpstreamMessage(
message: string,
opts: Parameters<typeof enrichOpenCodeZenRateLimitMessage>[1] & { upstreamErrorType?: string | null },
): string {
return enrichOpenCodeZenRateLimitMessage(message, opts);
}
/** The effective HTTP endpoint, never the configured row name, identifies Console. */
export function isConsoleGoDestination(outboundUrl: string | undefined): boolean {
if (!outboundUrl) return false;
try {
const url = new URL(outboundUrl);
return url.protocol === "https:" && url.hostname === "opencode.ai"
&& url.port === "" && url.username === "" && url.password === ""
&& url.search === "" && url.hash === ""
&& /^\/zen\/(?:go\/)?v1\/(?:responses|chat\/completions|messages)$/.test(url.pathname);
} catch {
return false;
}
}
/**
* The canonical refusal envelope, as served on both Console routes:
* {"error":{"param":null,"type":"invalid_request_error","message":"Error from provider
* (Console Go): Upstream request failed: [invalid_request_error] Invalid upload request."}}
*
* The gateway names itself Console on the Zen key route and Console Go on the Go route, so the
* anchor is the shared product name plus the refusal sentence. The message is matched whole: a
* bare string, a suffix, or any other envelope is a different refusal and must not be replayed.
* Being stricter than necessary is the safe direction: a missed match leaves the turn failing
* exactly as it does today, while a loose match spends an extra request on unrelated 400s.
*/
const CONSOLE_UPLOAD_REFUSALS = new Set([
"Error from provider (Console Go): Upstream request failed: [invalid_request_error] Invalid upload request.",
"Error from provider (Console): Upstream request failed: [invalid_request_error] Invalid upload request.",
]);
/**
* True only for the canonical Console upload refusal on a canonical Console destination.
* Route-gated on purpose: the message alone would let any other upstream that happens to answer
* with this English sentence trigger a second send from an unrelated provider.
*/
export function isTransientConsoleGoUploadRejection(opts: {
status: number;
errorBody: string | undefined;
outboundUrl?: string;
}): boolean {
if (opts.status !== 400 || !opts.errorBody) return false;
if (!isConsoleGoDestination(opts.outboundUrl)) return false;
let payload: unknown;
try {
payload = JSON.parse(opts.errorBody);
} catch {
return false;
}
const error = (payload as { error?: unknown } | null)?.error;
if (!error || typeof error !== "object" || Array.isArray(error)) return false;
// The whole envelope, not just the sentence: Console always answers this refusal as
// invalid_request_error with a null param, so a partial envelope is a different error.
const envelope = error as { param?: unknown; type?: unknown; message?: unknown };
if (envelope.type !== "invalid_request_error" || envelope.param !== null) return false;
// Matched without trimming: padding means the gateway wrapped or appended something.
return typeof envelope.message === "string" && CONSOLE_UPLOAD_REFUSALS.has(envelope.message);
}