@bitkyc08/opencodex
Version:
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM with Codex CLI/App/SDK and Claude Code
344 lines (315 loc) • 17.8 kB
text/typescript
import { parseUpstreamJsonPayload, safeUpstreamErrorString, sanitizeUpstreamErrorText } from "./upstream-http-error";
import { isLocationUnsupportedMessage } from "../lib/errors";
import { googleErrorDetails, isAntigravityTosViolationBody } from "./google-error-details";
export const ANTIGRAVITY_VALIDATION_REQUIRED_PREFIX = "Antigravity account validation required (VALIDATION_REQUIRED)";
/** Leading words of every normalized Antigravity 403 that is not a validation demand (see `classifyGoogle`). */
export const ANTIGRAVITY_ACCESS_DENIED_PREFIX = "Antigravity access denied";
/** Leading words of a normalized Antigravity refusal whose text names the credential itself. */
export const ANTIGRAVITY_AUTH_FAILED_PREFIX = "Antigravity authentication failed";
/**
* Written right after a normalized prefix only when the response carried Google's structured
* `error.status: "PERMISSION_DENIED"`. Message wording alone never produces it, so a reader of the
* normalized string can tell a refusal Google attributed to the account from a proxy page or an
* enum-less envelope that merely says "expired".
*/
export const GOOGLE_PERMISSION_DENIED_SUFFIX = " (PERMISSION_DENIED)";
/** Emitted only for a body `isAntigravityTosViolationBody` accepts; dispatch trusts nothing else. */
export const ANTIGRAVITY_TOS_VIOLATION_PREFIX = "Antigravity account suspended (TOS_VIOLATION)";
const ANTIGRAVITY_TOS_VIOLATION_MESSAGE = "Google disabled this account for a Terms of Service violation; appeal with Google, then sign in again";
function hasAntigravityValidationReason(payloadText: string): boolean {
const payload = parseUpstreamJsonPayload(payloadText);
if (!payload || typeof payload !== "object" || Array.isArray(payload)) return false;
const error = (payload as { error?: unknown }).error;
if (!error || typeof error !== "object" || Array.isArray(error)) return false;
const details = (error as { details?: unknown }).details;
return Array.isArray(details) && details.some(detail =>
detail !== null && typeof detail === "object" && !Array.isArray(detail)
&& (detail as { reason?: unknown }).reason === "VALIDATION_REQUIRED");
}
/** Pull the human detail out of the Google API error envelope `{error:{message,status,code}}`. */
function googleErrorDetail(payloadText: string): { message?: string; status?: string } {
const trimmed = payloadText.trim();
if (!trimmed || (!trimmed.startsWith("{") && !trimmed.startsWith("["))) {
return { message: trimmed || undefined };
}
const parsed = parseUpstreamJsonPayload(trimmed);
if (!parsed || typeof parsed !== "object" || Array.isArray(parsed)) return {};
const err = (parsed as { error?: { message?: unknown; status?: unknown } }).error;
return {
message: safeUpstreamErrorString(err?.message),
status: safeUpstreamErrorString(err?.status),
};
}
const GOOGLE_QUOTA_EXHAUSTED_NEEDLES = [
"quotafailure",
"quota exceeded",
"exceeded your current quota",
"billing",
"individual quota reached",
"quota reached",
"enable overages",
"exhausted your capacity",
"daily limit reached",
"weekly limit reached",
];
// Per-minute / per-second / concurrency limits are transient rate limits: they should be
// retried, not treated as hard quota exhaustion. These guards run before the needles so a
// message like "Per-minute quota exceeded" stays in the retryable bucket.
const GOOGLE_TRANSIENT_RATE_LIMIT_PATTERNS = [
"per minute",
"per-minute",
"per min",
"rpm",
"requests per minute",
"too many requests",
"rate limit",
"retry after",
// Upstream writes the header name both ways in prose ("retry-after: 60"); matching only the
// spaced spelling let a transient 429 fall through to the exhaustion needles below.
"retry-after",
"concurrent request limit",
];
/** Whether the text names a transient rate limit rather than hard quota exhaustion. */
export function isGoogleTransientRateLimitText(text: string): boolean {
const lower = text.toLowerCase();
return GOOGLE_TRANSIENT_RATE_LIMIT_PATTERNS.some(needle => lower.includes(needle));
}
export function isGoogleQuotaExhaustedText(text: string): boolean {
const lower = text.toLowerCase();
if (GOOGLE_TRANSIENT_RATE_LIMIT_PATTERNS.some(needle => lower.includes(needle))) return false;
return GOOGLE_QUOTA_EXHAUSTED_NEEDLES.some(needle => lower.includes(needle));
}
/**
* `ErrorInfo.reason` values that make a 429 a rate/quota signal the retry ladder may wait out.
* Google writes these into `error.details[]`; Cloud Code Assist answers a genuine capacity 429
* with `reason: "RATE_LIMIT_EXCEEDED"` and answers a request-shape/policy rejection with no
* `details` at all.
*/
const GOOGLE_RETRYABLE_429_ERROR_REASONS: Record<string, true> = {
RATE_LIMIT_EXCEEDED: true,
QUOTA_EXCEEDED: true,
RATE_LIMIT_EXCEEDED_MODEL: true,
};
/** Narrow a JSON value to a plain object without asserting a shape it may not have. */
function jsonRecord(value: unknown): Record<string, unknown> | undefined {
return value && typeof value === "object" && !Array.isArray(value)
? (value as Record<string, unknown>)
: undefined;
}
/** ProtoJSON type of a detail whose `reason` field carries an `ErrorInfo` verdict. */
const GOOGLE_ERROR_INFO_TYPE = "google.rpc.ErrorInfo";
/** ProtoJSON type of a detail whose `retryDelay` field states when to retry. */
const GOOGLE_RETRY_INFO_TYPE = "google.rpc.RetryInfo";
/**
* Whether a detail's declared `@type` admits `expected`.
*
* ProtoJSON spells a type either fully qualified (`type.googleapis.com/google.rpc.ErrorInfo`) or as
* the bare message name; both name the same message, and only the last path segment carries the
* identity. Suffix matching alone would accept a foreign `type.example.com/relay.google.rpc.ErrorInfo`,
* so the segment is compared whole. A detail with no `@type` asserts nothing and admits both.
*/
function detailTypeMatches(record: Record<string, unknown>, expected: string): boolean {
if (!Object.hasOwn(record, "@type")) return true;
const declared = record["@type"];
if (typeof declared !== "string") return false;
const segment = declared.slice(declared.lastIndexOf("/") + 1);
return segment === expected;
}
/**
* The `error` envelope of a Google error payload, or `undefined` when the text is not JSON.
*
* `error` is normally an object, but both the retry-delay extractor and Google's own fixtures
* accept the array spelling, so every reader here unwraps `error[0]` the same way rather than
* disagreeing about which payloads count as evidence.
*/
function googleErrorEnvelope(payloadText: string): Record<string, unknown> | undefined {
const trimmed = payloadText.trim();
if (!trimmed.startsWith("{") && !trimmed.startsWith("[")) return undefined;
const parsed = jsonRecord(parseUpstreamJsonPayload(trimmed));
if (!parsed) return undefined;
const error = parsed.error;
if (Array.isArray(error)) return jsonRecord(error[0]) ?? parsed;
return jsonRecord(error) ?? parsed;
}
/** Every `error.details[].reason` in a Google error envelope, in payload order. */
function googleErrorReasons(payloadText: string): string[] {
const details = googleErrorEnvelope(payloadText)?.details;
if (!Array.isArray(details)) return [];
const reasons: string[] = [];
for (const detail of details) {
const record = jsonRecord(detail);
if (!record) continue;
// `@type` names which protobuf message owns this object. A detail that declares a different
// message may carry an unrelated field spelled `reason`, so only an `ErrorInfo` detail (or one
// with no `@type` to contradict it) speaks for the rate-limit verdict.
if (!detailTypeMatches(record, GOOGLE_ERROR_INFO_TYPE)) continue;
const reason = safeUpstreamErrorString(record.reason);
if (reason) reasons.push(reason);
}
return reasons;
}
function isGoogleRetryDuration(value: unknown): boolean {
return typeof value === "string" && /^\s*\d+(?:\.\d+)?\s*s\s*$/i.test(value);
}
/**
* Whether a detail states a wait, including an explicit `0s`.
*
* `extractGoogleRetryAfterSeconds` drops `0s` because it answers "how long should the caller
* wait", and a zero there is no instruction. For eligibility the question is different: the
* provider named a wait at all, which says the refusal is a rate signal rather than a verdict on
* the request's shape. Local backoff still supplies the actual delay.
*/
function hasGoogleRetryDelayDetail(payloadText: string): boolean {
const details = googleErrorEnvelope(payloadText)?.details;
if (!Array.isArray(details)) return false;
for (const detail of details) {
const record = jsonRecord(detail);
if (!record) continue;
if (detailTypeMatches(record, GOOGLE_RETRY_INFO_TYPE) && isGoogleRetryDuration(record.retryDelay)) return true;
const metadata = jsonRecord(record.metadata);
if (detailTypeMatches(record, GOOGLE_ERROR_INFO_TYPE) && isGoogleRetryDuration(metadata?.quotaResetDelay)) return true;
}
return false;
}
/**
* The text a message-level needle may match: the decoded `error.message` and enum status for
* JSON, the whole payload for non-JSON.
*
* Reading the raw JSON would let any string inside it authorize a replay — a `BadRequest` field
* violation whose description quotes "rate limit" is part of a request-shape verdict, not a rate
* signal, and matching it re-enables exactly the futile replay this gate exists to stop.
*/
function googleMessageText(payloadText: string): string {
const trimmed = payloadText.trim();
if (!trimmed.startsWith("{") && !trimmed.startsWith("[")) return trimmed;
const envelope = googleErrorEnvelope(trimmed);
if (!envelope) return "";
return [safeUpstreamErrorString(envelope.message), safeUpstreamErrorString(envelope.status)]
.filter((part): part is string => typeof part === "string")
.join(" ");
}
/**
* Message wording that is evidence for a replay but must not change quota classification.
*
* Google's documented 429 for pay-as-you-go capacity is "Resource exhausted. Please try again
* later." — no header, no details, no rate-limit wording. Treating it as a general transient
* pattern would also veto hard-quota classification for every body that says it, so it is scoped
* to the evidence predicate instead.
*/
const GOOGLE_RETRYABLE_429_MESSAGE_NEEDLES = [
"try again later",
];
/**
* Whether a 429 says anything a replay can act on.
*
* The ladder replays a byte-identical body after 250 ms, doubling to 2 s. That is a sensible
* probe for a burst limit that clears, and meaningless for a refusal Google already made on the
* request's shape: the same bytes are refused again. Only evidence in the response separates
* the two. When there is no validated Retry-After, check for a typed delay detail, a
* transient rate-limit phrase, or a structured `ErrorInfo.reason` before replaying.
*
* Observed Cloud Code Assist shapes behind this split (same account, minutes apart):
* - capacity: `RESOURCE_EXHAUSTED` / "You have exhausted your capacity on this model. Resets in
* 0s." with `details[].reason: "RATE_LIMIT_EXCEEDED"` — already hard-quota classified, and
* evidence-bearing if it ever is not;
* - request-shape rejection: `RESOURCE_EXHAUSTED` / "Resource has been exhausted (e.g. check
* quota)." with no `details`, no `Retry-After` — replayed three times per turn, refused three
* times per turn.
*/
export function hasGoogle429BodyRetryEvidence(payloadText: string): boolean {
if (hasGoogleRetryDelayDetail(payloadText)) return true;
const messageText = googleMessageText(payloadText).toLowerCase();
if (isGoogleTransientRateLimitText(messageText)) return true;
if (GOOGLE_RETRYABLE_429_MESSAGE_NEEDLES.some(needle => messageText.includes(needle))) return true;
return googleErrorReasons(payloadText).some(reason => GOOGLE_RETRYABLE_429_ERROR_REASONS[reason] === true);
}
function classifyGoogle(label: string, status: number | undefined, enumStatus: string | undefined, text: string, reason?: string): string {
// Structured reasons outrank prose. Quota exhaustion is the same contract on every Google
// surface; RATE_LIMIT_EXCEEDED overrides quota-like prose only on Antigravity, as CPA reads it.
if (reason === "QUOTA_EXHAUSTED" || reason === "INSUFFICIENT_G1_CREDITS_BALANCE") return `${label} quota exhausted`;
if (reason === "RATE_LIMIT_EXCEEDED" && label === "Antigravity") return `${label} rate limit exceeded`;
const lower = `${enumStatus ?? ""} ${text}`.toLowerCase();
const quotaExhausted = isGoogleQuotaExhaustedText(lower);
if ((!enumStatus || enumStatus === "RESOURCE_EXHAUSTED") && quotaExhausted) return `${label} quota exhausted`;
if (status === 429 || enumStatus === "RESOURCE_EXHAUSTED" || lower.includes("rate limit")) {
return `${label} rate limit exceeded`;
}
if (status === 401 || enumStatus === "UNAUTHENTICATED" || lower.includes("unauthenticated") || lower.includes("invalid authentication") || lower.includes("expired")) {
// Keep the enum here too: the access-denial recovery accepts this wording only under it.
return `${label} authentication failed${enumStatus === "PERMISSION_DENIED" ? GOOGLE_PERMISSION_DENIED_SUFFIX : ""}`;
}
// Keep Google's explicit enum in the normalized text. Responses/combo handling receives
// only this string, so dropping it would let location wording override the authoritative
// permission reason during downstream classification.
if (enumStatus === "PERMISSION_DENIED") {
return `${label} access denied${GOOGLE_PERMISSION_DENIED_SUFFIX}`;
}
if (status === 403 || lower.includes("permission_denied") || lower.includes("permission denied") || lower.includes("access denied")) {
return `${label} access denied`;
}
// Google rejects unsupported geographic / datacenter locations with HTTP 400
// FAILED_PRECONDITION. The payload is not malformed, so it must not fall through to
// "invalid request" (#3467). Only the observed 400/precondition envelope permits
// this inference; other explicit enums and server statuses remain authoritative.
if (status === 400 && (!enumStatus || enumStatus === "FAILED_PRECONDITION") && isLocationUnsupportedMessage(lower)) {
return `${label} location not supported`;
}
if (status === 503 || enumStatus === "UNAVAILABLE" || lower.includes("overloaded") || lower.includes("unavailable")) {
return `${label} server overloaded`;
}
if (status === 400 || status === 404 || enumStatus === "INVALID_ARGUMENT" || enumStatus === "NOT_FOUND" || lower.includes("invalid") || lower.includes("not found") || lower.includes("malformed")) {
return `${label} invalid request`;
}
return `${label} upstream error`;
}
/**
* Normalize a Google/Vertex/Antigravity HTTP error body into a short, classified, secret-redacted
* message. Mirrors `kiro-errors.ts`. `label` is the provider-facing prefix ("Vertex AI",
* "Antigravity").
*/
export function safeGoogleHttpErrorMessage(label: string, status: number, payloadText: string): string {
// A suspension carries a fixed message: Google's text names an appeal path and the account.
if (label === "Antigravity" && status === 403 && isAntigravityTosViolationBody(payloadText)) {
return `${ANTIGRAVITY_TOS_VIOLATION_PREFIX}: ${ANTIGRAVITY_TOS_VIOLATION_MESSAGE}`;
}
const { message, status: enumStatus } = googleErrorDetail(payloadText);
const prefix = label === "Antigravity" && status === 403 && hasAntigravityValidationReason(payloadText)
? ANTIGRAVITY_VALIDATION_REQUIRED_PREFIX
: classifyGoogle(label, status, enumStatus, [message, enumStatus].filter(Boolean).join(" "), googleErrorDetails(payloadText).reason);
const detail = message ? sanitizeUpstreamErrorText(message).slice(0, 500) : `HTTP ${status}`;
return `${prefix}: ${detail}`;
}
/** Vertex AI HTTP error message (label = "Vertex AI"). */
export function safeVertexHttpErrorMessage(status: number, payloadText: string): string {
return safeGoogleHttpErrorMessage("Vertex AI", status, payloadText);
}
/** Antigravity (Cloud Code Assist) HTTP error message (label = "Antigravity"). */
export function safeAntigravityHttpErrorMessage(status: number, payloadText: string): string {
return safeGoogleHttpErrorMessage("Antigravity", status, payloadText);
}
/** Google-family retryable HTTP set (mirrors Kiro). Quota-exhausted is classified above and not retried. */
export function retryableGoogleStatus(status: number): boolean {
return status === 429 || status === 500 || status === 502 || status === 503 || status === 504;
}
/**
* True when a 429 body indicates hard quota exhaustion (not a transient rate limit). Quota
* exhaustion is generally not expected to recover for hours (AIP-194), so it must NOT be retried —
* unlike a plain rate limit. The HTTP status alone can't distinguish the two, so the retry layer
* inspects the body with this.
*/
export function isQuotaExhaustedBody(payloadText: string, label?: string): boolean {
const { reason } = googleErrorDetails(payloadText);
if (reason === "QUOTA_EXHAUSTED" || reason === "INSUFFICIENT_G1_CREDITS_BALANCE") return true;
if (reason === "RATE_LIMIT_EXCEEDED" && label === "Antigravity") return false;
const { message, status } = googleErrorDetail(payloadText);
if (status && status !== "RESOURCE_EXHAUSTED") return false;
return isGoogleQuotaExhaustedText(message ?? payloadText);
}
/**
* A server-stated retry delay in whole seconds, from RetryInfo.retryDelay, ErrorInfo.metadata.
* quotaResetDelay or a "retry after <duration>" message, in protobuf or Go duration syntax.
*/
export function extractGoogleRetryAfterSeconds(payloadText: string): string | undefined {
const ms = googleErrorDetails(payloadText).retryDelayMs;
return ms !== undefined && ms > 0 ? String(Math.ceil(ms / 1000)) : undefined;
}