UNPKG

@bitkyc08/opencodex

Version:

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM with Codex CLI/App/SDK and Claude Code

71 lines (63 loc) • 3.59 kB
import { CODEX_TEXT_GUARDED_BUDGET_POLICY, createRequestExecutionBudget, type RequestExecutionBudget } from "../../lib/request-execution-budget"; import { TRANSIENT_RETRY_MAX_ATTEMPTS, type TransientSendBudget } from "../../lib/upstream-retry"; import { GENERIC_OAUTH_MAX_ACCOUNTS_PER_REQUEST } from "../../oauth/generic-account-failover"; import type { RequestLogContext } from "../request-log"; import { attachRequestSpendTracker } from "../responses/request-spend"; import type { SpendAdmissionPolicy } from "../../lib/spend-reservation-ledger"; // Only ingress owns an expandable policy. Exact caller budgets and combo-derived scopes // never enter this map, even when their policy happens to equal the default profile. const oauthExpanded = new WeakSet<TransientSendBudget>(); const ingressPolicies = new WeakMap<TransientSendBudget, { maxTotalModelSends: number; baseSendAllowance: number; }>(); /** * The one construction of an ingress-owned send budget: the default guarded policy, no logical * request id, and this request's spend tracker as the send observer. Attaching the tracker * parks it on `logCtx`, so callers that inherit a holder must not call this at all. */ export function createInferenceSendBudget( req: Pick<Request, "headers">, logCtx: RequestLogContext, capturedPolicy?: SpendAdmissionPolicy, ): RequestExecutionBudget { const policy = { ...CODEX_TEXT_GUARDED_BUDGET_POLICY }; const budget = createRequestExecutionBudget(policy, undefined, attachRequestSpendTracker(req, logCtx, undefined, capturedPolicy)); ingressPolicies.set(budget, policy); return budget; } /** * Fund each account's normal transient ladder once, before the first physical send. The account * count is clamped here as well as at the caller, so no caller can raise the ceiling past * GENERIC_OAUTH_MAX_ACCOUNTS_PER_REQUEST × TRANSIENT_RETRY_MAX_ATTEMPTS. */ export function expandInferenceOAuthSendBudget(budget: TransientSendBudget | undefined, accounts: number): void { const fundedAccounts = Number.isSafeInteger(accounts) && accounts >= 2 ? Math.min(accounts, GENERIC_OAUTH_MAX_ACCOUNTS_PER_REQUEST) : 0; expandIngressSendBudget(budget, fundedAccounts * TRANSIENT_RETRY_MAX_ATTEMPTS); } /** Fund an explicitly configured standalone ChatGPT retry ladder before any send. */ export function fundChatGptRetryAttempts(budget: TransientSendBudget | undefined, attempts: number): void { if (Number.isInteger(attempts) && attempts > TRANSIENT_RETRY_MAX_ATTEMPTS && attempts <= 10) { expandIngressSendBudget(budget, attempts); } } function expandIngressSendBudget(budget: TransientSendBudget | undefined, sends: number): void { if (!budget) { return; } const policy = ingressPolicies.get(budget); if (!policy || oauthExpanded.has(budget) || budget.used !== 0 || ("physicalStarted" in budget && Number(budget.physicalStarted) > 0)) { return; } // One ingress expansion per request; the policy stays for the hosted-search allowance. oauthExpanded.add(budget); policy.baseSendAllowance = Math.max(policy.baseSendAllowance, sends); policy.maxTotalModelSends = Math.max(policy.maxTotalModelSends, sends); } /** Fund the hosted loop's bounded model sends before its first dispatch. */ export function expandInferenceSearchSendBudget(budget: TransientSendBudget | undefined, baseSends: number): void { const policy = budget && ingressPolicies.get(budget); if (!policy || baseSends <= policy.baseSendAllowance) return; policy.maxTotalModelSends += baseSends - policy.baseSendAllowance; policy.baseSendAllowance = baseSends; }