UNPKG

@bitkyc08/opencodex

Version:

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

167 lines (146 loc) • 7.86 kB
import { isOpenCodeGoGeminiDestination, OPENCODE_GO_BASE_URL, OPENCODE_GO_MODEL_WIRES, OPENCODE_GO_LEGACY_NAME_PINS, type OpenCodeGoDestination } from "./opencode-go"; import { openCodeZenBaseUrl, openCodeZenKeyBaseUrl, type OpenCodeZenDestination } from "./opencode-zen"; /** * Accepted values for the per-provider upstream HTTP-version pin (#1668). Shared by the * zod load schema, the management write boundary (POST/PATCH), and the fetch runtime, so * a value that one boundary accepts can never be rejected by another. */ export const UPSTREAM_HTTP_VERSION_VALUES = [ "auto", "http1.1", "h1", "http2", "h2", ] as const; export type UpstreamHttpVersion = (typeof UPSTREAM_HTTP_VERSION_VALUES)[number]; export const REASONING_SUMMARY_DELIVERY_VALUES = [ "sequential", "sequential_cutoff", "concurrent", "concurrent_cutoff", ] as const; export type ReasoningSummaryDelivery = typeof REASONING_SUMMARY_DELIVERY_VALUES[number]; /** * Anthropic adaptive `thinking.display` policy (#8363). `auto` is the built-in behavior: * native Opus 5.5 progress updates, summarized thinking elsewhere unless the caller hides it. * `updates` is only sendable to native Opus 5.5 and degrades to `auto` for every other model. * `omitted` sends adaptive thinking with no display field, matching hidden thinking. */ export const THINKING_DISPLAY_VALUES = ["auto", "summarized", "updates", "omitted"] as const; export type ThinkingDisplayPolicy = (typeof THINKING_DISPLAY_VALUES)[number]; /** Trusted runtime ownership for Codex-account credentials. Never persisted per provider. */ export type CodexAccountMode = "direct" | "pool"; export const OPENAI_PROVIDER_TIER_VERSION = 2 as const; /** * Wires that a per-model `modelAdapters` override may select. * * Deliberately narrow: provider-specific adapters (cursor, kiro, google, ...) carry * their own credential and base-URL semantics, so exposing them here would widen the * auth boundary rather than pick a wire. Widening this set needs a per-adapter * credential threat model first (#404). */ export const MODEL_ADAPTER_OVERRIDE_ALLOWED: ReadonlySet<string> = new Set([ "openai-chat", "openai-responses", ]); /** Native Go wire pins share the exact-model table with registry Responses defaults. */ export function captureWireAdapterHardPins(providerName: string, provider?: WirePinProvider): Readonly<Record<string, string>> { if (providerName !== "opencode-go") return Object.freeze({}); // The existing Go preset pins saved URLs to this endpoint before dispatch. Pure policy // captures must use that same destination even when handed an unnormalized config row. const destination = provider && { ...provider, baseUrl: OPENCODE_GO_BASE_URL }; return Object.freeze(Object.fromEntries(Object.entries(OPENCODE_GO_MODEL_WIRES).filter(([modelId, wire]) => (wire === "anthropic" && OPENCODE_GO_LEGACY_NAME_PINS.has(modelId)) || (wire !== "openai-responses" && isOpenCodeGoGeminiDestination(destination)), ))); } interface WirePinPrefixRule { /** The registry endpoint the rule describes; another destination under the same name is not covered. */ readonly endpoint: string; readonly prefixes: Readonly<Record<string, string>>; } /** * Provider-local model-id prefixes whose upstream accepts only one wire, bound to the endpoint that * behaves that way. Command Code's Provider API serves `claude-*` ids only on `/provider/v1/messages` * (live `supported_endpoints` on 2026-09-23 list `/messages` alone; `/chat/completions` answers 400 * "must be called via /provider/v1/messages"). A prefix covers Claude ids Command Code adds later. */ const WIRE_ADAPTER_PIN_PREFIXES: Readonly<Record<string, WirePinPrefixRule>> = Object.freeze({ commandcode: Object.freeze({ endpoint: "https://api.commandcode.ai/provider/v1", prefixes: Object.freeze({ "claude-": "anthropic" }), }), // TokenLab declares Claude ids as Chat + Anthropic Messages, never Responses // (`tokenlab.accepted_request_formats` on GET /v1/models/{id}, all 11 live claude-* ids on // 2026-09-30). Messages is their native wire; POST /v1/messages accepts x-api-key. tokenlab: Object.freeze({ endpoint: "https://api.tokenlab.sh/v1", prefixes: Object.freeze({ "claude-": "anthropic" }), }), }); /** Just enough of a provider config to tell whether it still points at the pinned endpoint. */ export interface WirePinProvider extends OpenCodeGoDestination, OpenCodeZenDestination {} function normalizedEndpoint(value: unknown): string | undefined { if (typeof value !== "string") return undefined; try { const url = new URL(value.trim()); return `${url.protocol}//${url.host}${url.pathname.replace(/\/+$/, "")}`.toLowerCase(); } catch { return undefined; } } /** * Providers whose adapter is their credential boundary: the adapter alone pins the destination and * the auth header for an account token. No model may switch wires, whatever `baseUrl` or the row's * own `adapter` says, because a generic wire would send that token as a Bearer key to the configured * URL. The empty prefix covers every model id. */ const CREDENTIAL_PINNED_ADAPTERS: Readonly<Record<string, Readonly<Record<string, string>>>> = Object.freeze({ "workbuddy-ai": Object.freeze({ "": "workbuddy-ai" }), "dsh-account": Object.freeze({ "": "dsh-account" }), "m365-copilot": Object.freeze({ "": "m365-copilot" }), }); function prefixPinsFor(providerName: string, provider: WirePinProvider | undefined): Readonly<Record<string, string>> | undefined { if (Object.hasOwn(CREDENTIAL_PINNED_ADAPTERS, providerName)) return CREDENTIAL_PINNED_ADAPTERS[providerName]; if (providerName === "opencode-zen" && openCodeZenKeyBaseUrl(provider)) { return openCodeZenBaseUrl(provider) ? { "gemini-": "google", "claude-": "anthropic" } : { "claude-": "anthropic" }; } if (!provider || !Object.hasOwn(WIRE_ADAPTER_PIN_PREFIXES, providerName)) return undefined; const rule = WIRE_ADAPTER_PIN_PREFIXES[providerName]!; return normalizedEndpoint(provider.baseUrl) === rule.endpoint ? rule.prefixes : undefined; } /** * Detached provider-local prefix pins for pure wire-policy resolution. Empty unless the provider * still points at the endpoint the rule describes. */ export function captureWireAdapterHardPinPrefixes( providerName: string, provider: WirePinProvider | undefined, ): Readonly<Record<string, string>> { return Object.freeze({ ...(prefixPinsFor(providerName, provider) ?? {}) }); } function prefixedWireAdapter(providerName: string, modelId: string, provider: WirePinProvider | undefined): string | undefined { const prefixes = prefixPinsFor(providerName, provider); if (!prefixes) return undefined; const folded = modelId.toLowerCase(); for (const [prefix, adapter] of Object.entries(prefixes)) { if (folded.startsWith(prefix)) return adapter; } return undefined; } /** * True when the upstream speaks exactly one wire for this model, so a configured * override must not apply. * * Deliberately independent of the provider's current adapter: the wire resolver runs * more than once per request, and a check phrased as "pin differs from the current * adapter" would pass on the first pass and then let the override win on the second. */ export function isWirePinnedModel(providerName: string, modelId: string, provider?: WirePinProvider): boolean { return pinnedWireAdapter(providerName, modelId, provider) !== undefined; } /** The wire a pinned model must use, or undefined when the model is not pinned. */ export function pinnedWireAdapter(providerName: string, modelId: string, provider?: WirePinProvider): string | undefined { const pins = captureWireAdapterHardPins(providerName, provider); return Object.hasOwn(pins, modelId) ? pins[modelId] : prefixedWireAdapter(providerName, modelId, provider); }