@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
text/typescript
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);
}