mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-26 09:02:11 +03:00
7cfabfc5c9
Validated in a combined 3-PR batch worktree off release/v3.8.51 tip (a sibling PR from the same author, #11495, was held out — a typecheck error in zai-web.ts only reproduced with this PR + #11495 boarded together, and cleared without #11495; isolated this PR alone confirmed clean on its own too, so the interaction belonged to #11495's side — see its comment). - Golden lock: executor-map-golden.test.ts — passes byte-identical (same keys, classes, provider identities, dispatch guards) - Focused tests part of batch's 94/94 node:test run - typecheck:core, file-size, changelog-integrity, complexity, cognitive-complexity — all OK - Full-repo lint: 228 pre-existing dashboard react-hooks/* findings, unrelated to this diff Thanks for the measured, careful methodology here — the golden-lock contract plus the isolated DATA_DIR benchmarking make this an easy PR to trust despite the wide surface (72 files).
46 lines
2.1 KiB
TypeScript
46 lines
2.1 KiB
TypeScript
import { getExecutor } from "../../../executors/index.ts";
|
|
import type { ExecuteInput, ProviderCredentials } from "../../../executors/base.ts";
|
|
import type { ChatTurn, ModelCallResult, ModelClient } from "./types.ts";
|
|
|
|
/**
|
|
* Production ModelClient adapter (Hard Rule #18 — NOT unit-tested; validated on a real
|
|
* VPS/account). Wraps the server executor: builds a minimal non-stream chat body, calls
|
|
* `getExecutor(provider).execute(...)`, reads the response text + (best-effort) usage cost.
|
|
*
|
|
* The pure runner depends only on the `ModelClient` interface; this adapter is the single
|
|
* place that touches credentials, the executor, and Response parsing — so the eval stays
|
|
* faithful to production while the runner/scorers remain fully testable with a stub.
|
|
*/
|
|
export function createExecutorModelClient(
|
|
provider: string,
|
|
credentials: ProviderCredentials,
|
|
costPerKTokenOut?: number
|
|
): ModelClient {
|
|
return {
|
|
async complete(model: string, messages: ChatTurn[]): Promise<ModelCallResult> {
|
|
// #11220: getExecutor is async (lazy registry) — resolve per call.
|
|
const executor = await getExecutor(provider);
|
|
const body = { model, messages, stream: false };
|
|
const input: ExecuteInput = {
|
|
model,
|
|
body,
|
|
stream: false,
|
|
credentials,
|
|
};
|
|
// BaseExecutor.execute resolves to { response, url, headers, transformedBody } — the
|
|
// upstream Response lives on `.response` (never a bare Response). Validated live on VPS.
|
|
const raw = (await executor.execute(input)) as { response: Response };
|
|
const response = raw.response;
|
|
const json = (await response.json()) as {
|
|
choices?: Array<{ message?: { content?: string } }>;
|
|
usage?: { completion_tokens?: number };
|
|
};
|
|
const text = json.choices?.[0]?.message?.content ?? "";
|
|
const outTokens = json.usage?.completion_tokens ?? 0;
|
|
const usdCost =
|
|
typeof costPerKTokenOut === "number" ? (outTokens / 1000) * costPerKTokenOut : undefined;
|
|
return usdCost === undefined ? { text } : { text, usdCost };
|
|
},
|
|
};
|
|
}
|