CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-13 16:38:56 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix: default cross-model workflows to frontier models

Browse Source
This commit is contained in:
Garry Tan
2026-09-09 02:48:34 +00:00
parent 0530392821
commit 939da0c203
69 changed files with 603 additions and 255 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/eval-model.test.ts
+3 -4
View File
@@ -1,6 +1,6 @@
/** OV11: the host-neutral eval-model resolver's contract. */
import { describe, test, expect } from "bun:test";
import { resolveEvalModel } from "../lib/eval-model";
import { CLAUDE_FRONTIER_EVAL_MODEL, resolveEvalModel } from "../lib/eval-model";
describe("resolveEvalModel", () => {
test("explicit argument wins over everything", () => {
@@ -13,11 +13,10 @@ describe("resolveEvalModel", () => {
expect(resolveEvalModel("distill", null, { GSTACK_EVAL_MODEL: "g" } as never)).toBe("g");
});
test("defaults per kind", () => {
// capture defaults to Sonnet per D1a (2026-08 review): Opus is opt-in via
// explicit arg or GSTACK_EVAL_MODEL_CAPTURE.
expect(resolveEvalModel("capture", null, {} as never)).toBe("claude-sonnet-4-6");
expect(resolveEvalModel("capture", null, {} as never)).toBe(CLAUDE_FRONTIER_EVAL_MODEL);
expect(resolveEvalModel("warmup", null, {} as never)).toBe("claude-haiku-4-5");
expect(resolveEvalModel("distill", null, {} as never)).toBe("claude-haiku-4-5-20251001");
expect(resolveEvalModel("judge", null, {} as never)).toBe(CLAUDE_FRONTIER_EVAL_MODEL);
});
test("unknown kind throws instead of silently defaulting", () => {
expect(() => resolveEvalModel("banana" as never, null, {} as never)).toThrow();