mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-11 23:49:01 +02:00
* fix: default cross-model workflows to frontier models * chore: bump version and changelog (v1.82.1.0) Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: repair frontier eval budgets and workflow instructions Preserve frontier models and quality thresholds while fixing truncated judge output, ordered section expansion, consent checks, QA scoring, and ship audit gates. Add regression coverage and refresh generated docs. Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: resolve workflow gaps exposed by frontier evals Clarify plan-review ordering and fallback modes, preserve deploy readiness gates, honor configured merge methods, correct benchmark and canary contracts, and restore vendored installs on setup failure. Cover recovery with real-shell regressions. Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: use agent capture budgets for deploy evals Multi-turn deploy and benchmark sessions were incorrectly limited to the single-call judge timeout. Use the existing capture tier and leave outer-test cleanup headroom, with a free policy regression test. Keep all behavioral assertions and frontier models unchanged. Co-Authored-By: OpenAI Codex <noreply@openai.com> * fix: clarify retro workflow and evaluate compare instructions Include compare mode in the frontier judge excerpt, define metric sources and snapshot ordering, and preserve the existing prompt-size budget. Co-authored-by: OpenAI Codex <noreply@openai.com> * fix: make documentation release review and publication consistent Review before commit, clarify changelog safeguards and unavailable reviewer modes, and preserve raw PR bodies across separate shell calls. Keep title sync in one shell and add regression coverage. Co-authored-by: OpenAI Codex <noreply@openai.com> --------- Co-authored-by: OpenAI Codex <noreply@openai.com>
25 lines
1.3 KiB
TypeScript
25 lines
1.3 KiB
TypeScript
/** OV11: the host-neutral eval-model resolver's contract. */
|
|
import { describe, test, expect } from "bun:test";
|
|
import { CLAUDE_FRONTIER_EVAL_MODEL, resolveEvalModel } from "../lib/eval-model";
|
|
|
|
describe("resolveEvalModel", () => {
|
|
test("explicit argument wins over everything", () => {
|
|
expect(resolveEvalModel("capture", "my-model", { GSTACK_EVAL_MODEL: "x" } as never)).toBe("my-model");
|
|
});
|
|
test("per-kind env beats the global env", () => {
|
|
expect(resolveEvalModel("warmup", null, { GSTACK_EVAL_MODEL_WARMUP: "w", GSTACK_EVAL_MODEL: "g" } as never)).toBe("w");
|
|
});
|
|
test("global env beats the default", () => {
|
|
expect(resolveEvalModel("distill", null, { GSTACK_EVAL_MODEL: "g" } as never)).toBe("g");
|
|
});
|
|
test("defaults per kind", () => {
|
|
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();
|
|
});
|
|
});
|