Project-2 baseline
This commit is contained in:
@@ -24,7 +24,7 @@ import { hideBin } from 'yargs/helpers';
|
||||
|
||||
import { stripAuthoringScaffolding, truncationIndex, turnsFromLines } from './harness-session.mjs';
|
||||
// This script must not call cpSync — it fails EACCES on a macOS docker bind mount.
|
||||
import { HOLISTIC_RUBRIC_SCAFFOLD } from './holistic-rubric-scaffold';
|
||||
import { holisticRubricScaffoldFor } from './holistic-rubric-scaffold';
|
||||
import { copyTree } from './lib/copy-tree';
|
||||
import { collectCwds, sanitizeSessionJsonl } from './sanitize-session-jsonl';
|
||||
|
||||
@@ -234,6 +234,7 @@ mkdirSync(join(taskDir, 'reference-runs'), { recursive: true });
|
||||
// task-shared/ are skipped by the existsSync guard below.
|
||||
const sharedFiles = [
|
||||
{ src: 'test.sh', dest: 'tests/test.sh' },
|
||||
{ src: 'codex-grader.py', dest: 'tests/codex-grader.py' },
|
||||
{
|
||||
src: 'grader-system-prompt-consolidated.md',
|
||||
dest: 'tests/grader-system-prompt-consolidated.md',
|
||||
@@ -663,6 +664,7 @@ gpus = 0
|
||||
allow_internet = true
|
||||
|
||||
[verifier.env]
|
||||
GRADER_HARNESS = "codex"
|
||||
ANTHROPIC_API_KEY = "\${ANTHROPIC_API_KEY}"
|
||||
ANTHROPIC_BASE_URL = "\${ANTHROPIC_BASE_URL}"
|
||||
|
||||
@@ -764,7 +766,7 @@ const holisticRubricMd = `<!--
|
||||
when you are done.
|
||||
-->
|
||||
|
||||
${HOLISTIC_RUBRIC_SCAFFOLD}`;
|
||||
${holisticRubricScaffoldFor(slug)}`;
|
||||
|
||||
writeFileSync(join(taskDir, 'tests', 'holistic-rubric.md'), holisticRubricMd);
|
||||
log.info('Scaffolded tests/holistic-rubric.md (needs manual editing)');
|
||||
|
||||
Reference in New Issue
Block a user