Project-2 baseline

worker-toolkit-potion-polyglot/explore/plugins/create-snapshot/bin/capture-snapshot.mjs

@@ -652,6 +652,13 @@ if (gitRepo) {
       git('read-tree HEAD', { env: indexEnv });
       git('add -A', { env: indexEnv });
       patch = git('diff --cached --binary --full-index HEAD', diffOpts);
+      if (patch) {
+        console.error(
+          'Warning: no turn checkpoint was found, so snapshot.patch holds every change in the ' +
+            'working tree, including edits the agent made during the captured turn. Check it ' +
+            'and remove those before converting the snapshot to a task.'
+        );
+      }
     }
 
     try {

worker-toolkit-potion-polyglot/explore/plugins/create-snapshot/bin/holistic-rubric-scaffold.ts

@@ -86,3 +86,14 @@ never a numeric magnitude, never points, never a cap or pinned score: the
 grader sizes the subtraction itself. Always state the behavior that does NOT trip the penalty.
 Never describe how criteria combine into an overall score.>
 `;
+
+/** The title names the task, not its author: a leading `<EUID>-` (the worker's 12-char id,
+ * which workers put on their task dir) is dropped. Anything else is used as given. */
+export function rubricTitleSlug(slug: string): string {
+  return slug.replace(/^(?=[A-Z0-9]*\d)[A-Z0-9]{12}-(?=\S)/, '');
+}
+
+/** The scaffold with `<task-slug>` filled in for a task whose name is already known. */
+export function holisticRubricScaffoldFor(slug: string): string {
+  return HOLISTIC_RUBRIC_SCAFFOLD.replace('<task-slug>', rubricTitleSlug(slug));
+}

worker-toolkit-potion-polyglot/explore/plugins/create-snapshot/bin/lib/copy-tree.ts

@@ -2,4 +2,4 @@
  * Plugin-side re-export, so snapshot-to-task.ts resolves `./lib/copy-tree`
  * both here and in the toolkit's flat scripts/ dir.
  */
-export * from '../../../../raccoon-worker-toolkit/static/scripts/lib/copy-tree';
+export * from '../../../../static/scripts/lib/copy-tree';

worker-toolkit-potion-polyglot/explore/plugins/create-snapshot/bin/snapshot-to-task.ts

@@ -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)');