ren worker folder adding orig, mv new one into root

This commit is contained in:
2026-09-25 10:34:29 -04:00
parent 10f0668e32
commit 5b010039d7
1308 changed files with 44597 additions and 1511 deletions

View File

@@ -24,6 +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 { copyTree } from './lib/copy-tree';
import { collectCwds, sanitizeSessionJsonl } from './sanitize-session-jsonl';
@@ -747,40 +748,23 @@ if (lastUserMessage) {
// --- Scaffold holistic-rubric.md ---
const holisticRubricMd = `<!--
HOLISTIC RUBRIC — the file trials grade against. Run
/write-holistic-rubric
to draft it interactively, or point Claude Code at this file,
session-full.jsonl, and task-shared/grading-standard.md.
Snapshot: ${basename(snapshotDir)}
Session: ${metadata.session_uuid}
Repo: ${metadata.remote_url}
Commit: ${metadata.commit}
## What happened in the snapshot conversation
What happened in the snapshot conversation
The worker was trying to: ${annotation.what_trying}
They hoped Claude would: ${annotation.what_hoping}
Instead, Claude: ${annotation.what_happened}
## What this file contains
The eight-criterion Grading Standard
(task-shared/grading-standard.md, embedded in
tests/grader-system-prompt-consolidated.md) defines Integrity, Narrow
Correctness, Broader Correctness / craft, Persistence, Communication,
Verification & Thoroughness, Common Sense, and Thought Partnership. This
file adds the task-specific knowledge the grader cannot infer: full task
context, the ground truth you established, what strong and weak responses
look like per criterion, and any dealbreaker penalties — stated as 0.0-1.0
fraction subtractions with a named criterion target, never points, never
caps. The document must stand alone: the grader sees only it and the
shared standard.
Draft this file with /write-holistic-rubric, or point your agent at it,
session-full.jsonl, and task-shared/grading-standard.md. Delete this comment
when you are done.
-->
<!-- Replace EVERYTHING in this file with the actual holistic rubric,
including the instructions above. -->
`;
${HOLISTIC_RUBRIC_SCAFFOLD}`;
writeFileSync(join(taskDir, 'tests', 'holistic-rubric.md'), holisticRubricMd);
log.info('Scaffolded tests/holistic-rubric.md (needs manual editing)');