第五轮：锁/续跑/超时/自动分支/R4 探针与 encode-once/控制台加固；阶段内断点续跑（gen 按条、prep 按 shard、训练与 APG 定时原子存档+体面停止）；分歧以实现方意见为准

2026-10-18 06:40:25 +08:00
parent 3675fbbd9b
commit f40a40c56b
36 changed files with 1199 additions and 285 deletions
@@ -74,5 +74,7 @@ writeNpy(path.join(OUTDIR, base + '.Y.npy'), cat(Y, H * 6), [n, H, 6]);
 writeNpy(path.join(OUTDIR, base + '.V.npy'), Float32Array.from(V), [n]);
 writeNpy(path.join(OUTDIR, base + '.SG.npy'), cat(SG, 13), [n, 13]);
 writeNpy(path.join(OUTDIR, base + '.TID.npy'), TID, [n], 'int32');
-fs.writeFileSync(path.join(OUTDIR, base + '.tasks.jsonl'), tasks.map(t => JSON.stringify(t)).join('\n') + '\n');
+// 2026-10-18 断点续跑：tasks.jsonl 最后写、先写 .tmp 再改名 —— 它存在就代表这个 shard 的 5 个 npy 都已写完，run_prep.sh 据此跳过
+const tf = path.join(OUTDIR, base + '.tasks.jsonl');
+fs.writeFileSync(tf + '.tmp', tasks.map(t => JSON.stringify(t)).join('\n') + '\n'); fs.renameSync(tf + '.tmp', tf);
 console.log(JSON.stringify({ shard: base, tasks: tasks.length, samples: n, aug: nAug, augRejected: nAugRej, gapDrop: nGapDrop, featVer: POL.FEAT_VER }));