feat: 诊断（任务书 18 第一块）：诊断数学、四种提交、一次运行跑多个实验、账本与材料、flow 诊断各步

消融默认关，关掉时解释阶段一并跳过；选诊断实验用信息价值减成本。
eval/diagnosis/research.json 为第三块配置。vocab 字段说明的出口文字随提示词一起改，见下一次提交的 prompts/ 与同文件改动（本次含在内）。

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

tests/vocab.test.ts

@@ -102,6 +102,14 @@ const samples: { [K in SubmissionKind]: Submission<K> } = {
     ],
   },
   claim: { choices: ["researcher-2-e1", "researcher-1-e2"] },
+  diagnosisProposal: {
+    explanations: [{ body: "卡在起点：……；若换成明显更强的起点分数不涨，这条解释就不成立" }],
+    experiments: [{ name: "更强的起点", spot: "solve.py 的起点生成", body: "换成……，交出答案", metrics: metrics.defined }],
+  },
+  diagnosisPrediction: { predictions: [{ explanation: "r2-dx1", experiment: "d1", range }], body: "理由" },
+  diagnosisImplementation: { locations: [{ experiment: "d1", locations: ["solve.py:10-40"] }], concerns: "无", body: "说明" },
+  diagnosisRepair: { locations: [{ experiment: "d1", locations: ["solve.py:10-40"] }], concerns: "无", body: "按核验意见补上" },
+  diagnosisVerification: { experiments: [{ experiment: "d1", followed: true, nothingElse: true, where: "solve.py:10-40" }], body: "无" },
   proposal: { factors, safeguards: ["final-shrink"], metrics, authorEstimate: range, body },
   firstPrediction: { range, body: "理由" },
   critique: { target: "p2", body: "（推测）扰动可能和起点数混杂" },