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/config-steps.test.ts

@@ -28,7 +28,7 @@ function assertReasons(list: StepList): void {
 }
 
 test("步骤清单：完整流程全开", () => {
-  const list = stepList(fullConfig());
+  const list = listOf((f) => (f.diagnosis = { enabled: true, perResearcher: 2, maxExperiments: 4 }));
   assert.equal(list.preset, "full");
   assert.deepEqual(rows(list.study), [
     ["freezeConfig", E, null],
@@ -44,6 +44,13 @@ test("步骤清单：完整流程全开", () => {
   assert.deepEqual(rows(list.round), [
     ["openRound", E, null],
     ["carryOverPool", E, null],
+    ["diagnosisProposal", E, null],
+    ["diagnosisDedupe", E, null],
+    ["diagnosisPrediction", E, null],
+    ["selectDiagnosis", E, { name: "valueMinusCost", version: 1 }],
+    ["diagnosisImplementation", E, null],
+    ["diagnosisRun", E, null],
+    ["diagnosisSettle", E, null],
     ["proposal", E, null],
     ["dedupe", E, null],
     ["firstPrediction", E, null],
@@ -95,6 +102,13 @@ test("步骤清单：只关第一次预测", () => {
   assert.deepEqual(rows(list.round), [
     ["openRound", E, null],
     ["carryOverPool", E, null],
+    ["diagnosisProposal", S, null],
+    ["diagnosisDedupe", S, null],
+    ["diagnosisPrediction", S, null],
+    ["selectDiagnosis", S, null],
+    ["diagnosisImplementation", S, null],
+    ["diagnosisRun", S, null],
+    ["diagnosisSettle", S, null],
     ["proposal", E, null],
     ["dedupe", E, null],
     ["firstPrediction", S, null],
@@ -128,6 +142,13 @@ test("步骤清单：只关挑刺与回应，协议照样冻结", () => {
   assert.deepEqual(rows(list.round), [
     ["openRound", E, null],
     ["carryOverPool", E, null],
+    ["diagnosisProposal", S, null],
+    ["diagnosisDedupe", S, null],
+    ["diagnosisPrediction", S, null],
+    ["selectDiagnosis", S, null],
+    ["diagnosisImplementation", S, null],
+    ["diagnosisRun", S, null],
+    ["diagnosisSettle", S, null],
     ["proposal", E, null],
     ["dedupe", E, null],
     ["firstPrediction", E, null],
@@ -154,13 +175,20 @@ test("步骤清单：只关挑刺与回应，协议照样冻结", () => {
   ]);
 });
 
-test("步骤清单：只关消融，解释照样写，选格没有规则", () => {
+test("步骤清单：只关消融，解释也跳过，选格没有规则", () => {
   const list = listOf((f) => (f.ablation = { enabled: false }));
   assertReasons(list);
   assert.deepEqual(rows(list.study), rows(stepList(fullConfig()).study));
   assert.deepEqual(rows(list.round), [
     ["openRound", E, null],
     ["carryOverPool", E, null],
+    ["diagnosisProposal", S, null],
+    ["diagnosisDedupe", S, null],
+    ["diagnosisPrediction", S, null],
+    ["selectDiagnosis", S, null],
+    ["diagnosisImplementation", S, null],
+    ["diagnosisRun", S, null],
+    ["diagnosisSettle", S, null],
     ["proposal", E, null],
     ["dedupe", E, null],
     ["firstPrediction", E, null],
@@ -177,7 +205,7 @@ test("步骤清单：只关消融，解释照样写，选格没有规则", () =>
     ["informationAccount", E, null],
     ["adopt", E, null],
     ["listCells", S, null],
-    ["explanation", E, null],
+    ["explanation", S, null],
     ["selectCells", S, null],
     ["ablationImplementation", S, null],
     ["ablationVerification", S, null],
@@ -205,6 +233,13 @@ test("步骤清单：朴素循环", () => {
   assert.deepEqual(rows(list.round), [
     ["openRound", E, null],
     ["carryOverPool", S, null], // 候选不留池
+    ["diagnosisProposal", S, null], // 不诊断
+    ["diagnosisDedupe", S, null], // 不诊断
+    ["diagnosisPrediction", S, null], // 不诊断
+    ["selectDiagnosis", S, null], // 不诊断
+    ["diagnosisImplementation", S, null], // 不诊断
+    ["diagnosisRun", S, null], // 不诊断
+    ["diagnosisSettle", S, null], // 不诊断
     ["proposal", E, null],
     ["dedupe", E, null], // 判重照常
     ["firstPrediction", S, null], // 不预测
@@ -264,3 +299,30 @@ test("步骤清单：换规则后清单里的规则跟着换", () => {
   assert.deepEqual(rule("selectBatch"), { name: "uniformRandom", version: 1 });
   assert.deepEqual(rule("selectCells"), { name: "randomSameCount", version: 1 });
 });
+
+test("步骤清单：诊断开、消融关（现行配置）：诊断七步执行，消融七步（含解释）跳过", () => {
+  const list = listOf((f) => {
+    f.diagnosis = { enabled: true, perResearcher: 2, maxExperiments: 4 };
+    f.ablation = { enabled: false };
+  });
+  assertReasons(list);
+  const status = (id: string) => list.round.find((s) => s.id === id)!.status;
+  for (const id of [
+    "diagnosisProposal", "diagnosisDedupe", "diagnosisPrediction", "selectDiagnosis",
+    "diagnosisImplementation", "diagnosisRun", "diagnosisSettle",
+  ]) {
+    assert.equal(status(id), "execute", id);
+  }
+  for (const id of [
+    "listCells", "explanation", "selectCells", "ablationImplementation", "ablationVerification", "ablationRun", "settle",
+  ]) {
+    assert.equal(status(id), "skip", id);
+  }
+  // 诊断七步排在留池之后、提案之前（方法.md 4.3"诊断"一段）。
+  const ids = list.round.map((s) => s.id);
+  assert.deepEqual(ids.slice(ids.indexOf("carryOverPool"), ids.indexOf("proposal") + 1), [
+    "carryOverPool", "diagnosisProposal", "diagnosisDedupe", "diagnosisPrediction", "selectDiagnosis",
+    "diagnosisImplementation", "diagnosisRun", "diagnosisSettle", "proposal",
+  ]);
+  assert.deepEqual(list.round.find((s) => s.id === "selectDiagnosis")!.rule, { name: "valueMinusCost", version: 1 });
+});