feat(consult): add an answer-step reasoning effort switch

The switch is off unless CONSULT_ANSWER_REASONING_EFFORT is set, so today's request body stays the same. A set value is sent as top-level reasoning_effort only on the answer step. The real A/B did not run: there is no model key.

Request-body probe, the named frontend tests (114 pass, 0 fail), tsc, and lint (0 errors) were run.

Co-Authored-By: Grok (agent loop)
Co-authored-by: Cursor <cursoragent@cursor.com>

frontend/src/app/api/consult/route.ts

@@ -75,6 +75,8 @@ import {
   createConsultationRunClock,
   consultationContinueGenerationSettings,
   consultationGenerationSettings,
+  consultationGeneralPrepareStep,
+  consultAnswerEffortProviderOptions,
   consultationNatalPrepareStep,
   consultationWindowPrepareStep,
   createConsultationAgentContext,
@@ -1288,6 +1290,8 @@ export async function POST(request: Request) {
       prepareStep: (input: { stepNumber: number }) => consultationNatalPrepareStep({
         stepNumber: input.stepNumber,
         rectificationOffer: true,
+        answerReady: state.consultationToolCompleted,
+        model: selectedModel.model,
       }),
     };
     const windowStreamOptions = {
@@ -1295,6 +1299,15 @@ export async function POST(request: Request) {
       prepareStep: (input: { stepNumber: number }) => consultationWindowPrepareStep({
         stepNumber: input.stepNumber,
         rectificationOffer: true,
+        answerReady: state.consultationToolCompleted,
+        model: selectedModel.model,
+      }),
+    };
+    const generalStreamOptions = {
+      ...streamOptions,
+      prepareStep: (input: { stepNumber: number }) => consultationGeneralPrepareStep({
+        stepNumber: input.stepNumber,
+        model: selectedModel.model,
       }),
     };
     const answerPhaseSignal = runClock.answerSignal;
@@ -1305,10 +1318,10 @@ export async function POST(request: Request) {
       agent: {
         stream: (
           messages: typeof baseMessages,
-          options: typeof streamOptions | typeof natalStreamOptions | typeof windowStreamOptions,
+          options: typeof streamOptions | typeof natalStreamOptions | typeof windowStreamOptions | typeof generalStreamOptions,
         ) => Promise<{ fullStream: AsyncIterable<unknown> | ReadableStream<unknown>; totalUsage: Promise<Usage> }>;
       },
-      options: typeof streamOptions | typeof natalStreamOptions | typeof windowStreamOptions = streamOptions,
+      options: typeof streamOptions | typeof natalStreamOptions | typeof windowStreamOptions | typeof generalStreamOptions = streamOptions,
     ) {
       try {
         const result = await agent.stream(baseMessages, options);
@@ -1369,14 +1382,14 @@ export async function POST(request: Request) {
     if (usesPublicDailyGeneralAgent(consultationMode, generalDailyContext)) {
       state.workflowReceipt = workflowReceipt;
       const agent = getGeneralJyotishAgent(selectedModel);
-      const result = await streamWithOverflowRetry(agent);
+      const result = await streamWithOverflowRetry(agent, generalStreamOptions);
       // This mode has no calculation to require and no chart method to bind,
       // so there is no contract for a retry to repair.
       const retryForAnswer = async (retryHint?: string) => {
         const retried = await agent.stream([
           ...baseMessages,
           { role: "user" as const, content: `上一轮没有输出任何回答文本。请直接给出这个问题的回答，不要只说明过程。${retryHint ? `\n${retryHint}` : ""}` },
-        ], { ...streamOptions, abortSignal: answerPhaseSignal() });
+        ], { ...generalStreamOptions, abortSignal: answerPhaseSignal() });
         usages.push(retried.totalUsage);
         return retried.fullStream;
       };
@@ -1472,7 +1485,11 @@ export async function POST(request: Request) {
             role: "user" as const,
             content: `服务器窗口计算已经完成，但上一轮没有输出任何回答文本。请重新取回本次计算结果，然后直接给出回答；不要只描述过程或工具调用。${retryHint ? `\n${retryHint}` : ""}`,
           },
-        ], { ...streamOptions, abortSignal: answerPhaseSignal() });
+        ], {
+          ...streamOptions,
+          abortSignal: answerPhaseSignal(),
+          ...consultAnswerEffortProviderOptions(selectedModel.model),
+        });
         usages.push(retried.totalUsage);
         return retried.fullStream;
       };