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;
       };

frontend/src/lib/agent-generation-settings.ts

@@ -16,6 +16,8 @@ export const AGENT_MAX_OUTPUT_TOKENS = AGENT_ANSWER_OUTPUT_TOKENS;
 
 export type ThinkingMode = "enabled" | "disabled";
 export type ReasoningEffort = "low" | "medium" | "high";
+/** Top-level OpenAI-compatible `reasoning_effort`, including DeepSeek's `max`. */
+export type ProviderReasoningEffort = "low" | "medium" | "high" | "max";
 
 export type PromptCacheUsage = Readonly<{
   readTokens: number;
@@ -100,6 +102,8 @@ export function agentGenerationSettings(
     answerTokens?: number;
     thinkingTokens?: number;
     reasoningEffort?: ReasoningEffort;
+    /** Written beside `thinking`, not inside it, so compatible gateways emit `reasoning_effort`. */
+    providerReasoningEffort?: ProviderReasoningEffort;
   } = {},
 ) {
   const thinkingMode: ThinkingMode = options.thinking ?? "disabled";
@@ -110,6 +114,9 @@ export function agentGenerationSettings(
         ? { reasoningEffort: options.reasoningEffort }
         : {}),
     },
+    ...(options.providerReasoningEffort
+      ? { reasoningEffort: options.providerReasoningEffort }
+      : {}),
   };
   const providerId = typeof model === "string"
     ? model

frontend/src/mastra/consultation-tools.ts

@@ -25,7 +25,7 @@ import { createConsultationPlan, type ConsultationPlan } from "../lib/consultati
 import type { TechniqueAuditRow, WorkflowReceipt } from "../lib/consultation-agent-events.ts";
 import { normalizeTechniqueAuditRows } from "../lib/consultation-technique-audit.ts";
 import type { AgentModelFinishReason, EvidenceCardTelemetry } from "../lib/agent-observability.ts";
-import { agentGenerationSettings, AGENT_SLICE_ANSWER_OUTPUT_TOKENS, AGENT_SLICE_THINKING_OUTPUT_TOKENS } from "../lib/agent-generation-settings.ts";
+import { agentGenerationSettings, AGENT_SLICE_ANSWER_OUTPUT_TOKENS, AGENT_SLICE_THINKING_OUTPUT_TOKENS, type ProviderReasoningEffort } from "../lib/agent-generation-settings.ts";
 import { chartCalculationProgressLabel, evidenceLookupActivityLabel } from "../lib/consultation-activity-labels.ts";
 import { consultDomainConcurrency } from "../lib/consult/prep-flags.ts";
 import {
@@ -176,6 +176,45 @@ export const CONSULTATION_EVIDENCE_LOOKUP_TOOL_ID = "read-consultation-evidence"
 export const MAX_EVIDENCE_LOOKUPS_PER_TURN = 3;
 export const CONSULTATION_WINDOW_CALC_TOOL_ID = "run-jyotish-window-consultation";
 
+/**
+ * Answer-step reasoning effort. Unset or blank keeps today's request body.
+ * An illegal value warns once and is treated as unset.
+ */
+const CONSULT_ANSWER_REASONING_EFFORTS = ["low", "medium", "high", "max"] as const;
+let consultAnswerReasoningEffortWarned = false;
+
+export function consultAnswerReasoningEffort(): ProviderReasoningEffort | undefined {
+  const raw = process.env.CONSULT_ANSWER_REASONING_EFFORT;
+  if (raw === undefined || raw.trim() === "") return undefined;
+  const value = raw.trim();
+  if ((CONSULT_ANSWER_REASONING_EFFORTS as readonly string[]).includes(value)) {
+    return value as ProviderReasoningEffort;
+  }
+  if (!consultAnswerReasoningEffortWarned) {
+    consultAnswerReasoningEffortWarned = true;
+    console.warn(`CONSULT_ANSWER_REASONING_EFFORT=${value} is not low, medium, high, or max; leaving reasoning effort unset.`);
+  }
+  return undefined;
+}
+
+type AnswerEffortInput = {
+  answerReady?: boolean;
+  answerFromStart?: boolean;
+  model?: unknown;
+};
+
+function answerEffortOptions(input: AnswerEffortInput) {
+  const effort = consultAnswerReasoningEffort();
+  const answerStep = input.answerFromStart === true || input.answerReady === true;
+  if (!effort || !answerStep) return {};
+  return {
+    providerOptions: agentGenerationSettings(input.model, {
+      thinking: "enabled",
+      providerReasoningEffort: effort,
+    }).providerOptions,
+  };
+}
+
 /**
  * Step 0 narrows with activeTools and leaves toolChoice auto. Thinking-mode
  * providers reject named and required toolChoice (BUG-282, BUG-937).
@@ -185,35 +224,77 @@ export const CONSULTATION_WINDOW_CALC_TOOL_ID = "run-jyotish-window-consultation
  * Later steps stay auto.
  *
  * Window and general agents must not share the natal hook.
+ *
+ * The answer step is any step that already holds a calculation (`answerReady`,
+ * the same flag as the answer clock) or a no-tool public-daily turn
+ * (`answerFromStart`). A retry starts a new stream at step 0 with the
+ * calculation already in hand, so the step number is not part of the check.
+ * The main loop's step 0 still has `answerReady` false.
  */
-export function consultationNatalPrepareStep(input: { stepNumber: number; rectificationOffer?: boolean }) {
-  if (input.stepNumber !== 0) return { toolChoice: "auto" as const };
+type ConsultPrepareInput = {
+  rectificationOffer?: boolean;
+  answerReady?: boolean;
+  answerFromStart?: boolean;
+  model?: unknown;
+};
+
+export function consultationNatalPrepareStep(input: { stepNumber: 0 } & ConsultPrepareInput): {
+  activeTools: string[];
+  toolChoice: "auto";
+};
+export function consultationNatalPrepareStep(input: { stepNumber: number } & ConsultPrepareInput): {
+  toolChoice: "auto";
+  activeTools?: string[];
+};
+export function consultationNatalPrepareStep(input: { stepNumber: number } & ConsultPrepareInput) {
+  const effort = answerEffortOptions(input);
+  if (input.stepNumber !== 0) return { toolChoice: "auto" as const, ...effort };
   if (!input.rectificationOffer) {
     return {
       activeTools: [CONSULTATION_NATAL_CALC_TOOL_ID],
       toolChoice: "auto" as const,
+      ...effort,
     };
   }
   return {
     activeTools: [CONSULTATION_NATAL_CALC_TOOL_ID, RECTIFICATION_OFFER_TOOL_ID],
     toolChoice: "auto" as const,
+    ...effort,
   };
 }
 
-export function consultationWindowPrepareStep(input: { stepNumber: number; rectificationOffer?: boolean }) {
-  if (input.stepNumber !== 0) return { toolChoice: "auto" as const };
+export function consultationWindowPrepareStep(input: {
+  stepNumber: number;
+  rectificationOffer?: boolean;
+  answerReady?: boolean;
+  answerFromStart?: boolean;
+  model?: unknown;
+}) {
+  const effort = answerEffortOptions(input);
+  if (input.stepNumber !== 0) return { toolChoice: "auto" as const, ...effort };
   if (!input.rectificationOffer) {
     return {
       activeTools: [CONSULTATION_WINDOW_CALC_TOOL_ID],
       toolChoice: "auto" as const,
+      ...effort,
     };
   }
   return {
     activeTools: [CONSULTATION_WINDOW_CALC_TOOL_ID, RECTIFICATION_OFFER_TOOL_ID],
     toolChoice: "auto" as const,
+    ...effort,
   };
 }
 
+export function consultAnswerEffortProviderOptions(model?: unknown) {
+  return answerEffortOptions({ answerReady: true, model });
+}
+
+/** Public daily has no chart tool. Its first step is already the answer. */
+export function consultationGeneralPrepareStep(input: { stepNumber: number; model?: unknown }) {
+  return answerEffortOptions({ ...input, answerFromStart: true });
+}
+
 const CONSULTATION_DOMAIN_DURATION_MS = 31_000;
 const CONSULTATION_ANSWER_RESERVE_MS = 45_000;
 export const CONSULTATION_DOMAIN_WALL_CLOCK_MS = AGENT_TIMEOUT_MS - CONSULTATION_ANSWER_RESERVE_MS;