fix(rectification): host-fallback empty evidence turns and choice range narration (BUG-633, BUG-634)

Evidence turns that already recorded a batch no longer fail the whole run when the model emits no text; unchanged ranges now name which clock spans lead or lag, and the timeline no longer says 收窄. Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-10 11:57:07 +08:00
parent 31f2a722aa
commit 0263658477
28 changed files with 817 additions and 49 deletions
@@ -59,6 +59,12 @@ import {
  type PublicStreamEvent,
 } from "./stream-mapping";
 import { mapModelFinishToErrorCode, userFacingRunFailure } from "./run-diagnostic";
+import {
+  batchResultFromToolChunk,
+  composeHostFallbackNarration,
+  lastCompletedPublicTool,
+  publicWriteToolCompleted,
+} from "./host-fallback";
 import {
  applyStepAnswerChunk,
  createStepAnswerState,
@@ -224,8 +230,14 @@ function isRetryableError(errorCode: string): boolean {
  return RETRYABLE_ERROR_CODES.has(errorCode);
 }

-function shouldAutoRetry(errorCode: string, signal?: AbortSignal): boolean {
-  return !signal?.aborted && isRetryableError(errorCode);
+function shouldAutoRetry(
+  errorCode: string,
+  signal?: AbortSignal,
+  status?: AttemptStatus,
+): boolean {
+  if (signal?.aborted) return false;
+  if (errorCode === "empty_stream") return status === "retryable";
+  return isRetryableError(errorCode);
 }

 function clockWindow(range: { start_time?: string | null; end_time?: string | null } | null | undefined): string | null {
@@ -484,7 +496,7 @@ export async function runV9AgentTurn(options: V9AgentRunOptions): Promise<V9Agen
    finalOutcome = outcome;
    if (outcome.ok
      || outcome.status === "failed"
-      || !shouldAutoRetry(outcome.errorCode ?? "run_failed", signal)
+      || !shouldAutoRetry(outcome.errorCode ?? "run_failed", signal, outcome.status)
      || attemptNumber === MAX_ATTEMPTS) break;
    await emit({ type: "attempt.reset" });
  }
@@ -671,12 +683,15 @@ export async function runV9AgentTurn(options: V9AgentRunOptions): Promise<V9Agen
    let intentClassified = false;
    let streamFailed = false;
    let finished = false;
+    let finishReason: ReturnType<typeof toAgentModelFinishReason> | null = null;
    let answerText = "";
    const answerDeltas: string[] = [];
    const phases: string[] = [];
    const toolsUsed = new Set<string>();
    const events: PublicStreamEvent[] = [];
    const toolTerminalStatus = new Map<string, "completed" | "failed">();
+    let batchToolResult: unknown = null;
+    let hostFallbackUsed = false;
    const emittedKeys = new Set<string>();
    const emittedActivities = new Set<string>();
    const repeatedCalls = new Map<string, number>();
@@ -771,7 +786,6 @@ export async function runV9AgentTurn(options: V9AgentRunOptions): Promise<V9Agen
            },
      });

-      let finishReason: ReturnType<typeof toAgentModelFinishReason> | null = null;
      const stepAnswer = createStepAnswerState();

      let spokenRaw = "";
@@ -819,6 +833,20 @@ export async function runV9AgentTurn(options: V9AgentRunOptions): Promise<V9Agen
        }
      };

+      const applyHostFallback = async (): Promise<boolean> => {
+        if (answerText.trim()) return false;
+        if (toolTerminalStatus.get("rectification-record-evidence-batch") !== "completed") {
+          return false;
+        }
+        const spoken = composeHostFallbackNarration(batchToolResult ?? {});
+        if (!spoken) return false;
+        hostFallbackUsed = true;
+        await recordPhase("answer.host_fallback");
+        await publish({ type: "answer.host_fallback" });
+        await emitVisibleSpoken(spoken);
+        return true;
+      };
+
      try {
      for await (const chunk of result.fullStream) {
        const rawToolName = typeof chunk.payload?.toolName === "string" ? chunk.payload.toolName : "";
@@ -868,6 +896,8 @@ export async function runV9AgentTurn(options: V9AgentRunOptions): Promise<V9Agen
            toolTerminalStatus.set(activityEvent.tool, activityEvent.status);
          }
        }
+        const capturedBatch = batchResultFromToolChunk(chunk as never);
+        if (capturedBatch != null) batchToolResult = capturedBatch;
        const phaseEvent = skipDuplicateToolCallReceipt
          ? null
          : mapStreamChunkToPhase(chunk as never);
@@ -972,14 +1002,36 @@ export async function runV9AgentTurn(options: V9AgentRunOptions): Promise<V9Agen
      if (streamFailed || abortController.signal.aborted) return failedAttempt(attemptId, mapped ?? "stream_aborted");
      if (!finished) return failedAttempt(attemptId, mapped ?? "stream_unfinished");
      if (mapped === "answer_truncated") {
+        if (!await applyHostFallback()) {
+          return {
+            ok: false,
+            status: "failed",
+            errorCode: "answer_truncated",
+            usage: { inputTokens: 0, outputTokens: 0 },
+            answerText,
+            answerDeltas,
+            phases,
+            toolsUsed: [...toolsUsed],
+            events,
+            skillBound,
+            caseLoaded,
+            attemptId,
+          };
+        }
+      } else if (mapped === "max_steps" || mapped === "provider_error") {
+        if (mapped !== "max_steps" || !await applyHostFallback()) {
+          return failedAttempt(attemptId, mapped);
+        }
+      } else if (!answerText.trim() && !await applyHostFallback()) {
+        const retryable = !publicWriteToolCompleted(toolTerminalStatus);
        return {
          ok: false,
-          status: "failed",
-          errorCode: "answer_truncated",
+          status: retryable ? "retryable" : "failed",
+          errorCode: "empty_stream",
          usage: { inputTokens: 0, outputTokens: 0 },
-          answerText,
-          answerDeltas,
-          phases,
+          answerText: "",
+          answerDeltas: [],
+          phases: [...phases],
          toolsUsed: [...toolsUsed],
          events,
          skillBound,
@@ -987,10 +1039,6 @@ export async function runV9AgentTurn(options: V9AgentRunOptions): Promise<V9Agen
          attemptId,
        };
      }
-      if (mapped === "max_steps" || mapped === "provider_error") {
-        return failedAttempt(attemptId, mapped);
-      }
-      if (!answerText.trim()) return failedAttempt(attemptId, "empty_stream");
      let latestDossier: V9CaseDossier;
      try {
        latestDossier = await loadV9CaseDossier(accounting, userId, caseId);
@@ -1038,6 +1086,21 @@ export async function runV9AgentTurn(options: V9AgentRunOptions): Promise<V9Agen
    } finally {
      clearTimeout(timeout);
      signal?.removeEventListener("abort", onAbort);
+      console.info(JSON.stringify({
+        scope: "RectificationRunDiagnostic",
+        runId: attemptId,
+        modelId: options.modelName,
+        finishReason: finishReason ?? "unknown",
+        inputTokens: null,
+        reasoningTokens: null,
+        outputTokens: null,
+        stepCount: toolsUsed.size,
+        toolCallCount: toolsUsed.size,
+        readCasePayloadBytes: null,
+        elapsedMs: Date.now() - startedAt,
+        lastCompletedTool: lastCompletedPublicTool(toolTerminalStatus),
+        stateMutationCommitted: publicWriteToolCompleted(toolTerminalStatus) || hostFallbackUsed,
+      }));
    }
  }

@@ -18,6 +18,7 @@ export const MACHINE_VOICE_LEXICON = [
  "请先说一件你记得大概时间的人生经历，比如升学、入职、搬家、结婚或生病",
  "有没有记得住时间的收入变化、大笔支出或欠债",
  "继续收窄",
+  "还在收窄",
  "范围还在",
  "领先",
  "落后",
@@ -19,6 +19,7 @@ import {
 } from "./choice-card";
 import {
  explainRangeChange,
+  explainScoreMovement,
  type ClusterScoreDelta,
 } from "./probe-explain.ts";

@@ -118,7 +119,12 @@ export function composeChoiceNarration(input: {
  }
  if (input.appliedInference) {
    const range = explainRangeChange(input.credibleBefore, input.credibleAfter);
-    return `已记录，${range || "范围没变"}。`;
+    if (range && range !== "范围没变") {
+      return `已记录，${range}。`;
+    }
+    const movement = explainScoreMovement(input.deltasByCluster ?? []);
+    if (movement) return `已记录，范围没变；${movement}。`;
+    return "已记录，范围没变。";
  }
  return "已记录你的选择。";
 }
@@ -192,6 +192,11 @@ export function displayDateLabel(
  return from || "日期不明";
 }

+/** Short event phrase from a ledger summary. Does not invent years. */
+export function eventPhraseFromSummary(summary: string): string {
+  return summary.replace(/\s+/g, " ").trim().replace(/[。．.！？!?]+$/u, "").slice(0, 24);
+}
+
 export function quoteIsGroundedInMessage(
  userMessage: string,
  quote: string,
@@ -0,0 +1,78 @@
+/**
+ * Host-spoken fallback when the model records evidence but emits no answer.
+ * Recap text comes only from the batch tool return.
+ */
+
+export const HOST_FALLBACK_WRITE_TOOLS = [
+  "rectification-record-evidence-batch",
+  "rectification-set-focus",
+  "rectification-compare-candidates",
+] as const;
+
+export type HostFallbackRecap = Readonly<{
+  display_date_label?: string;
+  event_phrase?: string;
+}>;
+
+export function publicWriteToolCompleted(
+  status: ReadonlyMap<string, "completed" | "failed">,
+): boolean {
+  return HOST_FALLBACK_WRITE_TOOLS.some((tool) => status.get(tool) === "completed");
+}
+
+export function lastCompletedPublicTool(
+  status: ReadonlyMap<string, "completed" | "failed">,
+): string | null {
+  let last: string | null = null;
+  for (const [tool, value] of status) {
+    if (value === "completed") last = tool;
+  }
+  return last;
+}
+
+function recapLine(item: HostFallbackRecap): string {
+  const label = typeof item.display_date_label === "string" ? item.display_date_label.trim() : "";
+  const phrase = typeof item.event_phrase === "string" ? item.event_phrase.trim() : "";
+  return [label, phrase].filter(Boolean).join(" ").trim();
+}
+
+function recapsFromBatchResult(value: unknown): HostFallbackRecap[] {
+  if (!value || typeof value !== "object" || Array.isArray(value)) return [];
+  const row = value as {
+    accepted_recaps?: unknown;
+    items?: unknown;
+  };
+  if (Array.isArray(row.accepted_recaps)) {
+    return row.accepted_recaps.flatMap((item) => {
+      if (!item || typeof item !== "object" || Array.isArray(item)) return [];
+      return [item as HostFallbackRecap];
+    });
+  }
+  if (!Array.isArray(row.items)) return [];
+  return row.items.flatMap((item) => {
+    if (!item || typeof item !== "object" || Array.isArray(item)) return [];
+    const entry = item as HostFallbackRecap & { outcome?: unknown };
+    if (entry.outcome && entry.outcome !== "accepted") return [];
+    if (!entry.display_date_label && !entry.event_phrase) return [];
+    return [entry];
+  });
+}
+
+export function batchResultFromToolChunk(chunk: {
+  type?: string;
+  payload?: { toolName?: unknown; result?: unknown; output?: unknown };
+  object?: unknown;
+}): unknown {
+  if (chunk.type !== "tool-result") return null;
+  if (chunk.payload?.toolName !== "rectification-record-evidence-batch") return null;
+  return chunk.payload?.result ?? chunk.payload?.output ?? chunk.object ?? null;
+}
+
+export function composeHostFallbackNarration(batchResult: unknown): string | null {
+  if (batchResult == null) return null;
+  const lines = recapsFromBatchResult(batchResult)
+    .map(recapLine)
+    .filter(Boolean);
+  if (lines.length > 0) return `记下了：${lines.join("、")}。`;
+  return "记下了。";
+}
@@ -7,6 +7,7 @@ export const RECTIFICATION_MESSAGE_ORIGINS = [
  "voice_input",
  "retry_replay",
  "system_recovery",
+  "host_fallback",
 ] as const;

 export type RectificationMessageOrigin = (typeof RECTIFICATION_MESSAGE_ORIGINS)[number];
@@ -211,15 +211,23 @@ export function clusterScoreDeltas(
  return [...summed.values()].filter((item) => item.delta !== 0);
 }

+function clockSpanLabel(range: readonly [string, string]): string {
+  const start = range[0]?.slice(0, 5) ?? "";
+  const end = range[1]?.slice(0, 5) ?? "";
+  if (!CLOCK.test(start)) return "";
+  if (!CLOCK.test(end) || start === end) return start;
+  return `${start}–${end}`;
+}
+
 export function explainScoreMovement(deltas: readonly ClusterScoreDelta[]): string {
  if (deltas.length === 0) return "";
  const rising = [...deltas].filter((item) => item.delta > 0).sort((a, b) => b.delta - a.delta)[0] ?? null;
  const falling = [...deltas].filter((item) => item.delta < 0).sort((a, b) => a.delta - b.delta)[0] ?? null;
-  const up = rising ? formatClusterRange(rising.range) : "";
-  const down = falling ? formatClusterRange(falling.range) : "";
-  if (up && down) return `${up}领先，${down}落后`;
-  if (up) return `${up}领先`;
-  if (down) return `${down}落后`;
+  const up = rising ? clockSpanLabel(rising.range) : "";
+  const down = falling ? clockSpanLabel(falling.range) : "";
+  if (up && down) return `${up} 领先，${down} 落后`;
+  if (up) return `${up} 领先`;
+  if (down) return `${down} 落后`;
  return "";
 }

@@ -23,6 +23,7 @@ export const PUBLIC_RECTIFICATION_PHASES = [
  "candidate.accepted",
  "birth_time.confirmed",
  "answer.composed",
+  "answer.host_fallback",
  "billing.settled",
  "answer.delta",
  "activity.changed",