Jyotisha/frontend/src/lib/rectification-agentic/v9/spoken-answer.ts

/**
 * Hydrate recovery for old Turns that stored process talk in
 * `assistant_message`. Live `answer.delta` is the model text as-is; the
 * runner and chat must not call these helpers on the live stream.
 */

import {
  RECTIFICATION_ACTIVITY_PROGRESS_LABELS,
  RECTIFICATION_TOOL_DONE_LABELS,
} from "../../rectification-activity-labels.ts";

const CJK_RE = /[\u4e00-\u9fff]/;
const INTERNAL_TOKEN_RE = /\b(?:datePrecision|occurredFrom|occurredTo|proposedKind|education_start|missing_evidence|SKILL\.md|rectification-[a-z0-9-]+|focusId|evidenceId|display_date_label|occupation_note|method_followup_plan|open_question|current_question|current_probe|next_action|next_user_action|not_separated|propose_allowed|selection_allowed|information_gain|event_probe|session_outcome|unique_minute_path|confirmation_allowed|collect_method_evidence|candidate_contrast(?:_packet)?|choice_frame|deferred_followup|resolve-focus|questionId|active[\s_-]?focus)\b/i;
const PROCESS_ZH_RE = /skill\s*规则|不得猜补|让我(?:调用|记录|batch|提交|继续|用|看看|自然)|我(?:决定|倾向|batch|需要用|需要继续|需要考虑|继续收集|继续访谈|继续自然|自然地|用自然语言|应该|认为|可以尝试|不能把|直接自然|确认理解|先向用户)|权衡：|内部矛盾|思维链|调用 batch|批量工具|写入(?:这些)?证据|datePrecision|occurredFrom|occurredTo|方法覆盖|方法资料已齐|还不能出牌|不得出牌|不得\s*offer|本轮对照了|这意味着|服务器给了|第.{0,4}条边界|不可分宽度|重新计算了候选|带评分日期|当前还应继续收集|根据 method_followup|根据规则|规则要求|不调用工具|严格来说|实际上规则|也许我应该|当前探针|这回应的是当前探针|账本|草稿|quote 路径|写入需要日期精度|没有具体日期|先确认草稿|纠缠草稿|自然访谈|待确认状态/;
const THIRD_PERSON_USER_RE = /用户/;
const AGENT_SELF_RE = /我(?:应该|认为|可以|先|需要|不能|直接)|让我|也许我/;
const ADDRESSES_USER_RE = /你|您|记下了|已经记下|已记录了|已收到|不用急|别担心|哪一年|有没有|哪件|大概年份|对吗|是不是|请你/;

const ACTIVITY_ECHO_LABELS = [
  ...Object.values(RECTIFICATION_TOOL_DONE_LABELS),
  ...Object.values(RECTIFICATION_ACTIVITY_PROGRESS_LABELS),
];

export type SplitSpokenAndThinking = Readonly<{
  thinking: string;
  spoken: string;
}>;

function isActivityEcho(text: string): boolean {
  const trimmed = text.trim().replace(/[。.…]+$/u, "");
  if (!trimmed) return false;
  return ACTIVITY_ECHO_LABELS.some((label) => {
    const bare = label.replace(/[。.…]+$/u, "");
    return trimmed === bare || trimmed === `正在${bare}`;
  });
}

export function isRectificationProcessNarration(text: string): boolean {
  const trimmed = text.trim();
  if (!trimmed) return false;
  if (/[A-Za-z]{4,}/.test(trimmed) && !CJK_RE.test(trimmed)) return true;
  if (isActivityEcho(trimmed)) return true;
  if (INTERNAL_TOKEN_RE.test(trimmed)) return true;
  if (PROCESS_ZH_RE.test(trimmed)) return true;
  if (THIRD_PERSON_USER_RE.test(trimmed)) return true;
  if (AGENT_SELF_RE.test(trimmed) && !ADDRESSES_USER_RE.test(trimmed)) return true;
  return false;
}

export function nextStableChannelDelta(published: string, next: string): string {
  if (!next.startsWith(published)) return "";
  return next.slice(published.length);
}

function splitSentences(text: string): string[] {
  const parts = text.split(/(?<=[。！？])\s*/u).map((part) => part.trim()).filter(Boolean);
  return parts.length > 0 ? parts : [text];
}

function splitUnits(text: string): string[] {
  const lines = text.split(/\n/).map((line) => line.trim()).filter(Boolean);
  if (lines.length > 1) return lines.flatMap(splitSentences);
  return splitSentences(text);
}

function isMixed(units: readonly string[]): boolean {
  return units.length > 1
    && units.some(isRectificationProcessNarration)
    && units.some((unit) => !isRectificationProcessNarration(unit));
}

function splitParagraphs(text: string): string[] {
  return text
    .split(/\n{2,}/)
    .flatMap((block) => {
      const trimmed = block.trim();
      if (!trimmed) return [];
      const units = splitUnits(trimmed);
      return isMixed(units) ? units : [trimmed];
    });
}

export function splitRectificationSpokenAndThinking(text: string): SplitSpokenAndThinking {
  const paragraphs = splitParagraphs(text);
  if (paragraphs.length === 0) return { thinking: "", spoken: text };

  const thinking: string[] = [];
  const spoken: string[] = [];
  for (const paragraph of paragraphs) {
    if (isRectificationProcessNarration(paragraph)) thinking.push(paragraph);
    else spoken.push(paragraph);
  }

  if (thinking.length === 0) return { thinking: "", spoken: text };
  const userFacing: string[] = [];
  for (const paragraph of spoken) {
    if (ADDRESSES_USER_RE.test(paragraph) || /[？?]/.test(paragraph) || paragraph.length > 60) {
      userFacing.push(paragraph);
    } else {
      thinking.push(paragraph);
    }
  }
  return {
    thinking: thinking.join("\n\n"),
    spoken: userFacing.join("\n\n"),
  };
}

export function finalizeRectificationSpokenAndThinking(text: string): SplitSpokenAndThinking {
  const split = splitRectificationSpokenAndThinking(text);
  if (split.spoken.trim()) return split;
  if (!split.thinking.trim()) return { thinking: "", spoken: text };
  return { thinking: split.thinking, spoken: "" };
}

export function settleRectificationSpokenAndThinking(
  answerRaw: string,
  thinkingRaw = "",
): SplitSpokenAndThinking {
  const leak = splitRectificationSpokenAndThinking(answerRaw);
  const channelThinking = thinkingRaw.trim();
  const spoken = leak.spoken.trim();
  if (channelThinking) return { thinking: channelThinking, spoken };
  if (!spoken && leak.thinking.trim()) return { thinking: leak.thinking, spoken: "" };
  return { thinking: leak.thinking, spoken: spoken || (!leak.thinking ? answerRaw.trim() : "") };
}