Jyotisha/frontend/src/lib/rectification-agentic/v9/collect-prompt.ts

/**
 * Server-owned collect stems join the same assistant turn. Comparison is
 * exact identity of the prompt string being attached, never a semantic
 * “did this body already ask”.
 */

const SENTENCE_SPLIT = /(?<=[。！？?\n])/;
const NARRATIVE_SENTENCE = /范围|记下|对照|\d{1,2}:\d{2}/;

export const EVIDENCE_VALUE_JUDGMENT_PHRASES = [
  "很有帮助",
  "很有价值",
  "很有分量",
  "特别有用",
] as const;

function spokenSentences(body: string): string[] {
  return body.split(SENTENCE_SPLIT).map((part) => part.trim()).filter(Boolean);
}

export function trimEvidenceTurnBody(body: string, options?: { maxSentences?: number }): string {
  const spoken = body.trim();
  if (!spoken) return "";
  const sentences = spokenSentences(spoken);
  const maxSentences = options?.maxSentences;
  let text: string;
  if (typeof maxSentences === "number" && maxSentences > 0) {
    text = sentences.length > maxSentences ? sentences.slice(0, maxSentences).join("") : spoken;
  } else {
    text = sentences.length > 2
      ? (/[。！？?]$/.test(sentences[0] ?? "") ? sentences[0] ?? "" : `${sentences[0] ?? ""}。`)
      : spoken;
  }
  for (const phrase of EVIDENCE_VALUE_JUDGMENT_PHRASES) {
    text = text.replaceAll(phrase, "");
  }
  return text.replace(/[，、]{2,}/g, "，").replace(/[ \t]+/g, " ").trim();
}

export function trimSpokenTurnForInterview(body: string, terminalNote: boolean): string {
  return terminalNote
    ? trimEvidenceTurnBody(body, { maxSentences: 3 })
    : trimEvidenceTurnBody(body);
}

function isQuestionSentence(text: string, stem: string): boolean {
  if (!text) return false;
  if (stem && text === stem) return true;
  const prefix = stem.slice(0, 12);
  if (prefix && text.startsWith(prefix)) return true;
  return /[？?]$/.test(text);
}

export function stripVerbalWindowChange(body: string): string {
  const stripped = body
    .replace(/以你说的.{0,40}为准/g, "")
    .replace(/[，、]{2,}/g, "，")
    .replace(/[ \t]+/g, " ")
    .replace(/[，、]+\s*(?=[。．.！？!?；;]|$)/g, "")
    .trim();
  if (!stripped || /^[，、。．.！？!?；;：:\s]+$/.test(stripped)) return "";
  return stripped;
}

export function stripQuestionSentences(body: string, stem: string): string {
  const prompt = stem.trim();
  const spoken = body.trim();
  if (!spoken) return "";
  const kept: string[] = [];
  let dropContinuation = false;
  for (const part of spoken.split(SENTENCE_SPLIT)) {
    const text = part.trim();
    if (!text) continue;
    if (isQuestionSentence(text, prompt)) {
      dropContinuation = true;
      continue;
    }
    if (dropContinuation && !NARRATIVE_SENTENCE.test(text)) {
      dropContinuation = false;
      continue;
    }
    dropContinuation = false;
    kept.push(part);
  }
  return kept.join("").trim();
}

export function composeCollectSpokenAssistantText(body: string, prompt: string): string {
  const stem = prompt.trim();
  const spoken = body.trim();
  if (!stem) return spoken;
  if (!spoken || spoken === stem) return stem;
  const stripped = stripQuestionSentences(spoken, stem);
  if (!stripped) return stem;
  const suffix = `\n\n${stem}`;
  if (stripped.includes(stem)) return stripped;
  if (stripped.length >= suffix.length && stripped.slice(stripped.length - suffix.length) === suffix) {
    return stripped;
  }
  return `${stripped}${suffix}`;
}

/** Idle-path gap copy joins the existing evidence recap instead of a second turn. */
export function composeIdleGapIntoSpoken(body: string, gap: string): string {
  const spoken = body.trim();
  const gapText = gap.trim();
  if (!gapText) return spoken;
  if (!/就能开始筛|现在记下的是/.test(gapText)) return spoken;
  if (!spoken) return gapText;
  if (spoken.includes(gapText) || spoken.includes("就能开始筛") || spoken.includes("现在记下的是")) {
    return spoken;
  }
  const prefix = /[。！？!?]$/u.test(spoken) ? spoken : `${spoken}。`;
  return `${prefix}${gapText}`;
}

export function detachCollectSpokenAssistantText(body: string, prompt: string): string {
  const stem = prompt.trim();
  const spoken = body.trim();
  if (!stem || !spoken || spoken === stem) return spoken;
  const suffix = `\n\n${stem}`;
  if (spoken.length >= suffix.length && spoken.slice(spoken.length - suffix.length) === suffix) {
    return spoken.slice(0, spoken.length - suffix.length).trim();
  }
  return spoken;
}