Function parseTranscriptForVotes

src/transcript-parser.ts:15–71

(transcriptPath: string)

 * from recall and reference markers in assistant messages.
 */
export async function parseTranscriptForVotes(transcriptPath: string): Promise<TranscriptVoteData> {
  const recalledSet = new Set<string>();
  const referencedSet = new Set<string>();

  try {
    const stat = await fs.promises.stat(transcriptPath);
    if (stat.size === 0) return { recalledDocIds: [], referencedDocIds: [] };
  } catch {
    return { recalledDocIds: [], referencedDocIds: [] };
  }

  const rl = readline.createInterface({
    input: fs.createReadStream(transcriptPath, { encoding: 'utf-8' }),
    crlfDelay: Infinity,
  });

  for await (const line of rl) {
    const trimmed = line.trim();
    if (!trimmed) continue;

    // Host transcript schemas vary. Keep a raw-line fallback for recalled
    // markers that may live outside message.content (for example a plain
    // content string or top-level toolUseResult.stdout). Parsed scans below
    // additionally handle multiline recall regions after JSON decoding.
    extractRecalledDocIdsFromComment(trimmed, recalledSet);

    let entry: Record<string, unknown>;
    try {
      entry = JSON.parse(trimmed) as Record<string, unknown>;
    } catch {
      continue;
    }

    const message = entry['message'] as Record<string, unknown> | undefined;
    if (!message || !Array.isArray(message['content'])) continue;

    for (const block of message['content'] as Array<Record<string, unknown>>) {
      // Subagent and Bash recall output lands in a tool_result. Scan its decoded
      // content recursively because some hosts represent it as nested blocks.
      if (block['type'] === 'tool_result') {
        extractRecalledDocIdsFromValue(block['content'], recalledSet);
      }

      if (entry['type'] !== 'assistant' || block['type'] !== 'text') continue;
      const text = block['text'];
      if (typeof text !== 'string') continue;

      extractRecalledDocIds(text, recalledSet);
      extractReferencedDocIds(text, referencedSet);
    }
  }

  return {
    recalledDocIds: [...recalledSet],
    referencedDocIds: [...referencedSet],
  };
}