Function labelSiblingClusters

src/tools/semantic-navigate.ts:147–183

(clusters: { files: FileInfo[]; pathPattern: string | null }[])

}

async function labelSiblingClusters(clusters: { files: FileInfo[]; pathPattern: string | null }[]): Promise<string[]> {
  if (clusters.length === 0) return [];
  if (clusters.length === 1) {
    const pp = clusters[0].pathPattern;
    if (pp) return [pp];
    return [clusters[0].files.map((f) => f.relativePath.split("/").pop()).join(", ").substring(0, 40)];
  }

  const clusterDescriptions = clusters.map((c, i) => {
    const fileList = c.files.map((f) => `${f.relativePath}: ${f.header || "no description"}`).join("\n  ");
    const pattern = c.pathPattern ? ` (pattern: ${c.pathPattern})` : "";
    return `Cluster ${i + 1}${pattern}:\n  ${fileList}`;
  });

  const prompt = `You are labeling clusters of code files. For each cluster below, produce EXACTLY one JSON array of objects, each with:
- "overarchingTheme": a sentence about the cluster's theme
- "distinguishingFeature": what makes this cluster unique vs siblings
- "label": EXACTLY 2 words describing the cluster

${clusterDescriptions.join("\n\n")}

Respond with ONLY a JSON array of ${clusters.length} objects. No other text.`;

  try {
    const response = await chatCompletion(prompt);
    const jsonMatch = response.match(/\[[\s\S]*\]/);
    if (!jsonMatch) return clusters.map((_, i) => `Cluster ${i + 1}`);
    const labels = JSON.parse(jsonMatch[0]) as { label: string }[];
    return labels.map((l, i) => {
      const pp = clusters[i].pathPattern;
      const base = l.label || `Cluster ${i + 1}`;
      return pp ? `${base} (${pp})` : base;
    });
  } catch {
    return clusters.map((c, i) => c.pathPattern ?? `Cluster ${i + 1}`);
  }
}

async function buildHierarchy(files: FileInfo[], vectors: number[][], maxClusters: number, depth: number, maxDepth: number): Promise<ClusterNode> {
  if (files.length <= MAX_FILES_PER_LEAF || depth >= maxDepth) {