Chunk Overlap Evaluation: Precision Versus Continuity for Long Functions

# eval/overlap_metrics.py
from dataclasses import dataclass

@dataclass
class OverlapReport:
 overlap_pct: float
 hit_at_5: float
 unique_symbols_in_topk: float
 duplicate_ratio: float # 1 - unique/len(topk)
 continuity_score: float # fraction of golds spanning adjacent chunks that both retrieve

def duplicate_ratio(ids: list[str]) -> float:
 if not ids:
 return 0.0
 # ✅ Normalize by symbol id so path::fn duplicates count
 base = [i.split("::")[0] + "::" + i.split("::")[-1] for i in ids]
 return 1.0 - (len(set(base)) / len(base))

def sweep_overlaps(chunk_fn, queries, gold, sizes=(512, 768), overlaps=(0.0, 0.1, 0.2, 0.35)):
 rows = []
 for size in sizes:
 for ov in overlaps:
 chunks = chunk_fn(size=size, overlap=int(size * ov))
 index = build_temp_index(chunks) # ephemeral OpenSearch / pgvector
 hits, dups, cont = [], [], []
 for q in queries:
 top = retrieve(index, q.text, k=5)
 hits.append(1.0 if gold[q.id] & {c.symbol for c in top} else 0.0)
 dups.append(duplicate_ratio([c.id for c in top]))
 cont.append(continuity(q, top, gold))
 rows.append({
 "size": size, "overlap": ov,
 "hit@5": sum(hits)/len(hits),
 "dup": sum(dups)/len(dups),
 "continuity": sum(cont)/len(cont),
 })
 return rows # ✅ Pick knee: max hit@5 with dup < 0.25

// chunk/continuity-header.ts
export function withContinuityHeader(symbol: {
 path: string; name: string; text: string; parent?: string; prevSibling?: string;
}) {
 const header = [
 `// file: ${symbol.path}`,
 symbol.parent ? `// class: ${symbol.parent}` : null,
 symbol.prevSibling ? `// prev: ${symbol.prevSibling}` : null,
 ].filter(Boolean).join("\n");
 // ✅ Continuity without overlapping the previous body into this chunk
 return `${header}\n${symbol.text}`;
}