Codebase Embeddings: Refresh Pipelines When Git SHAs Keep Moving

# CI on merge to main
PREV=$(cat s3://embed-state/last_sha || git rev-parse HEAD~1)
CURR=$(git rev-parse HEAD)
git diff --name-status $PREV...$CURR > /tmp/changed.txt

def work_items(diff_lines: list[str]) -> tuple[list[str], list[str]]:
    upsert, delete = [], []
    for line in diff_lines:
        status, path = line[0], line[2:].strip()
        if status == "D":
            delete.append(path)
        elif status in ("A", "M", "T"):
            if path.endswith((".ts", ".tsx", ".py", ".go")):
                upsert.append(path)
        elif status.startswith("R"):
            # rename: delete old, upsert new — parse git diff -M carefully
            pass
    return upsert, delete

// Prefer function/class boundaries for code RAG
export function chunkTypeScript(source: string, path: string): Chunk[] {
  // ts-morph or tree-sitter → symbol ranges
  // ✅ each chunk: {path, symbol, startLine, endLine, text, hash}
  // ❌ sliding windows that bisect signatures
  return [];
}

# OpenSearch example — analogous for pgvector
def upsert_chunks(chunks: list[dict], commit: str):
    for c in chunks:
        client.index(index="code", id=f"{c['path']}::{c['chunk_id']}", body={
            **c,
            "commit": commit,
            "embedding": embed(c["text"]),  # Bedrock embedding model
            "deleted": False,
        })

def tombstone(paths: list[str]):
    for p in paths:
        client.update_by_query(index="code", body={
            "query": {"term": {"path.keyword": p}},
            "script": {"source": "ctx._source.deleted = true"},
        })

s3://embed-state/last_sha
s3://embed-state/runs/{sha}.json  # counts, $ estimate, duration