Default CTranslate2 intra threads to 1 on macOS

[jmpnop]

Summary

Default ARGOS_INTRA_THREADS to 1 on Darwin instead of 0.

This keeps the existing behavior on non-macOS platforms and still allows users to override the value explicitly with ARGOS_INTRA_THREADS.

Why

On macOS no-OpenMP CTranslate2 wheels, intra_threads=0 delegates to the backend default. In local testing with Argos Translate + CTranslate2 on macOS arm64, that backend auto-threading path fanned out into CPU worker pools and performed poorly for Argos' typical workload of many small paragraph/sentence translation batches.

It also reproduced a native abort on CTranslate2 4.7.2 / Python 3.14.5:

libc++abi: terminating due to uncaught exception of type std::__1::system_error:
condition_variable wait failed: Invalid argument

The crash report showed:

BS::thread_pool_light::worker()
std::__1::condition_variable::wait(...)
ctranslate2::python::TranslatorWrapper::translate_batch(...)

Validation

Environment:

macOS 26.5.1 arm64
Python 3.14.5
Argos Translate current settings module
CTranslate2 4.8.0
English -> Russian Argos model

Benchmark on the same 30-unit Markdown slice:

intra=0  TIMEOUT >60s
intra=1  elapsed=31.012s user=36.103s  sys=0.120s
intra=2  elapsed=48.529s user=84.297s  sys=19.564s
intra=4  elapsed=38.526s user=139.771s sys=28.153s
intra=8  elapsed=37.895s user=275.805s sys=28.084s

Full sustained regression with intra_threads=1:

units 749
chars 197463
ALL DONE 749 791.3

This makes 1 a safer and faster Darwin default for the tested Argos workload while preserving explicit user control.