kevinveenbirkenbachandClaude Opus 5 79fde0e0ba perf(i18n): run the cheap languages first and stop saturating the model ...

Every catalog got a lane derived from the CPU count, so twenty requests met one model instance. That is not throughput, it is self-inflicted saturation: a single catalog recorded 425 translated, 9 discarded and 40 requests refused with HTTP 503, and a discarded entry is simply left pending.

The work is now split by the backend that will answer it. The languages the engine serves keep the wide pool, because Argos answers in about 0.15s; the rest run after them with two lanes, one to occupy the model and one to refill it while the first writes back. Each pass builds its own client, so the chat pass does not inherit the worker count the engine pass was sized with.

Order is the larger half of this. The table is alphabetical, which is why the last run spent its first 45 minutes on af, a language with no Argos model, while fr and de sat untouched. Cost order delivers the engine languages first. For domain=docs that is 47 catalogs of 3963 entries each in roughly an hour; for domain=core it changes nothing today, because those catalogs are already translated.

The test picks aa against fr on purpose: both orders agree on every pair the fixtures held before, so a test built from them would have passed against the old single pass as well.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-10-18 12:49:04 +02:00

..

docs

…

i18n

perf(i18n): run the cheap languages first and stop saturating the model

2026-10-18 12:49:04 +02:00

__init__.py

…

test_graph.py

…

test_tree_shadow_folder.py

…

test_tree.py

…