The /admin/api/batch aggregator fans every sub-path to the PRIMARY ENGINE. After
moving cache-stats/cached-models/downloads to the coderai-system worker and
settings to the front, batching them still sent them to the (busy) engine — so the
models page kept loading its data from the slow engine.

Those endpoints now route to fast targets (front + system worker), so the batch's
connection-saving no longer applies and was actually the bottleneck. The models
page now loads each first-paint read directly to its correct target: settings →
front, cache-stats/cached-models/downloads → coderai-system, only models/
quantize-status → engine. The main model cards come from cached-models (system
worker), so the list paints fast even mid-generation.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011DDv7BchtZQWsnPG6Jm49m