Fixes the models page's 6-7s stall and reduces engine hits generally:

- loadCachedModels awaited /admin/api/models (engine) before painting the cached-
  models cards, so the fast list waited on the slow engine. /admin/api/models (and
  accel-presets/accel-loras/turboquant-info/model-enable/model-disable) are pure
  config reads/edits, so they now route to the coderai-system worker (it has
  config_manager + models.json) — fast, off the engine.

- model-loaded-status is now served from the FRONT's own state: loaded comes from
  the registry (the front issues every load/unload; the supervisor keeps each
  engine's resident set fresh via the cheap engine-state poll) and running from the
  front's in-flight tracking. Per-model instance detail is synced from the engine
  ONLY when it's idle (inflight==0) and cached otherwise — no engine hit during
  generation. This is the "front maintains its own list, syncs when not under load"
  model.

- The 1s Tasks poll now skips the engine entirely when the primary is mid-
  generation, serving the merged/synthesized list from cache + live in-flight
  tracking instead of burning the timeout.

Verified: model-loaded-status returns front-native loaded/running with no engine
call while busy; compiles.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011DDv7BchtZQWsnPG6Jm49m