Load sentence-transformers on the existing cache miss and construct the
preloaded model off the shared background event loop. Start warm-up before
chat restoration inside extensible init_a0, preserving start-hook control
and sharing the loaded model with ordinary runtime requests.
Remove unused speech preload imports and dead warm-up functions. Seed APT
indexes only when absent, skipping the refresh on normal container boots.
Keep the existing Python tunnel service and its provider lifecycle.
Validation: 49 focused framework tests passed, including extension-hook
short-circuit behavior, concurrent embedding-cache reuse, APT cache states,
tunnel behavior and CSRF origins. Three cold Fable chat trials per version:
median submit-to-first-token 9.588s -> 4.234s;
local preparation 6.904s -> 1.197s;
HTTP readiness 42.637s -> 41.139s;
boot-to-first-token 52.093s -> 46.657s.
Provider timing varies; these are local repeated measurements. The live
baseline already omitted APT refresh, so it receives no timing credit.
Cache the underlying SentenceTransformer by its effective constructor options so startup preload and first-chat initialization share one instance while wrappers keep their own runtime configuration. Pass the runtime embedding configuration through preload and cover reuse, concurrency, option changes, and failure handling.
