feat(server): hot-reload config store and reloadable infra clients

- Replace single Load() with a watching Store that re-reads config files
  (and config.local.yaml) and fans out a ReloadEvent with a per-field diff
  so consumers can decide whether the change is hot-applicable or requires
  a process restart.
- Wrap llm, retrieval, vector store, and object storage clients in
  Reloadable* shells so the bootstrap can swap their underlying impls when
  config changes without re-instantiating handlers.
- Make jwt.Manager and ops TokenIssuer mutable under a lock so secrets and
  TTLs can be rotated live; thread default plan code through a setter on
  the ops AdminUserService.
- Wire ConfigStore through bootstrap and every cmd/main.go, scheduler /
  worker / tenant-api / ops-api start the watcher; services and handlers
  take a config.Provider so they always read current values for things
  like generation.stream_enabled, scheduler dispatch, retrieval, etc.
- Switch shared/config decoding off viper to a Kratos-derived runtime
  package so env placeholders (\${VAR:default}) resolve consistently and
  the same source machinery powers both the loader and the watcher.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

server/internal/tenant/app/article_selection_optimize_service.go

@@ -39,6 +39,7 @@ type ArticleSelectionOptimizeService struct {
 	pool                *pgxpool.Pool
 	llm                 llm.Client
 	defaultMaxOutTokens int64
+	configProvider      runtimeConfigProvider
 	cache               sharedcache.Cache
 }
 
@@ -59,6 +60,11 @@ func (s *ArticleSelectionOptimizeService) WithCache(c sharedcache.Cache) *Articl
 	return s
 }
 
+func (s *ArticleSelectionOptimizeService) WithConfigProvider(provider runtimeConfigProvider) *ArticleSelectionOptimizeService {
+	s.configProvider = provider
+	return s
+}
+
 func (s *ArticleSelectionOptimizeService) ValidateRequest(
 	ctx context.Context,
 	articleID int64,
@@ -174,6 +180,11 @@ func (s *ArticleSelectionOptimizeService) ensureArticleEditable(
 
 func (s *ArticleSelectionOptimizeService) resolveMaxOutputTokens(selectedText string) int64 {
 	limit := s.defaultMaxOutTokens
+	if s != nil && s.configProvider != nil {
+		if cfg := s.configProvider.Current(); cfg != nil {
+			limit = cfg.LLM.MaxOutputTokens
+		}
+	}
 	if limit <= 0 {
 		limit = 1200
 	}