feat(agentic): Add 8 advanced optimization features for agentic workloads

perf(cache): Optimize cleanup for agentic workloads

feat(cache): Add auto cleanup at 90% capacity + fix config

feat(perf): Add 4 performance features - token cache, compression, dedup, stream cache

feat(cache): Add response caching layer with LRU memory backend

test: align signature cache tests with cache behavior

test: update signature cache tests

refactor(cache, translator): refine signature caching logic and tests, replace session-based logic with model group handling

refactor(cache, translator): remove session ID from signature caching and clean up logic

refactor(cache): simplify signature caching by removing sessionID parameter

fix(translator): update `HasValidSignature` to require `modelName` parameter for improved validation

feat(cache): handle gemini family in signature cache with fallback validator logic

fix(translator): enhance signature cache clearing logic and update test cases with model name

chore(translator): update cache functions to include model name parameter in tests

feat(translator): unify model group references by introducing `GetModelGroup` helper function

feat(translator): improve signature handling by associating with model name in cache functions

refactor(cache): remove max entries logic and extend signature TTL to 3 hours

fix(server): resolve memory leaks causing OOM in k8s deployment

refactor: Improve cache eviction ordering and clean up session ID usage

feat(cache): add signature cache for Claude thinking blocks