argenis de la rosa 18cb38b09e feat(cache): wire two-tier response cache, multi-provider token tracking, and cache analytics ... - Two-tier response cache: in-memory LRU (hot) + SQLite (warm) with TTL-aware eviction - Wire response cache into agent turn loop (temp==0.0, text-only responses only) - Parse Anthropic cache_creation_input_tokens/cache_read_input_tokens - Parse OpenAI prompt_tokens_details.cached_tokens - Add cached_input_tokens to TokenUsage, prompt_caching to ProviderCapabilities - Add CacheHit/CacheMiss observer events with Prometheus counters - Add response_cache_hot_entries config field (default: 256)		2026-03-24 15:17:14 +03:00
..
assertions.rs	test: restructure test suite into five-level taxonomy	2026-03-11 11:03:33 -04:00
helpers.rs	test: restructure test suite into five-level taxonomy	2026-03-11 11:03:33 -04:00
mock_channel.rs	test: restructure test suite into five-level taxonomy	2026-03-11 11:03:33 -04:00
mock_provider.rs	feat(cache): wire two-tier response cache, multi-provider token tracking, and cache analytics	2026-03-24 15:17:14 +03:00
mock_tools.rs	test: restructure test suite into five-level taxonomy	2026-03-11 11:03:33 -04:00
mod.rs	test: restructure test suite into five-level taxonomy	2026-03-11 11:03:33 -04:00
trace.rs	test: restructure test suite into five-level taxonomy	2026-03-11 11:03:33 -04:00