Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
docs(architecture): note the web search kind and tier filters
AkitaOnRailsb33a0c32148c
diff --git a/docs/ARCHITECTURE.md b/docs/ARCHITECTURE.mdindex 28f844ec..84672981 100644--- a/docs/ARCHITECTURE.md+++ b/docs/ARCHITECTURE.md@@ -738,6 +738,10 @@ once and hands the same embedder and rerank stage to the MCP server and to`WebState` (`ai_memory_web::Recall`); the stage's four-call concurrency gate isshared, so the web search cannot add provider calls past it. A search with noscope stays the cross-project FTS5 ranker, as `memory_query(global=true)` is.+The web search also takes `kind` and `tier` filters, which every stream applies+in its own query (`PageFilter`), so a filtered search narrows each stream+before fusion and the reranker only sees pages the filter keeps;+`memory_query` and `/api/v1/search` pass no filter.`ai-memory-mcp/tests/suite/web_search_parity.rs` holds the orders together.`explain=1` on a project search renders, per hit, each stream's rank, raw scoreand RRF contribution, the fused score, the authority multiplier, the intent