Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
docs(changelog): reference #798 for C1 access reinforcement
AkitaOnRails85d8a79bb72c
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 0bfec8ac..e5dc57e8 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -19,7 +19,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0actor, throttled to ≤1 per (page, operator) per minute, and FTS-exempt. It isstrictly additive — reinforcement only raises retention scores, never blocks,never touches the response payloads, and adds no new MCP tool (still 23)- (#NNN).+ (#798).- Reasoning tier on the LLM synthesis paths: an opt-in `reasoning` argument on`memory_query` (its `answer` path) and `memory_explore` (borrowed fromHoncho's reasoning-effort ladder; targets the 2.4 line). The knob is a schema