Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
Merge pull request #1376 from A220man/portfolio/ryan/7cda5ed614b0
AkitaOnRailscbfd49eef554
diff --cc CHANGELOG.mdindex 1eb4e308,e4ad050f..34d6db2f--- a/CHANGELOG.md+++ b/CHANGELOG.md@@@ -12,18 -12,11 +12,23 @@@ version in [`docs/changelog/`](docs/cha## [Unreleased]### Fixed+ - Corrected stale claims in `docs/comparison.md` and `docs/competitive-parity.md`+ that said Windows has no service step and the Windows install is experimental.+ The 3.1 `install.ps1` + `setup` Windows service step is shipped production,+ not experimental; the "3.0 (unreleased)" observation-stream note is corrected+ to reflect the released 3.0 line. (#1271)+- Made the executable auto-improvement eval policy server-owned. Manual CLI and+ HTTP reviews now use `[auto_improve.eval]` from the server process, and legacy+ requests that try to supply an `eval` object fail closed with an upgrade+ message.+- Made managed cross-harness continuation survive quota exhaustion without a+ voluntary handoff. The startup packet now places its server-authored resume+ directive outside the untrusted transcript fence, and refreshed+ `CLAUDE.md` / `AGENTS.md` routing tells an incoming agent that "continue",+ "resume", and "pick up where we left off" must consult the private+ `AI_MEMORY_PREVIOUS_SESSION_HISTORY` dossier when the managed-run variables+ are present. The dossier remains untrusted evidence and stays local to the+ launcher machine.## [3.1.0] - 2026-10-16