Skip to content

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.md
index 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