Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
Rust
docs(changelog): word the operation-id entry as a fix
AkitaOnRails0a2317023c56
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 8e015743..a1c67e30 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -12,11 +12,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0provider. (#1026)### Fixed-- The provider-health wrapper now forwards the operation-id completions- (`complete_with_operation_id`, `complete_structured_raw_with_operation_id`).- They fell to the trait defaults, which drop the caller's id, so every retry- of one logical operation got a fresh id and, for OpenCode, a new session- header on every call. (#1085)+- Fixed the provider-health wrapper dropping the caller's operation id: its+ `complete_with_operation_id` and `complete_structured_raw_with_operation_id`+ fell to the trait defaults, so every retry of one logical operation got a+ fresh id and, for OpenCode, a new session header on every call. The wrapper+ now forwards both. (#1085)- Fixed interrupted launchers blocking an immediate managed-workstream restartby adding explicit `ai-memory run --force-unlock` recovery. The serveratomically expires and replaces only a lease attributed to the same