Skip to content

Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

Rust

Merge PR #637: support Podman without Docker in the wrapper (#636) [2.1]

AkitaOnRails614a8bdadb28
diff --cc CHANGELOG.md
index 7f6bcf6c,80dea219..67e8465f
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@@ -103,9 -44,6 +103,15 @@@ and this project adheres to [Semantic V
`dest_free_bytes`, so the same number is visible right before a migration.
### Fixed
++- The `bin/ai-memory` container wrapper now runs on Podman without Docker
++ (#636). It auto-selects the engine (`AI_MEMORY_DOCKER` override → `docker` →
++ `podman`), defaults to the fully-qualified `docker.io/akitaonrails/ai-memory`
++ image so Podman's non-interactive short-name resolution does not fail, and
++ preserves the selected engine in the standalone-container recovery script
++ `ai-memory upgrade` emits instead of hard-coding `docker`.
+- The OpenCode provider now sends `gpt-5.6-luna` requests to OpenCode Go's
+ Responses endpoint. Luna is not served through Chat Completions, where plain
+ and structured ai-memory calls returned HTTP 500 (#618).
- The pre-migration safety archive is now taken **before** the SQLite schema
is migrated, so it is a genuine pre-2.0 recovery point a 1.x binary can
reopen — restoring the documented "reversible upgrade" (#633). Previously the