Skip to content

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

Rust

docs(design): note that V81 and the 24th tool are taken on release/3.1

AkitaOnRails8f6a15b3a2f6
diff --git a/docs/design-message-decisions.md b/docs/design-message-decisions.md
index f38dfb76..0285a427 100644
--- a/docs/design-message-decisions.md
+++ b/docs/design-message-decisions.md
@@ -71,7 +71,9 @@ CREATE INDEX idx_agent_messages_work
WHERE state = 'pending' AND work_id IS NOT NULL;
```
-V81 is the next free number today. Rust validates `decision` before the
+V81 was the next free number on `main` when this was written; `release/3.1`
+has since taken V81 (CodeBuddy's agent kind), so the migration takes the next
+free number when it is implemented. Rust validates `decision` before the
insert; a bad stored value becomes `MemoryError::MalformedRecord`, as a bad
`state` does. `AgentMessage` serializes the new fields only when they are set.
@@ -356,7 +358,8 @@ control, and fails with its guard removed.
## 9. Alternatives
- The convention-only route has no rule and no link.
-- A `memory_message_reply` tool is a 24th tool and a copy of the send path (Q7).
+- A `memory_message_reply` tool is one more tool (the 25th, since
+ `release/3.1` added `memory_restore_page`) and a copy of the send path (Q7).
- An answer on the question row needs a read of the decision project, which
the asker cannot do.
- With `requires_root: bool`, a new rule needs a new field.
@@ -404,7 +407,7 @@ control, and fails with its guard removed.
distinguished. **Recommended: (a)**: a single operator has one identity, and
the root rule covers risky decisions where agents cannot reach root.
- **Q7. Fields on `memory_message_send`, or a new `memory_message_reply`
- tool?** (a) Fields. (b) A new tool, which is a 24th tool and a copy of the
+ tool?** (a) Fields. (b) A new tool, which is one more tool and a copy of the
send path. **Recommended: (a)**: one send path, one scrub, one admission.
- **Q8. Is polling the only wait for 3.2?** (a) Yes. (b) A bounded `wait_ms`
now. **Recommended: (a)**. A later bounded wait needs no migration.