Skip to content

docs(skills): objectstack-ai says agent memory is enforced by the AI runtime, not declared only #21652

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
os-zhuang merged 1 commit into from
Oct 4, 2026
Merged

docs(skills): objectstack-ai says agent memory is enforced by the AI runtime, not declared only #21652

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions skills/objectstack-ai/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -309,8 +309,11 @@ there is **no top-level `temperature` / `maxTokens`** on an agent

1. **Mistaking `guardrails` for a gate.** `guardrails` is enforced per user turn
by the AI runtime ☁️ — token and time limits, blocked tool names and categories
refused — but it is a limit, not an approval; `memory` is declared only — no
runtime reads it. For a gate that is **enforced**, use
refused — but it is a limit, not an approval; `memory` is enforced by the AI
runtime ☁️ too — long-term notes are recalled and reflected on, `maxEntries`
and `reflectionInterval` are required once `longTerm.enabled` is true, and
there is no storage backend to choose — and neither is a gate. For a gate
that is **enforced**, use
`enableActionApproval: true` (approval queue ☁️), `ai.requiresConfirmation` on
the **action**, or `approval: 'always'` on an MCP tool binding. AI metadata
edits are already gated: they land as drafts a human must publish (ADR-0033).
Expand Down
Loading