diff --git a/docs/4-implementation/agent-state/config-changes.md b/docs/4-implementation/agent-state/config-changes.md index da14096fc..8276d9768 100644 --- a/docs/4-implementation/agent-state/config-changes.md +++ b/docs/4-implementation/agent-state/config-changes.md @@ -197,9 +197,10 @@ hive-c0re pushes nothing to it, keeps no clone and reads nothing from it: forge Each agent is a **read collaborator on its own** `agent-configs/` repo, so it can clone it and open a config PR through the AGit flow (no push access needed), but not a member of any other agent's, so it can't reach -another agent's config through the forge. A grant of more than read, made by -an operator or before agents got read, is left as it is: the `AddRepoMember` -node only adds read where the agent has none. Branch protection keeps the agent off the `main` push +another agent's config through the forge. The `AddRepoMember` node +leaves a grant of more than read, made by an operator or before agents got +read, as it finds it, and only adds read where the agent has none. Branch +protection keeps the agent off the `main` push allowlist and allowlists merging to the `operators` team only, so an agent can't fast-forward its own config or self-merge its PR (see [Config changes](#config-changes) above). hive-c0re passes the credential to