Auth patterns for agent tools
Agent tools need identity, delegation, tenant scoping, and least privilege from the first production run.
An agent using a tool is still acting on behalf of a user, team, application, or service account. That identity must be explicit.
AstraRunner treats this as an execution-platform concern: the run needs durable state, traceable decisions, cost visibility, and enough structure for teams to review what happened after the agent finishes.
Patterns that work
- Use scoped service identities for background agents.
- Delegate user authority only when needed.
- Bind tenant and app context to every tool call.
- Record the actor chain in audit logs.
Implementation checklist
- Define allowed scopes per tool.
- Rotate secrets and tokens.
- Block cross-tenant access by default.
- Review high-privilege tools regularly.
Watch outs
- Shared API keys erase accountability.
- Agents can overuse broad user tokens.
- Auth failures should halt, not prompt around policy.
Related reading
How this fits the Astra stack
AstraRunner owns the operational path for agent work: orchestration, scheduling, approval gates, traces, costs, and role-agent handoffs. AstraMemory owns durable context and retrieval. AstraGenie turns those capabilities into product workflows for teams that want automation without rebuilding the platform layer.