Observers, watches, and alerts

When to use

• Observability — log model responses, tool calls, token usage.
• Runtime safety — block dangerous tool arguments, halt the agent.
• Reactive metrics — fire on every Nth response, or every M seconds.
• Loop / repetition detection — catch infinite tool-call loops.
• Stateful monitoring — anything that needs to remember prior events to decide what to do next.

Two observer shapes

Both are stream subscribers under the hood — registered on the agent rather than directly on the stream.