> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Observability Hooks • AI Agent SDK
> ObservabilityHooks: Observability hooks for escalation pipeline.
# ObservabilityHooks
> Defined in the [**observability**](../modules/observability) module.
AI Agent
Observability hooks for escalation pipeline.
Provides:
* Event emission
* Metrics collection
* Custom handler registration
* Tracing support
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
%%{init: {'theme': 'base', 'themeVariables': { 'primaryColor': '#8B0000', 'primaryTextColor': '#fff', 'primaryBorderColor': '#710101', 'lineColor': '#189AB4', 'secondaryColor': '#189AB4', 'tertiaryColor': '#fff' }}}%%
graph TD
event["Event Trigger"] --> hook["Hook: ObservabilityHooks"]
hook --> decision{"Decision"}
decision -- "Allow" --> proc["Process"]
decision -- "Deny" --> block["Block"]
style hook fill:#189AB4,color:#fff
style event fill:#8B0000,color:#fff
style proc fill:#8B0000,color:#fff
style block fill:#8B0000,color:#fff
```
## Constructor
No description available.
## Methods
Register an event handler.
Unregister an event handler.
Emit an event.
Set current session ID.
Set current stage.
Increment step counter.
Add to token count.
Get all recorded events.
Get collected metrics.
Reset all state.
Mark execution start.
Mark execution end.
Get execution summary.
## Usage
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
hooks = ObservabilityHooks()
# Register handler
hooks.on(EventType.STAGE_ESCALATE, lambda e: print(f"Escalated to {e.stage}"))
# Use with pipeline
pipeline = EscalationPipeline(observability=hooks)
```
## Source
`praisonaiagents/escalation/observability.py` at line 116
***
## Related Documentation