Skip to main content
Centralized instrumentation hook for Strands agents with Fiddler integration. This hook provider automatically captures telemetry data from Strands agents and enriches OpenTelemetry spans with Fiddler-specific attributes. It handles three key events: before invocation, after tool execution, and after model calls. The hook is automatically injected when using StrandsAgentInstrumentor, so users typically don’t need to manually add it to their agents.

​
Example

from strands import Agent
from fiddler_strandsagents import FiddlerInstrumentationHook

# Manual usage (not needed with StrandsAgentInstrumentor)
agent = Agent(
    model=model,
    system_prompt="...",
    hooks=[FiddlerInstrumentationHook()]
)

​
register_hooks()

Register hook callbacks with the Strands agent registry. This method is called by the Strands framework to register callbacks for various agent lifecycle events.

​
Parameters

​
registry
HookRegistry
required
The HookRegistry to register callbacks with

​
tool_end()

Handle the completion of a tool invocation. Enriches the current OpenTelemetry span with:
  • Custom attributes set via set_span_attributes() (prefixed ‘fiddler.span.user.’)
  • gen_ai.tool.input — JSON-serialised input arguments passed to the tool
  • gen_ai.tool.output — Text extracted from the tool result content

​
Parameters

​
event
AfterToolCallEvent
required
AfterToolCallEvent (or legacy AfterToolInvocationEvent) containing tool execution details

​
model_end()

Handle the completion of a model invocation. Enriches the current OpenTelemetry span with:
  • gen_ai.llm.context — retrieved context set via set_llm_context()
  • Custom attributes set via set_span_attributes() (prefixed ‘fiddler.span.user.’)
  • gen_ai.llm.output — text extracted from the model’s response message

​
Parameters

​
event
AfterModelCallEvent
required
AfterModelCallEvent (or legacy AfterModelInvocationEvent) containing model execution details

​
before_invocation()

Handle the start of an agent invocation. Enriches the current OpenTelemetry span with:
  • Conversation ID set via set_conversation_id()
  • Session attributes set via set_session_attributes()
  • gen_ai.llm.input.user — text of the last user message in the invocation
Session attributes and conversation ID are also written to event.agent.trace_attributes so that Strands (>=1.19.0) propagates them natively to all child spans (model invoke, tool call, event-loop cycle, etc.) without needing manual parent-to-child denormalisation in a SpanProcessor.

​
Parameters

​
event
BeforeInvocationEvent
required
BeforeInvocationEvent containing agent invocation details