Maple agent tracing for Agno

Goal: every conversation with the Agno app shows up in Maple Agent Sessions as exactly one session, one turn per run(), with transcript, model calls, tool calls (failures marked), team-member lanes, tokens and cost where the provider returns it.

Mechanism: openinference-instrumentation-agno + OTel SDK + OTLP/HTTP exporter to Maple. Agno's setup_tracing(db=...) and AgentOS(tracing=True) only write to the AgentOS database; they never export OTLP.

Step 0: Detect versions and existing setup

1. Find the Python project file (pyproject.toml, requirements*.txt, uv.lock, poetry.lock) and the installed agno version. Target agno>=3.0 (verified 3.0.11). On Agno 2.x, openinference-instrumentation-agno needs agno>=2.5.0; the rest of this skill applies unchanged.
2. Grep for existing tracing: TracerProvider(, set_tracer_provider, AgnoInstrumentor, setup_tracing(, tracing=True, phoenix.otel.register, openlit.init, logfire.configure, langfuse, OpenAIInstrumentor, LiteLLMInstrumentor.
   • Existing TracerProvider of the app's own: reuse it. Add a BatchSpanProcessor(OTLPSpanExporter(...)) for Maple to it. Do not create a second provider.
   • Existing AgnoInstrumentor().instrument(...): edit that call (add config=); never call instrument() a second time (the second call is a silent no-op).
   • AgentOS(tracing=True) or setup_tracing(db=...): see Step 2c.
   • Any other LLM instrumentor on the same calls (OpenAI/LiteLLM OpenInference instrumentors, OpenLIT, register(auto_instrument=True)): remove it or scope it away from Agno, or every model call is recorded twice.
3. Find every place an Agent, Team or Workflow is run: .run(, .arun(, .print_response(, .aprint_response(, .continue_run(, .acontinue_run(. Note where the conversation/thread id lives in the request.

Step 1: Key and region