CrewAI

Trace crews built with CrewAI  with Rius: the model calls the framework makes arrive as generations with tokens and cost, and observe wrappers give the run and its tools their shape. This guide covers the Python framework; the runnable example behind it lives in agent-observability-examples .

How coverage works

CrewAI 1.x drives the OpenAI client natively (it is a hard dependency), so the openai integration captures its model calls. LiteLLM is an optional fallback the framework uses only when it is installed; in that setup, use the litellm integration instead.

As with other frameworks covered through a client-library integration, the crew structure runs inside the framework where auto-instrumentation cannot see it: wrap the entrypoint and the tool bodies with observe.

CrewAI also ships its own tracing product and asks about it interactively on first run; set CREWAI_TRACING_ENABLED=false to keep it off non-interactively (CI, containers).

Setup

pip install "glassflow-rius[openai]" crewai

import rius
from crewai import Agent, Crew, Task
from crewai.tools import tool
from rius import SpanKind
 
rius.init(api_key="gf_...", service_name="my-agent")
 
 
@tool("account_status")
@rius.observe(kind=SpanKind.TOOL)
def account_status(email: str) -> str:
    """Fetch a customer's account standing by email."""
    return lookup(email)
 
 
support_agent = Agent(
    role="Support specialist",
    goal="Answer support tickets accurately and concisely.",
    backstory="You resolve product and account questions.",
    tools=[account_status],
    llm="gpt-5-mini",
)
 
 
@rius.observe(name="handle-ticket", kind=SpanKind.AGENT)
def handle_ticket(ticket: str) -> str:
    task = Task(
        description=f"Resolve this support ticket: {ticket}",
        expected_output="A short, direct answer.",
        agent=support_agent,
    )
    return str(Crew(agents=[support_agent], tasks=[task]).kickoff())

The decorator order on tools matters: @tool outermost, observe on the function body. The TOOL span parents under the run through ambient context.

What lands where

A run that calls a tool looks like this (real trace from the example, crewai 1.15.18):

handle-ticket                AGENT   8.4s
├─ ChatCompletion            LLM     3.9s   agent decides to call the tool
├─ search_knowledge_base     TOOL    0ms
└─ ChatCompletion            LLM     4.3s   agent answers

Blind spots

Verified against crewai 1.15.18:

• Crew and task structure produces no spans. Which task a generation belongs to is not visible from the trace; wrap per-task entrypoints with observe if that matters to you.
• Generation span names are generic (ChatCompletion).
• First run prompts interactively about CrewAI’s own tracing; set CREWAI_TRACING_ENABLED=false where no terminal is attached.

Sessions

One conversation or job is one session: scope each kickoff with rius.session(), reusing your own id.

Verify

Run one ticket that calls a tool, then open the trace in the console: the root AGENT span, the LLM generations with model, tokens, and cost, and your named TOOL spans should all be there.