Documentation Index
Fetch the complete documentation index at: https://docs.bitfab.ai/llms.txt
Use this file to discover all available pages before exploring further.
Bitfab integrates with the OpenAI Agents SDK via a tracing processor that automatically captures agent runs, tool calls, handoffs, and guardrails as traced spans — no manual withSpan or @span decorators needed.
Canonical signatures: TypeScript reference · Python reference
Supported Languages
| Language | Method | Status |
|---|
| TypeScript | getOpenAiTracingProcessor() | ✅ Supported |
| Python | get_openai_tracing_processor() | ✅ Supported |
| Ruby | — | Not yet supported |
| Go | — | Not yet supported |
Quick Start
import { Bitfab } from "bitfab"
import { setTraceProcessors } from "@openai/agents"
const bitfab = new Bitfab({ apiKey: process.env.BITFAB_API_KEY })
const processor = bitfab.getOpenAiTracingProcessor()
setTraceProcessors([processor])
// All agent.run() calls are now automatically traced
TypeScript
Installation
npm install bitfab @openai/agents
Method Signature
bitfab.getOpenAiTracingProcessor(): BitfabOpenAITracingProcessor
BitfabOpenAITracingProcessor instance that implements the OpenAI Agents SDK TracingProcessor interface.
Usage
import { Bitfab } from "bitfab"
import { Agent, run, setTraceProcessors } from "@openai/agents"
const bitfab = new Bitfab({ apiKey: process.env.BITFAB_API_KEY })
const processor = bitfab.getOpenAiTracingProcessor()
setTraceProcessors([processor])
const agent = new Agent({
name: "my-agent",
instructions: "You are a helpful assistant.",
model: "gpt-4o",
})
const result = await run(agent, "What's the weather?")
What Gets Captured
The processor implements the TracingProcessor interface and captures:
| Event | What’s Captured |
|---|
onTraceStart | Trace ID, workflow name, group ID |
onTraceEnd | Trace completion with timing |
onSpanStart | Span ID, parent ID, span type, name |
onSpanEnd | Output data, error (if any), timing |
Nesting with Core Tracing
If you wrap an agent invocation with withSpan, the OpenAI Agents spans nest as children:
const pipeline = bitfab.getFunction("my-pipeline")
const tracedRun = pipeline.withSpan(
{ name: "RunAgent", type: "agent" },
async (query: string) => {
return run(agent, query)
},
)
await tracedRun("What's the weather?")
// OpenAI Agents spans appear nested under the "RunAgent" span
Error Handling
All processor callbacks are wrapped in try/catch — errors are logged but never thrown. Your agent execution is never affected by tracing failures.
Python
Installation
pip install bitfab-py[openai-tracing]
openai-tracing extra installs openai-agents as a dependency.
Method Signature
bitfab.get_openai_tracing_processor() -> BitfabOpenAITracingProcessor
BitfabOpenAITracingProcessor instance that implements the OpenAI Agents SDK TracingProcessor interface.
Usage
import os
from bitfab import Bitfab
from agents import Agent, Runner, set_trace_processors
bitfab = Bitfab(api_key=os.environ["BITFAB_API_KEY"])
processor = bitfab.get_openai_tracing_processor()
set_trace_processors([processor])
agent = Agent(
name="my-agent",
instructions="You are a helpful assistant.",
model="gpt-4o",
)
result = await Runner.run(agent, "What's the weather?")
What Gets Captured
Same as TypeScript — the processor implements the TracingProcessor interface:
| Event | What’s Captured |
|---|
on_trace_start | Trace ID, workflow name, group ID |
on_trace_end | Trace completion with timing |
on_span_start | Span ID, parent ID, span type, name |
on_span_end | Output data, error (if any), timing |
Nesting with Core Tracing
@bitfab.span("my-pipeline", type="agent")
async def run_agent(query: str):
return await Runner.run(agent, query)
await run_agent("What's the weather?")
# OpenAI Agents spans appear nested under the "my-pipeline" span
Error Handling
All processor callbacks are wrapped in try/except — errors are logged but never raised. Your agent execution is never affected by tracing failures. Traces flush automatically via atexit hook.
