1989366844
- Remove duplicate span append + tool call decision logging block (lines 328-426) - Fix _extract_tool_calls_from_response to use getattr() instead of .get() on objects - Fix _calculate_cost to use exact match first, then longest-prefix match (prevents gpt-4o-mini matching gpt-4 pricing) - Fix test mock setup: set return_value BEFORE wrap_openai() so wrapper captures correct original - All 11 OpenAI integration tests + 8 SDK tests passing (19/19)
AgentLens Python SDK
AgentLens provides observability for AI agents by tracing decisions, not just API calls.
Installation
pip install agentlens
Quick Start
from agentlens import init, trace
# Initialize AgentLens
init(api_key="your-api-key", endpoint="https://agentlens.vectry.tech")
# Trace your agent functions
@trace(name="research-agent")
async def research(topic: str) -> str:
return f"Researching: {topic}"
Features
- Decision Tracing: Log and visualize agent decisions with alternatives
- Context Awareness: Monitor context window utilization
- Cost Intelligence: Track token usage and costs per operation
- Integrations: Native support for LangChain and OpenAI
Documentation
Full documentation available at https://agentlens.vectry.tech/docs
License
MIT © 2026 Vectry