Fenil Faldu

[Bug]: Parsing error while patching Openai calls using litellm.completion with gpt-4o

1

### Contact Details [email protected] ### 📦 Package Version 0.3.26 ### 🎞️ Framework Version Litellm 1.58.2 ### 🔎 Describe the Bug @areibman At first it seemed it was an error from...

Sentry Integration Added

2

## 📥 Pull Request **📘 Description** This PR introduces Sentry integration into AgentOps SDK, providing robust error tracking and monitoring capabilities. The integration allows for flexible error tracking configuration at...

Updated AutoGen Provider for V4

3

## 📥 Pull Request This pull request closes the https://github.com/AgentOps-AI/agentops/issues/682 issue. **📘 Description** ->Added AutogenInstrumentor class that extends OpenTelemetry's BaseInstrumentor to capture Autogen-specific telemetry ->Implemented instrumentation for key Autogen functions...

Sessions detected with CrewAI

3

## 📥 Pull Request This pull request closes this https://github.com/AgentOps-AI/agentops/issues/907 issue. **📘 Description** Added a check in the `init() `method to log a warning if AgentOps has already been initialized....

### Contact Details [email protected] ### 📦 Package Version 0.4.6 ### 🎞️ Framework Version Open AI Agents SDK ### 🔎 Describe the Bug Reproduction Script: ``` AGENTOPS_API_KEY = os.getenv("AGENTOPS_API_KEY") agentops.init(api_key=AGENTOPS_API_KEY) agentops.start_session(tags=["simple-example"])...

feat: add AgentOps integration

1

# AgentOps Integration Added comprehensive documentation for AgentOps integration with Mem0, The documentation follows Mem0's standard format and provides users with clear instructions for setting up and using AgentOps monitoring...

introduce AutoGen instrumentation.

7

## 📥 Pull Request **📘 Description** - Added AutoGen instrumentation modules to support agent interactions, including agent-specific instrumentors and utilities. - Implemented new agent types and team structures for enhanced...

Closes #2258 Before After --- > [!NOTE] > Capture LLM model name and detailed token usage in `BaseOpenAIChatCompletionClient.create` and `.create_stream`, with streaming usage injection and end-of-stream attribute setting. > >...

Auto-inject include_usage for streaming for litellm calls

2

closes #2268 Some providers return usage only on the final streaming chunk when include_usage is requested. Without this, Phoenix undercounts tokens on streaming spans Before After