[FR] Add tracing support for Other coding agent CLI tools

Willingness to contribute

No. I cannot contribute this feature at this time.

Proposal Summary

Add support for Other coding agent CLI tools

Currently MLflow supports tracing for only Claude Code. Apart from Claude Code, there are other numerous tools which are both free and paid to use such as Gemini CLI(Free to use) Codex CLI(Openai API/ Using subscription) Opencode CLI(Both paid as well as free using local models) Qwen Code(Open-source free to use) Droid Aider CLI Tool Goose CLI

Motivation

What is the use case for this feature?

MLflow already supports evaluation of traces. Having support for other cli tools help in evaluating the performance of each tool specific to the codebase which would enable in selecting the most appropriate CLI tool for each specific use case.

Why is this use case valuable to support for MLflow users in general?

MLflow already supports evaluation of traces. Having support for other cli tools help in evaluating the performance of each tool specific to the codebase which would enable in selecting the most appropriate CLI tool for each specific use case.

Why is this use case valuable to support for your project(s) or organization?

MLflow already supports evaluation of traces. Having support for other cli tools help in evaluating the performance of each tool specific to the codebase which would enable in selecting the most appropriate CLI tool for each specific use case.

Why is it currently difficult to achieve this use case?

There isn't any way to trace the cli tools for observability and have evaluation for the same.

Details

No response

What machine learning domain(s) is this feature request about?

• domain/genai: LLMs, Agents, and other GenAI-related use cases
• domain/classical-ml: Traditional machine learning, such as linear regression.
• domain/deep-learning: Deep learning and neural networks.
• domain/platform: MLflow platform foundation, not specific to a particular machine learning domain.

What area(s) of MLflow is this feature request about?

• area/tracking: Tracking Service, tracking client APIs, autologging
• area/model-registry: Model Registry service, APIs, and the fluent client calls for Model Registry
• area/scoring: MLflow model serving, deployment tools, Spark UDFs
• area/evaluation: MLflow model evaluation features, evaluation metrics, and evaluation workflows
• area/prompt: MLflow prompt engineering features, prompt templates, and prompt management
• area/tracing: MLflow Tracing features, tracing APIs, and LLM tracing functionality
• area/gateway: MLflow AI Gateway client APIs, server, and third-party integrations
• area/projects: MLproject format, project running backends
• area/uiux: Front-end, user experience, plotting
• area/docs: MLflow documentation pages