hidai25/eval-view

v0.1.8 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 5mo Developer Productivity

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-benchmark agent-evaluation agentic-ai ai-agents anthropic autogen

+12 more

cli crewai evaluation langchain-agent langgraph llm mcp openai-assistants pytest python regression-testing testing

Summary

AI summary

Fixed the demo agent's division operation and unshadowed the list builtin.

Full changelog

What's New

uv Support for Faster Development

Added uv as an optional package manager for 2x faster installs
Both pip and uv are fully supported - use whichever you prefer
New Makefile targets: make install (uv) and make pip-install (pip)

CI Hardening

Config file support for ci.fail_on and ci.warn_on
Exit code 2 for execution errors (network, timeout) vs exit code 1 for test failures
Model/provider validation to catch mismatches early (e.g., llama3.2 + openai)

LangGraph Example

Added complete LangGraph example agent at examples/langgraph/agent/
Includes ReAct agent with search and calculator tools

UX Improvements

Diverse quickstart test cases (division, weather, multi-tool, multiplication)
Demo agent now supports division operations
GitHub star CTA always shows after quickstart
evalview connect shows actual paths instead of placeholders

Bug Fixes

Fixed list builtin being shadowed by CLI command
Fixed demo agent division support

Installation

pip install evalview==0.1.8

Full Changelog

https://github.com/hidai25/eval-view/compare/v0.1.7...v0.1.8

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track hidai25/eval-view

Get notified when new releases ship.

About hidai25/eval-view

Regression testing framework for AI agents. Save golden baselines, detect behavioral drift, and block regressions in CI. Works with LangGraph, CrewAI, OpenAI, Claude, and any HTTP API.

All releases →