Version updated for https://github.com/hidai25/eval-view to version v0.1.7. This action is used across all versions by ? repositories. Go to the GitHub Marketplace to find the latest changes. Action Summary EvalView is a testing framework designed for AI agents, enabling developers to write test cases in YAML and automate the detection of regressions in behavior, cost, and latency during CI/CD workflows. By integrating with tools like LangGraph, CrewAI, OpenAI Assistants, and Anthropic Claude, it automates tasks such as tracking token costs, validating tool calls, and catching hallucinations, solving the challenges of manual testing and ensuring reliable agent performance before deployment.

Version updated for https://github.com/hidai25/eval-view to version v0.1.5. This action is used across all versions by ? repositories. Go to the GitHub Marketplace to find the latest changes. Release notes What’s New Statistical Pass/Fail System Variance-aware testing - Run tests multiple times to get statistically significant results Confidence levels - Configure how confident you want to be in pass/fail decisions CLI integration - New --runs flag to run tests multiple times # Run each test 5 times for statistical analysis evalview run --runs 5 LangGraph Adapter Fix Fixed adapter compatibility issues for better LangGraph integration Config-Free Runs Run evalview run without requiring a config file Automatically discovers test cases in the current directory Templates Added test case templates for common evaluation patterns Quick-start templates for tool calling, RAG, and multi-turn scenarios Node SDK License Fix Fixed license mismatch - now correctly uses Apache 2.

Version updated for https://github.com/hidai25/eval-view to version v0.1.4. This action is used across all versions by ? repositories. Go to the GitHub Marketplace to find the latest changes. Release notes What’s New Ollama Support (Free Local Evaluation) Ollama as LLM-as-judge - Run evaluations locally with zero API costs Auto-detection - Automatically detects Ollama running on localhost:11434 New adapter - Test LangGraph agents powered by local Llama models # Free local evaluation evalview run --judge-provider ollama --judge-model llama3.

Version updated for https://github.com/hidai25/eval-view to version v0.1.3. This action is used across all versions by ? repositories. Go to the GitHub Marketplace to find the latest changes. Release notes EvalView GitHub Action Pytest-style testing framework for AI agents — now available as a GitHub Action. Usage - uses: hidai25/eval-view@v0.1.3 with: openai-api-key: ${{ secrets.OPENAI_API_KEY }} Features - 🧪 Test LangGraph, CrewAI, OpenAI, Anthropic, and custom agents - ⚡ Parallel test execution (4 workers by default) - 📊 Auto-generated HTML reports - 💬 PR comments with test results - 🤖 LLM-as-judge output evaluation - 💰 Cost and latency threshold checks Action Inputs | Input | Description | Default | |----------------|---------------------------------|-----------------------| | openai-api-key | OpenAI API key for LLM-as-judge | - | | config-path | Path to config file | .