Release history

hidai25/eval-view releases

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.

Back to tool Latest release

All releases

33 shown

No immediate action

v0.8.1 Mixed 14h

Watch fix + PEP561 + check --watch

Open

No immediate action

v0.8.0 New feature 2mo

Cassettes + schedule cron

Open

No immediate action

v0.7.1 Breaking risk 2mo

TOML test cases + CSV log import

Open

No immediate action

v0.7.0 New feature 3mo

Aider CLI adapter

Open

No immediate action

v0.6.2 New feature 3mo

Closed-model drift detection

Open

No immediate action

v0.6.1 New feature 4mo

MCP feature parity + new tools

Open

No immediate action

v0.6.0 New feature 4mo

Auto-heal engine

Open

No immediate action

v0.5.5 New feature 4mo

Commands + Native adapters

Open

No immediate action

v0.5.4 New feature 4mo

LLM model update + OpenClaw

Open

No immediate action

v0.5.3 Breaking risk 4mo

HTML report redesign

Open

No immediate action

v0.5.2 New feature 4mo

Cold‑start test generation + GPT‑5 support

Open

No immediate action

v0.5.1 New feature 4mo

evalview generate + approvals

Open

No immediate action

v0.5.0 New feature 4mo

Regression monitoring + Slack alerts

Open

Review required

v0.4.1 New feature 4mo

RCE / SSRF Auth

PII evaluation

Open

No immediate action

v0.4.0 New feature 4mo

Multi-turn conversation testing

Open

Review required

v0.3.2 Bug fix 4mo

Auth

Auth fix + timeout increase

Open

No immediate action

v0.3.0 Breaking risk 5mo

Claude Code MCP integration

Open

No immediate action

v0.2.9 Bug fix 5mo

Strip ANSI from MCP output

Open

Upgrade now

v0.2.8 Bug fix 5mo

Breaking upgrade

Bug fixes enable full workflow

Open

No immediate action

v0.2.7 Bug fix 5mo

Adapter method fix + CLI version

Open

No immediate action

v0.2.6 New feature 5mo

Claude Code integration

Open

No immediate action

v0.2.5 New feature 5mo

AGENT HEALTHY/REGRESSION DETECTED

Open

Config change

v0.2.4 New feature 5mo

Auth

/skill command + --dangerously-skip-permissions

Open

No immediate action

v0.2.3 New feature 6mo

Partial credit for sequence evaluation

Open

No immediate action

v0.2.1 New feature 6mo

/run, /test, /adapters, /compare

Open

No immediate action

v0.2.0 New feature 6mo

Subsequence matching + reliability metrics

Open

No immediate action

v0.1.9 Feature 6mo

Interactive chat + Ollama

Open

No immediate action

v0.1.8 Bug fix 6mo

Division fix + list shadowing

Open

No immediate action

v0.1.7 Bug fix 6mo

Goose fix + Skill Doctor example

Open

No immediate action

v0.1.6 New feature 6mo

Claude Code & OpenAI Codex testing

Open

No immediate action

v0.1.5 New feature 7mo

Statistical Pass/Fail System

Open

No immediate action

v0.1.4 New feature 7mo

Ollama support

Open

No immediate action

v0.1.3 New feature 7mo

EvalView GitHub Action

Open