v1.8

agent0ai/agent-zerov1.8Apr 8, 2026by github-actions[bot]

AI Summary

This release introduces a built-in Skills Selector UI, significantly hardens memory integrity verification, and fixes a critical bug in tool argument validation.

Key Highlights

Built-in Skills Selector UI accessible from the chat input menu
Memory hardening via SHA-256 sidecar files and restricted filter evaluation
Tool argument validation fix handling empty `tool_args` dictionaries safely

New Features

Skills selector for browsing and activating skills directly in context
Memory integrity verification using SHA-256 sidecar files
Improved tool validation to prevent crashes on no-argument tool calls

Full Release Notes

## Agent Zero – Release Notes

**Key highlights: skill selector UI, memory hardening, and tool-arg validation fixes.**

- **Built-in Skills Selector** – A new plugin accessible from the chat input `+` menu lets you browse and activate available skills directly in the current context or project. Default configs now allow skills to be active from the start, saving time and tokens on setup.

- **Memory hardening** – FAISS index integrity is now verified via a SHA-256 sidecar file (`index.faiss.sha256`), written on every save. Filter evaluation in `memory_load` is hardened with an allowlist, length cap, and restricted `simple_eval` execution. Consolidation scoring now uses real relevance scores with best-score deduplication by memory ID. Input history is truncated before sending to the utility model to prevent context overflows.

- **Tool argument validation fix** – `validate_tool_request` previously crashed on any tool call that passed an empty `tool_args` dict (e.g. scheduler `list_tasks`, health checks) because an empty dict is falsy. The check is now a proper key-existence test, restoring correct behaviour for all no-argument tool calls.