Skip to content

Agent AFK

v5.46.1 Bugfix

This release fixes issues for SREs watching stability and regressions.

Published 13d AI Agents & Assistants
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

afk agent-framework agents ai anthropic autonomous-agent
+14 more
claude claude-code cli coding-agent daemon harness-engineering llm mcp model-context-protocol openai self-improving subagent telegram-bot typescript

Summary

AI summary

Fixed subagent handling by bounding read‑only research agents and degrading empty runs with no terminal output.

Changes in this release

Bugfix Medium

Fixes read-only research agents being unbound and degrades empty no-terminal runs to marked partials.

Fixes read-only research agents being unbound and degrades empty no-terminal runs to marked partials.

Source: llm_adapter@2026-07-14

Confidence: low

 —
Bugfix Low

Binds read-only research agents in subagent.

Binds read-only research agents in subagent.

Source: granite4.1:30b@2026-07-14-audit

Confidence: low

 —
Bugfix Low

Degrades empty no-terminal runs to marked partials in subagent.

Degrades empty no-terminal runs to marked partials in subagent.

Source: granite4.1:30b@2026-07-14-audit

Confidence: low

 —
Full changelog

What's Changed

  • fix(subagent): bound read-only research agents + degrade empty no-terminal run to a marked partial by @griffinwork40 in https://github.com/griffinwork40/agent-afk/pull/597

Full Changelog: https://github.com/griffinwork40/agent-afk/compare/v5.46.0...v5.46.1

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 Agent AFK

Get notified when new releases ship.

Sign up free

About Agent AFK

Coding-agent harness built for unattended, away-from-keyboard runs across four surfaces sharing one session manager: one-shot CLI, REPL, cron-friendly headless daemon, and a Telegram bot. Editable agent loop (prompts, permission gates, model routing, explicit terminal states), MCP (stdio/HTTP/SSE + OAuth), lifecycle hooks, background subagents, plan mode, cross-session memory, and an append-only trace receipt (`afk trace show`). Works with Anthropic and any OpenAI-compatible endpoint (GPT, Codex, local MLX/llama.cpp/Ollama)

All releases →

Related context

Beta — feedback welcome: [email protected]