Skip to content

This release adds 2 notable features for engineering teams evaluating rollout.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agentic-ai agentic-coding ai autonomous-agent cli codegolf
+6 more
coding-agent developer-tools harness llm repl sandbox

Affected surfaces

auth breaking_upgrade

ReleasePort's take

Light signal
editorial:auto 13d

v1.7.7 forwards OPENAI_API_KEY to sandbox containers and prevents recursive sandboxing when MI_SANDBOX is set in config.

Why it matters: Developers using the sandbox with OpenAI models can now pass API credentials. The recursive sandboxing fix prevents configuration errors in nested environments. Routine upgrade for most users.

Summary

AI summary

Forward OPENAI_API_KEY environment variable to sandbox container and prevent recursive sandboxing by setting MI_SANDBOXED=1.

Changes in this release

Feature Medium

Forward OPENAI_API_KEY to sandbox container via -e.

Forward OPENAI_API_KEY to sandbox container via -e.

Source: llm_adapter@2026-05-21

Confidence: low

Bugfix Medium

Prevent recursive sandbox when MI_SANDBOX is set in config.

Prevent recursive sandbox when MI_SANDBOX is set in config.

Source: llm_adapter@2026-05-21

Confidence: high

Full changelog
  • Forward OPENAI_API_KEY to sandbox container via -e
  • Prevent recursive sandbox when MI_SANDBOX is set in config: container gets MI_SANDBOXED=1 to skip the sandbox code path

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

Track Tiny agentic loop with Docker sandbox

Get notified when new releases ship.

Sign up free

About Tiny agentic loop with Docker sandbox

All releases →

Related context

Earlier breaking changes

  • v1.8.0 Goal tool's `check` parameter now a judge prompt, not bash command.

Beta — feedback welcome: [email protected]