Skip to content

great_cto

v2.64.1 Bugfix

This release fixes issues for SREs watching stability and regressions.

Published 1mo AI Agents & Assistants
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agentic-coding claude-code-plugin claude-code-skills claude-code-subagents code-review cto
+2 more
multi-agent sdlc

Affected surfaces

auth

Summary

AI summary

Unauthenticated claude board triggers now show a clear error with fix hint and child agents no longer inherit parent Claude-Code session identity.

Changes in this release

Bugfix Medium

Unauthenticated `claude` board trigger now shows clear error and fix hint instead of misleading success message.

Unauthenticated `claude` board trigger now shows clear error and fix hint instead of misleading success message.

Source: llm_adapter@2026-06-10

Confidence: high

 —
Bugfix Medium

Spawned agent's environment no longer inherits parent Claude-Code session identity.

Spawned agent's environment no longer inherits parent Claude-Code session identity.

Source: llm_adapter@2026-06-10

Confidence: high

 —
Full changelog

Patch on the v2.64.0 launch control:

  • A board-triggered claude that can't authenticate now shows a clear error + fix hint ('run the board where claude is logged in, or set ANTHROPIC_API_KEY') instead of a misleading 'result (success)'.
  • The spawned agent's env is stripped of this process's Claude-Code session identity so a board launched from inside a Claude Code session doesn't hand the child its parent's identity.

Note: the 401 some saw when triggering from inside an automated agent session is an env artifact (host-brokered auth) — a normal logged-in terminal authenticates fine.

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 great_cto

Get notified when new releases ship.

Sign up free

About great_cto

Engineering-management layer of 34 specialist AI agents covering the full SDLC (architect, PM, senior-dev, reviewer, QA, security, devops, L3-support + 18 archetype-specific reviewers) with auto-detected archetypes and compliance gates (PCI-DSS, HIPAA, FedRAMP, GDPR, EU AI Act). Runs in Claude Code, Cursor, Codex CLI, Aider, and Continue via AGENTS.md + MCP. MIT.

All releases →

Related context

Earlier breaking changes

  • v2.72.2 Removes Autopilot sidebar item and Operate topbar button from dev board.
  • v2.55.0 Hard-gates the Build board; redirects invite sessions to Operate for operators.
  • v2.43.0 Runtime now blocks autonomous execution of irreversible actions without prior human checkpoint.
  • v2.43.0 Adds reversible and blastRadius fields to every flow step.
  • v2.32.0 Removed AgentShield scanner and its CLI commands.

Beta — feedback welcome: [email protected]