great_cto

v2.77.2 Breaking

This release includes breaking changes for platform teams planning a safe upgrade.

Published 24d AI Agents & Assistants

View tool

✓ 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

Summary

AI summary

Board now self-heals duplicate project slugs and retains task view during transient failures.

Full changelog

Board bughunt wave 2 + honest storefront

Board: projects registry self-heals — duplicate slugs are deduped, entries
with existing paths win, a moved repo updates its entry instead of adding a
second one. Fixes the "board shows 0 tasks after a repo move" failure.
Board: transient bd failures no longer wipe the view — the server keeps
the last-good task cache on a lock/timeout and the UI re-verifies an empty SSE
snapshot before accepting it.
Board: zero external calls — marked, DOMPurify and Geist/Geist Mono
variable fonts (latin, ~56 KB) are vendored into public/assets/; a new
no-cdn test guards regressions. Works fully offline now.
Board: .beads watcher picks up a late-created interactions.jsonl.
README/CLAUDE.md trust pass — agent count aligned to the real 61, dead
proof link removed, "one gate" promise now states the irreversible-change
caveat explicitly, older pivots compressed to CHANGELOG pointers, telemetry
policy reworded to match reality (opt-in, off by default).
Tests: full suite 163/163 (+20 new across registry/cache/watchers/no-cdn).

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.

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

Related tools

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.