great_cto

v2.72.4 Breaking

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

Published 1mo 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

Flow tab now defaults to a graphical block-flow diagram with colour‑coded agent steps and special nodes for human gates and irreversible actions.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Low	Flow tab defaults to graphical block-flow diagram view. Flow tab defaults to graphical block-flow diagram view. Source: llm_adapter@2026-06-13 Confidence: high	—
Feature	Low	Toggle between Diagram and List views in Flow tab. Toggle between Diagram and List views in Flow tab. Source: granite4.1:30b@2026-06-13-audit Confidence: low	—
Feature	Low	Agent steps colour-coded by blast radius (green, amber, red). Agent steps colour-coded by blast radius (green, amber, red). Source: granite4.1:30b@2026-06-13-audit Confidence: low	—
Feature	Low	Human gate represented by distinct shield node with signer and gate ID. Human gate represented by distinct shield node with signer and gate ID. Source: granite4.1:30b@2026-06-13-audit Confidence: low	—
Feature	Low	Irreversible steps highlighted with red ring and warning badge. Irreversible steps highlighted with red ring and warning badge. Source: granite4.1:30b@2026-06-13-audit Confidence: low	—
Feature	Low	Legend and summary added to Flow tab view. Legend and summary added to Flow tab view. Source: granite4.1:30b@2026-06-13-audit Confidence: low	—
Feature	Low	Flow tab view state is persisted across sessions. Flow tab view state is persisted across sessions. Source: granite4.1:30b@2026-06-13-audit Confidence: low	—

Full changelog

The operator console's Flow tab gains a graphical block-flow as the default view (toggle Diagram | List): a vertical chain of nodes with arrows, rendered from the existing /api/autopilot/flow data — pure render layer.

Agent steps colour-coded by blast radius (low=green / medium=amber / high=red) with 🤖, action, agent + 🔌 connector chips.
Human gate = distinct 🛡️ shield node (signer + gate id).
Irreversible step = red ring + ⚠ badge. Legend + summary; view persisted.
Free-form canvas constructor stays out of scope by design. Verified live (rcm + a 2-gate vertical).

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.