great_cto

v2.45.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

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

Eight new live connectors close the data gap, adding real adapters for five previously zero‑live verticals and deeper brains for prior‑auth, AML, freight.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Medium	Adds 8 new live connectors for all 16 autopilots. Adds 8 new live connectors for all 16 autopilots. Source: llm_adapter@2026-06-07 Confidence: high	—
Feature	Medium	Introduces keyless mode as default for live adapters. Introduces keyless mode as default for live adapters. Source: llm_adapter@2026-06-07 Confidence: high	—
Feature	Low	Updates eval rubric to fix benign over‑blocking in scorecard verdicts. Updates eval rubric to fix benign over‑blocking in scorecard verdicts. Source: llm_adapter@2026-06-07 Confidence: high	—
Refactor	Low	Dispatcher now owns `mode`; adapter sub-mode retained as `adapterMode`. Dispatcher now owns `mode`; adapter sub-mode retained as `adapterMode`. Source: llm_adapter@2026-06-07 Confidence: high	—

Full changelog

8 new live connectors close the gap: all 16 autopilots now run on real data. The 5 zero-live verticals (soc, insurance, mortgage, credentialing, collections) each get a real adapter, plus deeper brains for prior-auth, aml, freight.

threat-intel (soc) · fraud-score (insurance) · aus (mortgage, DU/LPA) · primary-source (credentialing, OIG/SAM exclusion) · comms-outreach (collections, Reg F/TCPA guardrail) · carrier-vet (freight, FMCSA SAFER) · um-criteria (prior-auth, never auto-denies) · sar-filing (aml, blocked without BSA Officer).
Keyless by default (deterministic real logic / curated public slice); POST to the real provider when keyed.
Dispatcher now owns mode (live-adapter result is always mode:live; adapter sub-mode kept as adapterMode).
17 live connectors; all 16 verticals exercise ≥1 live connector. 252 lib tests.
Eval: fairer scorecard verdict rubric (judge a design on its stated scope — fixes benign over-blocking).

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.