Skip to content

great_cto

v2.56.0 Feature

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

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

crypto_tls

Summary

AI summary

Auto case-ingestion via webhook, tamper‑evident audit logs, and AES-256‑GCM at‑rest encryption are introduced.

Changes in this release

Security Medium

Rejects requests with bad HMAC-SHA256 signatures by returning 401 Unauthorized.

Rejects requests with bad HMAC-SHA256 signatures by returning 401 Unauthorized.

Source: granite4.1:30b@2026-06-08-audit

Confidence: low

 —
Feature Medium

Adds auto case-ingestion via POST /api/autopilot/ingest with HMAC-SHA256 signature verification.

Adds auto case-ingestion via POST /api/autopilot/ingest with HMAC-SHA256 signature verification.

Source: llm_adapter@2026-06-08

Confidence: high

 —
Feature Medium

Implements tamper-evident audit logging with hash-chained entries and verification endpoint.

Implements tamper-evident audit logging with hash-chained entries and verification endpoint.

Source: llm_adapter@2026-06-08

Confidence: high

 —
Feature Medium

Enables encryption at-rest for run files using AES-256-GCM when GREAT_CTO_ENCRYPT_KEY is set.

Enables encryption at-rest for run files using AES-256-GCM when GREAT_CTO_ENCRYPT_KEY is set.

Source: llm_adapter@2026-06-08

Confidence: high

 —
Feature Medium

Adds submission receipt recording and exponential backoff retry mechanism for connectors.

Adds submission receipt recording and exponential backoff retry mechanism for connectors.

Source: llm_adapter@2026-06-08

Confidence: high

 —
Feature Medium

Introduces license attestation on every signature and regulator-format /export endpoint.

Introduces license attestation on every signature and regulator-format /export endpoint.

Source: llm_adapter@2026-06-08

Confidence: high

 —
Feature Medium

Adds purgeRuns() retention utility for run data cleanup.

Adds purgeRuns() retention utility for run data cleanup.

Source: llm_adapter@2026-06-08

Confidence: low

 —
Feature Low

Transforms demo into a fully-operated pipeline (reference: rcm).

Transforms demo into a fully-operated pipeline (reference: rcm).

Source: granite4.1:30b@2026-06-08-audit

Confidence: low

 —
Performance Low

Adds 293 library tests to improve test coverage.

Adds 293 library tests to improve test coverage.

Source: llm_adapter@2026-06-08

Confidence: high

 —
Full changelog

Turns the demo into a really-operated pipeline (reference: rcm).

  • Auto case-ingestion (webhook) — POST /api/autopilot/ingest (HMAC-SHA256) starts a run from a source-system payload and pushes the signer; a bad signature → 401.
  • Tamper-evident audit — every entry hash-chained; verifyAudit() + /verify detect any edit.
  • Encryption at-rest — AES-256-GCM run files when GREAT_CTO_ENCRYPT_KEY is set; transparent decrypt.
  • Submission receipt + retry — the post-gate write records generated-vs-submitted · connectors · attempts, with backoff retry against a real provider.
  • License attestation on every signature · regulator-format /export (the signed determination, not JSON) · retention purgeRuns().

293 lib tests.

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]