This release adds 6 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+2 more
Summary
AI summaryAdds evidence-linked explainability and AI-drafted determinations with configurable confidence thresholds.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Low |
Adds configurable confidence floor in admin Settings per tenant. Adds configurable confidence floor in admin Settings per tenant. Source: llm_adapter@2026-06-07 Confidence: high |
— |
| Feature | Low |
Introduces QA sampling queue processing ~20% of closed cases with scores 1–5. Introduces QA sampling queue processing ~20% of closed cases with scores 1–5. Source: llm_adapter@2026-06-07 Confidence: high |
— |
| Feature | Low |
Adds bulk actions for multi-select approve/reject/escalate with RBAC checks. Adds bulk actions for multi-select approve/reject/escalate with RBAC checks. Source: llm_adapter@2026-06-07 Confidence: high |
— |
| Feature | Low |
Adds agent-run observability showing per‑connector latency and replay feature. Adds agent-run observability showing per‑connector latency and replay feature. Source: llm_adapter@2026-06-07 Confidence: high |
— |
| Feature | Low |
Introduces new endpoints: /config, /qa, /qa-score, /bulk. Introduces new endpoints: /config, /qa, /qa-score, /bulk. Source: llm_adapter@2026-06-07 Confidence: high |
— |
| Feature | Low |
Completes the console gap-roadmap. Completes the console gap-roadmap. Source: granite4.1:30b@2026-06-07-audit Confidence: low |
— |
| Feature | Low |
Adds evidence-linked explainability in the drawer's Evidence section. Adds evidence-linked explainability in the drawer's Evidence section. Source: granite4.1:30b@2026-06-07-audit Confidence: low |
— |
| Feature | Low |
Introduces AI-drafted determination reviewed before signing on every run. Introduces AI-drafted determination reviewed before signing on every run. Source: granite4.1:30b@2026-06-07-audit Confidence: low |
— |
| Performance | Low |
Adds 288 library tests to the test suite. Adds 288 library tests to the test suite. Source: llm_adapter@2026-06-07 Confidence: high |
— |
Full changelog
Completes the console gap-roadmap.
Wave C — Evidence-linked explainability (the drawer's Evidence section lists what each connector found behind the AI recommendation) · AI-drafted determination on every run (the signer reviews it before signing) · Configurable confidence floor (admin Settings, per-tenant; low-confidence approve → escalate, clean → auto-eligible).
Wave D — QA sampling (~20% of closed cases → a QA queue scored 1–5) · Bulk actions (multi-select / select-auto-eligible → bulk approve/reject/escalate, RBAC-checked) · Agent-run observability (per-connector latency + ⟳ Replay).
New endpoints: /config, /qa, /qa-score, /bulk. 288 lib tests.
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
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.
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.
Beta — feedback welcome: [email protected]