great_cto

v2.59.0 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

Adds deterministic cost modeling, dead‑letter handling, connector health checks, and metering for autopilot.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Medium	Adds deterministic cost model for autopilot operations. Adds deterministic cost model for autopilot operations. Source: llm_adapter@2026-06-08 Confidence: high	—
Feature	Medium	Introduces fault-injection seam for offline testing of autopilot failures. Introduces fault-injection seam for offline testing of autopilot failures. Source: llm_adapter@2026-06-08 Confidence: high	—
Feature	Medium	Implements per‑vertical latency budgets via `budgets.mjs`. Implements per‑vertical latency budgets via `budgets.mjs`. Source: llm_adapter@2026-06-08 Confidence: high	—
Feature	Medium	Adds dead‑letter handling for writes that exhaust retries. Adds dead‑letter handling for writes that exhaust retries. Source: llm_adapter@2026-06-08 Confidence: high	—
Feature	Medium	Provides `/api/autopilot/metering` endpoint for connector billing and metering. Provides `/api/autopilot/metering` endpoint for connector billing and metering. Source: llm_adapter@2026-06-08 Confidence: high	—
Feature	Medium	Adds `/api/autopilot/health` endpoint reporting connector health metrics. Adds `/api/autopilot/health` endpoint reporting connector health metrics. Source: llm_adapter@2026-06-08 Confidence: high	—
Feature	Low	Adds 5 new library tests for autopilot tier‑3 implementation. Adds 5 new library tests for autopilot tier‑3 implementation. Source: llm_adapter@2026-06-08 Confidence: high	—
Feature	Low	Flags over‑budget runs with `runMetrics()`. Flags over‑budget runs with `runMetrics()`. Source: granite4.1:30b@2026-06-08-audit Confidence: low	—
Feature	Low	Provides `deadLetters()` queue and `/api/autopilot/requeue` endpoint to reprocess dead‑letter writes. Provides `deadLetters()` queue and `/api/autopilot/requeue` endpoint to reprocess dead‑letter writes. Source: granite4.1:30b@2026-06-08-audit Confidence: low	—
Feature	Low	Implements `connectorHealth()` function exposing failure rate, p95 latency, last error, and healthy flag. Implements `connectorHealth()` function exposing failure rate, p95 latency, last error, and healthy flag. Source: granite4.1:30b@2026-06-08-audit Confidence: low	—

Full changelog

Tier-3: ops. Makes the operated autopilot operable — see what it costs, catch a failing connector, recover a write that didn't land. Deterministic cost model + a fault-injection seam, so it's all testable offline.

Cost/latency budgets — budgets.mjs: per-vertical latency budgets + a flat (env-overridable) connector unit cost; runMetrics() flags over-budget runs.
Retry / dead-letter — a post-gate write that exhausts its 3× retries now lands in status:'dead-letter' (not a silent completion) + audit; deadLetters() queue + requeue(id) re-runs the write to recover. POST /api/autopilot/requeue.
Billing / metering — metering() aggregates connector calls, latency, cost (USD), retries, per-vertical breakdown; GET /api/autopilot/metering.
Connector health — connectorHealth(): failure rate, p95 latency, last error, healthy flag; GET /api/autopilot/health + cron connector.health.
Test seam — GREAT_CTO_FAULT_INJECT=1 deterministically fails stub calls (chaos / dead-letter / health testing).

Implements docs/plans/PLAN-autopilot-tier3.md. 5 new lib tests (304/304), all ops endpoints admin/compliance-gated.

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.