Skip to main content

Release 0.4.15 — Curl Private Endpoints

Sri Aradhyula
Sri Aradhyula

Released: 2026-05-20 Chart: oci://ghcr.io/cnoe-io/charts/ai-platform-engineering:0.4.15 Previous release: 0.4.14

Highlights​

0.4.15 is a small follow-up release. The curl builtin tool gains an opt-in allow_non_public_urls flag so dynamic agents can reach private or internal endpoints when explicitly configured, while domain ACLs still apply. The release also quiets noisy Jira MCP logs by default and closes several CodeQL findings by removing sensitive data from logs and stdout.

Release 0.4.13 — Workflow Service and Default Agent

Sri Aradhyula
Sri Aradhyula

Released: 2026-05-18 Chart: oci://ghcr.io/cnoe-io/charts/ai-platform-engineering:0.4.13 Previous release: 0.4.12

Highlights​

0.4.13 introduces the Workflow Service — a multi-step orchestration engine with a ReactFlow visual editor, fire-and-forget execution, HITL interrupts, and config-driven seeding that runs natively inside the Next.js UI. It also adds a configurable default agent so new chats can open against a chosen dynamic agent instead of the supervisor, an AI Review module that grades skills and agent prompts against an admin rubric, and a curl builtin tool for dynamic agents to call write APIs. Security hardening closes a class of SSRF-prone URL fetches across RAG ingestion and agent fetch tools.

Release 0.4.12 — LiteLLM FinOps MCP Server

Sri Aradhyula
Sri Aradhyula

Released: 2026-05-13 Chart: oci://ghcr.io/cnoe-io/charts/ai-platform-engineering:0.4.12 Previous release: 0.4.11

Highlights​

0.4.12 adds a standalone LiteLLM MCP server for FinOps reporting, letting dynamic agents query LiteLLM cost and usage data directly. The chart gains a new optional litellmMcp section — disabled by default — so existing deployments are unaffected until you opt in. Dynamic agents now expose their persisted agent ID through the self_identity tool. This is a drop-in Helm upgrade; the only values change is the new opt-in litellmMcp block.

Release 0.4.11 — Skills Gallery Controls & Cleaner Metrics

Sri Aradhyula
Sri Aradhyula

Released: 2026-05-12 Chart: oci://ghcr.io/cnoe-io/charts/ai-platform-engineering:0.4.11 Previous release: 0.4.10

Highlights​

0.4.11 gives operators finer control over which skills appear in the Skills Gallery: a new HIDE_BUILTIN_SKILLS flag and a default of BUILTIN_SKILL_IDS: "none" keep built-in templates out of the gallery until you import them explicitly. The VictorOps MCP is consolidated around the v2 incidents reporting API and stops silently dropping fields. Several charts fixes stop Prometheus from firing spurious TargetDown alerts on services that never exposed /metrics, and the session-expiry sign-in flow no longer relies on a brittle new-tab refresh. This is a drop-in Helm upgrade — no values.yaml edits are required.

Release 0.4.10 — Overthink Boilerplate Template Variable

Sri Aradhyula
Sri Aradhyula

Released: 2026-05-08 Chart: oci://ghcr.io/cnoe-io/charts/ai-platform-engineering:0.4.10 Previous release: 0.4.9

Highlights​

0.4.10 reworks how "overthink" gating instructions reach agent prompts. Instead of a per-config custom_prompt string, the platform now injects a built-in OVERTHINK_BOILERPLATE template variable server-side, so agent prompts can opt into standard [DEFER]/[LOW_CONFIDENCE] gating with a single {{ client_context.overthink_boilerplate }} reference. A follow-up fix relocates that logic from the agent runtime to the slack-bot, where it belongs. This is a drop-in Helm upgrade — no values.yaml edits are required.

Release 0.4.9 — HITL Tool Approval, GridFS, and Docs Redesign

Sri Aradhyula
Sri Aradhyula

Released: 2026-05-07 Chart: oci://ghcr.io/cnoe-io/charts/ai-platform-engineering:0.4.9 Previous release: 0.4.8

Highlights​

0.4.9 ships Human-in-the-Loop tool approval for dynamic agents, a GridFS-backed store for large tool results, custom agent color themes, an improved agent-selection UX, an automated release-docs coding-agent skill, and a fully redesigned documentation site.

Release 0.4.8 — AWS MCP Server and PSS Baseline

Sri Aradhyula
Sri Aradhyula

Released: 2026-05-06 Chart: oci://ghcr.io/cnoe-io/charts/ai-platform-engineering:0.4.8 Previous release: 0.4.7

Highlights​

0.4.8 introduces a new AWS MCP server, configurable call-limit middlewares for the supervisor, and Kubernetes Pod Security Standards Baseline compliance across all Helm charts. A tracing fix resolves silent OTLP batch drops to Langfuse caused by oversized spans, and several long-standing compatibility and correctness bugs are resolved.

Release 0.4.6 — Installer UX and Runtime Simplification

Sri Aradhyula
Sri Aradhyula

Released: 2026-05-05 Chart: oci://ghcr.io/cnoe-io/charts/ai-platform-engineering:0.4.6 Previous release: 0.4.5

Highlights​

0.4.6 significantly improves the setup-caipe.sh installer experience with Docker auto-detection, back-navigation, and upgrade-aware prompts. The dynamic agents runtime is simplified with a shared-client memory model, lazy provider loading, and a single-flight init pattern that prevents duplicate runtime startup. Several UI agent editor polish items round out the release.

Release 0.4.7 — Skills Platform Overhaul

Sri Aradhyula
Sri Aradhyula

Released: 2026-05-05 Chart: oci://ghcr.io/cnoe-io/charts/ai-platform-engineering:0.4.7 Previous release: 0.4.6

Highlights​

0.4.7 delivers a comprehensive end-to-end overhaul of the Skills platform and a new unsaved-changes guard in the dynamic agent editor. The Skills Workspace is redesigned with a standalone scanner microservice, multi-source hub support, install history, ZIP export, and AI Assist — resolving four pre-existing UX bugs rooted in architectural mismatches.

Release 0.4.5 — DocumentDB Compatibility Fix

Sri Aradhyula
Sri Aradhyula

Released: 2026-04-29 Chart: oci://ghcr.io/cnoe-io/charts/ai-platform-engineering:0.4.5 Previous release: 0.4.4

Highlights​

0.4.5 is a focused bug-fix release. The most impactful change is a DocumentDB/CosmosDB compatibility fix that removes $facet aggregation from conversation list and audit log routes — operators running CAIPE against Amazon DocumentDB or Azure CosmosDB will see these admin views work correctly for the first time. RAG server JavaScript rendering is also repaired on x86_64.