"studies" 태그로 연결된 4개 게시물개의 게시물이 있습니다.

v1.0.9 — Protocol-to-Publication, FHIR Interoperability, and Copilots Everywhere​

Where v1.0.8 grew the research surface (Publish, Library Lifecycle, the first copilots), v1.0.9 is the release that makes that surface trustworthy and reproducible. It lands the deterministic protocol-to-publication pipeline (ADR-0020) — provenance, empirical calibration, scientific gates, and manuscript synthesis — brings FHIR ingestion to Medgnosis parity and proves it against the live Epic sandbox, puts the Abby copilot on every page with a local-model backend so Community Edition can run it on-prem, and closes a long list of production-readiness items: RBAC on every PHI route, R/HADES analytics proven end-to-end, no "coming soon" in primary workflows, and a fresh-machine install that starts cleanly from docker compose up.

Parthenon v1.0.8 is the release where the research surface grows up.

v1.0.7 was a platform release: the Community/Enterprise fork, AGPLv3, extension points, and the deployment plumbing underneath everything. It mattered, but it lived below the waterline. v1.0.8 comes back up to the surface researchers actually touch — and it does three substantial things at once. It gives every artifact in the library a real lifecycle. It turns a finished study into a shareable, server-persisted manuscript. And it brings the first two AI copilots into the workspace, behind a single switch an administrator controls.

More than 200 commits landed in 18 days (May 10 to May 28). This post is the engineering story behind them.

v1.0.8 — Publish, Library Lifecycle, and Agentic Copilots​

After the v1.0.7 platform/architecture release (CE/EE fork, extension points, AGPLv3), v1.0.8 returns to the research surface and lands three intertwined feature lines at once: the Publish module for authoring and sharing study write-ups, Library Lifecycle management that gives every cohort, concept set, and analysis a draft → active → archived state machine plus an admin console, and the first two Claude Agent SDK copilots — a Study Designer and a Publication assistant — gated behind a single runtime toggle.

For a year, every AI feature in Parthenon spoke to a model the same way: build a prompt, send it, get one answer back. Abby answers a question. The publication writer drafts a paragraph. Useful — but fundamentally a vending machine. You put a prompt in, a completion comes out, and the model never gets to look around, use a tool, or change its mind.

This milestone changes that. Parthenon now runs genuine agentic copilots — built on Anthropic's Claude Agent SDK, the same autonomous loop that powers Claude Code — inside two workflows: the Study Designer and the Publication assistant. The agent decides which tools to call, iterates (search → draft → validate → refine), keeps a session across turns, streams its work to the browser, and — critically — asks for permission before it writes anything. It ships on a reusable, profile-agnostic core, behind a super-admin runtime switch, with PHP still holding the pen on every database write.

This post is the full story: the architecture, the four pull requests that built it, the human-in-the-loop approval gate, and the engineering discipline (and bugs) along the way.