junior-ml-dev

Architecture

A planner proposes one step at a time. The runner checks every step against a policy, runs it through a tool server, checkpoints the result and writes an audit entry. Nothing the planner says can bypass the runner.

Architecture of junior-ml-devA planner proposes steps; a guarded runner executes them through four tool servers; a reviewer and a report close the run; deployment needs an approval.Plannerscripted, or LLM via gatewayJob queueSQLite (arq is a stub)Agent runnerpolicy guard, budgets, checkpoints, hash-chained auditRun storeone checkpoint per stepdata-toolsprofile, leakageexperimentstrain, tune, comparesandbox-execcode policy, Dockerdeploypackage, local deployApprovalssingle-use tokenReviewerdeterministic checks; advisory LLM criticReportHTML, markdown, model card

What is enforced, and where

What the live demo would disable

A hosted demo runs the same runner with uploads, deployment and the code sandbox switched off, the scripted planner only, a 90 s hard wall clock (the agent itself stops searching at a shorter soft wall and wraps up, which is why the example runs list both), a 20 s AutoML ceiling, one run at a time and per-address rate limits. That mode exists in the repository (DEMO_MODE=1), is covered by tests and runs live on a free Render instance at https://junior-ml-dev-demo.onrender.com/. The free instance has a throttled CPU, so it skips the leakage detectors (recorded as a partial check), turns FLAML off and keeps a warm worker process. The source repository is currently private, so file references below (result JSONs, code) are names only, not links.