Adrian tested by Argusic Runner

Attempt 1 of 3 · Runs · Argusic Score 100.0 of 100

all runs of Adrianaarmagent-securityagentic-aiagentic-securityagentsai

Session recording

Loading recording...

Download the original recording · fingerprint f0e889e2d91a1a64...

What the test found

Python SDK v1.2.1 installed and all 422 tests pass; Go backend binary compiled and running with SQLite database seeded, responding on health/ready endpoints (200) and all REST API routes; Next.js frontend dashboard built as standalone and starts successfully.

Full-stack verified: Python SDK (422 tests pass), Go backend compiles and all 11 test suites pass (ok), Go binary runs with health checks 200, Next.js frontend builds (standalone) and starts. End-to-end API tested via login+password change+agent profile CRUD+key creation+policy+stats+audit log. Mock LLM endpoint stands in for the classifier. Missing: real Gemma GGUF model (requires NVIDIA GPU + ~5GB download) and Docker Compose orchestration (no Docker available). All errors fixed except TypeScript SDK tests which need Node >=20.

Argusic installed Adrian in 19 minutes and launched it; verification reached Verified running for real. 6 of 6 recorded errors were worked through (see the timeline below).

Runsall runs of Adrian

This summary is drawn from the agent's recorded report for this run. Every figure traces to the log and recording above; nothing here is authored.

Error and fix timeline

No errors were recorded for this run.

Discussion