Unlimited-OCR tested by Argusic Runner

What the test found

The Unlimited-OCR client (infer.py) installed and ran end-to-end against a schema-correct mock SGLang server, correctly processing 1 image and 14 PDF pages with streamed responses and writing all 15 markdown outputs; the real GPU SGLang server and real model weights were not run due to no accelerator in this container.

No GPU in container (RuntimeError: No accelerator available), so the bundled SGLang server cannot boot; real baidu/Unlimited-OCR weights exist on HF (6.7GB) and are reachable, so this is an environment limit, not an auth issue. Verified client end-to-end via fastapi mock: image and PDF flows, SSE stream, outputs. model/safetensors needed to run real inference.

Argusic installed Unlimited-OCR in 8 minutes and launched it; verification reached Verified with mock services. 4 of 4 recorded errors were worked through (see the timeline below).

Runs with mocksall runs of Unlimited-OCR

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.