Plugins
Browse, filter, and install DeepSeek-Harness plugins.
3 plugins found
dsh-custom-model
sayzwx/dsh-custom-model
Custom-model console for the Models page: manage hand-declared llm-pi-ai providers in one list, fetch the model list an endpoint serves, and fill each model context window, max output and the reasoning levels the endpoint accepts straight into the configuration. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-model-probe
vhow123/dsh-model-probe
Fingerprint configured DSH models without trusting their reported token counts: a 55-vector tokenizer reference, four greedy identity probes, refusal-prose and stop-vocabulary probes, and a local 18-item weighted intelligence battery scoring 0-100 with a tier and per-question evidence, plus animated or custom SVG and HTML drawing probes, quick SVG limits, concurrency controls, and latency and token metrics. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-model-probe
xiaomao49/dsh-model-probe
Measures what an llm-pi-ai endpoint really accepts — context window from its own model list, output-token limit and reasoning levels read out of its own range errors, image support from a generated test image — then reports declared values that contradict that evidence and rewrites them only after confirmation.