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.
Author: xiaomao49 · Models & Providers · Catalog snapshot: 2026-09-19Canonical semantic path
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.
Imported third-party catalog description; not a Registry verification conclusion.0 stars · 1866 downloads
Signals were provided by the source catalog and do not imply quality or safety. 2026-09-19Active analysis coverage 1/5. Historical chains are retained but do not count toward current coverage.
Source structure has not been analyzed.
Repository metadata has not been analyzed.
npm release metadata has not been analyzed.
Conclusion: Compatibility verification passed. Installation, profile loading, and sustained startup all completed. Test environment: DSH 0.1.6-alpha.2, web profile.
Conclusion: This bounded audit reported 0 known vulnerabilities. It covers only the locked versions and audit source; zero reports is not proof of safety.
The plugin’s advertised feature has not been automatically verified. Passing installation and startup does not prove that feature works.
Conclusion: The scan observed 4 code capabilities: contains credential or token handling code, may read environment variables, may create or modify files, may access the network. No predefined elevated-risk condition was triggered; this is not proof of safety.
Conclusion: Package name, version, entrypoints, and checksum passed validation. Artifact: dsh-model-probe@0.1.14; SHA-256: 205ce0bee0812cf21d6f9856167455bafbd45ec22aa181160dbef49342d08bce.
Automated evidence is scoped to the named artifact, DSH target and profile. It is not a blanket safety or feature-completeness claim.
Describe your task in a DSH conversation and mention dsh-model-probe. After installing or updating the manager from npm latest, it can find this candidate through Registry, then inspect its actual source and version locally.
dsh-model-probeAnalyzed 0.1.14github:xiaomao49/dsh-model-probeExact version not resolved