dsh-model-probe
DeepSeek Harness plugin to audit and correct llm-pi-ai model capability declarations by probing the endpoint itself: out-of-range maxTokens, contextWindow, reasoning levels, image input.
369 results
DeepSeek Harness plugin to audit and correct llm-pi-ai model capability declarations by probing the endpoint itself: out-of-range maxTokens, contextWindow, reasoning levels, image input.
DeepSeek Harness 权限记忆插件:把某类命令加进允许列表,之后同类命令不再询问。 / Remember sandbox-escalation approvals so the same commands stop asking.
Fix and diagnose DeepSeek Harness on native Windows. Official PowerShell, Workspace Write, shortcuts, and legacy preset repair. No WSL.
Deny an AI agent access to .env files, credential stores, keys and any path you hide — across file tools, shell commands, search selectors and run_code. A DeepSeek Harness (dsh) plugin.
Bitwarden/Vaultwarden credentials in every DSH session: vault tools + proactive prompt guidance + a settings card for the master password.
Allowlisted git execution for DeepSeek Harness: a model-facing git tool that runs outside the file sandbox, with a settings page where the user ticks which git subcommands are permitted and, per path, which reads and writes are allowed, prompted or refused
Model-reviewed Auto Approve permission preset: only review-passed actions are auto-approved, everything else is handed back to the user, with an approval-log panel
TOTP-only access control for DeepSeek Harness Web, with in-app enrollment, recovery codes, live protection controls and lock-all.
Static trust audit for DeepSeek Harness plugins: capabilities, injected prompts, token cost, provenance, and a reproducible 0-100 trust score