5 results
Agent-decided approvals for DeepSeek Harness: a workspace-write base permission mode where an independent approval subagent judges every sandbox escalation (risky operations are rejected), with a configurable approval model and a per-session audit trail in the conversation window's 审批 tab.
DSH WebUI capability controls for skills, MCP servers, tools, prompt injections, approvals, and safety guards at session, project, and global levels.
LLM pre-review for sandbox-escalation approvals: an independent-context LLM gate answers sandbox escalation requests before they reach the user, falling back to the user on any failure.
Governed platform access for DeepSeek Harness — no credential on the machine
Bridges vendor agent SDKs into DeepSeek Harness as selectable LLM providers. Works in any DSH mode; DSH keeps its own prompt, tools, sandbox and approvals.