dsh-automode: Adding an auto mode with deterministic guardrails to DeepSeek Harness
To enable an agent to execute tasks continuously, there are typically only two permission options available: using a conservative preset that halts for manual confirmation at every write operation, or switching directly to danger-full-access. While the latter is faster, it grants the agent unrestricted autonomy without any safeguards if issues arise. DeepSeek Harness (DSH) permission presets—read-only, workspace-write, and danger-full-access—exist at these two extremes, lacking a middle tier that is "loose but has gatekeepers for dangerous actions." The dsh-automode introduced below fills this gap: it is a DSH plugin that provides a Claude Code-style auto mode, allowing...
Read MoreClaude Code Launches Default Auto Mode on August 14: AI Programming Agents Move from "Review Line-by-Line" to Autonomous Execution
Anthropic announced that starting August 14, newly created Claude Code sessions for Pro, Max and Team users will enable Auto Mode by default, replacing one-by-one permission pop-ups with a safety classifier. Official controlled experiments show that the classifier intercepts approximately 89% of dangerous commands, far higher than the approximately 14% interception rate of manual approval; PR output for Team users increased by about 25%. This article sorts out the Auto Mode mechanism, safety data, applicable scope of each subscription plan, and developer response suggestions.
Read More