dsh-auto-driving: DeepSeek Harness Agent Self-Healing Coding Session Plugin
The DeepSeek Harness (DSH) plugin `dsh-auto-driving` is a self-healing workflow plugin designed to resolve interruption issues in agent development. It provides five core capabilities: automatic fallback for model failures, exponential backoff retries for network issues, fully automatic approval takeover, silent hang detection, and real-time notifications with responsive interaction. After enabling “Auto Driving” in the settings, the plugin can handle permissions and approvals automatically without manual intervention, with all decisions recorded in the `AUTO-MODE.md` file. It supports SSE fallback and long-lived connection state synchronization, making it suitable for complex agent scenarios that require long-term, unattended operation.
Read Moredsh-polyglot: Providing OpenAI-Compatible Endpoint Switching and Automatic Fallback for DSH
dsh-polyglot is an MIT-licensed DSH plugin developed by Jesse-njx, designed to address challenges in DSH when invoking external models, including multi-endpoint management, unstable free quotas, and rate limiting. This plugin consolidates multiple OpenAI-compatible providers into a single virtual provider, `polyglot`, utilizing a universal adapter to handle streaming, tool calls, and usage extraction, while employing declarative configuration to accommodate variations across different services. At its core is an automatic fallback router that, upon encountering 429 rate limits, quota exhaustion, 5xx errors, or missing API keys, automatically switches to the next available provider in the chain, implementing exponential backoff and retry strategies for cooldown. The plugin maintains provider information through JSON preset files and records the service source, status, and token usage for each request in session logs.
Read More