dsh-auto-retry: DSH Workflow Auto-Recovery Plugin
The dsh-auto-retry plugin is designed to address network instability, server-side errors, and interrupted streaming output in DeepSeek Harness workflows. It provides request-level supplementary retries (covering eight error types), turn-level automatic continuation with a circuit breaker mechanism, and unresponsive watchdog functionality. The plugin adopts a main/sub-agent divide-and-conquer strategy, offering real-time status display, data dashboards, and input optimization to automate cumbersome manual intervention. Users can install it via a command and flexibly configure retry counts, delays, and policies in the settings, making it suitable for unstable network environments or long-running task scenarios.
Read Moredsh-auto-retry: DSH Bounded Fallback Recovery Plugin
`dsh-auto-retry` is a bounded fallback recovery plugin for DeepSeek Harness (DSH), designed to address specific issues after the official retry policy gives up. It primarily handles cases where a relayer mislabels transient rate limiting as balance exhaustion, a request completes normally without visible output, or the output is truncated. By identifying error patterns, implementing an automatic continuation mechanism, and enforcing budget controls, the plugin performs additional retries for errors such as `RATE_LIMIT` and `EMPTY_RESPONSE`, while limiting retry counts and wait times. After installation, `cordis.patch.yml` must be configured. It applies to the DSH Web profile and does not conflict with other global retry plugins.
Read More