DeepSeek Harness Plugin Hub
← Plugins

dsh-llm-extra-retry

Llm Extra Retry

Extra model-request recovery for the DeepSeek Harness: retries a failed model request once after a fixed delay when the provider classifies the failure as PI_AI_ERROR (unrecognized upstream error text). All other error codes stay on the built-in dsh-llm-retry default policy (5 bounded exponential-ba

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:lim12137/dsh-llm-extra-retry#37c85c373eb2e6186a7354ff6b2a88107d6872fb

Description

Extra model-request recovery for the DeepSeek Harness: retries a failed model request once after a fixed delay when the provider classifies the failure as PI_AI_ERROR (unrecognized upstream error text). All other error codes stay on the built-in dsh-llm-retry default policy (5 bounded exponential-backoff retries). Composes safely with @deepseek-ai/dsh-llm-retry via the agent/request-error waterfall using its own policyKey bookkeeping.

Compatibility and provenance

Llm Extra Retry is published as dsh-llm-extra-retry and currently resolves to version 0.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
github
Registry updated

Versions

0.1.0stable