502399493zjw-lgtm/dsh-model-retry

502399493zjw-lgtm★ 0TypeScript最后同步: 2026-08-20

在 GitHub 打开

DeepSeek Harness plugin for configuring the global model-request retry budget

README 摘要

@zhongjingwei/dsh-model-retry English 中文 DeepSeek Harness Web plugin for configuring active providers' model-request retry budget from Settings → General . Compatibility: pinned to stock DSH 0.1.0-rc.8 . rc.8 moved retry ownership into provider profiles, so this version writes each active normal provider's retryPolicy.maxRetries through the published settings API. Demo The demo uses stock DSH 0.1.0-rc.8 and a plugin tarball packed from this source, all under an isolated DSH HOME . It changes the retry budget from 2 to 5 , then uses DSH's deterministic local LLM mock to return retryable server errors on attempts 1–5 and succeed on attempt 6. Session-title generation is disabled so those six mock requests belong only to the demonstrated model request. DSH executes and reports the retries; the plugin owns the shared retry-budget setting. Install For stock rc.8: Restart Web after installation. Remove the plugin with: Behavior - Adds one numeric retry-count row to Settings → General and shows its provider scope. - Accepts finite, non-negative integers, including 0 . - Discovers active configurable providers through llm.providers and uses revision-fenced settings.mutate calls. - Writes r…

在 GitHub 查看完整 README →
工具/开发dsh-plugin

分类