dsh-ttft-hedge
Manifest validHedged requests for streaming /v1/messages LLM calls: fires a second attempt when response headers miss a deadline and races them, retries immediately on 5xx/504, passes through 4xx/429, with statisti
dsh-ttft-hedge
TTFT 优化：对发往 LLM 中继 /v1/messages 的流式请求做对冲（hedged request）——deadline 内未收到响应头则并行发第二个请求，先到先用；5xx/504 立即重抽；4xx/429 原样返回。附统计工具与 stats 文件。
由 dsh-super-injector dev_scaffold_plugin 生成。
构建与注入
bash scripts/build.sh
# 注入器环境内：dev_inject_plugin <本目录>
Comments
Loading…
Similar plugins
by liaoyuqing
LLM request retry plugin for DeepSeek Harness: when a model request fails with a configured HTTP status code, machine code, or provider field=value match, it sleeps for the per-rule delay and re-issue
★ 0
MIT
JavaScript
Sep 5, 2026
dsh plugin --profile web add dsh-llm-error-retryA Deepseek Harness Plugin to Shape The Entry of LLM.
★ 0
MIT
JavaScript
dsh plugin --profile web add dsh-entry-shaperby striveh
Local request and response inspector for session-associated DeepSeek Harness LLM calls
★ 0
MIT
TypeScript
Aug 31, 2026
dsh plugin --profile web add dsh-llm-call-inspectorby QiE2035
为 DeepSeek Harness 的自定义 LLM API 请求注入 HTTP Headers（典型用途：改写 user-agent，例如网关要求 UA 带指定品牌字样）。
★ 4
MIT
TypeScript
Sep 11, 2026
dsh plugin --profile web add dsh-llm-headersby jyao-SUSE-power-group
Rate-limits LLM requests per provider and per model using a reservation-based token bucket, with queue or reject modes, plus gateway identity rules that rewrite user-agent and inject custom headers.
★ 4
MIT
JavaScript
Oct 16, 2026
dsh plugin --profile web add dsh-provider-rate-limitby bainianlaoyao
DSH plugin: after official llm-retry (n/5), keep retrying transient API failures on the same open step until success, cancel, or pause.
★ 3
↓ 153/wk
MIT
JavaScript
Sep 13, 2026
dsh plugin --profile web add dsh-session-robustness