dsh-llm-rate-limit
LLM API rate limiting, concurrency control, queuing, and adaptive cooldown for DeepSeek Harness
5 results
LLM API rate limiting, concurrency control, queuing, and adaptive cooldown for DeepSeek Harness
DSH plugin: deliver the real failure reason (e.g. RATE_LIMIT 429) to the parent agent when a background subagent fails, instead of an empty "Its closing message:"
DeepSeek Harness 插件:为 OpenCode Zen 免费模型补上官方客户端头,缓解伪 429 限流
Patient auto-retry for DeepSeek Harness: honor the upstream gateway's retry_after_seconds on a 429 capacity cooldown instead of giving up after two fast retries, wait out the mislabeled modality 400 a saturated gateway replays from its client-error circuit, and journal every wait as the built-in's own llm/retry records so the console renders its live countdown card. Optional floating countdown badge included.
Agnes AI 图像 / 视频生成插件:注册 agnes_image 与 agnes_video 工具,内置跨进程 RPM 限流、429 退避与本地 ffmpeg 转 GIF;带 Web 配置卡(API Key / RPM 预设 / ffmpeg 检测)。