rate-limit 17

Per-provider API key rotation for DeepSeek Harness: a key pool per provider, auto-created clone routes, and switching to the next key on quota/rate-limit errors. Includes a Settings section (Key Rotation) to edit the key pools, cooldown and switch codes.

「DSH·禁止梁文峰」：拦截官方 DeepSeek API 请求：北京时间工作日高峰时段 09:00-12:00、14:00-18:00，中国法定节假日全天谷价不拦截，自动拦截发往官方 provider `deepseek-official` 的模型请求，可切换到第三方中转或预留的本机转 API 端口，未配置则阻止并提示；非高峰不拦、正常走官方，避开高峰双倍计价。标准可安装 dsh 插件，host 单半身，设置经 cordis 配置文件注入。

Seamless API-key rotation for DeepSeek Harness LLM providers when subscription limits are hit

DSH 模型代理插件：按模型走代理（Clash 等），有官方出站代理包时复用其传输层，设置 → 插件 页实时生效（dsh 0.1.7）。

DSH 并发请求监控与门闩：挂钩 llm/stream 瀑布，统计全部在途模型请求并按来源分类（主会话/子代理/插件/压缩/标题）与会话活跃聚合，达到上限 FIFO 排队，防止并发超限被供应商锁号；v1.5.0 新增会话级并发控制——实时给在线活跃会话设置并发数（rootId 解析到顶层会话，含子代理），面板新页签「会话并发」；v1.5.1 异常明细改 tab 切换并新增「按分类×错误信息」汇总报表；v1.5.2 异常明细加「今日/全部」范围切换、逐条明细改倒序、新增历史数据清理（保留最近 N 天 / 分

让 DeepSeek Harness 自动重试商汤 429/QUOTA 等瞬时网关故障直到任务完成——启动时给所有 llm-pi-ai provider 热注入加固版 retryPolicy，运行中新增的 provider 也会自动补上，再也不用手动发「继续」。

Auto-continue on 429 rate limit and quota-exhausted errors for DeepSeek Harness Web UI. Host-side RATE_LIMIT/QUOTA recovery plus an on/off switch at the bottom of the chat input area.

LLM API rate limiting, concurrency control, queuing, and adaptive cooldown for DeepSeek Harness

Provider/model-aware adaptive pacing and visible rate-limit retries for DeepSeek Harness free models.

Provider failover for DeepSeek Harness: on rate-limit (429) or quota exhaustion, automatically switch between providers with configurable per-provider models, fall back to the last one (e.g. DeepSeek official), and show a visible notice in the UI.

Peak / off-peak rate badges and switch countdown for DeepSeek Harness — per provider, per model, in the model selector and the composer tool row. Judges each provider by its own time zone and schedule instead of DeepSeek-only hours.

Rate & budget governance for DeepSeek Harness — 429 backoff windows, daily token budgets, tool-call storm control; monitor by default, enforce opt-in, JSONL audit.

Rate-limit plugin for DeepSeek Harness: FIFO queue per provider/model bucket with minIntervalMs and maxConcurrent

DSH 模型代理插件：按模型走代理（Clash 等）+ 失败自动重试 + 直连失败自动回退代理，设置页实时生效。

Per-provider requests-per-minute rate limiting for DeepSeek Harness, with its own Settings tab

DSH 模型管理层：网关可达性探测、模型目录拉取、DeepSeek + MiniMax/智谱/Moonshot/StepFun 余额与配额、本月用量统计、余额预警、Provider 健康看板，再把本机装好的 codex / claude / agy 注册成子代理（装了才出现）。零运行时依赖，不改动 DSH 安装。

Per-route API-key rotation + retry for dsh. When a provider request ends with a retryable failure (default: QUOTA, AUTH — the codes where waiting cannot help), this plugin (1) repoints the provider's credential reference (e.g. llm-deepseek's apiKeyEnv) to