Bundle
Out-of-tree dsh plugin: GitLab, GitHub, Gitee, Gitea, and Bitbucket tokens stay out of the model context, stored encrypted (AES-256-GCM) in a plugin-owned file; the model calls forge API tools on demand, and the web settings page manages sites and tokens.
Bundle
Cross-session persistent cost ledger for DeepSeek Harness: logs every LLM token usage to SQLite and exposes record/query/budget tools. Built-in DeepSeek pricing, overridable via config.
Bundle
Curate tool output before it enters the model's context: keep error/warning lines and head/tail, spill the full text to disk with a pointer. Faster turns, smaller context, sharper attention — for every tool, not just bash.
Bundle
DSH (DeepSeek Harness) v0.1.x Cordis 插件:自动监听每轮模型 API 调用的缓存命中/未命中/输出 tokens,实时统计缓存命中率与按官方定价(含峰谷时段)预估的 API 费用,注册 cache_report 工具,并在浏览器每条消息末尾低调显示本轮 tokens 与人民币消耗。
Bundle
模型路由网关:一个端点连接 290+ AI 提供商(90+ 免费、1200+ 模型),Claude Code/Codex/Cursor/Cline/Copilot 全兼容——配额感知自动回退、19 种路由策略、RTK+Caveman 叠加压缩省 15-95% token、免费层聚合预算(~1.5B tokens/月)、MCP/A2A、本地优先。受 diegosouzapw/OmniRoute(51k★ MIT)启发。
Bundle
Native DeepSeek API balance and local token usage dashboard for DeepSeek Harness
Bundle
第三方模型思考努力度配置(DeepSeek Harness 插件):在设置页为模型声明 reasoningEfforts 档位、路由默认档位与 Anthropic token 预算,写入 llm-pi-ai 命名空间;档位调节复用原生模型框 Effort 面板。
Bundle
Durable per-session and agent-tree Token admission budgets
Bundle
DSH plugin: per-step timestamped API usage timeline (usageTimeline projection) + peak/off-peak cost readout for DeepSeek V4 Pro
Bundle
DSH agent-fleet hygiene audit: credential-file permissions, embedded credentials in git remotes (masked), provider token-prefix literals. Read-only, zero-dependency, deterministic.
Bundle
A collect-em-all safari for DeepSeek Harness: your real work is the tall grass. Turns, tool calls and errors roll wild encounters; throw balls, fill a 28-slot dex, build a team of six. Zero tokens, zero tools, the model never knows.
Bundle
DSH multimodal input plugin: route file attachments (images, video, audio, text) through per-preset model chains and feed the results to the session model as prompt tokens. Adds a Multimodal settings page.
Bundle
DeepSeek Harness 鐢ㄩ噺缁熻鎻掍欢锛氭寜鍘傚晢(璁㈤槄/瀹樻柟API)脳KPI(token/缂撳瓨/杈撳嚭)鑱氬悎锛孏itHub 椋庢牸鏃ュ巻鐑姏鍥?+ 鏃?鏈?鍘傚晢缁熻鐪嬫澘
Bundle
DSH Web GUI 桌面宠物「宇昊」:可拖拽/投喂/玩耍/洗澡/打针吃药/学习/打工/积分商店,token 消耗自动攒积分。
Bundle
DeepSeek Harness 插件:把文本形式的会话统计(轮/步、LLM/工具耗时、首 token、tok/s、缓存命中、输入/输出 token)替换为页面右侧直观醒目的图表面板,每秒刷新。
Bundle
每轮提问的 LLM 用量记录:左侧栏按钮 + 抽屉面板,列出每轮的 tokens/耗时/工具调用,点击跳转到对应会话
Bundle
DeepSeek Harness web plugin: static 余额 badge that fetches the active provider's plan limit or prepaid balance on expand, with token usage and spend estimated from the DeepSeek pricing table.
Bundle
DSH web GUI token-consumption heatmap: a daily/weekly total-token usage panel fed by session-log usage events
Bundle
LLM cost tracker for the DeepSeek Harness: bills every model call from provider token usage (cache hit/miss included), shows per-call cost in the conversation stats line, a per-session summary, and a CC-Switch-style usage statistics dashboard
Bundle
A neon cyberpunk appearance plugin for the DeepSeek Harness web surface: refined RGB ambient lighting, CRT scanlines, and a cohesive cyan/magenta/violet token palette.
Bundle
Standalone premium-palette plugin for dsh Web: eight curated color schemes plus custom palette import (name + scheme + seed colors -> derived full token map), a Palette row in General settings, durable per-plugin persistence, and hot-plug install via dsh plugin
Bundle
Agent FinOps / token analytics for DeepSeek Harness: usage collection, time-aware cost engine, cache analysis, and session drill-down
Bundle
DeepSeek Harness plugin: model sampling sliders (temperature / maxTokens) applied to every provider via the agent/request hook, with live settings persistence.
Bundle
Static and runtime security guard for the DeepSeek Harness: scans plugins and workspaces for malicious code, context injection and token waste (block/warn/clean), intercepts dangerous runtime tool calls and prompt steps, and exposes /scan, plugin_scan, the scan web panel and a user-managed allowlist. Fully static analysis — never executes scanned code.