@kober-basket/dsh-cachescope
Prompt-cache observability and logical-input diagnostics for DeepSeek Harness
930 results
Prompt-cache observability and logical-input diagnostics for DeepSeek Harness
VS Code / IDEA-style run control for the DeepSeek Harness web GUI: run buttons, task run configurations (LLM prompt / background command), configuration CRUD, and an LLM-exposed configuration tool with an on-demand usage skill
Clean-room Grok Build provider for DeepSeek Harness with official CLI browser authentication
Semantic-Linter plugin and CLI for narrowing wide-boundary wording in LLM instruction files.
Vision sidecar for text-only coding agents.
DSH web plugin: a bottom-right bubble showing the live usage/quota of every configured LLM model provider (OpenCodeGo, OpenRouter, OpenAI, DeepSeek…), with a configurable update policy (on user request / every N steps / interval / window reset / hover), theme-aware styling, device-local times and zh/en i18n.
Two-tier model router for DeepSeek Harness: an LLM Judge sends each turn to the cheap Fast chain or the Smart chain by expected cost, with multi-model fallback chains, exponential-backoff failover, cache-aware switching and task-level orchestration. A DSH adaptation of pi-shift-router.
DSH 插件配装引擎:任务 → 双检索(规则+LLM) → 组合评分(协同/冲突/成本/信任) → 配装建议。区别于目录/搜索:按任务自动配整套插件,含冲突检测与安装命令导出。
DeepSeek Harness 插件:审查最近改动的代码,就清晰度、一致性与可维护性提出改进(移植自 pi-simplify)
Multi-agent orchestration and LLM model routing for DeepSeek Harness (DSH): semantic AI agent Specialists, exact model routes, declarative Cohorts and Strategies, and bounded subagent delegation.
dsh-vision — a DeepSeek Harness plugin (tool template).
Token usage statistics for the DeepSeek Harness Web UI: captures per-request LLM usage from the llm/stream waterfall, persists it, and renders animated charts grouped by API (provider), model, and date.
Code reference & reuse-survey plugin for DeepSeek Harness (DSH): search local code + GitHub/npm before building, evaluate reuse vs rewrite, ask the user, architecture-level reuse. 开发前检索本地与开源可复用代码并询问用户的复用调查插件。
Fail-closed LLM-assisted approval reviewer for DeepSeek Harness
ChatGPT OAuth and Codex models for DeepSeek Harness, with browser callback and device-code login
模型能力画像: 回顾式分析 ~/.dsh 历史会话 → 按模型的能力画像(擅长面/易翻车/建议用法) + 会话区只读观察窗 tab
Feishu (Lark) IM bot channel for DeepSeek Harness agents — per-chat sessions, native thinking process, interactive approval cards, WebSocket long connection.
LLM 自动重试设置卡片:在 设置 → General 里修改重试次数(maxRetries)与退避时间(initialDelayMs/maxDelayMs/jitterRatio),宿主 dsh-llm-retry 实时生效
Universal local vision bridge tool for DSH: describe/answer questions about images via any OpenAI-compatible local inference framework (llama.cpp / Ollama / LM Studio / vLLM), vision models auto-detected
理解任何东西技能包(移植自 Understand-Anything)
deepseek-eyes:给 DeepSeek Harness 的纯文本模型装上眼睛——把粘贴的图片经 OpenAI 兼容视觉 API 转成文字描述,再转发给真实的文本模型(Give text-only models in DeepSeek Harness eyes: describe pasted images via an OpenAI-compatible vision API, then forward to the real provider. Not affiliated with DeepSeek.)
Zhipu AI BigModel and GLM Coding Plan LLM Provider model catalog plugin for DeepSeek Harness
DSH-native vision bridge for text-only models with native image attachments, multi-image evidence batching, and session-scoped validated Evidence caching.
DSH LLM adapter plugin: use OpenAI ChatGPT subscription (GPT-5.6-Sol, GPT-5.5, ...) via OAuth — no API key. Reuses your local Codex CLI login.