dsh-llm-opencode-go
OpenCode Go models, mixed Completions/Responses/Messages chat, and subscription usage for DeepSeek Harness
854 results
OpenCode Go models, mixed Completions/Responses/Messages chat, and subscription usage for DeepSeek Harness
DSH subagent provider that delegates tasks to the OpenAI Codex CLI (codex exec), exposing the subagent_codex tool
TradingAgents for DeepSeek Harness: the 14-role A-share multi-agent analysis pipeline (analysts → bull/bear debate → research manager → risk debate → trader) behind the /trading-agent command. · A股多智能体投研分析插件。
Prompt enhancement plugin for DeepSeek Harness: an "✨ Enhance" composer button that rewrites prompts with first-principles thinking using session context, and asks clarifying questions when key info is missing.
DeepSeek Harness native plugin: give text-only LLMs (e.g. DeepSeek) vision via free Gemini / GLM vision APIs — describe images, OCR, VQA, screenshots, charts; integrated browser paste & drop.
DeepSeek Harness plugin: automatically adds a stable per-conversation x-opencode-session header to OpenCode / OpenCode Go provider requests — fixes 400 MissingSessionID and keeps OpenCode's session affinity / prompt-cache routing working.
DeepSeek Harness LLM provider for Codex models using managed ChatGPT OAuth
DeepSeek Harness plugin — manage an LLM-Wiki knowledge base from the agent: wiki_search / wiki_read / wiki_stats / wiki_validate / wiki_fix / wiki_errorbook / wiki_ingest
Cancelable auxiliary-model runtime for DeepSeek Harness with a provenance-preserving usage ledger outside official tokenUsage
提示词增强(DSH 通用插件):三种模式(基础/标准/专家)读取会话工作区项目上下文并调用 LLM 增强输入框提示词,支持结果对比确认、采用后撤回、失败模型回退链、按模型能力自动适配推理档位(网关不支持时自动去参重试)、待确认问答闭环(逐条回答后带答案重新增强)、组合行 config 可配置、可取消。Host 半提供 /api/prompt-enhance/enhance;浏览器半在 composer 工具行注册模式选择与 ✦ 按钮、对比面板与忙碌状态卡。随 harness 启动自动加载,无需手动重新加载。
DeepSeek usage monitor as a DeepSeek Harness (DSH) plugin: balance / day-month-all-time token & cost panels in the chat UI with drag-reorder config, plus an optional local usage proxy
DSH tool-call compatibility: strips sandbox_permissions/justification from tool-call arguments for third-party models (GPT etc.), and lets the user skip possibly-stuck tool calls with an LLM-facing notice.
MCP server that searches the Roblox DevForum and official creator docs so AI coding agents can debug Roblox games against real community and engine knowledge.
Optional local runtime dependencies for Chat2Skill plugin features.
分层长期记忆 MCP 服务器:本地 MiniLM 或 OpenAI 兼容嵌入 API,供 LLM Agent(DeepSeek Harness / Claude Code)做可语义检索的长期记忆
DeepSeek Harness 自动审批插件:在 workspace-write 沙箱之上增加 Auto 档——确定性规则放行/拒绝,模糊操作由 LLM 裁决,危险操作转人工。保留工作区沙箱边界,不放宽为 full-access。
Expose a DeepSeek Harness agent over the Agent2Agent (A2A) protocol: agent card, JSON-RPC endpoint, LLM-powered replies, and a live status card.
Witness — the quality gate for agent-built web apps. Independent browser acceptance testing: CLI, MCP, AI-drafted checklists, visual regression, multi-browser. Agents self-test and pass; real browsers tell the truth.
Adaptive model routing for DeepSeek Harness: per-request complexity classification with automatic provider routing.
AI approval answerer using the unified ctx.llm route with fail-closed local policy checks
DSH 费用统计插件:会话费用行 + 成本归因报告,llm-pricing 动态价格。 / DSH cost attribution and usage dashboard, priced by llm-pricing.
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 / 分项清理 / dayRetention 自动保留);提供 WebUI 实时面板(含历史清理)、HTTP JSON 端点、状态文件与 concurrency_status / concurrency_session_list / concurrency_session_set 工具。
Humanize Mode for DeepSeek Harness — the humanfia flow philosophy (draft → check → lock → review → run/resume, SHA-256 lock identity, HMAC review gate, event-sourced resumability) as an agent preset. Installing this bundle auto-installs the preset into the DSH preset root.
DSH 草稿润色:发送按钮左侧 ✨ 一键调用 LLM 润色输入框草稿,可选携带会话上下文帮助模型理解意图;走 DSH llm 渠道,会话进行中也能用