@dsh-external/dsh-subagent-model-picker
让主会话模型从已配置模型里自主选择子代理模型
197 results
让主会话模型从已配置模型里自主选择子代理模型
Multi-agent orchestration plugin for DeepSeek Harness: team presets, subagent delegation, sequential pipelines, and policy gates.
DeepSeek Harness 插件:规划/执行分离。主模型负责分析、规划与汇总,通过 delegate_execution 工具把执行工作委派给独立的执行子代理;执行子代理的模型、LLM 提供方、人格与工具范围在 Web 设置「规划与执行」分节配置(默认继承主模型)。子代理中间步骤永不进入主会话,最大化节约主模型 token。零构建依赖、纯 JS 即装即用:`dsh plugin --profile web add "github:mikuuuuuue/dsh-planner-executor"`。
DSH named-subagent pool: 可独立配置子代理的预设、模型、推理等级,且主代理可通过描述的内容知晓什么时候调用此子代理
Per-stage model routing for dsh-TUI: let subagents run on a different provider/model/reasoning-effort, configured in /settings (model-switch namespace), status via /model-switch.
AgentTeams for DeepSeek Harness: multi-agent team collaboration (captain, members, tasks with dependencies, messaging) driven by natural language, with a tree monitor in the web GUI
ResearchCraft as a DeepSeek Harness profile: DSH web UI and agent, scientific skills, lab notebook, specialist subagents.
Terminals view tab for the DSH web UI: live count of background shells/subagents per session, Chinese purpose titles, collapsible command bodies with streaming output, and one-click kill
Run every DeepSeek Harness task directly in the FlowText Agent UI
Processes tab for DeepSeek Harness: a live per-process console (main agent and every subagent) with raw tool requests, responses and timing, installed as one profile bundle.
Claude Code as a real, streaming dsh subagent: session-backed child, free model/effort choice per call, live model list from the CLI
Installable DeepSeek Harness Web UI for replaying a completed session step
Research-assistant plugin suite (literature search, research wiki, LaTeX compile, independent subagent review) for the DeepSeek Harness
Prevent the OS from sleeping while any DSH agent, subagent, or background job runs (SetThreadExecutionState / caffeinate / systemd-inhibit), with a web settings page
Two-way Codex↔DSH bridge: skills from ~/.codex/skills, session import with workspace attach, live MCP mirroring of mcp_servers, and a Codex-side reverse MCP installer.
DSH client plugin — flip to the back of the page for a floating glass task console: live background jobs, subagents, session overview and workspace of the current session, with mouse-draggable cards; the top-right card conversation calls a temporary agent session to refactor each card's style and internal controls from natural language, and any conversation can author cards via [taskcard] blocks (text/heading/note/stats/progress/trend/kv/links/chips/checklist/counter/button/table/code/toggle/countdown/bars).
格物审视面插件:gewu_prep(HTML 逐页截图 + subagent_vision 简报契约生成,宿主直起 Chrome)+ gewu_locate(真值核验:文字定位到页码/行号)。让无视觉能力的主脑经 subagent_vision 完成视觉检验。
GROX Network for DeepSeek Harness: find agents and workers on grox.life, hire one for a task, get the work back — paid, escrowed, refunded on failure, disputable. Also a `grox` subagent provider, so the harness can hand a lane to a GROX agent like it hands one to Claude Code.
Litefuse observability for DeepSeek Harness: every user turn becomes one agent trace with per-call generations, tool spans, and subagent subtrees
A bundle built on DeepSeek Harness that registers Claw Orchestrator as an ACP subagent provider — delegate a dsh subagent to a multi-engine council across Claude Code, Codex and Cursor.
常驻视觉服务:直连视觉模型(默认 opencode-go/minimax-m3,回退 zai-coding-cn/glm-4.6v)。describe_image / subagent_vision 工具 + 粘贴图片自动转译(llm/stream 钩子)+ 输入框视觉状态小胶囊与详情页(活动日志:指令/思考过程/输出)。零子代理、零 agent 上下文开销,按会话记忆窗支持视觉追问与验收。
Multi-agent orchestration for DeepSeek Harness: delegate, adversarial review, diverse explore, background runs + converge. One prompt. A team of agents.
A2A client provider plugin for DeepSeek Harness
DSH skill bundle: competition math (IMO/Putnam/USAMO/AIME) solved with a pure-reasoning pass, an adversarial verifier in a fresh subagent context attacking concrete failure modes, and calibrated confidence output (high / medium / honest "no confident solution"); optional LaTeX→PDF rendering.