subagent 96

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.

A Codex delegation tool for DeepSeek Harness that can carry a model and a reasoning effort per call.

Per-conversation subagent model selection for DeepSeek Harness Desktop.

基于「三省六部制」的极简高质跨环境 AI 研发工作流引擎与 DeepSeek Harness 插件 (Vue 3 + .NET 8 / Core 3.1 深度优化)

Agile pair programming for DeepSeek Harness: a self-contained Driver/Navigator/Challenger protocol runtime with quality gates, on host subagent primitives. No third-party plugin dependencies.

Installable DeepSeek Harness Web UI for replaying a completed session step

Primary-controlled deliberation and opt-in masked review for DeepSeek Harness

DSH agent preset: chief coordinator + 17 domain-expert subagents with taskboard scheduling, quality gates, and real inter-expert communication bus (专家模式)

Role-based subagent delegation for DeepSeek Harness: one delegate tool over a folder of role files, with a roster that ships and stays overridable

Declarative task-DAG orchestration plugin for DeepSeek Harness workflows

DSH plugin: deliver the real failure reason (e.g. RATE_LIMIT 429) to the parent agent when a background subagent fails, instead of an empty "Its closing message:"

Task Runner 任务拆解模式：主代理把大任务拆成独立子任务、派给子代理（默认本地模型）并行执行再综合结果；并发数与 worker/fallback/orchestrator 模型可在设置面板图形化配置。安装时自动把 agent preset 装进 ~/.dsh/.agent-presets/。

Deterministic fault injection, recovery, and side-effect auditing for DeepSeek Harness agents.

Agent team runtime layer for DeepSeek Harness: named subagents, per-agent personas and tool surfaces, explicit delegation graph, and absolute depth/width budgets.

Intelligent sub-agent orchestration for DeepSeek Harness, with model discovery, routing, planning, and parallel delegation.

Declarative multi-agent pipeline executor for DeepSeek Harness (dsh): runs a manifest of confined role dispatches with mechanical gates and a machine-written evidence ledger. dsh 声明式多角色流水线执行器：按 manifest 派发受限子代理、机械门禁、机器写证据账本。

One-shot Grok CLI subagent provider for DeepSeek Harness

A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, hidden-models blacklist, live per-task cost, prices and context windows, a refresh button that re-syncs every provider model list from its live API, and the

DeepSeek Harness plugin that asks which provider and model should run each delegation before the child starts, so a subagent can go to a cheap or local route instead of the parent's.

A DeepSeek Harness plugin that mounts one subagent delegation tool per configured role and model, each bound to its own model provider route.

DSH 对抗多智能体三层失效的防御插件：读取台账去重度量(read-ledger)、免疫压缩规则区+完成机械门禁(immutable-core+completion-gate)、低成本审查lane(role-router)。零外部依赖，注入即用。

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

AgentTeams for DeepSeek Harness: durable teammates, task DAG, read-only role isolation

DeepSeek Harness plugin: subagents with their own model and reasoning effort 闂?GUI settings card (plugin-owned config file), config defaults, and a parent-model-controlled delegation tool (subagent_select).

Better subagents for DeepSeek Harness: choose the default subagent model, see each subagent conversation's model in its header, and wait for subagents with a blocking wait_subagents tool instead of sleeping or polling.

Per-agent scoping for the dsh workspace instruction chain (discussion #7361). @deepseek-ai/dsh-agent-instructions injects the workspace instruction chain into every agent in the tree; its Config governs which files are discovered, globally, and nothing ex

Three-mode visible-session advisor plugin for DeepSeek Harness with configurable tool permissions, local-subagent coverage, and task-tree budgets.

把「不着急但需要 agent 能力」的活外包给豆包工作桌面端：任务卡 + 契约 + 台账 + 技能沉淀，省 DSH 的 token。运行时依赖只有 schemastery（宿主自带，用于设置页 schema）。

Role-based model manager for DeepSeek Harness: assign models to planning, execution, vision and main roles, route subagent work by role, and report which model every subagent used.

In-process DeepSeek Harness subagent provider that seeds a child with only the last N completed parent turns (fork-lite), leaving official fork untouched.

Live subagent progress dock for DeepSeek Harness: folds each child session's events into a subagentProgress projection (turn/step, last tool, latest assistant preview, notify_user updates) and renders a frosted-glass status dock above the parent conversat

dsh bundle: subagent_vision — delegate image reading to a vision-capable model from a text-only session, plus paste-to-path so pasted images reach the subagent as file paths.

Report-and-ledger plugin for DSH: front-matter 汇报 as the first-class agent-to-agent interaction primitive, with upward/downward delivery, co-authorship, CC, and a complete transfer-path audit trail; plus a conversation timeline tab.

Active wait for background continuable subagents in DeepSeek Harness: registers a wait_subagent tool that blocks until the named subagent settles, then returns its stop reason and closing message — closing the gap between run_in_background fire-and-return

dsh plugin: Jev-guided dispatch advice — before a turn starts, a TypeSafe Jev call decides whether the task belongs to a registered agent and which one, then injects a four-line, ignore-if-unsuited recommendation. Jev-optional: no key means silence.

Configurable domain-scoped expert agents for DeepSeek Harness

DSH host plugin: enforces the subagent-model-selection whitelist for subagent, agent teams, and every other child-Agent creation.

DSH plugin: a Settings switch that disables the subagent tool family (subagent/subagent_fork/workflow/ralph/list_subagent_models/send_message) and tells the model to use Agent Teams instead.

Offloads large, low-judgement DeepSeek Harness tool results to small one-shot worker agents before they enter the main model context

GUI settings card for dsh-subagent-effort: choose the subagent model and reasoning effort in Settings 鈥?no config files to edit.

dsh harness for dsh-local-agent: delegate to dsh itself as a local CLI — scoped DSH_HOME under the shared homes root, one-shot sub-dsh runs visible in the 子代理 surface, caller-supplied session ids, resume across rounds, DeepSeek toggle in settings

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。

DeepSeek Harness bundle that registers Claw Orchestrator as an ACP subagent provider — delegate a dsh subagent to a multi-engine council across Claude Code, Codex and Cursor.

dsh Web UI admin plugin: eleven management panels (extensions, skills, MCP servers, subagents, commands, hooks, automation - cron / webhook / workflow, sessions & web search, usage dashboard, todo dock) inside the official dsh settings UI

MiOpIIk one-shot execution policy adapter over native DSH subagents: explicit zero-default routing, leaf depth, persona/tool scope, timeout/cancel and bounded result presentation. 原生 DSH subagent 上的执行策略适配层

Per-delegation reasoning effort for dsh subagents: makes AgentOptions.reasoningEffort reach child requests (the agent loop silently ignored it) and adds a subagent_effort tool that accepts reasoning_effort and model per call