@jypjypjypjyp/dsh-agent-teams
AgentTeams for DeepSeek Harness：通过自然语言驱动多智能体团队协作（队长、成员、带依赖关系的任务、消息传递），并在 Web GUI 中提供树状监视器
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:jypjypjypjyp/dsh-agent-teams#e839599aada133b67211e522559e4169f8569163Agent Teams 以 @jypjypjypjyp/dsh-agent-teams 发布，当前版本为 0.1.16-rc.1。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
English · 简体中文
dsh-agent-teams turns one DeepSeek Harness session into a coordinated multi-agent team
🍴 Forked from NanmiCoder/dsh-agent-teams (original package
@nanmicoder/dsh-agent-teams, up to0.1.16-rc.1); continued here as@jypjypjypjyp/dsh-agent-teams.
dsh-agent-teams turns the current DeepSeek Harness session into a captain that can assemble durable sub-agents, split a goal into dependency-aware tasks, and coordinate work through direct messages.
Ask in natural language. The plugin provides the team protocol, eleven coordination tools, persistent state, an automatic shared-task scheduler, and a live Web UI—without requiring a separate workflow engine.
Continued from upstream 0.1.16-rc.1, with fixes for startup, member messaging and task collaboration across supported Harness RC / Alpha versions. Choose a version pair below.
| Capability | What it changes |
|---|---|
| Captain-led delegation | The current session creates the team, assigns roles, and consolidates the final result. |
| Durable members | Members are continuable DSH sub-agents that can be woken for focused follow-up turns. |
| Dependency-aware tasks | Tasks move through explicit states and cannot be claimed before their dependencies finish. |
| Automatic reuse and safe takeover | Idle members claim the next ready task; reassignment revokes stale attempts before new work starts, and cold recovery retries stranded open attempts. |
| Direct messaging | Members send durable mailbox messages directly to teammates or the captain—no relay required. |
| Live activity panel | The Web UI combines segmented progress, a collapsible roster, and an interactive task DAG; running tasks show the member's model, and completed archives retain their full member and task history. |
| Plan before execution | Normal /agent-teams runs stage an unspawned roster and DAG first. The Web panel uses the host model catalog for member routes. Returning to chat stops the planning turn, asks what should change, and revises the same draft; discarding archives the draft, aborts the turn, and explicitly prevents automatic recreation. Only Approve & Run creates members and starts scheduling. |
| Quality gates | Opt-in quality tasks support requirements → implementation → verification → review → integration contracts, automatic repair/re-review, and explicit resume. Scope control is a completion-time audit, not host write interception. See docs/quality-gates.md. |
The conversation card and activity panel use Harness's official locale service. They follow live language changes between English and Simplified Chinese—including status labels, dynamic summaries, controls, archive markers, and accessibility text—without a page reload or a separate plugin setting.
Recommended pair: DeepSeek Harness 0.1.2-rc.1 + AgentTeams 0.1.16-rc.1. Both are still prereleases.
| Use case | DeepSeek Harness | AgentTeams plugin |
|---|---|---|
| Recommended installation | 0.1.2-rc.1 | 0.1.16-rc.1 |
| Developer Alpha testing | 0.1.2-alpha.5 | 0.1.16-rc.1 |
| Retaining an older Alpha | 0.1.2-alpha.2 | 0.1.16-rc.1 |
[!NOTE] The live activity panel is hosted inside the dsh-better-sidebar tab. Install
dsh-better-sidebar(v0.13+) to see the AgentTeams tab and the in-card button. Without it the coordination tools, conversation card, and durable state still work — only the visual tab and its button are hidden.This package intentionally does not declare
dsh-better-sidebaras an npm peer dependency: it is an optional runtime host probed viactx.get('betterSidebar'), and declaring it would force pnpm's auto-install-peers to add node-pty/native builds to this project's lockfile. The runtime contract is the structural service described insrc/client/better-sidebar.d.ts.
npm install --global @deepseek-ai/dsh@0.1.2-rc.1
dsh --version
Skip this if you already run this version. Alpha is opt-in: select an exact Alpha version from the table and lock all host dependencies as described in the maintenance guide.
This installs into the web profile. Replace web with your actual profile name if different:
dsh plugin --profile web add github:jypjypjypjyp/dsh-agent-teams
Optional — host the live activity panel in a sidebar tab:
dsh plugin --profile web add dsh-better-sidebar
After installation, stop and restart Harness for that profile, then refresh the browser.
This fork installs from the GitHub source above; the upstream-era npm next/latest channel notes no longer apply.
Desktop users must check the app's embedded Harness core; upgrading the global CLI does not upgrade it. For older
0.1.0-*/0.1.1-*or unlisted hosts, keep a working pair and follow the older-version and diagnostic guide.
See the full compatibility matrix and the source installation and Alpha testing guide.
Then ask for a team directly:
Use AgentTeams to review the commits after v0.5.3 from performance, security, and product perspectives. Return one consolidated report.
running / idle / ready state to atomically claim one ready task per idle member and wake it. An interrupted resident attempt stays parked and can resume through a direct message without losing its capability; after a cold process restart, the scheduler retries stranded open work with a fresh attempt.attempt_id; reassignment or captain takeover revokes the old attempt and waits for the old worker to quiesce before a new attempt starts.Team state is stored under <workspace>/.agent-teams/; the AgentTeams tab reads that disk truth and combines it with live sub-agent activity.
Member creation is zero-interaction by default: a member on the captain's current LLM route snapshots that provider, model, and reasoning effort, while a member on a requested alternative route snapshots the target model's default effort; later continuations restore the resolved snapshot. Only an explicit heterogeneous-team request (for example, “backend on provider A/model X, frontend on provider B/model Y”) supplies a member-specific provider + model; there is no per-member model or reasoning prompt.
No “use AgentTeams” phrasing required. The plugin registers the
closed-namespace /agent-teams host command, so the Web GUI slash menu shows
an agent-teams placeholder with an input hint: pick it (or type the
command), describe the goal, and press Enter.
/agent-teams research the pricing pages of three competitors
The command pipeline claims the line, then preserves that exact input as an
ordinary user follow-up so it remains visible in the main chat. The gesture
boundary adds the deterministic activation directive at pre-step, so the
captain protocol still starts immediately. The invocation is also durably
logged (command/run / command/done).
Surfaces without command adjudication (for example the headless CLI) get the
same deterministic activation through a gesture boundary: any genuine user
message starting with /agent-teams activates the protocol for the rest of
the text. Mid-sentence mentions stay ordinary prose.
Defaults work without extra setup. A trusted profile can override member behavior:
- id: agent-teams
config:
stateDir: .agent-teams
memberProvider: spawn
memberModel: deepseek-v4
memberMaxDepth: 1
maxMembers: 8
memberProvider is the sub-agent runtime backend (spawn / fork), not an LLM provider. Cross-LLM-provider routing uses the optional provider + model fields of agent_teams_add_member; memberModel is only a model default for all members. A member on the captain's current provider/model inherits the captain's reasoning effort, while a changed provider or model automatically uses the target model's default. To request a particular effort, pass the optional reasoning_effort field — one of the target model's supported effort ids, or "default" to force the model's own default.
slashCommand: false disables the deterministic /agent-teams activation surfaces (slash command and gesture boundary), leaving the natural-language trigger as the only entry point.
See docs/usage.md for the full tool reference, state model, Web UI behavior, configuration, and known limits.
Community upgrade, audit, benchmark, testing and release skills are vendored with a pinned source revision. See skills/README.md for local rules and CONTRIBUTING.md for the contribution workflow.
The repository also ships the open Agent Skills package dsh-plugin-development:
npx skills add jypjypjypjyp/dsh-agent-teams --skill dsh-plugin-development
| Guide | Covers |
|---|---|
| Usage | Architecture, UI behavior, tools, configuration, limits, and validation |
| Verification | Offline, composition, real e2e, and GUI verification |
| Plugin development | Human-readable guide built from this plugin |
| README writing | Repository documentation conventions |
pnpm install
pnpm build
pnpm verify
Configure one or more complete team profiles in cordis.patch.yml. A profile always supplies the roster (independent provider/model/role/reasoning effort). Set taskPlanning: captain when the Captain should derive the DAG from the user's goal; omit it or set taskPlanning: seed to keep a fixed template workflow:
profiles:
demo-delivery:
description: Ship a small feature
protocol: Discuss requirements, review, test, then prepare release; do not deploy automatically.
members:
- name: analyst
model: gpt-5.6-sol
role: Analyze requirements
- name: implementer
model: gpt-5.6-terra
role: Implement the approved solution
tasks:
- id: requirements
subject: Requirements discussion
assignee: analyst
- id: implementation
subject: Implement solution
assignee: implementer
dependencies: [requirements]
Use an explicit profile flag: /agent-teams --profile demo-delivery implement the feature. The first ordinary token is never treated as an implicit profile. Normal command runs call agent_teams_create({ profile, approval: "required" }): the roster and seed/Captain-designed DAG remain staged, no child session is created, and no task is claimed. Edit the plan in the activity panel using the host model catalog, return to chat so the Captain asks what to revise and then atomically updates the same draft, discard it, or click Approve & Run. Return/discard actions cancel any planning turn still running; discard also parks model-facing context that forbids silently creating a replacement team. Approval resolves the final provider/model/reasoning choices, atomically spawns the roster, and starts only ready tasks. A running team is stopped from its own panel header through a confirmation dialog rather than from the composer. Direct tool clients may pass approval: "automatic" for the legacy immediate path. Failed review/test tasks do not unlock downstream work; automatic repair/review tasks do not depend on the failed review.