@nanmicoder/dsh-agent-teams 0.1.17 → 0.1.19

package/README.md

@@ -22,7 +22,7 @@
 
 `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, 13 coordination tools, persistent state, an automatic shared-task scheduler, and a live Web UI—without requiring a separate workflow engine.
+Ask in natural language. The plugin provides the team protocol, 14 coordination tools, persistent state, an automatic shared-task scheduler, and a live Web UI—without requiring a separate workflow engine.
 
 <p align="center">
   <img src="./assets/ui.png" width="100%" alt="DeepSeek Harness conversation with the AgentTeams live activity panel, members, tasks, dependencies, and reports">
@@ -42,7 +42,7 @@ Ask in natural language. The plugin provides the team protocol, 13 coordination
 | **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. |
+| **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** enables scheduling; each member starts with its first ready task. |
 | **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](./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.
@@ -100,7 +100,7 @@ Team state is stored under `<workspace>/.agent-teams/`; the Web panel reads that
 
 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.
 
-Captain sessions keep the concise core protocol and the original 13 native team tools from their first request. All business tools are directly available; no loading tool or extra activation call is needed. Configured profiles retain their bounded directory in the fixed system prompt. Creating, approving, continuing or ending a team does not rewrite the system prompt or tool schemas. Core rules remain available after history compaction or discarded code-mode tool results. Members receive four team tools, fixed member instructions, and their ordinary coding/research tools. Web approval wakes the captain with a control message; later member reports wake it again. See the [fixed protocol and benchmark contract](./docs/progressive-loading.md).
+Captain sessions keep the concise core protocol and the original 14 native team tools from their first request. All business tools are directly available; no loading tool or extra activation call is needed. Configured profiles retain their bounded directory in the fixed system prompt. Creating, approving, continuing or ending a team does not rewrite the system prompt or tool schemas. Core rules remain available after history compaction or discarded code-mode tool results. Members receive four team tools, fixed member instructions, and their ordinary coding/research tools. Web approval wakes the captain with a control message; later member reports wake it again. See the [fixed protocol and benchmark contract](./docs/progressive-loading.md).
 
 ## Slash command
 
@@ -136,10 +136,12 @@ Defaults work without extra setup. A trusted profile can override member behavio
     stateDir: .agent-teams
     memberProvider: spawn
     memberModel: deepseek-v4
-    memberMaxDepth: 1
+    memberMaxDepth: 0
     maxMembers: 8
 ```
 
+`memberMaxDepth` defaults to `0`: team members cannot create nested subagents. Set `1` to explicitly permit one descendant level; the limit also covers runtime/code-tool calls. Default members report through team messages only, avoiding duplicate native parent reports. Idle roster members make no model requests. Task assignments start distinct turns; coordination joins the nearest model step. Acceptance and consumption are tracked separately. Removal/archive drains the selected branch and its pending input before reporting success.
+
 `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.
@@ -206,7 +208,7 @@ profiles:
         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.
+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, commits the roster, and creates each member session only when its first task is ready. 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.
 
 ## License
 

package/README_ZH.md

@@ -22,7 +22,7 @@
 
 `dsh-agent-teams` 让当前 DeepSeek Harness 会话成为队长：创建可续聊的子 Agent、把目标拆成有依赖的任务，并通过直达消息协调成员工作。
 
-你只需用自然语言提出目标。插件会提供精简的固定团队协议、13 个业务工具、持久化状态、自动共享任务调度和实时 Web UI，不需要额外的 Workflow 引擎。
+你只需用自然语言提出目标。插件会提供精简的固定团队协议、14 个业务工具、持久化状态、自动共享任务调度和实时 Web UI，不需要额外的 Workflow 引擎。
 
 <p align="center">
   <img src="./assets/ui.png" width="100%" alt="DeepSeek Harness 对话与 AgentTeams 实时活动面板，展示成员、任务依赖和回报">
@@ -86,7 +86,7 @@ npm 默认标签 `latest` 现指向 `0.1.17`，因此新 profile 使用 `dsh plu
 
 > 使用 AgentTeams 审查 v0.5.3 之后的提交，分别从性能、安全和产品角度分工，最后输出一份汇总报告。
 
-队长会话从第一轮起保留精简的固定核心协议和原有 13 个业务工具，直接调用，无需额外的加载工具或激活调用。已配置模板的精简目录固定保留。创建、批准、继续或结束团队都不会改写系统提示词和工具 schema，会话压缩或代码模式丢弃工具结果也不会丢失核心规则。成员保留四个团队工具、固定成员说明及普通编程/研究工具。Web 批准后会通知并唤醒队长，后续成员报告会再次唤醒它，无需忙轮询。详见[固定协议与 benchmark 标准](./docs/progressive-loading.md)。
+队长会话从第一轮起保留精简的固定核心协议和原有 14 个业务工具，直接调用，无需额外的加载工具或激活调用。已配置模板的精简目录固定保留。创建、批准、继续或结束团队都不会改写系统提示词和工具 schema，会话压缩或代码模式丢弃工具结果也不会丢失核心规则。成员保留四个团队工具、固定成员说明及普通编程/研究工具。Web 批准后会通知并唤醒队长，后续成员报告会再次唤醒它，无需忙轮询。详见[固定协议与 benchmark 标准](./docs/progressive-loading.md)。
 
 ## 工作方式
 
@@ -123,10 +123,14 @@ npm 默认标签 `latest` 现指向 `0.1.17`，因此新 profile 使用 `dsh plu
     stateDir: .agent-teams
     memberProvider: spawn
     memberModel: deepseek-v4
-    memberMaxDepth: 1
+    memberMaxDepth: 0
     maxMembers: 8
 ```
 
+`memberMaxDepth` 默认 `0`，团队成员不能再创建子代理；显式设为 `1` 可允许一层后代，运行时和代码工具调用同样受限。默认成员统一通过团队消息汇报，避免再走宿主消息重复通知队长。无任务成员不调用模型；任务分配开启独立轮次，纠正消息进入最近的模型步骤。消息投递与读取分别记录；移除和归档必须等成员分支及待处理输入清理完成后才报告成功。
+
+普通调研、仓库审计可用 `agent_teams_create({name, description, approval:"required", plan:{members:[{name:"researcher"}], tasks:[{id:"audit", subject:"审计现有实现", assignee:"researcher"}]}})` 一次创建完整草案。任务的 `dependencies` 引用同一批中的 `id`，支持前向引用并校验环；结果返回实际任务 ID。`kind=review` 专用于对既有 implementation/repair 任务的质量复审，普通仓库审计使用默认的 `kind=work`。
+
 这里的 `memberProvider` 指子 Agent 的运行后端（`spawn` / `fork`），不是 LLM provider。跨 LLM provider 由 `agent_teams_add_member` 的可选 `provider` + `model` 参数表达；`memberModel` 只是所有成员的模型默认覆盖。成员沿用队长当前 provider/model 时会继承队长的思考强度；provider 或 model 任一改变时会自动使用目标模型的默认档。需要指定特定强度时，可传入可选的 `reasoning_effort` 参数（目标模型支持的档位 id，或 `"default"` 表示强制使用模型自身默认档）。
 
 `slashCommand: false` 可关闭确定性的 `/agent-teams` 激活面（slash 命令与手势边界），仅保留自然语言触发。
@@ -172,7 +176,7 @@ pnpm verify
 
 在 `cordis.patch.yml` 的 `profiles` 中配置完整团队模板。每个 profile 都提供成员阵容，可独立指定 provider、model、role、reasoning_effort。`taskPlanning: captain` 表示只提供阵容和约束，由 Captain 根据用户目标设计 DAG；省略该字段或设为 `seed` 时，展开模板中的固定任务图。使用 `/agent-teams --profile <名称> <目标>` 显式激活；不会把首个普通 token 隐式识别为 profile。
 
-普通 `/agent-teams` 流程继续已有团队，按需调用 `agent_teams_status` 确认状态；仅在没有当前团队时调用 `agent_teams_create({ profile, approval: "required" })`：只落盘可编辑的成员占位和 DAG，不创建子会话、不领取任务。成员模型和推理等级直接读取 Harness 的模型目录。「返回对话修改」会终止仍在运行的规划轮次，让队长先追问修改方向，再用一次原子操作更新同一份草案；「放弃本次计划」经二次确认后会归档草案、中止轮次，并向模型注入不得自动重建团队的控制上下文。只有点击「确认并启动团队」才会按最终配置原子创建成员并启动就绪任务。运行中团队的停止入口位于该团队的面板标题，点击后需要二次确认，不再占用输入区域。直接工具调用方可显式传 `approval: "automatic"` 保留旧的立即执行路径。审查或测试失败不会解锁下游；自动 repair/review 不依赖 failed review。
+普通 `/agent-teams` 流程继续已有团队，按需调用 `agent_teams_status` 确认状态；仅在没有当前团队时调用 `agent_teams_create({ profile, approval: "required" })`：只落盘可编辑的成员占位和 DAG，不创建子会话、不领取任务。成员模型和推理等级直接读取 Harness 的模型目录。「返回对话修改」会终止仍在运行的规划轮次，让队长先追问修改方向，再用一次原子操作更新同一份草案；「放弃本次计划」经二次确认后会归档草案、中止轮次，并向模型注入不得自动重建团队的控制上下文。只有点击「确认并启动团队」才会提交最终配置并调度就绪任务；成员有就绪任务时才创建会话。运行中团队的停止入口位于该团队的面板标题，点击后需要二次确认，不再占用输入区域。直接工具调用方可显式传 `approval: "automatic"` 保留旧的立即执行路径。审查或测试失败不会解锁下游；自动 repair/review 不依赖 failed review。
 
 ## 许可证
 

package/lib/client/AgentTeamsCard.js

@@ -50,5 +50,5 @@ export function AgentTeamsCard({ node, openMember, sessionId, t }) {
     return (_jsxs("section", { className: css.root, "data-agent-teams-card": true, "data-team-id": resolved.teamId, children: [_jsxs("header", { className: css.head, children: [_jsx("img", { className: css.leadAvatar, src: LEAD_ART, alt: "", "aria-hidden": true }), _jsx("span", { className: css.teamName, title: resolved.teamName, children: resolved.teamName }), _jsx("span", { className: css.memberCount, children: t('card.memberCount', { count: resolved.members.length }) }), _jsx("button", { type: "button", className: css.panelButton, onClick: () => { openActivityPanel(resolved); }, "aria-label": t('action.openActivityPanel'), title: t('action.openActivityPanel'), children: t('activity.panelButton') })] }), resolved.members.length > 0 && (_jsx("div", { className: css.members, children: resolved.members.map((member) => (_jsxs("button", { type: "button", className: css.member, onClick: () => {
                         if (member.id !== '')
                             openMember(owner, member.id);
-                    }, title: member.role === '' ? member.name : `${member.name} · ${member.role}`, children: [memberArtUrl(member.name, member.role) !== null ? (_jsx("img", { className: css.memberArt, src: memberArtUrl(member.name, member.role) ?? '', alt: "", "aria-hidden": true })) : (_jsx("span", { className: css.memberInitial, children: member.name.trim().slice(0, 1).toUpperCase() || '?' })), _jsx("span", { className: css.memberName, children: member.name })] }, member.id))) }))] }));
+                    }, title: member.role === '' ? member.name : `${member.name} · ${member.role}`, children: [memberArtUrl(member.name, member.role) !== null ? (_jsx("img", { className: css.memberArt, src: memberArtUrl(member.name, member.role) ?? '', alt: "", "aria-hidden": true })) : (_jsx("span", { className: css.memberInitial, children: member.name.trim().slice(0, 1).toUpperCase() || '?' })), _jsx("span", { className: css.memberName, children: member.name })] }, member.id || member.name))) }))] }));
 }

package/lib/client.js

@@ -554,7 +554,7 @@ window.__ModuleLoader__.load({
 							className: AgentTeamsCard_module_css_default.memberName,
 							children: member.name
 						})]
-					}, member.id))
+					}, member.id || member.name))
 				})]
 			});
 		}