Long-task orchestration loop: Codex plans/scores/reviews, DeepSeek executes, Kimi supplements (vision acceptance, summarization, cross-check).
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:rocker2018-droid/dsh-longtask-orchestrator
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time. Only install sources you trust, and pin a commit (github:owner/repo#sha).
README
长任务编排插件:Codex 当管理层(规划/打分/审核),DSH 当执行层,Kimi 当补充层(视觉验收/摘要/交叉验证)。
架构
长任务 ──► Codex 规划(codex_plan)──► 子任务清单(含验收标准/依赖)
│
▼
DSH 执行(agent 自己的工具 / subagent)
│
▼
Codex 打分(codex_score,7/10 及格)── 不过 → 按建议重做(最多 3 次)
│ 通过
▼
Kimi 补充(kimi_summarize 压缩 / kimi_review 交叉验证 / kimi_call 视觉验收)
│
▼
Codex 终审(codex_review)──► Kimi 摘要 ──► 最终报告
工具(9 个,全局注册)
| 工具 | 作用 |
|---|---|
codex_call(prompt, cwd?, model?) |
底层 Codex 桥(只读沙箱、自动代理、串行队列) |
kimi_call(prompt, image_path?, model?) |
底层 Kimi 桥(文本/视觉) |
codex_plan(task, context?) |
Codex 拆解计划 → JSON 子任务清单 |
codex_score(task, criteria, result) |
Codex 打分 0-10 + 修改建议 |
codex_review(plan, results) |
Codex 终审 |
kimi_summarize(text, max_chars?) |
大结果摘要压缩 |
kimi_review(result, criteria) |
Kimi 交叉验证(第二意见) |
orchestrate_state(action, state?) |
状态文件读写(read/save/clear) |
longtask_begin(goal, context?) |
初始化长任务:Codex 规划 + 写入 state.json |
其他组成部分
- skill
longtask-orchestrator:循环模板,长任务时自动触发 - 模型组「DeepSeek + 长任务编排」:delegating adapter,选中后每轮注入编排提示
配置
| 项 | 默认 | 说明 |
|---|---|---|
| codex 二进制 | /Applications/ChatGPT.app/Contents/Resources/codex(不存在则回退 PATH 的 codex) |
ORCHESTRATE_CODEX_BIN 可覆盖 |
| 代理 | 自动检测 macOS 系统代理(scutil) | 子进程会带上 HTTPS_PROXY/HTTP_PROXY |
| Kimi | 复用 ~/.dsh/vision.env(VISION_API_KEY/BASE_URL/MODEL) |
ORCHESTRATE_KIMI_* 可覆盖 |
| 状态目录 | <工作区>/.orchestrate |
ORCHESTRATE_STATE_DIR 可覆盖 |
安装
dsh plugin --profile web add link:/绝对路径/dsh-longtask-orchestrator
重启 dsh web 生效。
使用
- 新会话,切到「DeepSeek + 长任务编排」模型组(或直接提出长任务,skill 自动触发)
longtask_begin(goal)初始化 → 按计划的子任务逐个执行 →codex_score打分 → 迭代- 全部通过 →
codex_review终审 → 报告
注意事项
- Codex 走 ChatGPT 订阅额度,与 Codex++ 共用登录态 → codex 调用已串行化,长任务期间尽量少用 Codex++
- Codex 不可用时任务会暂停并提示,不会用 Kimi 顶替规划/评审
Links
More in this category
NanmiCoder/dsh-agent-teams★ 327
AgentTeams multi-agent teams.
icetomoyo/dsh_workflow★ 59
UltraCode-style multi-agent orchestration: a generatable, savable, governable, observable, resumable workflow layer.
btspoony/mstar-harness★ 46
Skill-driven harness/loop engineering workflow agent plugin.
titanwings/dsh-automation★ 41
Scheduled coding runs in fresh agent sessions with auditable history.
whyihaveyou/dsh-suite#plugin-team-board★ 27
Shared multi-agent task board (create/claim/transition/query) over a Cordis service key.
omdsh-dev/dsh-deep-research★ 12
Adaptive deep-research orchestrator built on the official workflow engine.