Workflow & Automation

Workflow One - Visual AI workflow orchestrator for DeepSeek Harness (dsh), with multi-agent DAGs, live execution, recovery, and Feishu integration

Automatically continues a native continuable DSH subagent once when it ends with explicit max-tokens termination, then stops.

The task-center plugin set for DeepSeek Harness in one package: task ledger, model tools, human commands, wake patrol, quota-resume guard, idle-session mining, the reaper, scheduled sends, and the web kanban.

DeepSeek-Harness (dsh) plugin that streams sessions, turns, and tool activity to a JARVIS Mission Control board

Appends ambiguity-handling rules to the dsh system prompt so the agent asks clarifying options before guessing.

Falsification-driven correction loop for agent sessions: risky work commits an evidence-checkable claim first, deterministic gates verify it, falsified claims force mutually exclusive replacement hypotheses with discriminating experiments, and every event lands in an append-only evidence ledger.

DeepSeek Harness 的 APEX 实验插件：Minimal 锚定启动、按需 Standard 工具、持久任务状态与 V4 Flash 定向研究。

DeepSeek Harness 的实验性 agent preset：锚定轮路由、按 epoch 晋升、渐进式工具解锁、Windows Git Bash 执行器与可选预热回放。

DeepSeek Harness Workspace Plugin

DeepSeek Harness plugin and bundled Skill for safely evolving Cordis Candidates with Harbor.

Composable working, reasoning, quality, and human-reviewed self-evolution controls for DeepSeek Harness Web.

Composable working, reasoning, and quality controls for DeepSeek Harness Web.

Self-learning habit engine for the DeepSeek Harness — detects user-correction signals, judges habits with a low-cost model on threshold, settles candidates behind a two-level human gate

Machine-level cron jobs for DeepSeek Harness: configure scheduled tasks in the Web settings page; the host fires internally-driven agent requests into a dedicated session, hands-off.

A local-first, human-gated authorial film workflow for DeepSeek Harness

Cron/one-shot scheduled tasks: run shell commands or fire webhooks on a schedule, with optional ServerChan/DingTalk/Feishu/webhook delivery of results.

Provider-neutral CI/CD capability for DeepSeek Harness with GitHub Actions support, bounded failure evidence, source-aware diagnostics, and approval-gated rerun/cancel controls.

Installs two selectable Agent Presets: a shell-restricted general-purpose agent and a repository-focused coding agent.

A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→commit→push→review→close sequence. One skill instead of the same rules copy-pasted into every agent's instructions.

Clusters arXiv, first-party lab, official artifact, hardware-vendor, and opt-in X signals into versioned release evidence bundles, then gates claim-level reproduction on commands, artifacts, metrics, and verifiers.

Cordis-native, evidence-driven full-stack engineering workflow: inspect-first planning, explicit verification evidence, and approval-aware gating for sensitive operations.

Recurring/scheduled tasks (轮询任务/定时任务) plugin for DeepSeek Harness: cron-driven polling jobs as real sessions, natural-language creation, model tools (polling_create/list/edit/delete/trigger) and a web UI. Install-and-go via `dsh plugin add`.

Same-runtime cross-Session discovery and communication for DeepSeek Harness

Independent read-only acceptance layer: spawns a read-only verifier before each top-level turn closes and steers non-pass gaps back into the agent.