51 results
Task Flow / Execution Graph plugin for DeepSeek Harness (DSH): visualize a single task's full execution — turns, LLM steps, tools, skills, subagents, retries, parallel branches — as an interactive DAG with live updates and trajectory linkage.
DSH plugin: safe auto-continue-once recovery for native continuable subagents that end with explicit max-tokens termination. No timers, no polling, no private APIs.
/code-review slash command for DeepSeek Harness — multi-agent review of pull requests and local code, with configurable confidence scoring
DSH web plugin: a ZCode-style agent activity pill (top-right status capsule) plus a popover summary panel (goal / subagents / agent status / workflow runs / background jobs) with full control verbs, toggled by Ctrl+Alt+P.
Custom reusable Subagent Definitions with a Settings page and one delegate_agent tool for DeepSeek Harness
DeepSeek Harness plugin: ownership-checked delete_subagent / release_subagent / list_subagents tools and host routes that permanently remove subagent sessions from the web UI list.
DSH plugin: Codex-style side conversations (/side, /btw) in an ephemeral right-workspace panel with Side/Subagents/Goal sections and a ChatGPT-style pinned-notes board (置顶摘要小黑板), plus a best-effort sidebar collapse hotzone.
DeepSeek Harness plugin: run subagents on a local llama.cpp model via the OpenAI Responses (/v1/responses) protocol, with a subagent delegation skill
Drop-in replacement for the Codex subagent provider that projects the app-server stream into a harness child session, so Codex runs render as ordinary subagents in the Web UI
Say the secret handshake: DSH subagents start on the Minimal two-tool condition to unlock DeepSeek's full RL-trained strength, then get the whole toolbox.
Live Mission Control for DeepSeek Harness agents, tools, subagents, and token usage
Configure the default provider, model and reasoning effort for new subagents from the Web settings page; optionally apply changes to existing idle subagents. · DSH 插件：在设置页可视化配置 subagent 默认的提供商、模型与思考等级，新创建的 subagent 立即生效，可选的让空闲 subagent 也跟随新设置。
Stavros RedTeam for DeepSeek Harness (DSH) — authorized red-team persona + scope-guarded pentest tooling (persona, 24 subagents, methodology and 78 zero-dependency guard tools).
Packaged multi-agent adversarial code review for DeepSeek Harness — one finder per lens in parallel, then a verifier per finding whose task is to refute it, so only confirmed defects are reported.
Map-reduce council of subagents for the DeepSeek Harness: one task fans out to independent members, their findings are deduplicated, verified by a separate panel, and reduced to a quorum report
Starship-bridge orchestration for DeepSeek Harness: the captain issues plain-language orders from the bridge; the XO drafts verifiable missions; away-team subagents (recon/engineer/medic/scribe) execute in isolated workspaces with evidence-based acceptance and an append-only campaign ledger.
Read-only live subagent viewer for dsh-TUI: /subagents lists a session's subagents and opens a full-screen, real-time trajectory view.
DSH plugin that injects a solo orchestrator preset with explore/editor/verify/general subagents and subagent-only minimal anchoring.
Two-way Codex↔DSH bridge: skills from ~/.codex/skills, session import with workspace attach, live MCP mirroring of mcp_servers, and a Codex-side reverse MCP installer.
DSH client plugin — flip to the back of the page for a floating glass task console: live background jobs, subagents, session overview and workspace of the current session, with mouse-draggable cards.
Per-stage model routing for dsh-TUI: let subagents run on a different provider/model/reasoning-effort, configured in /settings (model-switch namespace), status via /model-switch.
Focused child-agent delegation (scout, researcher, worker, reviewer, oracle, delegate) and multi-agent workflows (council, parallel review, review loop) for DeepSeek Harness.
ResearchCraft as a DeepSeek Harness profile: DSH web UI and agent, scientific skills, lab notebook, specialist subagents.
Terminals view tab for the DSH web UI: live count of background shells/subagents per session, Chinese purpose titles, collapsible command bodies with streaming output, and one-click kill