Plugins

Select-all cleanup for archived DeepSeek Harness sessions: deletes the session log, projection cache, workspace accounting and archive marker, cascades subagent logs, and can also remove unreferenced attachments, the request-image cache, the workspace files a Session wrote and leftovers of already-deleted Sessions.

QQ (OneBot 11 / NapCat) channel for DeepSeek Harness: bridges QQ private chats and group chats into their own dsh sessions. Ships group guardrails (mention-only, quiet hours, cooldowns, daily quota, peak-hour mute), a tool gate with write-action audit, an outbound filter that stops the model from echoing input tags, voice transcription, media and forwarded-card support, dryRun and usage stats. Forked from dsh-onebot-qq 0.9.4. Cannot be installed alongside the upstream dsh-onebot-qq (two QQ channels on one NapCat crash-loop DSH). Private chats answer admins only (an empty admin list means nobody); group chats default to all groups and answer any @-mention, so set groupPolicy to allowlist to restrict who can drive the agent.

Adds a model picker to teammate (continuable subagent) sessions: switch a quota-exhausted teammate to a model that still has quota and let it continue, without rebuilding it or touching the Lead session.

Customize per-provider User-Agent headers and stream idle timeouts, set retry counts and intervals with visible progress, and optionally send bounded continuation messages after retries run out.

Writes one model and reasoning effort into every session at once from a control beside the composer model picker, since the shipped picker only changes the session you are in. Sessions that already match are skipped, subagent sessions follow their parent instead of being written, and the same selection can be pinned as the default for new sessions.

Estimated CNY API cost for each conversation turn and for the session token total, using DeepSeek peak/off-peak and per-model pricing; subagent costs are listed separately.

Intercepts DSH tool results before the model reads them: dedupe cache for repeated calls, a declarative decision graph that replaces large outputs with structured digests, an injection gate, and an honest token ledger that includes a negative-return account for over-compression. Measured 1400-1600 tokens saved per hit; the cumulative ledger is currently negative and the README says why, including that it cannot skip model turns.

Session Console: a sidebar dashboard over every conversation that shows run state, token spend, cache hit rate, context pressure and a heat score, resolves a plain-language sentence such as "how is the example project going" to the matching session, and dispatches that sentence as a queued task into it. Ships five agent tools (overview, find, tail, dispatch, cancel) over the same data.

Sticky-note wall in the sidebar: six paper colors, pin and search, up to six images per note, local backups, and an agent tool that lets a session or an IM bot add a note without opening the browser.

A conversation view beside Chat and Trajectory that turns a DSH session into a character stage, with Codex Pet sprites, comic bubbles and a completion report listing the files and attachments the turn produced.

General-purpose chat agent on a parent agent + worker sub-agent split, for DSH Desktop only: a sidebar row opens each assistant's long-running conversation, where the parent chats, records schedule, lists, memos, logs, profile, persona and projects as plain files in that assistant's workspace folder, and hands other work to background workers through the bundled complete-subagent, picking each worker's model from the ones you enable and approving their write access. A heartbeat wakes it for reminders, a daily brief and wake-ups it sets itself, and holds back during quiet hours. Through the bundled im-robot it chats over WeChat: the model decides per reply with im_route whether the reply also goes to WeChat, and images and files sent from WeChat appear in the conversation and stay in the workspace's IM/WeChat folder for a set number of days. Its tools never appear in normal sessions.

Fail-closed retry protection and evidence-backed recovery for DeepSeek Harness (DSH) tools.

人格框架插件：62 个模块的通用人格框架，外挂注入，不覆盖人格文件；带出口自检、结构自检、槽位体检、长文预处理、心情状态。

DeepSeek Harness 插件：闲置会话自动归档、回到会话自动取消归档，带设置卡片与归档历史。

Browse GitHub issues, milestones, labels, priority, and linked PR status inside DeepSeek Harness, and hand an issue to the agent by dragging it into the composer.

Hy-Memory 2.0 as a native DeepSeek Harness memory component: three-tier memory (personal / project / session), three scenes (chat / working / coding), automatic recall and capture with tool traces, a Settings > Memory panel, and MemHub interoperability.

鱼塘社区插件 for DeepSeek Harness：右下角 🐟 入口 + fishpond skill，让 agent 用邀请码自己注册、记规则、发帖回帖。

Map a remote server directory over SSH and SFTP into a controlled local cache workspace, so the model, agent, session and memory keep running on the local machine.

Drive locally installed Codex CLI and Claude Code from DeepSeek Harness through a settings page and agent tools, exposing their sessions, configuration and run state.

Records a session as a run, replays it in an isolated workspace copy with another model or prompt, diffs the two trajectories side by side, aggregates runs into a task × variant matrix, and gates regressions with task assertions and a CI exit code.

Streams a running Godot game into a DSH sidebar panel as MJPEG by driving a native Godot process, so Forward+ projects and GDExtensions keep working. The panel can start, stop, capture and fullscreen the view and inject clicks, and the agent gets tools to read status, drive input and take screenshots.

Task list panel docked to the left of the conversation column: five states, parent/child folding, abandoned and completed docks, shared with the agent through task_list / task_write.

File-based task pool and dispatcher for DeepSeek Harness: keeps a P0-P3 backlog as Markdown, hands one task at a time to a background subagent, gates delivery by rerunning the project test command, and accepts the result against a git commit or a file snapshot; git and non-git directories both work.

A five-stage engineering loop for agent-built projects — spec, build, verify, ship, learn — with one artifact and one gate per phase, so an agent always knows the single next action. Role policy, project templates and deployment sit behind explicit ports: swap the implementation without rewriting the loop. Its scaffold generator lays out the internal layers of a project — `init --layout {none,webapp,service,plugin} --stack {python,node,none}` — from nine layers sampled out of three unrelated production projects: entry docs, an OpenSpec plan face, a spec truth layer (INDEX, one file per domain, TESTING, CONSTITUTION), a wiki split into knowledge / progress / runbook, the six `.agents/` slots, server+web, scripts/deploy/config, tests+e2e and a gitignored out/. Non-none layouts also gate the directory contract and compile every source root. Ships a Python CLI (init/next/check/ship/new) plus a local command adapter and an SSH/systemd adapter with release directories, an atomic current/previous switch, a deploy lock, a commit-versioned JSON probe and automatic rollback on a failed probe; bootstrap and teardown provision and remove the unit and the reverse-proxy block idempotently and refuse to delete a root they did not create. Includes a runnable example workspace and a skill that keeps the agent on one phase at a time. Requires Python 3.10+ and PyYAML; remote deploys need SSH access, rsync, systemd and Caddy on the target.