Plugins

Session-header button that previews and downloads the exact request frame DeepSeek Harness sends to the model: the full system prompt, the declared tools array, and the wire message array (system/user/assistant/tool-result) rebuilt from the session log via the same folds the agent loop reads.

Self-built DSH memory plugin: SQLite persistent storage + database-level audit guard (enforceAudit) + audit log. Auto-captures knowledge after conversations, agents recall via memory_recall, supports Claude Code/Codex/Cursor multi-agent sharing. Zero external dependencies.

Approval-gated workspace instructions and memory for DeepSeek Harness

Two-way agent bridge for Feishu (Lark) and DingTalk groups: chat with a DeepSeek Harness agent from IM groups via long-connection / Stream Mode — no public port needed. Workspace selection/creation, session switching, archiving (synced with DSH GUI), configurable from the DSH settings page. Feishu uses interactive cards, DingTalk uses text commands.

Decides whether Python code is original or a derivative work: reports the longest identical expression span against an upstream tree, an exemption rationale per finding, and a risk list. Pure stdlib `ast` analysis — offline, no model calls.

Browser automation for DeepSeek Harness: agent-driven real-browser control (managed Chrome with an isolated persistent profile, or attach to your daily Chrome over CDP) with snapshot, click, fill and page-reading tools; records manual operation flows and replays them with variable slots to create test data on demand; ships 27 browser_* tools plus a Settings panel.

Injects one system-prompt section so the agent's chain-of-thought, planning and tool-invocation reasoning stay in Simplified Chinese. Zero external dependencies - clone and link-install from any local directory, no npm build or publish required.

Model switching, model capability configuration, fixed compaction models, subagent routing, and input history enhancement.

Token-cost pipeline for DeepSeek Harness: pressure-aware layered compaction (lossless projection below 40% context pressure, LLM summarization above), per-agent tool allowlisting, long-text-to-image with vision summarization, and a /token-status command tracking pressure, tiers, and saved tokens.

Multi-agent frugality defense plugin: read-ledger dedup metrics, compaction-immune rules, completion gate, cheap-model review lane.

NPM-installable DSH Web plugin for safely loading and managing skills across DSH and common local Agents.

Primary-controlled deliberation and opt-in masked review for DeepSeek Harness

Visual Kanban board for DeepSeek Harness with Gitea-backed tasks, workflow columns and a dedicated agent session per task.

WhaleHarbor desktop pet for DeepSeek Harness: an always-on-top transparent float window hosts a chibi whale-maid built from 13 AI-generated parts and animated as a CSS paper-doll (breathing, blinking, ahoge sway, sweat, hops, tremors), mirroring work state in eight moods — idle, busy, approval, question, error, celebration, nap, and subagent clones — with poke, drag, three sizes, tray toggle, and live stats in the speech bubble. Requires the WhaleHarbor desktop shell (Windows build).

XiaoShuang desktop pet for DSH: six-layer memory, persona injection, mood-driven video avatar, manual emotion menu, and TTS replies.

Whole-book translation production line for DeepSeek Harness: deterministic chapter detection and segmentation, per-chapter subagent translation, glossary control, full-book review, targeted revision, and auditable meta.json evidence.

Multi-role parallel argumentation for DeepSeek Harness: runs the real Codex and Claude CLIs in parallel, has the DSH model (Judge) write a third-party verdict back into the conversation, plus Obsidian-style single-agent direct chat and per-role model config.

OMC-style multi-agent orchestration for DeepSeek Harness: 29 omd-* skills and 12 /omd-* slash commands over the plan-execute-review-verify pipeline and team/autopilot/ralph modes.

DSH knowledge-graph memory with a better-sidebar tab and a standalone /graph-memory/app dashboard: extracts TASK/SKILL/EVENT nodes, recalls across sessions, and ships as the npm package dsh-graphmemory.

Coding retrospect distilled memory for DSH: distills rejected solutions, pitfalls and constraints from each turn via a local LLM, tags them into MemOS (type:rejected_solution), and boosts weighted recall on coding tasks via agent/pre-step.

Audit each finished assistant turn with an independent reviewer model and steer the agent to fix failed output, with at most 2 review rounds per turn and SOP-folder standards injected as an extra review dimension.

Local Obsidian vault as the agent knowledge store, with read-only DSH tools that route status, preference, correction, memory, project, search, and suggest to the matching page.

Multi-bot workbench for DeepSeek Harness: bridges the sdk-bots orchestration gateway (group chats, single bots) into the dsh web shell with official-styled UI.

Workspace-scoped Git graph with history search and diffs, multi-worktree WIP and agent-session views, and guarded Git operations with recovery refs.