プラグイン

Realtime token counter beside the deep-thinking indicator in chat, with merged or split input/output display, per-step operation counts, and auto-scaling K/M/G/T units.

Registers an apiCost session projection that estimates DeepSeek spend from reported token usage at published peak / off-peak rates, in CNY and USD, over self, delegation-tree or verified-team scopes: a composer-dock pill and its detail panel, the /cost command, a session_cost tool, and GET routes for the view and the current rate card. A panel switch parks model requests at the llm/stream waterfall while peak rates apply and dispatches them unchanged once the off-peak window opens, so the call is billed at the off-peak rate with no failure reported to the session.

A composer switch between running always and running only in off-peak hours, set per session: a task is judged by the session that owns it, so changing one session no longer changes the others, and a session without its own choice follows a default. In off-peak mode every task, including one already running, is held at its next agent step or tool dispatch when a Beijing peak window starts (Monday to Friday 09:00-12:00 and 14:00-18:00, statutory holidays excluded), and one timer releases it at the boundary; weekends and holidays are idle all day. The holiday calendar lists every statutory day off in 2025 and 2026 from the State Council notices, and a year with no data is reported as unknown rather than assumed to be a workday.

Read-only clinic for DSH session logs: 22 named diagnostics (token waste, retry and failure loops, context bloat, cross-session amnesia, idle MCP servers and skills), each reported with a replayable evidence locator such as session.v4.jsonl.zstd#L101-L110, and each finding turned into an executable prescription — a profile-patch YAML snippet or a command with current to suggested values, risk, verification and source — plus a feedback command that retires a prescription you reject, after which the report states it was removed by your feedback. Zero dependencies, default zero egress, session files are never written.

Adds a configurable bubble behind assistant replies, with an optional liquid-glass material and matching chrome for process, tool-call and reasoning rows.

Replaces the session topbar title with a workspace and session breadcrumb, switching workspaces, sessions and subagents from dropdowns in the topbar.

Select text in any Windows app and read the translation in an always-on-top card next to the cursor: streaming text follows the newest line, up to 15000 characters per request. Windows only.

Hierarchical workspace tree and multi-view manager for DSH: workspace and session naming creates virtual folders (/), multi-view support (workspace tree, flat workspaces, single list, time timeline), session pinning, and independent sections for workspaces and sessions.

Use DeepSeek's web chat inside DSH: real chat history in the leftmost sidebar, a Chat/Work switch beside the agent mode, plus streaming answers, thinking, web search and file uploads.

Replace the model picker with global search, favorites, recent selections, model-family navigation, and reasoning effort selection.

Your real Obsidian vault in the DSH right Sidebar: the vault tree, full-vault search, notes rendered with read-view typography, wikilink navigation, in-place editing, and a clickable outline.

Select text in a DSH conversation, a file preview or the terminal to quote it: the floating bar offers Comment, Add to chat and Side chat, and Alt+Q / Alt+C / Alt+B do the same three things. The quote - and its comment, kept in the same chip - is inserted as a native reference chip, and a sent quote stays one rounded capsule in the message that expands on click and can be copied. A hover card can jump back to the message a quote came from, and the right sidebar carries a quote list page that searches every quote of the session, jumps back to any of them and exports them as Markdown. Side chat writes the quote into the composer of one dsh-better-sidebar side thread per conversation without sending it, and that page can bring the thread conclusion back into the main composer or export it as a file. A sent quote can also be revised: the card puts its old comment back in the comment box, the corrected quote is sent as a new message, and the old capsule is marked as superseded (the transcript itself is append-only).

Peer collaboration between a DeepSeek Harness agent and the local Codex CLI: split a goal into a shared work list, hand tasks over, review what comes back, and keep every prompt, event stream, and answer on disk.

Let Agents directly control independent local DSH instances with zero intrusion—no plugins or components required on the target. Isolated environments enable autonomous configuration and testing, while Agents with different models and personalities can chat, role-play, or form nested control chains. Supports conversational setup, user-like operations, incremental reading, saved references, and remote session/workspace search.

Skill manager for DSH with a pack system. Installs skills as versioned packs and never overwrites files you have edited - upgrades skip your changes and report them. Also ships 6 built-in skills, a problem-grouped settings panel, and tools that let the agent read and write the skill library in conversation.

Binds a Feishu/Lark bot to DeepSeek Harness over a WebSocket long connection: incoming messages run through an agent session and stream back to the chat, chat commands such as /attach manage the live session, and feishu_* tools let the model push messages.

Aborts a DSH reasoning stream that starts repeating itself instead of letting the turn stall: five rules over the streamed reasoning text (periodic unit, repeated block, repeated line above a share floor, 64-gram density, and a long trailing run of punctuation or whitespace), plus a JSONL fire journal, a Web GUI log panel, and opt-in recovery that retries with a corrective message.

Branch and worktree management for DeepSeek Harness: the workspace toolbar shows the current branch with in-place switching, plus an IDEA-style branch selector, remote branch checkout, context menus (create, rename, delete, copy), push and update, and branch isolation into standalone worktrees with managed creation and deletion.

Right-sidebar page for DSH that draws the current session's repository as a VS Code-style commit graph - colored branch/merge lanes, ref chips and per-commit details - with a working-tree Changes area above it (staged/unstaged sections with inline diffs) for every working tree of the repository; read-only, works with or without dsh-better-sidebar, and follows the session's worktree label when dsh-session-worktree is installed.

Self-organizing multi-agent clusters with no orchestrator. Real DSH subagents coordinate through a shared append-only log that each agent reads and writes on its own schedule, with no topology and one dispatch per agent; a snapshot mode is also included where the harness freezes each neighbour view into the prompt and drives a ring/mesh/swarm cluster to convergence.

Let Codex dispatch tasks to DeepSeek Harness workspaces, follow execution, read results, and continue collaboration through a local bridge and companion Codex skill.

Compiles a rough need into a versioned task book (goal / context / constraints / acceptance / decisions / open gaps, all numbered) and hands it to any AI window losslessly: the receiver must pass a read-back handshake — restate, list gaps, declare READY — before work starts; /answer closes gaps with an automatic version bump, /forge-list tracks which window holds which version.

One hub over every coding IDE you run — dsh, Claude Code, Codex, ZCode, Qoder, CatPaw, Trae, OpenCode. Zero-API: it reads each tool's own on-disk state and gives a session inventory, per-IDE usage with cache-hit rates, one-line resume commands, and a single .hub/ rule body wired into all eight via marker-delimited pointer files. The domestic-IDE adapters (Trae/Qoder/CatPaw) were verified against the installed binaries — a gap no overseas tool covers.

Browse, search and install skills from the public SkillHub catalogue, then enable, disable, update or remove them without leaving Harness. Category chips carry the upstream total for each category; the details drawer has tabs for the file tree, version history, permissions, third-party security-scan results and upstream metrics. An installed skill is written into the harness skill root as an ordinary local skill, and disabling one moves its directory out of that root rather than flagging it.