Plugins

Live usage gauge injected into the system prompt every turn: session tokens and estimated spend, a next-turn estimate, and two predictions the model can act on — which step fills the context window and which step burns the budget. /qm panels, zero-config by default, optional price table, and it publishes a summary.json budget contract sibling plugins read.

Turns file and directory paths in DSH chat into clickable buttons: click one to preview the file in the right sidebar, or open it with the system default application.

Mobile push when a DSH task goes idle, over 10 channels: ntfy, Bark, DingTalk, WeCom, Feishu, ServerChan, PushPlus, Telegram, Qmsg and generic webhooks. The message carries the session, workspace, elapsed time, turn number and a reply excerpt, and it runs host-side rather than in the browser page.

Shows what each assistant turn cost under every reply, priced from the token usage of that turn at the official peak and off-peak CNY rates, together with the account and bonus balances; when a turn cannot be priced it states the reason instead of guessing.

Estimate session and turn costs with model prices in USD or CNY and price sync from models.dev, OpenRouter, or DeepInfra.

Conversation management for DSH: bulk-archive idle conversations (archiving only marks them; by default it also sends their snapshot ledgers to the Windows Recycle Bin), permanently delete conversations after confirmation, star the ones worth keeping, undo the last reply with a per-turn snapshot, and clean up snapshots and archived files from one panel. Adapts DSH kernel 0.2.2-rc.1.

Host-layer Windows toast notifications for DeepSeek Harness: agent turn done, error or interruption, subagent done, and background job done, plus alerts when the model asks you a question or a tool approval is pending. The notification logic runs in the DSH host process, so toasts still arrive with the tab or the browser closed; a Win32 foreground probe suppresses them while you are looking at DSH. Windows only.

Replaces the left sidebar session list with a tree of every session and its nested subagent descendants, with click-through to each conversation's multi-turn history and a tree_send tool for messaging any continuable session anywhere in the tree.

Cross-workspace worker fleets: one orchestrating session spawns named worker sessions in other project workspaces, queues or steers tasks into them, watches them in the background via a real host job, and collects their reports. Worker completions deliver themselves to the orchestrator's session rather than needing to be polled, so an idle orchestrator still reacts. Escalations and failed workers deliver by steer when the orchestrator is mid-turn and by queue when it is idle; a turn that ends without a report counts as a failure and the worker is replaced after a configurable limit. The roster persists to disk and each worker session carries a durable title, so a restart neither loses the fleet nor spawns duplicate sessions. Ships five agent presets at full plugin parity with the standard preset.

Bridges DSH to a local MemVault store: core memory blocks injected into the system prompt, finished turns extracted through MemVault's own pipeline, and a panel to browse, trace, review and replay what was stored.

Call between DSH sessions in different working directories or projects: message any session (next-step delivery or a new turn), end a blocking tool call on request, and read transcripts and usage without waking the target.

Select text in a reply and quote it into the composer as an atomic reference chip: delete the whole chip in one keystroke, click it to scroll back and highlight the quoted turn, and expand it into a bounded reference block at send time so the model can tell the quote apart from what the user typed. Also opens the snippet in a side chat, or copies it to the clipboard.

Per-turn and per-session estimated cost in the DSH Web UI, computed from provider-reported token usage in four buckets with the built-in official DeepSeek CNY peak/off-peak card — peak hours are Monday-Friday 9:00-12:00 and 14:00-18:00 Beijing time, weekends and Chinese statutory holidays are off-peak all day. An optional local JSON rate table overlays prices for other or self-hosted models, and models without a price show tokens only.

Shows per-turn changes in cyclomatic complexity, cognitive complexity, and maximum nesting depth for TypeScript, Python, and Go in the Web UI, with expandable file and function summaries for code review.

Per-project MCP servers: a project declares servers in its own documents (`.dsh/mcp.json` by default; the local and global file lists are settings), and they are mounted only for the sessions working in that project — on the first turn of a session, released when it goes idle. A right-sidebar tab and a Settings page list each project with a live session, the status of every server and the session holding each mount, with `Sync` / `Retry` / `Release`, an `enabled` switch and an editor over one existing entry; a per-project tool policy (`disclosure` / `direct` / `off`) with pins and `mcp_search_tools` decides what the model sees; `${VAR}` references resolve through the project `.env` files and the credentials file; per-server call counters outlive the sessions that produced them.

TRAE-style conversation rollback rebuilt for DSH 0.1.7-rc.2: per-turn file checkpoints restore touched files and truncate the model context in place under the same session id. Adds a /rollback doctor framework-contract self-check, an affected-file diff preview computed against the current on-disk state so it stays correct after a restart, a one-click undo-last action with a Ctrl+Shift+Z shortcut, a setting for whether rolled-back messages stay hidden, and English UI text.

Persistent work-progress row in the band below the composer: task completion, a progress bar, and what the agent is doing right now (generating a reply or running a tool), expandable into the full task list with turns, steps, timings and context usage.

Turns large text pastes into pastes/*.txt attachments with a dock above the composer and a minimal, recognisable badge in the draft.

Google-AI-Studio-style turn controls for DeepSeek Harness, in one install: edit a prompt and re-run it, re-run a reply in place, delete a turn from the model context, and render sent prompts as Markdown. Self-contained: the plugin list shows this one row;

Lets the model trigger compaction itself at a safe point via a compact_now tool (works mid-turn), plus a context_status tool reporting real token usage against the session's actual context window.

Readable transcript export for DeepSeek Harness: turn any Session into a Markdown / HTML / ZIP transcript with reasoning blocks, tool calls and results, images and usage — from the Session header or the /export-md command.

Personal dsh preferences: a tunable companion to the official compaction engine (threshold, retention, summarization model/reasoning, turn-end compaction), llama.cpp model import for the Models page, and tab/notification helpers (status-light favicon, bro

Turn a dsh session into a shareable, redacted idea and deliver it to DeepHub friends. Built on DeepSeek Harness.

Cut LLM costs: a Jev (System One) classifier vets each turn against a declarative policy and recommends the subagent model route, so routine work runs at flash rates while the main model keeps the hard parts; explicit /route trigger, runtime delegation-capability gate, credential redaction, and offline policy replay over the verdict log.