Plugins

Derived from joeseesun/qiaomu-reader-dsh (not an official successor; do not install both - both use the qiaomu-reader plugin id): read documents beside native DSH chats, explain or translate selected passages, and return through document history. Development preview verified only on Windows with DSH 0.2.1-rc.5.

Exa search provider for the dsh-web seam: the web_search tool sends queries to Exa's /search API and returns the results as sources, in dsh web, dsh-TUI and headless runs. Needs an Exa API key (EXA_API_KEY, the credential store or a key file read on every search). web_fetch is unchanged and there is no UI.

Rolling-window batch scheduler for DeepSeek Harness subagents: one subagent_batch call carries a queue of independent subtasks plus a user-owned concurrency window, a settled child's slot is refilled immediately, and the call returns every child's final answer, stop reason and child id as one acceptance report. async mode keeps the pool running in the background for subagent_batch_status, and the window comes from config, DSH_SUBAGENT_BATCH_CONCURRENCY or a hardware recommendation.

Utilities for DSH sessions: ask another session a question with a context guard, pause the running turn from the UI, restart DSH on Windows and resume automatically (via the scheduled task that install-restart.ps1 creates), enforce peak-hour discipline and per-feature allowed time windows, and periodically scan session logs for interrupted turns.

Local-first, file-native long-term memory for DSH with per-turn preflight, compact context injection, citations, human-approved writes, manual consolidation, nightly report-only maintenance, and a Web panel that is read-only for knowledge while allowing workspace-config edits.

Three ledgers for a model that loses context between restarts. Self-note: what I have become — capped at 40 entries, and every eviction first leaves a one-line crease recording which entry was dropped and why. Judgment ledger: record a claim together with how to verify it, come back when it is due, and mark it right or wrong; wrong ones stay in a mistakes book so you stop assuming you were always correct. Handoff: where this run stopped and what the next one should read first — a baton, not a memory. Three tools each taking an action parameter instead of a dozen separate ones (the prompt is paid every turn). Data lives in ~/.dsh/*.jsonl and is shared with the same-named CLI scripts. Zero dependencies.

Delivers a queued chat message at the next step boundary instead of waiting for the whole turn to end, without aborting the model call already in flight; aborting is an opt-in mode rather than the default.

Replaces the built-in compaction provider: at a configurable fraction of the context threshold (85% by default) a detached task summarizes everything up to the previous turn, and the next step boundary commits that held summary as a checkpoint with zero model calls, so the swap itself takes milliseconds. /bcompact \[message] starts the same generation on demand and then sends the message. A settings page sets the trigger ratio, the summarization model, and how many consecutive failures stop background generation until a half-open probe gets through. Subagent sessions, a changed prefix or an expired summary fall back to the built-in synchronous path.

Turns "restarting the host" into one interrupt that many sessions can share. Several sessions queue onto the same restart (8 by default, configurable, joinable at any time including mid-wait); the host is closed once and relaunched once; then each waiting session is woken separately with its own reason and starts running its own work without waiting for the others. Each session decides independently whether to resume, one failed delivery never affects the rest, and a session can drop only itself without cancelling everyone else's restart. Windows desktop only.

Idle-time context truncation for a single DeepSeek Harness session. After a configurable number of idle hours the older conversation is dropped without a summary, so one long-lived session cannot leak one task into the next; it ships a per-session toggle, a tab next to the chat, and a /truncate command that IM bridges can drive.

Cross-session messaging: deliver a user message to another DSH session by session id. Every message carries the sender session id and a reply hint, so windows can authenticate each other and hand work over. One tool, no extra DSH dependencies; mode "steer" injects into a running turn instead of queuing a new one.

Turn on the built-in session full-text search backend (session-query-sqlite, SQLite FTS5) that dsh ships disabled by default, so the sidebar magnifier searches message bodies with snippets instead of titles only.

Local Ollama worker tools for DeepSeek Harness: model inventory, a single unverified ask, and a batch runner that chunks long text, checks every item deterministically, returns a small verbatim sample for review and can optionally write the labelled result inside the session workspace.

Turn a logged-in DeepSeek web account into an OpenAI and Anthropic compatible endpoint, with tool calling, image input, an account pool and a local admin console. First use needs a one-time `node scripts/fetch-assets.mjs` in the installed plugin directory to download DeepSeek's PoW runtime from the vendor CDN; without it the proxy starts but every upstream request fails.

Turns the DSH web UI into the H.D.D Hollow Deep Dive terminal from Zenless Zone Zero: the sidebar and composer are reskinned. Ships a small read-only host half plus the web skin; switch it off and DSH returns to its native light UI.

DeepSeek balance, today's spend, peak/off-peak countdown and per-turn cost rendered as one text line embedded in the DSH sidebar footer, plus a low-balance alert. A text-only derivative of dsh-whale-widget (MeteorNOX/DeepSeek-Balance-Whale-Widget); do not install both - they register the same /dsh-whale/* routes and share the same ledger files.

Appends the current turn's estimated token cost in CNY to the assistant action row, right after the usage/time indicator. Prices come from a built-in DeepSeek peak/off-peak CNY table (Beijing time, Monday-Friday 9:00-12:00 and 14:00-18:00) and can be overridden from the profile's cordis.patch.yml; a model without a configured price shows a dash instead of a made-up amount. Follows the shipped Performance & usage - Compact setting and hides together with the usage pill. Token cost only, per turn only.

Adds a space-key Quick Look preview to DSH deliverable cards. Hovering a card and pressing Space opens the native macOS QLPreviewPanel for the file, which covers docx, xlsx, pptx, pdf, images and media that the sidebar preview cannot render. The panel zooms out from the card's position, returns focus to the composer when closed, and exposes hover delay, focus-return and double-click behaviour in Settings > General.

Turns the DSH sidebar into a message view, where a bell button groups sessions by priority and date and each row carries its preview and workspace name.

Live step pill in the DSH session header: folds the durable session event stream into the agent's current action (tool name plus its argument summary), the step index inside the running turn, the elapsed turn time and the todo progress, polls it every 1.2 seconds, and renders blue pulse while working, green for a finished turn and red for a failed tool call; hides itself 9 seconds after a turn ends. On Windows it also opens an always-on-top desktop HUD (set DSH_AGENT_STATUS_HUD=0 to disable).

Replaces the DSH sidebar list with a workspace rail: pinned chats and folders, projects that are folders with their own AGENTS.md and files, a virtualized Recents list ordered by the last finished turn, a project_search tool, unread markers, a collapsed icon column with an unread count and a live browser tab title.

Select any passage in a DSH conversation to annotate it in place; the quoted text, the turn it came from and your comment are folded into the message on send, so the model can tell exactly what each remark refers to.

Keeps a DSH agent turn open when the model ends it by narrating work it has not done: on agent/turn-stopping the guard replays the turn log and classifies the trailing message with regexes — in the default mode wait / ask / done / gray end the turn with no model call, and only a promise of pending work reaches the judge — then has a judge chain of four dialect kinds (System One three-question noul, OpenAI-compatible, OpenAI Decisions, or the session LLM) rule on whether the turn is really over, and steers the same turn with agent.steer when it is not.

Plugin do DeepSeek Harness (dsh): diga “clear everything above” e os turnos anteriores deixam de ser enviados ao modelo, economizando tokens. Também funciona no Cherry Studio.