Plugins

Registers a `dispatch_task` tool that hands scoped or routine work to an isolated subagent, waits for it to finish, then checks the expected files and runs an optional verification command before returning a short report to the main conversation.

Trim tools for long chats: trim_context / estimate_context_tokens keep the system persona and the last message, drop the oldest user/assistant pairs to fit a turn or token budget, and report before/after estimates; the conversation is not trimmed unless something calls the tools.

Six-tier memory plugin that captures each conversation turn, injects a stable memory block as a user snapshot, and compacts the host's own history into a single placeholder without calling a model.

Timed send for the chat composer: pick a moment and the host delivers the message then. Inside an existing conversation tasks join that conversation; from the new-session screen each task gets its own pre-created session.

Opens a native side conversation forked from the active conversation, with live parent context, Inline & Spill chain recall, relay to the main conversation, and usage stats.

Shows a six-character session id badge next to the conversation title in the DSH web UI; clicking it copies the full session id and shows a short confirmation.

Marks a Session as focus or parked in one click from its sidebar row, its hover card, or the conversation header, and keeps a count visible at the foot of the sidebar and next to workspace folder names when those groups are collapsed. A panel lists every marked Session alongside the states the sidebar already tracks (waiting for a reply, running, finished-unread), and the sidebar foot opens whichever one needs a reply first.

Peak/off-peak and balance pill for the DSH composer, forked from xiangrikuibaize/dsh-tide-badge. Unlike the original, the conversation cost is priced from that session's token usage (uncached input, cache-read, cache-write and output tokens) against the official price table, so other conversations and API keys on the same account are not charged to it. It keeps the upstream package name, so it replaces the npm version — install one or the other, not both.

A tiny always-on floating tree of the DSH workspaces, conversations and subagents that are running, waiting on you or on a schedule — live running state, who is waiting for your call, per-row model, scheduled-run countdowns, other local dsh instances with their ports, and local claude/codex CLI processes with their codex subagent threads.

Zero-friction quick ask for DSH: select text in chat, Markdown/code, rendered HTML reports, or the better-sidebar editor. The default answer starts automatically (English prose is translated, a term is explained, a question is answered); typing cancels it. Answers stream from a one-shot completion on the main window's model, inherit a read-only conversation snapshot, read the selected file as context (up to 20,000 characters by default), and never write to the main session. One-line install; host routes, client slots, document renderers and the iframe selection bridge are separable extension points.

Adds an independently toggled native file explorer beside the conversation, with local and SSH file operations, fast remote @ completion, and native previews in the right sidebar.

Plain click on an Obsidian vault file in the DSH conversation opens it in the right app: notes in the Obsidian app, configured types (for example .tex) in VS Code with their project folder as the workspace; Cmd/Ctrl-click keeps the in-app preview. The open_vault_file tool follows the same routing, and every open is confined to the configured vaultRoot.

Opens a dedicated question chat in the right sidebar for text selected in a DSH conversation, so follow-up questions do not push the main conversation away and never appear in the session list.

Adds a sparkle button left of the model selector in the composer toolbar: one click rewrites the draft in place through the host and briefly offers an undo that restores the original text. A Prompt Enhancement settings section picks the lane — the conversation model (the provider/model the next message would use, falling back to the configured default) or a keyless Pollinations channel that needs no login and no token budget but allows one reply per 30 seconds. During that cooldown a click completes through the conversation model instead of being refused, and the first click after the window reopens returns to the keyless channel on its own. The rewrite keeps the draft's language, and a result in a different language is rejected rather than pasted over the draft.

Rewrites the composer draft, or only the selected text, with one model call that uses the recent conversation as context, with cancel, revert, fidelity and length checks, and an optional preview.

Pins the conversation column of the dsh UI to a fixed width — a pixel value or a percentage of the column — from a row in General settings, and hides the built-in drag handles so the width stays put.

Temporary side conversations seeded from the main context, with quoted questions, main-task status updates, and replies returned to the main draft.

Find text inside the open conversation with Ctrl+F: matches are highlighted in the message text, previous/next step through them, clicking the count lists the matches and jumps to any of them, and the count grows while the scan runs. No collapsed block is opened and the reading position does not move.

Comment on any passage of a DSH Web conversation and get a brief reply from the session's own model in a small thread next to it, without touching the main chat.

Message box for DeepSeek Harness: finished-conversation and pending-approval notifications with jump-to-conversation and inline approval.

Sends a VS Code selection or file path into the open DSH conversation as an @path reference with its line range, inserted at the composer without sending it. Requires the companion VS Code extension shipped as a .vsix inside the bundle (one-click install from the composer, or install it by hand).

When a live session's context passes a threshold, append older messages to a per-conversation folder on disk, then release the oldest finished turns from the model-visible context; the chat transcript and the session log stay untouched.

Right-click a sent message to edit or withdraw it. The running answer is stopped first, then that message and everything after it are replaced in the conversation: withdrawing leaves a short withdrawn marker and stops there, while editing asks the model again with the new text.

Shows per-answer and conversation cost estimates from recorded token usage, with automatic model pricing updates and detailed price-source breakdowns.