Plugins

Search four free libraries from one window: Project Gutenberg through its OPDS catalog, Shuge through its WordPress search plus the s.shuge.org short links on each book page, and NCPSSD through its Solr-backed endpoint. The Chinese Text Project is deliberately link-only, because its terms forbid automated access. Two tools: readbook_search and readbook_open; the second returns real download URLs for Gutenberg and Shuge, and only a page link for NCPSSD.

Rejects foreground waiting in DSH agents: waiting commands (sleep, wait, tail -f, watch, ping without -c, infinite loops), blocking wait tools (wait_agent, job_output with wait: true), progress polling (the same check command repeated within a window) and commands that need human input/confirmation (sudo without -n, ssh without BatchMode, login flows, interactive editors, docker -it) are refused with an actionable retry to run in the background or end the turn. Configurable budget and polling window, message language follows the system (zh/en), zero runtime dependencies.

Weather care for DeepSeek Harness: turns a forecast into one sentence you can send — clothing and umbrella advice from feels-like temperature, humidity and air quality, adjusted for how cold-sensitive the user is and how they commute. Also a switchable daily care push, extreme-weather alerts and reminders, evaluated when the agent wakes (a host such as qq-bridge can wake it on schedule). Preferences stay on the local machine.

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.

Runs the local nanobot CLI agent as a DSH subagent through a nanobot_run tool: each call carries one self-contained task and returns only the agent's final answer, either as a fresh process or through a persistent OpenAI-compatible server.

Turns archived sessions into durable memory instead of dead disk. Distils each archive into reusable skills, a fact ledger with ADD/UPDATE/NOOP decisions plus validUntil and supersededBy so stale facts retire instead of piling up, and topic clusters by single-linkage similarity. Also digests sessions that are still in progress through a read-only seq watermark, leaving the session log byte-for-byte untouched, and can self-check the growing memory to merge duplicate facts, retire stale ones and consolidate duplicate skills — measuring only unless you opt in, and never hard-deleting, only superseding.

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.

Cross-session long-term memory for DeepSeek Harness: pinned rules injected every turn, the rest recalled by IDF-weighted keyword evidence, fact-key dedup, plain JSON storage, and a settings page to edit or delete entries.

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.

Watches the context budget of a DeepSeek Harness session: a colour dot in every turn footer (green <50%, yellow 50-65%, orange 65-80%, red >=80%) read from the official contextPressure projection, a reminder panel with a one-click new-session handoff at orange/red, the /context-watch and /handoff commands, and a static reasoning-rule prompt section. Budget and handoff read local session files only; the badge and reminder spend no tokens until the button is clicked.

Adds four tools to a Session. create_session opens a new Session in a named workspace or in any existing folder and delivers one prompt into it; session_message adds one more message to a Session that is still running — the host is asked to splice it into that turn at once, instead of queueing it until the turn ends; a Session that has gone idle is refused, pointing back to create_session; read_session_transcript reads back what a Session said and whether its current turn has finished; list_dispatched_sessions lists what this plugin dispatched and each one's state right now. Host-half plugin, no UI — it calls the host's own session primitives rather than reimplementing them. Restart DSH after installing.

Agent-to-agent mail between DSH sessions on the same host. `send_session_message` delivers after the target's turn or injects into the running one, stamps the sender id itself and rejects forged From headers; every message carries an id, so replies quote it with replyTo, a thread stops the same task being queued twice, and supersedes recalls messages that are still pending. `read_session_info` reads a peer read-only: title, last reply, the files of its last present call, and busy/queue state.

Splits a long QQ reply into separate messages sent a second apart, instead of one wall of text. Works only with the QQ channel streaming output turned off (im-qqbot streaming: false); with streaming on, replies bypass this plugin.

Retry failed model requests automatically: intercepts every request error and replays the same step after a 2s / 5s / 10s / 20s backoff ladder, so gateway blips and rate limits no longer end the turn.

Sets a CNY spending cap for each DeepSeek Harness turn (¥5 by default) and stops the run before the next model request once the cap is reached; the switch and amount sit at the right end of the composer dock.

GLM Coding Plan usage quota ring in the composer dock - 5-hour and weekly credit windows with level, auto-refresh and one-click retry. Requires a GLM Coding Plan subscription and key, plus your BigModel organization and project IDs (the team quota API returns empty without them).

Renders a ui-blocks file named by a ::dsh-ui <name> \[res=WxH]:: line in a sandboxed canvas, and turns an element token into a composer chip that serializes back to the token verbatim.

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.

A permanent status card in the top-right corner of the DSH content area: one line for where this turn's time went (model, tools, waiting), plus collapsible to-dos with a progress bar, the session goal (edit/pause/resume/clear), submitted plans that open in the preview pane, the files this session changed, subagents with their token and duration figures, and this session's background jobs: running rows carry a two-step stop button, finished ones fold into a count line that stays collapsed until opened; it yields space to the content as the area narrows and folds into a round button at the limit.

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

Recovers a DeepSeek Harness turn that ended with reasoning only, with no text and no tool call, by steering the same turn one more step. Structure-only detection, so it costs no extra model call.

DSH plugin: detect assistant turns that end with no visible text (zero-width placeholder) and re-prompt the model to write the answer; also injects a visible-closing-answer system prompt rule.

Deterministic auto-dispatch for native DeepSeek Harness Agent Teams: wakes idle members when a task becomes ready, and turns advisory write scopes into an effective soft lock.

Long-term memory backed by a local SQLite store: project-scoped memory auto-injection with junk filtering, rule-based or model-assisted memory extraction from recent turns, write-side dedup and feedback-weighted ranking. The Python bridge runs on $NEXUS_PYTHON or the DSH-bundled interpreter at <DSH home>/dsh-runtimes/dsh-primary-runtime/dependencies/python/ (Python 3.8+).