Plugins

Adds a squeeze tool: the agent hands a long web page, a batch of pages, a text file or a text PDF (via pdftotext) plus one question to a helper model and gets back only the answer, so the material never enters the chat. A settings page picks up to three helper models from the DSH model list, each with a nickname, a fixed thinking level and a "when to use" note, with optional fallback and size limits taken from each model's context window.

Event-based memory for long-lived chat bots: emotion-weighted decay, three confidence levels on recall, superseding outdated facts, per-subject isolation, plus relationship, fact, chapter, skill and gap tables. Ships a CLI, an HTTP endpoint and a DSH plugin bundle.

A bilingual overlay layer for DSH: it overlays Chinese names and functional descriptions for plugins, commands and skills, supports three display modes and manually-triggered AI translation, and does not modify a single line of DSH source code.

DeepSeek Harness (DSH) plugin — connects DSH to JLCEDA Pro (EasyEDA Pro) via a local MCP bridge and draws schematics through the JLCEDA extension API.

Keep a multi-PR effort on one board you can trust at a glance: the hub agent keeps a tree of steps, each linked to its issue, PR, branch and worktree, through four board tools, and you see what is done, what is blocked and what needs you in a right-sidebar Board tab and a progress strip above the composer. Each board is one plain JSON file your scripts can read, and an optional drift command you configure flags steps whose status no longer matches their work.

E-commerce customer-service desk that answers buyers only from the fields the shop itself wrote down (price, SKU table, shipping, after-sales), has the DSH model rephrase those facts under a check that rejects invented numbers and platform red lines, and moves the conversation to a human queue when a field is missing. Ships Taobao TOP and JD JOS gateway adapters, a local bridge and webhook channel, and a standalone 24/7 daemon.

Monitors IEEE Xplore journal Early Access through Crossref, has an LLM screen every new paper against your keywords, and emails a Markdown weekly digest.

Memory for long-form RP and companion chats: three fading layers, per-turn recall, source labels, character and world boundaries, a relationship graph, image attachments and a WebUI.

Creates a throwaway workspace with its own folder and session, manages running ones from a sidebar panel, and moves finished folders to the system Trash.

Ask about one sentence without derailing the chat: select a passage in a Web conversation, comment, and the session's own model answers in a small thread beside it while the main chat stays untouched. The replier can read the session, the working directory and, if you turn it on, the web, but changes nothing. Commented passages stay highlighted with a badge that shows unread replies, and Send to chat hands a thread to the agent when you want it acted on.

Fetches Tsinghua MadModel API tokens and renews them from the saved SSO session on a 20-minute timer in a windowless browser, writes the token into the DSH credential MADMODEL_API_KEY and creates or reuses the madmodel model provider; one manual Get captures that session through the campus login window.

Lets the model turn an answer into a web page that lives right inside the chat. The show_page tool either fills one of 8 built-in templates (report, compare, checklist, dashboard, timeline, flashcards, quiz, flow), where the model writes only the content and the plugin does layout, interaction and saving, or saves a full page the model wrote itself (calculators, games, custom layouts). Hand-written pages get the same design as base styles inside a CSS @layer, so the page's own CSS still wins. The page appears under the reply at its content height, interactive and following DSH's light/dark theme. The page's localStorage is stored in DSH per page, so what users tick or type survives reopening and new versions, and the same page open in the chat and the right sidebar stays in sync. Each edit is saved as a new version you can flip back to. After saving, the page is checked in a hidden local Chrome or Edge (script errors, horizontal overflow, dark mode not applied) and problems go back to the model. The right sidebar shows the page full-size with versions, a gallery of all pages and export to PNG, PDF or HTML. Pages run in a sandboxed, separate-origin frame with a strict CSP: no access to DSH data and no fetch, XHR or WebSocket. Works on phones with dsh-mobile.

Adds a Restart button to the DeepSeek Harness title bar so newly installed plugins can take effect. The first click arms the button and the second one ends the current desktop instance and relaunches the executable. The restart runs in a PowerShell script created through WMI, outside the application job object and without a console window, and every step is written to $DSH_HOME/logs/dsh-restart-plugin.log. Windows desktop app only.

Reads and edits STEP models through FreeCAD, measures geometry (distance, angle, diameter), and generates first-angle 2D machining drawings with a hole table as SVG, DXF, PDF or PNG.

Folds oversized tool results into on-disk spill files with deterministic head and tail markers, indexes compaction summaries in a searchable ledger, and extracts cross-session memories with per-project scoping. Any folded content is restored byte-for-byte on demand through one tool call.

Sidebar category groups for DSH workspaces: the flat project list becomes collapsible named sections, workspaces re-file by dragging a row onto a group or picking one from a dropdown, one toolbar button collapses every group at once, an appearance panel sets font size, text color and background tint for each of the three levels, and Ctrl+Tab cycles recently opened sessions.

ChatGPT plan connection for DeepSeek Harness through Sign in with ChatGPT 通过官方接口将你的ChatGPT订阅接入dsh使用

Layered long-term memory for DeepSeek Harness: each turn injects a persona frame plus a relevance-ranked memory index while full transcripts stay on disk and are expanded on demand, so the vault never floods the context window. Facts are slot-keyed, so a changed mind retires the old value instead of recalling two contradictory answers. The persona frame is derived from memory by the model itself, behind three anti-pollution gates (rejecting development chatter, blocking echoes of its own injection, and merging restatements by shared content words). Periodic consolidation merges near-duplicates, rolls long topics into digests, and archives low-value old entries by tagging only — raw text is never deleted. The append-only store is compacted in place (measured 4.7 MB to 355 KB). Zero third-party dependencies, no build step. Note: per-turn injection inevitably lowers prompt-cache hit rates, so this plugin is not recommended for work scenarios.

Remote-control DeepSeek Harness from a HarmonyOS phone: list, switch and create sessions; send prompts (the phone follows the host's busy-enter behaviour, queue or steer); stream assistant text, reasoning and tool steps; answer approval requests and questions; view session images as inline thumbnails with on-demand full-size fetch; switch model and reasoning effort; cancel running tasks; receive push notifications. Traffic is end-to-end encrypted (AES-256-GCM with HKDF-SHA256 key derivation) and travels through a dumb-pipe relay that only sees ciphertext; v1.1.3 adds a session-epoch anti-replay handshake and optional native TLS for the relay. The relay can be hosted on the local machine (managed by the plugin) or on a VPS; the phone app and the plugin ship in one repository. 5 Remote methods.

Runtime plugin firewall for sessions started through its launcher (the DSH Desktop app cannot be injected and is not covered): filesystem, network and subprocess calls plugins make are attributed to the plugin that made them and judged against what that plugin declares, so a plugin doing its declared job stays silent and leaving it is recorded. Attribution is best-effort, not a guarantee - uncovered calls fall back to host, never to another plugin. Also adds a pre-install health card (capability surface, red-line combinations, PASS/WARN/BLOCK), boundary judging, opt-in pre-execution blocking with a credential-exfil rule, update diff with a trial install in an isolated child process, SARIF/CSV audit export, and multi-source aggregation. Local-only storage, no telemetry; the optional webhook is off by default.

Progressive tool discovery through tool_list, tool_search and tool_load, exposing tool schemas on demand while preserving host execution permissions.

Browses Bilibili on your behalf and actually takes part: search videos, like, coin, send danmaku, post comments, reply to other people, and keep replying when someone answers back. Reads the video's Bilibili AI subtitle (or transcribes the audio locally when there is none) so its comments talk about what the video really says, and it reads that same content before choosing whom to reply to. Instead of copying other people's sentences, it distills rules about how to sound like a person and gets less AI-ish the more it runs. Skips videos it already browsed, de-duplicates replies per thread, and after too many rounds with the same person in one comment section it reviews whether the exchange has any substance -- if it looks like two bots complimenting each other, it says one last line and stops replying to that person there. Checks whether each comment is genuinely public or only visible to your own account, can scan any time window (last hour / day / 3 days / all) and lists the ones others cannot see, warning you on the overview when replies got folded. Six-tab settings panel where every change takes effect immediately with no restart, a manual run that queues behind the background listener instead of being refused, and an environment self-check that tells you exactly what to install. Requires Python 3 for the Bilibili actions; the built-in check lists any missing packages.

Control plane for the harness's own Agent Teams: members are ordinary independent sessions created through the same seam the GUI uses, each with its own model, so they open and continue like any other conversation while a sidecar roster and task board coordinate them. Task entries carry a definition of done, a member's completion is submitted and waits for the Lead's review, and availability tells idle apart from awaiting-review or a failed last turn. With delegationEngine=auto it uses independent sessions, continuable subagents, or the kernel roster depending on what the composition provides.

Windows native toast notifications for DSH desktop sessions: turn ends, approvals, questions and a reminder for an unanswered wait — each with its own sound and popup text (up to three named templates per situation), three delivery modes, previews, and imported custom sounds. Clicking a toast raises the DSH window.