Plugins

Shell-style prompt history in the DSH composer: ↑ in an empty composer recalls the previous prompt and keeps walking back, ↓ walks forward to the empty draft; history is kept per workspace, persisted across restarts and records only human input, while typing or editing a draft returns ↑/↓ to normal caret movement. Adds a Settings page to export, import and clear the history.

Five skills for a reviewable engineering incident journal: record an event only when a counterfactual can be written, quiz yourself from the existing entries, audit the journal for decay, ingest outside material together with its provenance, and rename a layout directory while rewriting every reference to it.

Connects the hosted Knowra MCP server: search arXiv papers by topic, author or exact UTC dates without an account, and sign in with OAuth from the plugin page to read Scout reports on methods, evidence and limitations.

Layered long-term memory for DeepSeek Harness: a ~600-character hot layer that evicts its own overflow, month-archived cold entries recalled by keyword and ranked by usage, and extractive day/week/month summaries.

Registers the models bundled with the Xunfei Loomy desktop app as a `loomy` provider in DSH, reading the app's local sign-in session instead of an API key. Fork of gdrpzym/dsh-loomy-connect adapted to DSH 0.2.1, adding a per-model enable/disable switch. Requires the Loomy desktop app installed and signed in; it cannot be installed alongside gdrpzym/dsh-loomy-connect because both register the same `loomy` provider.

The durable-agent engine for DeepSeek Harness: a host-plane cordis service mounting @earendil-works/pi-durable (conversations, exactly-once submissions, fork-at-entry, tasks) over a SQLite storage backend with an OpenAI-compatible relay provider.

Brings the models available in the logged-in WorkBuddy desktop app into the model picker, reusing the app login and credits; the domestic and international builds appear as two separate provider groups. Continuation of the now-deleted corrinehu/dsh-workbuddy-connect; it registers the same workbuddy / workbuddy-ai provider ids, so it cannot be installed alongside other WorkBuddy bridges.

Native workbench to select project sources, distill and test capability candidates, configure scoped Slack access, and review approvals and persistent tasks.

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.

Connect a DSH Agent to Minecraft Java servers with Mineflayer, a live game view alongside native reasoning and tools, configurable personas, server-scoped notebooks, and optional local survival knowledge retrieval. Reuses the host model; installation does not connect to a game or start inference.

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.

Samples a video the way a person does instead of downloading it: metadata and chapters first, then timestamped frames as images, subtitle-first transcripts (local ASR only when the platform carries no subtitles), AudioSet 527-class sound tags and top comments — 21 tools sharing one on-disk cache behind a cross-process lock. Needs Python 3.10+, ffmpeg and the vidlens package (pip install vidlens-mcp); a missing install comes back with the two ways to fix it instead of a bare ImportError.

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.

Connect several OpenAI-compatible gateways at once: each one is its own group in the model picker, can be hidden without losing its settings, and can fetch its own public info from its address, alongside per-gateway model management, model tests and optional quota reporting.

Windows-only model provider for Google Antigravity CLI, continuing Darkings/dsh-agy-provider (install as dsh-agy-cli; do not install alongside the original). It reads the Antigravity token from the Windows Credential Manager and sends it only to the Google Cloud Code endpoints, lets DSH own the harness tool policy, streams the tail without rollback, and tracks the real quota windows.

Removes the inherited ELECTRON_RUN_AS_NODE variable from the environment the open-in-app package hands to launched editors, so the desktop host's "Open in ..." launches stop failing with HTTP 502 launch-failed; app.asar is untouched.

Draggable bubble graph of DeepSeek Harness workspaces and sessions in the Web UI: workspaces are large bubbles, sessions are small ones, and lines show real membership. The canvas supports pan, zoom and fit; filters cover workspace, status, type and archive state; search covers workspace names, paths and session titles; native actions open or create sessions, rename workspaces, and archive or restore sessions. Layouts are saved in the browser.

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.

DeepSeek Harness plugin that catches an agent weakening tests to make them pass: added skips, deleted assertions or test cases, trivial asserts, swallowed failures, and deleted test files.

把 Qoder 模型接入 DeepSeek Harness：用 PAT 调用与 Qoder CLI 同源的模型服务，支持国内版 / 国际版双区域、模型开关、上下文窗口与每日签到，并提供只读的额度概览。

Builds presentations by driving the LibreOffice installed on the machine over UNO instead of writing OOXML in JavaScript: `lo_build` opens a real Impress document from structured slides and lets LibreOffice export editable PPTX/ODP plus PDF and per-slide PNG, `lo_render` re-renders an existing PPTX/PPT/ODP, `lo_convert` converts between Office formats, `lo_probe` reports the detected soffice path, version and UNO bridge, and `lo_config` edits the stored settings. Needs a local LibreOffice (verified on 26.8.1.1); it uses the bundled Python, so no system Python is needed, and it keeps one warm soffice process between calls. Fully verified on Windows only; on Linux it falls back to the system python3, which needs python3-uno.

On-demand tool groups for DeepSeek Harness, with optional role-scoped tool surfaces. Role masks are off by default; Settings can enable or disable review/build/research, and add custom roles with a group allow-list. The role key comes from the host's session label, subagent marker or preset, so an orchestrator's child agents each see only their own allow-list. Also auto-groups tool families by name prefix, lets the agent classify ungrouped tools once, restores a hidden tool when it is actually called, and reports per-session visibility health.