Plugins

Registration agency matching plugin — recommends data exchange/registration agency based on data type.

Zhejiang provincial government data inspection config pack with runtime config loading and validation.

Research data provenance auditor: audits lineage integrity, reproducibility and FAIR principles compliance, outputs provenance audit reports for research integrity and open science.

Geospatial data quality inspector: checks elevation accuracy, topology consistency and coordinate system compliance, outputs weighted quality scoring reports per GB/T 24356-2023.

Registration document generation plugin - generates the three registration materials: data description, source legality statement, and ownership explanation (three-rights separation).

Financial AML compliance checker: detects large/suspicious transaction thresholds, exemptions and timeliness, outputs auditable AML compliance reports across banking, insurance and securities.

Data quality scoring plugin — multi-dimensional scoring (completeness/accuracy/consistency/timeliness).

Data inventory plugin — directory scan + value assessment + classification annotation.

Rewrites the reasoning row: instead of the raw chain of thought it shows first-person working notes, written segment by segment while the reasoning streams in, with a toggle back to the original. Notes are stored per session so history rows keep them after a reload, the note writer runs on a configured provider or a downloadable local llama.cpp model, and the model still reads the full reasoning.

Exposes a running DeepSeek Harness as an MCP server over Streamable HTTP or a bundled stdio bridge, so an external agent can create workspaces and sessions, prompt, fork, rename and switch the model on them, read and write files, run foreground and background shell commands, call the instance's own agent tools by name, and read per-turn and cumulative token usage with a cost receipt when a price plugin is installed.

飞牛文件与目录桥：选目录/选文件进对话、文件树与交付卡片操作、目录权限体检、诊断与中英文界面。fnOS picker, composer/file-tree/deliverable bridge, workspace access checks, diagnostics, and i18n for DeepSeekRuntime.

Telegram sessions, topics, model controls and approvals for DeepSeek Harness.

In the DSH desktop file preview, click an HTML element (with its source line and column) or lasso part of an image for the vision model to identify, then send your change request to the current session; local HTML edits keep a history with before/after previews, line diffs and rollback.

Five tools for reading a video as raw material rather than as something to watch. video_outline maps a whole file as text and draws nothing at all: 4-60 equal windows, each with its cut count, speech share, intensity bar and tags, then the windows worth opening and the exact start/end for the call that follows -- zero image tokens. video_probe returns metadata and a reading plan without decoding frames. video_storyboard turns a window into one contact sheet plus a text index binding every cell to its timecode, cut count and frame time; cells whose text would be illegible at that scale are marked zoom, and dedupe global folds a picture that comes back after a cut. video_zoom re-renders 1-9 cells from a short window at a larger scale. video_read decodes only keyframes, OCRs each screen, and returns an outline plus \[mm:ss] text -- the path for lectures, slide decks and screen recordings, where the words are the content. It also reads a file with sound and no picture as a transcript (subtitle track, then DSH_ASR_CMD, then a transcript file you pass; long audio is cut at 45 s onto silence), composes six changed frames into one sheet when a file has no readable text at all, and can write the result out as SRT, WebVTT or text. Cuts, dissolves and one-frame flashes are found in a single ffmpeg pass; from ten minutes up a file is analysed on its keyframes only, 2.7x faster on a two-hour lecture; and a cell is never shrunk below a fifth of the source, so a 1440p sheet spends the same tokens on fewer, bigger cells. OCR is the engine Windows ships, tesseract with line boxes, or DSH_OCR_CMD. It takes a B station link (bilibili.com/video/BV..., a bare BV id, an av id or a b23.tv short link) wherever it takes a file: up to 300 seconds is read from the CDN in place with nothing written to disk, longer videos are downloaded once and cached within a 4 GB / 24 video budget, play URLs are cached for ten minutes, and a link that is not a single video says what it is. Needs ffmpeg, uses ffprobe when present, and has no other runtime dependencies. It is a wire-compatible reimplementation of SAOS-3624/dsh-video-storyboard: it registers the same video_probe / video_storyboard / video_zoom tool names, so the two cannot be enabled together.

Data packaging plugin for product manual generation and compliance attachments.

Data-circulation assessor: scores how readily a dataset can circulate, covering trusted-data-space access readiness and transaction-compliance pre-checks, with improvement recommendations.

Data asset valuation plugin with cost-based (replacement cost) and income-based valuation.

Data asset registration helper: runs a disallowed-scenario and ownership-dispute pre-check, matches a registration agency by data type and region, and returns a registration checklist with the triple-audit standard and seven-step flow.

Data asset inventory scan plugin — deep metadata scan + triple-condition check, outputs asset catalog.

Data asset compliance check plugin — checks source compliance, processing compliance, usage compliance.

Data asset attestation plugin that generates certification-level data quality reports with evidence chains.

Construction data asset inventory plugin — inventories BIM/IFC classification, asset encoding, outputs asset catalog.

City data AI classification plugin — auto-recommends data classification based on GB/T 47949, supports structured/semi-structured/unstructured data.

Persistent identity layer for DSH: editable kernel, evidence-based traits, on-demand memory, mood, bond, energy pacing, autonomy and empathy — QQ is one optional channel.