Plugins

JSON queries with a JMESPath subset.

Layered context compression for DeepSeek Harness: folds old turns into model-written L1–L3 summary blocks, maps what each layer holds, and wakes the model when the context crosses a size line or keeps growing. By default it requires DSH's experimental Session Search plugin (session_event_read / session_event_search); without it the tools stay disabled unless requireSessionQuery is turned off.

Database structure the agent already knows: dbgraph indexes a remote catalog into local SQLite, answering schema questions offline and fetching data in one query.

Two-stage session deletion for DSH on Windows: move a conversation to the recycle bin and restore it to its original sidebar slot; deletion confirmed in two steps to prevent deleting files by mistake, clearing the whole subagent tree, sidebar ledger, projection cache, log lines and exclusive attachments along the way. It also scans the files a conversation actually wrote, adds a file query that pastes the path information into the conversation so an agent can judge which files are safe to delete, highlights them in Explorer, and copies the paths grouped by type. Both this and iamwuzhanglin/dsh-session-recycler install under the package name dsh-session-recycler, so install only one of them.

Database access for DeepSeek Harness through the DBHub MCP server: configure MySQL, MariaDB, PostgreSQL, SQLite and SQL Server connections per workspace and environment, then let the agent configure, list, query and search SQLite objects through four fixed tools. Passwords and full connection strings are entered in the settings UI and never accepted as tool arguments, so the model only sees metadata such as mysql://host:3306/db; each environment can be read-only (the model may enable it but not clear it) or reached through a manual SSH tunnel. Every call runs its own short-lived dbhub process and dbhub installs itself when missing.

On-demand memory for DeepSeek Harness: session logs are distilled into layered markdown (a summary, an index and per-topic files), and a mem_query tool returns only the matched entries rather than the whole index. Nothing is injected per turn, there are no dependencies, and every entry keeps a source pointer back to the conversation it came from.

Read-only Sentry tools: project listing, issue search at organization or project scope, single issue detail, and the latest or a specific event with a trimmed stacktrace. Local variables, request headers and bodies, query strings, packages and secret-looking tags are removed before the event reaches the model, and oversized events degrade through source context, breadcrumbs and frames rather than failing.

Read-only Grafana tools that query metrics through the data source proxy: instance health, data source listing, instant and range PromQL queries, current alert state, and provisioned alert rules. Range queries downsample to a point budget; an explicitly supplied step that would exceed it is rejected rather than silently changed, so the model never receives data at a resolution it did not ask for.

DSH Usage Monitor: auto-query provider credit balances and time-window limits from configured API keys, with input capsule and custom provider support.

Conversation query map for dsh web: a left rail with one bar per sent question, hover wave + preview, click-to-jump with older-page backfill, and tunable bar length/spacing.

Let a local DeepSeek Harness Agent use BailingHub to query data, update records, and run permitted actions in an online store, SaaS, or other admin system.

Native per-workspace memory on the harness's own seams: facts and a bounded always-on profile on the storage-domain JSON unit, approval-gated writes with `(sessionId, seq)` citations, deterministic recall plus session-query FTS over past sessions — no external server, no custom SQLite.

Read Zotero PDFs inside the DSH right sidebar and let the model work on them directly. Requires Zotero 10 or newer with the local API enabled (Zotero 7/8 is read-only and cannot accept annotations). The model gets three tools: search_zotero_library to search your library, read_zotero_paper to read a paper by page or by query, and ask_zotero_paper for page-cited answers. Annotation handling mirrors Zotero's own reader: click an annotation to open a card with page number, quoted text, a comment box and tags; the three-dot menu recolors or deletes it; multi-line selections get a single surrounding box rather than one box per line. Comments, tags, colors and deletions are written back through the Zotero local API, so they show up in Zotero and annotations made in Zotero show up here. Selection actions cover translate, explain, ask and highlight; the reader remembers the exact reading position (page plus offset) and zoom level per paper, and keeps opened PDFs mounted so switching tabs does not reload them. MinerU re-parsing is available for scanned or broken-text PDFs and is off by default.

Connect SQLite, PostgreSQL, or MySQL databases in DeepSeek Harness: browse table structure and data, run SQL, and let the assistant query and edit data directly in the conversation.

Connect to databases in DeepSeek Harness (DSH), then query and edit data right in the conversation.

Database workbench inside DSH: import the connections DBeaver already stores (data-sources.json, decrypting saved passwords locally) or register SQLite, PostgreSQL, MySQL and Oracle sources by hand, then hand them to the agent through eight mcp__db__ tools — list_datasources, list_tables, describe_table, sample_rows, execute_sql, explain_query, get_ddl and test_connection. Sources start read-only; one global switch enables INSERT/UPDATE/DDL, every call is row-capped and appended to a JSONL audit log. Also covers groups, bulk actions, a read-only schema browser and a bundled Python MCP server whose dependencies install from the panel. No DSH files to edit.

Controls the Browser panel DSH renders in the right Sidebar: numbered refs from a snapshot, click/type/press/select/scroll, query-scoped reads and change diffs, up to 12 steps in one call, and multi-tab focus/close.

Dynamics 365 CE / Dataverse toolkit for DSH: 15 tools for querying metadata and solution layers across environments, snapshots and diffs, field impact analysis, migration risk assessment, GitLab merge-request checks, contract drift, environment health, and review-gated metadata writes.

FOFA cyberspace mapping inside the conversation: check the account quota, run FOFA queries and export the full result set into CSV/JSON/TXT files in the session workspace by paging through a time cursor. A CSV or TXT export stopped by its time budget or by an upstream error continues into the same file from the saved cursor, so rows already fetched are kept. Results render as conversation cards (query, match count, file path), and the API key is saved from the plugin page into the Harness credential store.

Read-only knowledge gateway over a local Markdown vault, in four tools: `wiki_recall` returns the matching section in full with page-level citations plus vault health checks and a page skeleton for writing a good answer back; `wiki_context` returns one evidence pack with per-page excerpts, a support verdict and an explicit list of gaps; `wiki_verify` re-checks a drafted answer against that pack and reports claims the evidence cannot back, including unsupported numbers; `wiki_observe` reports how often answers needed correcting. The settings page and sidebar panel share the same query path as the model, so a search you run by hand cannot disagree with what the model was given. The three knowledge-gateway tools (`wiki_context`, `wiki_verify`, `wiki_observe`) need a local Python 3 bridge — `bridge.python` plus `bridge.toolsRoot` containing `wiki_bridge.py`; without it they return `E_PYTHON_UNAVAILABLE`.

Persistent cost ledger for the DeepSeek Harness: every priced model call lands in a monthly JSONL file; /ledger renders monthly reports, /ledger-export writes CSV, and the agent can query its own spend via ledger_query.

Refuses agent-generated SQL that reads tables or columns outside a configured blacklist or whitelist, returning a structured permission reason instead of rewriting the query.

DSH File Converter: local file conversion across 20 tool chains and 1000+ format pairs — convert files, query the format matrix, and check converter availability via model tools. DSH 文件格式转换插件：跨 20 个转换器、覆盖 1000+ 格式对，以模型工具提供本地文件转换、格式矩阵查询与转换器可用性检测

Parametric CAD tools for the DeepSeek Harness: CadQuery 3D modeling, ezdxf 2D DXF drafting, STEP/IGES/STL/3MF/DXF export, and design preview