플러그인

DSH Web GUI 数据库管理面板：侧边栏入口 + 独立面板，统一管理 SQLite / MySQL / Redis（数据源配置、实时连接池、SQL 浏览器、Redis 键浏览器），并提供受审批保护的 agent 工具。 | Database management panel for the DeepSeek Harness Web GUI: a sidebar entry and a dedicated panel managing SQLite / MySQL / Redis (source co

Unified @ mentions in the DeepSeek Harness web composer: five built-in categories (file, folder, skill, past chat, plugin) plus a data-source seam any plugin can register through, references to absolute paths outside the workspace, and a candidate menu that can be scoped by a folder named earlier in the draft and pages with PageUp/PageDown instead of hiding rows.

A newspaper-style front page for a session you left running, as a Conversation View tab beside Chat and Trajectory: a per-turn timeline (duration, steps, tools, tokens, outcome), file churn counted per file, where the wall clock went and how much of it was the model rather than tools, which single turn ate the spend, failures nobody retried quoted with their failing command, and a context-pressure gauge measured against the routed model's own declared capacity. The briefing is folded from the durable session log and never generated by a model, so it costs no tokens, cannot hallucinate, and is byte-identical for the same log and clock; it appends nothing to the session and reaches no model, and it reports a pending approval without ever answering it. Pages are offered only when they have content, and the tab refreshes itself on turn settle and on a two-speed poll backed by a metadata-only tail probe.

Paper library and reading workbench: arXiv search, a local plain-file library (metadata / PDF / extracted full text), and three-level reading notes (overview / understanding / critique) kept as markdown beside the PDFs; seven model tools plus a web panel.

SparkElf-maintained fork of dsh-quant: AI-native & DSH-native quant toolkit — 59 tools across 6 pluggable domains (data/alpha/ML/risk/execution), one end-to-end PDAT→PET research pipeline. Fork adds A-share-correct annualization, cross-sectional IC, and u

Shared infrastructure for data assetization plugins: business rules loader, file format adapter, report generator, path validator, audit logger Also known as @deepseek-ai/dsh-data-asset-shared.

Cumulative token usage tracking for DeepSeek Harness, with per-model and per-day breakdowns, a settings-page dashboard and an online-changeable data directory.

Long-term memory for DeepSeek Harness, read-only as of 0.1.0: a scribe_recall tool that reads a plain-markdown memory room, path rules that refuse directory traversal, Unicode smuggling and NTFS alternate data streams, and a bounded index whose truncation is always reported rather than silent.

Code graph and knowledge base over an embedded FalkorDB: AST symbols, caller/callee tracing, refactor blast radius, affected-test discovery, clone detection, cross-language porting contracts and spec-to-code traceability.

Pre-execution safety valve for DSH that judges with TypeSafe Jev: it hooks tools/pre-execute and decides every bash/pwsh call by first applying offline static rules, then by asking the Jev model — the System One model from TypeSafe, which returns a structured decision instead of prose — one yes-no question ("will this command irreversibly delete or overwrite real data?"), turning the answer into allow, revise, block or escalate; revise hands the model a safer rewrite, escalate offers a one-shot human token; exhausted credit or a missing API key degrades loudly instead of failing silent, and a missing key is requested in the conversation itself (`guard key set`, read from stdin); every verdict is appended to a shared audit log and the text people read is bilingual zh-CN/en.

Agent 行为守护桌宠：跨 agent 监控可疑外传（加密打包直传对象存储 / DNS 外泄线索 / 敏感密钥被读），发现即告警，明确确认后按「一次一个」终止目标 agent；事件写入只追加 guard-events.jsonl，并通过 DSH host 工具 + MCP(stdio) 供其它 agent 查询

AlphaRSI — three-role self-improvement loop that evolves the training recipe of alpha sequence models. Operator runs walk-forward, Evaluator grades with OOS RankIC, Refiner proposes hyperparameters via TPE Bayesian search; only strictly-better recipes are kept. Offline one-command run, data bundle shipped with sha1 reconciliation, GPU auto-detect. Ships one skill.

33 github_* tools covering REST reads, issue writes, Git data writes, private repo creation, and clone; in-process permission gate and cost-discipline companion skill; no gh CLI required.

Database connections and SQL for DeepSeek Harness: register data sources, browse and comment schemas, run AST-checked SQL with a per-source read-only toggle, and render bar, line and pie charts, from chat or the Settings page.

Local file recall: indexes the folders you choose into one local SQLite database, so 'where did I put that file?' is one query instead of a disk walk. Caches, VCS and program folders are pruned per directory; each folder keeps its own incremental anchor, so a folder added later is backfilled in full. Read-only: it never modifies, moves or deletes your files.

Data stage — data discovery and quality assessment for asset pricing and machine learning research. Ships one skill.

DSH plugin: matches a model you declared on a custom gateway to the capability metadata it should have — context window, output cap, reasoning levels and image support — by looking the bare model name up at runtime; the plugin never writes your settings document.

Task management for the DeepSeek Harness: the session todo list, a project task board backed by a queryable SQLite database, and board cards dispatched to the agent as background jobs

Ten live-data tools over eight keyless public APIs: FX rates, weather, npm/PyPI versions, GitHub repo stats, Bilibili video stats, A-share/index/gold quotes, and IP geolocation. Tool defaults are configurable in settings.

Resume screening plugin for HR in DeepSeek Harness: ingest up to 100k Word/PDF/Excel resumes into one searchable library with skills / coarse categories / ingest time, auto-ingest & de-dupe new resumes, then screen by plain-language criteria — rule pre-filter in the database plus LLM fine-judge on the shortlisted few, CSV export.

Measures what an llm-pi-ai endpoint really accepts — context window from its own model list, output-token limit and reasoning levels read out of its own range errors, image support from a generated test image — then reports declared values that contradict that evidence and rewrites them only after confirmation.

Shows selectable DeepSeek, Kimi, Zhipu GLM, and TeamoRouter balances in the DSH Web sidebar, with per-provider details, usage data, and refresh controls.

A plugin for dsh: quantify every dsh Agent interaction as a visualized performance metric and automatically sync it to WakaTime -- use data to showcase your productivity with Agent.

Injection scheduler for DeepSeek Harness injection planes: cross-plugin sections register/order/account on the official storageDomain, with conflict detection and per-session budget summaries (B10 panel data source).