PerryLink/dsh-fund-research
dsh-fund-research
DeepSeek Harness plugin: deterministic research reports for Chinese public mutual funds
Install
npx @deepseek-ai/dsh plugin --profile web add dsh-fund-researchRestart `dsh web` after install. Bundle APIs can change during the developer preview.
README badge
[](https://dshhub.dev/plugins/dsh-fund-research)Paste this into your README. The star count updates with every catalog sync.
From the README
Excerpt from PerryLink/dsh-fund-research, cleaned of badges and images.
📊 dsh-fund-research
Deterministic research reports for Chinese public mutual funds, on DeepSeek Harness.
Every key number in every report traces back to a hashed source snapshot — gaps declared, never invented. Research only; not investment advice.
English · 简体中文 · Español · Português · हिन्दी
Compatibility
| Component | Version |
|---|---|
| DeepSeek Harness | 0.1.1-rc.2 (peer dependencies pinned) |
| Node.js | ^22.19.0 || >=24.0.0 |
| Package manager | [email protected] |
| Platform | Windows / macOS / Linux (host-only plugin) |
| Data sources | Tiantian Fund / Eastmoney public endpoints (no key, no login) |
What you get
fund_researchtool — one fund code in, a versioned Markdown research report out: overview, performance decomposition, holdings penetration, simplified style attribution, manager profile, risk & gap declarations, disclaimer, and a number-traceability appendix mapping every key figure to its snapshot JSON path and verification verdict. Sealed tofund-reports/{code}/{YYYYMMDD-HHmmss}/asreport.md+manifest.json+snapshot.json.background: trueruns it as afund-reportbackground job.fund_snapshottool — a light snapshot card (latest NAV, published stage returns, scale, manager, top-3 holdings) sealed into the fund's day directory.- Deterministic metrics, zero model arithmetic — period/annualized return, volatility, max drawdown, Sharpe; top-N concentration, HHI, industry distribution, quarter-over-quarter holdings comparison; size-value style bands; manager tenure and peer comparison. All pure functions over the sealed snapshot.
- Traceability as a first-class feature — before sealing, every key number is checked against the sealed
snapshot.jsonthrough the optionaldsh-data-qualityservice when it is installed, or through the built-in isomorphic fallback checker (builtin-fallback) otherwise. The appendix table records value ↔ path ↔ verdict. - Honest gaps — a failed or degraded data source produces an explicit 数据缺口 (data gap) declaration in the affected section. The plugin never fills a gap with an invented number.
- Offline mode —
offline: true(config or tool argument) serves everything from the storage-domain snapshot layer or the newest on-disk version snapshot, with zero outbound requests. Ideal for tests and reproduction. - asOf cutoff —
asOfDate(ISOYYYY-MM-DD) truncates the NAV series to data on or before that date and stamps the snapshot + report with the cutoff; invalid or future dates fail loudly. - Checkpoint resume —
<reportRoot>/.run-state.jsonrecords each pipeline stage (snapshot/report) with timestamps and an input fingerprint;resume: truecontinues from the first incomplete stage, reusing sealed artifacts, and rejects a fingerprint mismatch. - Source discovery record — every acquisition seals a code-generated
sources-discovery.json(endpoint roster, primary/fallback resolution, per-source coverage and gaps, degradation reasons) and folds it into the report appendix as 数据源与缺口声明. - Multi-fund fan-out —
codesaccepts an array of fund codes; each fund runs the pipeline independently with per-fund failure isolation (failures become summary gaps), and the result is a summary card (code / asOf / seal hash / verdicts / failure reason). - Tracking ledger — every successful s
…
