Plugin

Strumenti di stabilità dei test: esegui ripetutamente suite vitest/jest/pytest/node:test, classifica i casi instabili, mantieni la cronologia, un manifesto di quarantena e l'autocontrollo di salute.

Guardia di coerenza tra documentazione e codice: verifica intestazioni di versione, tabelle dei changelog, alberi di directory, conteggi di moduli e test e riferimenti incrociati tra documenti alla ricerca di scostamenti, con suggerimenti di correzione in sola lettura ordinati per gravità.

Affida lavori singoli alla CLI di Cursor con accesso effettuato sulla stessa macchina, con diagnostica di prontezza della CLI e del proxy, impostazioni del modello figlio e un test di connettività in sola lettura.

Verificatore di aggiornamenti (edizione npm): una pagina di impostazioni che confronta le versioni locale e più recente di @deepseek-ai/dsh e di ogni plugin installato, con promemoria a pallino rosso nella navigazione e comandi di aggiornamento pronti.

Harness di regressione dei contratti per autori di plugin: un adattatore LLM scriptato guida la pipeline reale in processi figli isolati con asserzioni sugli eventi di sessione (livelli load/contract/behavior/fault); senza chiavi API, pronto per la CI.

Guardia all'avvio: ripara registri di sessione corrotti, preispeziona la composizione dei plugin, verifica con vm gli artefatti del client, fa smoke test dell'apply() dell'host e mette in quarantena i bundle che causano crash, così un plugin rotto non può mai bloccare l'avvio.

Impacchetta una libreria di skill di metodologia ingegneristica in un unico plugin Cordis: 14 Agent Skills (pianificazione, test, debug, revisione, consegna) registrate su ctx.skills per DeepSeek Harness.

Registra la skill Inspiration Deck Workshop per DSH: presentazioni HTML statiche locali (6 modelli, oltre 25 layout, 23 temi e showroom di animazioni) con CLI di validazione ed esportazione PNG/PDF e smoke test, senza dipendenze a runtime.

Crea/modifica/inietta messaggi di test dell'assistente e importa/ripara log di sessione session.jsonl(.zstd) in nuove sessioni.

Raggruppa pensiero, chiamate di strumenti e contesto di ogni turno di DSH Web in riquadri di processo bordati, tagliati a ogni porzione di testo del modello; un riquadro compresso mostra i suoi ultimi due elementi, le righe impilate sopra il bordo aprono quel riquadro, il bordo stesso lo richiude, mentre dialogo utente, domande interattive e testo del modello restano fuori.

Strumento di esecuzione test strutturato (test_run): rileva automaticamente Vitest/Jest/pytest/node:test, esegue i test e analizza i riepiloghi dei fallimenti per il modello

La CLI compagna mancante per DeepSeek Harness (dsh): gestisci i server MCP con un solo comando — add/list/remove/test con controlli di connessione in dry-run, più importazione una tantum da Claude Code / Codex. Si monta anche come plugin dsh in modo che l'agente possa gestire MCP da solo

Profiler del contesto delle richieste per DeepSeek Harness — osserva cosa è cambiato tra le richieste al modello e come è cambiato di conseguenza il riutilizzo della cache

DeepSee: visione per DeepSeek Harness, instradamento multi-modello e autoverifiche visive con Gemini prima della consegna

DSH 测试自动修复：给 agent 一个 run_tests 工具，跑测试并把结构化失败（文件/行号/断言）直接交给它修复。自动识别 pytest / jest / vitest / cargo / go / npm，Windows 中文断言不乱码，同一失败反复出现时自动停止。

DSH plugin: inventory your Windows dev/test toolchain, spot the gaps, and fill them with one click.

DSH plugin: deterministic, offline Python/Django production-report diagnostics — traceback root cause, pytest summaries, unapplied migrations, N+1 SQL, manage.py check --deploy and Celery backlog. Does not execute Python, start subprocesses or touch the n

Pre-claim gate: a commit, push or tag claim like "tests pass" is checked against the session evidence ledger before it is written.

Outbound route pool for DeepSeek Harness. Ships 15 seed routes plus a 20-entry candidate pool covering 7 target kinds (GitHub raw/codeload/main, npm registry, PyPI index, HuggingFace, general). Routes are verified before use: upstream IP lists go through a TLS handshake with full certificate-chain validation (a bare TCP check can be answered locally and report dead IPs as healthy), and failures advance a cooldown ladder of 2/5/15 minutes with the fastest healthy route picked per target kind. Routes are applied by rewriting the URL with one of four rules (prefix, registry, index, host-replace), reaching git, pip, npm, pnpm, gh, curl and wget through three paths: the shell seam (download commands the model runs through the bash tool are intercepted and rewritten automatically; commands wrapped by the pwsh tool, and fetches made by the host itself or the renderer, are not covered), two registered tools the model can call directly (line_pool_status, line_pool_run), and child-process spawn. Multi-line commands keep their line breaks and only the download segment is touched. URLs carrying credentials (user:token@host) are never rewritten, so tokens are not forwarded to third-party mirrors. No global config is modified. A sidebar panel lists every route with latency, failure reason and cooldown countdown, supports per-route retest and enable/disable, and shows live TUN/proxy status from network-adapter and loopback port checks. The candidate pool is re-verified every 24 hours so newly usable routes are added and dead ones dropped. 570 tests, 87% line coverage.

Keep a DSH profile identical across machines through any WebDAV server. The plugin collects the five parts that make up a setup — models (the llm-pi-ai line of cordis.patch.yml), defaults (the agent-default-model line), patch (the remaining loader lines), plugins (package.json dependencies plus dsh.profile.bundles) and dirs (extra absolute-path directories picked in the panel, carried whole and restored to the same path, add-only, at most 5 with 2000 files / 8 MiB each) — encrypts them on this machine with a passphrase (AES-256-GCM, PBKDF2-SHA256 at 600000 iterations) and uploads one ciphertext file to <address>/dsh-webdav/dsh-profile.prop, so the server only ever holds the sealed copy (the older dsh-profile.dshsync name is still read). Merging is per part and three-way against the last synced baseline; a conflict keeps the newer copy and archives the losing one under sync/ (latest 5 per tag), every overwrite is sealed beforehand, and deletions propagate except in the plugins part, on the first sync, and in the dirs part, where dropping a directory on one machine only stops syncing it there and never deletes its files. Uploads carry ETag If-Match and If-None-Match so a concurrent change is refused instead of being clobbered. Sync runs on demand or on a 3/15/30/60 minute timer from a settings panel, and an optional local forwarder (off by default, loopback-only) re-serves the same target with locally generated credentials, rewritten PROPFIND hrefs and .prop aliases for extensionless resources. The local state lives in <profileDir>/.dsh-webdav-sync/ (sync.json is written 0600 and holds the WebDAV password and the passphrase).

Plugin development toolset: mark files read by shell commands, sync code into a profile, mock a plugin backend, preview a plugin frontend, verify plugin loading, spin up an isolated test instance, run named shell shortcuts, and list the plugin's tools.

Turns what a design, plan or document claims into a model and decides it: UML diagrams rendered, read and reviewed; state machines, protocols and data models checked as models; migrations tested for coverage and rollback symmetry; concurrency claims mined and routed to the checker that can decide them; dependency graphs audited; reports diffed.

Generic monitor plugin for DSH Desktop: an HTTP polling rule engine. Poll any endpoint on schedule (multi-step, variable extraction, JS condition expressions); when conditions hit, wake a visible agent session to act — zero model calls otherwise. Configure everything in a sidebar GUI panel: create/edit/pause/test/fire-now/run history, same UX as the built-in scheduler plugin.

Test work framework for DSH that scaffolds a product, module and version directory tree, registers seven test_framework_* tools and four runtime skills, and adds a prompt-level gate that reports which requirement-document splits, versions, related documents and environment credentials are still unrecorded before testing starts. Requires the playwright MCP server (no fallback).