Plugins

DeepSeek Harness native immersive roleplay studio & companion system. Unifies decoupled character cards with Hindsight graph memory.

Standards-based OIDC identity, enterprise API-key binding, declarative branding, and OpenAI-compatible model integration for DeepSeek Harness

Capture selected DSH, local MCP, or native WebMCP calls as reviewed, parameterized routines, expose typed tools, and replay with fresh approval.

A customized fork of TQSY114514/dsh-ui-appearance for theme palettes, wallpapers, and glassmorphism, with a layout fix for duplicate blank space alongside better-sidebar 0.18.0.

Custom script manager for DSH: turn verified operations into reusable scripts that run directly via /script or register as agent tools, with parameterized scripts, declared expected outcomes, and execution history.

Text-to-image and image-to-image generation via OpenRouter's unified Image API: configurable model aliases with parameters gated against the live model capability listing, reference-image inputs, a settings card, and inline chat display of results.

Memory consolidation tuning for dsh-mneme (autoDream enabled, schema-max output budget, deepseek-chat route) plus the llm-deepseek reasoning-effort fix, an MCP bridge to the auditable seed-society agent runtime, and six yogacara seed skills.

Cross-app project memory for DeepSeek Harness with role-separated writeback, a visual knowledge workspace, confirmed corrections, session controls, local Writer and organizer settings, and an account-free Windows local installation preview.

Daily rotating anime companion persona: deterministic date pick from JSON character cards, roster/reroll tools, and a voice-map route.

Add missing reasoning-effort declarations to custom pi-ai models through DSH settings, enabling the native effort picker and handling models added later.

Browse the skill library from a floating-ball panel: you choose the skill root yourself through a native directory chooser (defaults to ~/.dsh/skills, no path is shipped with the plugin), skills are grouped into first and second level categories, descriptions are read from each SKILL.md frontmatter, search filters by skill name, description or original text, and a card opens the full SKILL.md. Skills can be switched on and off per card, per category or for the whole library — the toggle rewrites disable-model-invocation in that SKILL.md and keeps a .bak-toggle backup, and disabled cards grey out until restored. A failure ledger separates automatic from manual entries and records skill successes and failures by listening to tools/result events, reusing an existing ledger file if one is found in the library and otherwise creating one under skill-master/references. The DSH settings page gains a floating-ball section that shows or hides the three balls and offers one-click restore of a ball dragged off-screen.

Shows a 0-100 conversation coherence badge and commentary by running parallel contradiction analysis on the live DSH session, with a manual trigger and interval-based auto-analysis (on by default, editable per session or globally).

Composer code-quote collapse for the DSH Web UI: pasting a `path:line` header followed by code folds the input into one compact inline quote chip, and at send time the `agent/pre-step` hook injects the full pasted snapshot to the model as a separate context message. 0.5.x also folds sidebar file-selections that insert only a `path:lines` line (large selections), fetching the code from disk by session cwd, and preempts Ctrl+V paste interception.

Per-provider concurrency gate on the llm/stream waterfall: holds surplus model requests in a FIFO queue inside DSH so main agent, subagents and compaction take turns on a single-slot local server (llama.cpp --parallel 1) instead of timing out; maxConcurrent / maxQueued / queueTimeoutMs.

Runs a parallel code review squad of read-only reviewer subagents (security, correctness, tests, style), each optionally on its own model, and aggregates one severity-grouped report from /review or a code_review tool call.

Adds parametric CAD modeling, geometry validation, previews, design history, and STEP/STL export to DSH.

DSH-Web-Plugin zur Sitzungsverwaltung: archivieren/wiederherstellen, garantiertes physisches Löschen (transcript-Dateien und Durchlauf von ~/storages/*.json), Workspace-Neuzuordnung per Drag-and-drop sowie Branch-basierte Nachrichtenbearbeitung (edit/retry/reroll mit umkehrbarem Versionsverlauf).

Leichtes Erscheinungsbild-Theme für DeepSeek Harness mit eigenem Hintergrundbild, glasartiger Panel-Transparenz und Akzentfarbe. Einstellungen werden serverseitig gespeichert und geräteübergreifend geteilt; der native Hell-/Dunkelmodus bleibt unverändert.

Ein KI-Kollaborationspostfach in DeepSeek Harness für Nachrichten, Aufgabenübergaben und Zustellbestätigungen. Ein Paket enthält MCP-Integration und eine Postfach-Benutzeroberfläche. Erfordert einen separat installierten Agent Mail 1.0.0-alpha.7-Provider; kein automatisches Aufwecken des Modells und kein kontinuierlicher Online-Status.

Helles Whale Girl-Theme für die DSH-Web-UI, portiert aus einem DreamSkin-Skin-Paket: registriert ein natives Laufzeit-Theme mit vollständiger Neuzuordnung der --dsw-*-Tokens, abgeleitet aus der Quellpalette, legt das Artwork als ambiente feste Hintergrundtapete hinter einer Milchglas-Oberfläche ab und fixiert das Theme gegen Zurücksetzungen der Darstellungspräferenzen.

Hybrid-Modell-Router für DeepSeek Harness: deklarative Regeln, benutzerkonfigurierbare Kostenkontrolle (Cost-First / Quality-First / Balanced), optionaler LLM-Aufgabenklassifizierer und Failure-Fallback-Ketten.

DeepSeek-Harness-Plugin: direkte multimodale Bildtransferdeklarationen + Löschen von Bildern pro Sitzung (surface replace), mit einer Einstellungsseite und Composer-Steuerelementen.

Kontinuierlicher Wasserfluss für den Turn-Status „Deep diving...“ von dsh web: drei parallaxartige Farbverlaufsströme durchziehen den Text wie fließendes Wasser und ersetzen das ursprüngliche Schimmern mit einem einzelnen Band. Helles/dunkles Theme und reduced-motion werden respektiert.