Zum Hauptinhalt springen

Plugins

Durchsuche, filtere und installiere DeepSeek-Harness-Plugins.

138 Plugins gefunden

H

dsh-ui-polish

hiocobueno653-pixel/dsh-ui-polish

UI-Polish-Schicht für den DSH-Webclient: Milchglas-Menüflächen, verschiebbarer Reasoning-Effort-Slider statt Radioliste und Modellmenü-Navigation mit einem Klick zur Liste und Schließen per einmaligem Esc.

1vor 14 TagenUI-Erweiterungen
C

dsh_gearbox

ctianye/dsh_gearbox

Reasoning-Gear-Presets für Drittanbietermodelle: 16 Anbieter-/Modellprofile mit eigenen Wire-Werten je Modus; Übernahme in dsh-llm-pi-ai erst nach Vorabprüfung, Ablehnung je Regel. Pro Modell Wechsel zwischen OpenAI Chat Completions, OpenAI Responses und Anthropic Messages mit automatischer Neugruppierung der Routen. Optimize-Schaltfläche im Composer und Einstellungsbereich schreiben den Eingabetext mit dem gewählten Modell um.

1vor 2 MonatenModelle & Anbieter
W

dsh-seed-society

woshishadowhunter/dsh-seed-society

Optimiert die Speicherkonsolidierung von dsh-mneme (autoDream an, schema-max-Ausgabebudget, deepseek-chat-Route), behebt reasoning-effort in llm-deepseek, ergänzt eine MCP-Brücke zum auditierbaren seed-society-Agent-Runtime und sechs Yogacara-Seed-Skills.

1letzten MonatGedächtnisMIT
S

dsh-reasoning-options

scorp1o117/dsh-reasoning-options

Ergänzt fehlende Reasoning-Effort-Deklarationen für benutzerdefinierte pi-ai-Modelle über DSH-Einstellungen, aktiviert den nativen Effort-Picker und berücksichtigt später hinzugefügte Modelle.

1vor 8 TagenModelle & AnbieterMIT
W

dsh-reasoning-slider

wsl043/dsh-reasoning-slider

Ergänzt einen modellabhängigen Regler für den Reasoning-Aufwand mit nativen und animierten Modi, hellen und dunklen Paletten sowie gemeinsamen oder modellspezifischen Farben.

1vor 26 TagenUI-ErweiterungenMITArchiviert
J

dsh-maestro

junqingv587/dsh-maestro

Planer-/Executor-Delegierung mit benannten Rollen: Ein starker Planer steuert, wegwerfbare Executor-Subagenten (rollenspezifische Routen und Prompts) setzen um. Standardrolle plus Überschreibung pro Delegierung, ein globaler Regler für den Reasoning-Aufwand im Eingabefeld-Chip und eine Einstellungsseite für die Rollenverwaltung.

1vor 3 MonatenModelle & AnbieterMIT
W

dsh-native-reasoning-slider

wsl043/dsh-native-reasoning-slider

Fügt einen modellbewussten Schieberegler für den Reasoning-Aufwand hinzu, mit nativen und animierten Modi, hellen und dunklen Paletten und Farben pro Modell.

1vor 3 MonatenUI-ErweiterungenMIT
T

dsh-model-reasoning

tikaflow/dsh-model-reasoning

Füllt Reasoning-Effort-Stufen, Kontextfenster, Output-Limits und Bild-Modalität für Modelle inoffizieller (eigener) Provider automatisch aus, mit Daten von models.dev.

1vor 3 MonatenModelle & AnbieterMIT
V

better-reasoning-slider

vvvspec/better-reasoning-slider

Modell-Trigger im offiziellen Stil für den Composer mit schwebendem Reasoning-Effort-Slider-Popup.

1vor 3 MonatenUI-ErweiterungenMIT
Z

dsh-model-switcher-pro

zsqs88/dsh-model-switcher-pro

Composer model picker with searchable providers and grouped fuzzy model search, plus a reasoning-effort slider with named tiers, magnetic detents, a damped drag glide, per-tier colors, and dark/light themes. Optional host-composer restyle is off by default.

0vorgesternModelle & AnbieterMIT
J

dsh-llm-effort-zh

jyz48prsbr-netizen/dsh-llm-effort-zh

Shows reasoning-effort levels in Chinese in the model selector; display names only, the reasoning_effort values sent to the provider are unchanged.

0gesternThemen & Aussehen
D

dsh-max-reasoning-effort

devzer0o0/dsh-max-reasoning-effort

Pins reasoning effort to the highest level every model offers, and keeps it pinned for agents created after the plugin loads.

0vor 4 TagenModelle & AnbieterMIT
J

dsh-qwen-reasoning

jasocheung/dsh-qwen-reasoning

Auto-enhances manually-declared Qwen models with the full reasoning-effort levels (off/minimal/low/medium/high/xhigh/max) and defaults to max. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

0vor 5 TagenModelle & AnbieterMIT
X

dsh-dragon-maid-pet

xnwang1999/dsh-dragon-maid-pet

A desk pet for the DSH web GUI whose illustration follows the current model's reasoning effort across five stages, taken from one of three art sets that auto-select for Claude and DeepSeek models. Draggable and collapsible, with a custom image per stage, and it also fills in reasoning-effort levels for custom model providers in Settings → Models.

0vor 4 TagenNur zum Spaß
D

online_model_discovery

dhllib/online_model_discovery

Adds live model discovery and per-model reasoning-effort editing for third-party pi-ai providers, and automatically fills compat switches for models missing from the bundled catalog, fixing 400 errors caused by an unsupported developer role.

0gesternModelle & Anbieter
C

dsh-model-fallback

carlcn2003/dsh-model-fallback

Primary and multi-level backup model failover router for DSH, with cross-provider reasoning-effort clamping, exponential cooldown, per-turn recovery, and a settings panel.

0vor 9 TagenModelle & AnbieterMIT
T

dsh-composer-model-controls

timxiang-948/dsh-composer-model-controls

Reasoning-effort control for the DSH composer — an adaptive effort slider whose track and composer border tint with the level, plus Shift+Tab cycling; the built-in model menu stays untouched.

0vor 4 TagenUI-ErweiterungenMIT
L

dsh-gpt-adapter

lxjmaster/dsh-gpt-adapter

DeepSeek Harness plugin for GPT models and Codex instructions, skills, plugin resources, and MCP configuration.

0vor 11 TagenMCP & KonnektorenMIT
C

dsh-model-radar

chip-g0202/dsh-model-radar

Runs a four-task, 150-point model intelligence benchmark inside DeepSeek Harness (Qin 60, Pompeii 45, Pelican 22.5, Candy 22.5): each selected model × reasoning-effort pair executes every task in its own isolated subagent session, Qin and Pelican are graded by the selected judge model against rubrics, Pompeii and Candy programmatically, and batches keep scores, artifacts and cost. Adds a 0–1000 real-world performance score per model × effort computed from local session logs across seven dimensions (output speed, first-token latency, reasoning speed, tool cadence, tool latency, tool success rate, cache hit), with baseline deltas and controlled speed runs, plus a sidebar page with ranking, performance, history and settings views. Each batch spends real tokens of the candidate and judge models, and candidate subagents get file and bash tools inside an isolated run directory.

0vor 12 TagenModelle & AnbieterMIT
D

dsh-model-effort-chips

dreamaniax/dsh-model-effort-chips

Splits the composer model seat into a model chip and a reasoning-effort chip: the effort chip opens a draggable, wheel-adjustable slider, and the panel behind it animates 36 canvas effects across 12 categories.

0vor 11 TagenUI-ErweiterungenMIT
A

dsh-model-quick-selector

arrosam/dsh-model-quick-selector

Adds a quick-select model list to the DSH composer model button: a settings icon on the Model row of the model menu opens a dialog to pick and reorder favourite models, dragging vertically on the model button switches between them on release, and dragging left or right steps the reasoning effort; the menu's reasoning-effort row also gets a draggable slider (based on Microqian2th/dsh-codex-effort-slider). Text follows the DSH language setting (English / Chinese).

0vor 12 TagenUI-ErweiterungenMIT
L

dsh-model-tabs

lycorisradiatax/dsh-model-tabs

A zero-config composer model picker with one provider per tab, independent scrolling per provider, cross-provider search with provider badges and reasoning-effort chips; selections stay in sync with the built-in /model dialog.

0vor 13 TagenModelle & AnbieterMIT
X

dsh-effort-menu

xuanfenglajiao/dsh-effort-menu

Replaces the composer model menu with a recent-models list, a searchable all-providers flyout and a draggable reasoning-effort slider; a Manage models row at the bottom of the flyout opens the Models settings directly. It takes over the composer model slot, so install only one model-menu plugin.

0vor 6 TagenUI-ErweiterungenMIT
D

dsh-auto-router

dakouchiya/dsh-auto-router

Routes model and reasoning effort per turn: a cheap classifier reads each request and picks one of five tiers, a supervisor model re-routes on tool errors and checkpoints, and upgrading to the stronger model waits for confirmation.

0vor 13 TagenModelle & AnbieterMIT