dsh-model-modes
Capability-aware reasoning controls and provider-native Fast mode for the DeepSeek Harness web composer
1138 results
Capability-aware reasoning controls and provider-native Fast mode for the DeepSeek Harness web composer
DSH plugin: official-model Honcho v3 memory plus a perspective-safe shared knowledge base
Modellix Design, LLM, and Web providers for DeepSeek Harness
DSH plugin (NInfer engine only): fixes compaction failure on local qwen3.8-27b gateways served by NInfer — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters; the same idea applies to other launch methods
Role-based AI swarm orchestration for DeepSeek Harness: duty-table model pinning per role, parallel task DAG with review loops, and a live Swarm dashboard tab in the web GUI.
DSH LLM adapter plugin that connects local Devin CLI into DSH model provider via stdio ACP.
复用 CodeBuddy CLI 的登录态,把 CodeBuddy 包含的模型自动接入 DeepSeek Harness — reuse the CodeBuddy CLI sign-in to bring its models into DeepSeek Harness with zero configuration.
Model-driven context-window rollover bundle for the DeepSeek Harness: fresh working context, durable model-managed notes, a small verbatim recent tail, and targeted history recovery — no summarization.
DSH vision/image-recognition plugin: enables AI to understand images with a configurable vision model
CodeBuddy (copilot.tencent.com) provider bundle for DeepSeek Harness (dsh): 18 models (DeepSeek, GLM, Kimi, MiniMax, Hunyuan, auto) with adjustable reasoning efforts, CodeBuddy web search / web fetch backends for the stock dsh tools, and a settings card in the Web UI.
Claude Pro/Max OAuth model provider for DeepSeek Harness with Google/Gmail login in Settings, auto-token refresh, live model discovery, and real-time quota tracking
DeepSeek Harness (Cordis) plugin: control Alibaba Cloud ECS instances through the local Workbench CLI — list/exec/log/upload/download/diagnose/deploy/session model tools plus a visual settings panel
DeepSeek Harness plugin (temporary, pre-upstream-fix): automatically injects a CPython tempfile shim (PYTHONPATH -> sitecustomize) into every confined shell command on the Windows sandbox, so python/pytest tempfile use works with zero extra tools, zero model-context overhead, and zero escalation.
3D printing & additive manufacturing capabilities for DeepSeek Harness: parametric STL generation, calibration G-code, STL/G-code analysis and toolpath rendering as model tools, plus slicing / modeling / analysis / diagnosis knowledge skills.
DSH user addons: file drop-upload, archived-session manager, model/token usage dashboard (auto-loads with the web profile)
Raise Node's HTTP timeouts for the whole DeepSeek Harness process so slow local models are not cut off at 5 minutes
Decision-driven AI company orchestration with HR governance, monetary budgets, model discovery, and deterministic audit for DeepSeek Harness
DSH web plugin: token usage statistics in the sidebar footer — today badge (wide/rail) opening a detail panel with per-model/provider breakdown, session list, daily trend curve and heatmap (host scans session logs, serves usageStats Remote methods)
DeepSeek Harness client plugin: adds an 'Invert selection' button to the fetch-models dialog of the Models settings section, so only the rows that are already in the model list stay checked on a second fetch + add pass.
DeepSeek Harness (dsh) profile bundle that registers the MathWorks MATLAB/Simulink MCP server into the GUI so agent sessions get mcp__matlab__* tools.
Per-workspace MCP scoping for the DeepSeek Harness — decide which MCP servers a session may see from the directory it was opened in.
AI response quality review for DeepSeek Harness: audits each finished assistant turn with an independent reviewer model and steers the agent to fix unreasonable output (up to 2 review rounds).
Unofficial DeepSeek Harness settings panel for Command Code: credits, usage windows, and model-catalog sync.
MCP manager settings page for DeepSeek Harness: list, enable, configure and add MCP servers from the browser, written durably to the profile's user patch layer.