dsh-matlab
DeepSeek Harness plugin: matlab.run tool — run MATLAB code via matlab -batch and return output plus saved figures.
130 results
DeepSeek Harness plugin: matlab.run tool — run MATLAB code via matlab -batch and return output plus saved figures.
Live streaming terminal output for DeepSeek Harness
DeepSeek Harness plugin that turns silent tool failures into loud ones: a tools/post-execute policy that matches warning signatures in successful tool output and blocks the result or attaches a notice
DSH plugin: fixes compaction failure on local qwen3.8-27b gateways — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters
88API Image Studio for DSH: six Image2, Image 2.5, and Nano Banana models for text-to-image, multi-reference editing, 2K/4K output, and sequential batches.
Image generation for DeepSeek Harness via OpenRouter's unified Image API: text-to-image and image-to-image with capability-gated parameters, workspace file output, an inline chat card and a settings card
Turn-outline sidebar tab for dsh-better-sidebar: fold a session into user turns (input + tool steps + output) with structured jump-back into the conversation | DSH 轮次轨迹侧边栏:按用户轮次折叠会话(输入+工具步骤+输出),一键定位回对话原位
Infrastructure as Code (Terraform) integration for DeepSeek Harness: plan/apply/diff, state inspection, output querying and resource listing.
Real-time repetition guard for DeepSeek Harness (DSH): stops model generation when the same string repeats >=10 times in the streamed output. 实时检测 DSH 大模型流式输出中的重复内容,同一字符串重复十次以上立即停止生成。
Curate tool output before it enters the model's context: keep error/warning lines and head/tail, spill the full text to disk with a pointer. Faster turns, smaller context, sharper attention — for every tool, not just bash.
Codex-style turn folding: collapse each group of reasoning + tool-call nodes (between visible outputs) into a single disclosure unit
Structured, machine-readable CI output for DeepSeek Harness (dsh): session event capture with JSON/NDJSON reports, JUnit XML, semantic exit codes, artifact collection and privacy redaction. Ships as a dsh profile bundle and a standalone CLI.
DSH web plugin: one live model and timing summary during every output
DeepSeek Harness plugin converted from ayghri/i-have-adhd: ADHD-friendly output shaping that takes effect in a single session, never globally.
Open same-origin Markdown output links inside DSH Better Sidebar instead of an external app.
Fix garbled non-ASCII output from the pwsh tool on Windows: native output (ANSI or UTF-8) is captured byte-preserving inside pwsh and decoded per-segment (strict UTF-8 else ANSI) before re-emitting as UTF-8. 修复 pwsh 工具中文/非 ASCII 输出乱码(兼容 GBK 与 UTF-8 两种原生输出)。
Local Claude Code provider for DeepSeek Harness: a configurable 'claude-code' LLM route that runs your locally installed `claude` CLI and streams its output into the harness
Dual-face (host + client) plugin: independent text-output ocr_image tool + tools/execute read_image capability dispatch + ctx.ocr seam, with a conversation.input.left OCR toggle button.
Event monitor for DeepSeek Harness — background processes and WebSocket streams whose output lines wake the agent as asynchronous events.
Overlay reader for agent output files: Markdown/GFM rendering, in-panel PDF preview, DOCX/XLSX/PPTX text extraction, reply-end file chips. Pure JS, zero dependencies, no persistent UI.
Content-addressed proof for body-free DSH tool-result custody stages
DeepSeek Harness web GUI: collapse the agent trace (tool calls, thinking, workflow steps) while always keeping the agent's final output. A setting controls whether the trace is default-collapsed after the final output completes (default on).
dsh plugin: opencode-style json_schema structured output via a generic StructuredOutput tool, /json-schema command, and native JSON Schema validation.
DSH plugin that applies an explicit, RTK-based command-output filter to bash tools at boot.