147 results
Clinical documentation toolkit for DeepSeek Harness: SBAR and I-PASS handovers, SOAP and APSO notes, admission H&P, discharge summaries with pending-results enforcement, patient-instruction readability scoring, HIPAA Safe Harbor de-identification, and cited FDA label/FAERS/recalls/Drugs@FDA, MedlinePlus, PubMed/PMC/Europe PMC, and ClinicalTrials.gov (search/details/eligibility/investigators/endpoints) lookups. Drafts only; not a medical device.
Local-first vision for text-only DeepSeek Harness agents: route image understanding to a local OpenAI-compatible vision model, return structured JSON evidence (summary / OCR / layout / semantics / visual / uncertainty).
Inject a configurable dsh-ui status card instruction before every DSH agent reply
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.
Reasonix-style cache-aware compaction backend for DeepSeek Harness (DSH). Replaces/enhances compaction-basic with compact_ratio, one structured summary checkpoint, and a stable recent tail.
Infrastructure as Code (Terraform) integration for DeepSeek Harness: plan/apply/diff, state inspection, output querying and resource listing.
DSH conversation checkpoints: list every user instruction, jump/scroll to it, roll the visible conversation back to it (optionally with file snapshots), recall/edit sent instructions, show this round's file changes inline under the conversation, and a VS Code-like diff viewer (unified/side-by-side) with per-file undo.
Palette infrastructure for DeepSeek Harness: scheme-mapped theme palettes with built-in VSCode Red, Solarized Dark, and Solarized Light, plus a third-party registration API
Leaderless flat agent teams for DeepSeek Harness: cross-window structured task dispatch, recorder service, and web dashboard
DSH microsandbox bundle: Linux microVM shell executor and ctx.sandbox provider (msb run) with workdir/env preservation, fail-closed probing, and shell-free argv construction
My Habits for DeepSeek Harness: edit the user-global AGENTS.md from the Web settings — injected into every session by the built-in agent-instructions loader.
DeepSeek Harness plugin: outline and lint Markdown document structure (heading tree, level skips, duplicate headings, unclosed code fences).
DSH standard vision skill: Qwen dynamic-resolution preprocessing + OpenAI-compatible VLM chain with failover/429 backoff, structured evidence mode, local tesseract-first long-screenshot OCR, paste-to-path (no framework patch). 8 tools + runtime skill.
Edit DeepSeek Harness global AGENTS.md instructions and memory directly in Web settings.
Semantic-Linter plugin and CLI for narrowing wide-boundary wording in LLM instruction files.
AI turns repeated dev commands, prompts, and instructions into one-click DeepSeek Harness actions.
DSH plugin: structured test runner tool (test_run) — auto-detect vitest/jest/pytest/node:test, run tests, parse failure summaries for the model.
mm-vision (通感编码器) for DeepSeek Harness — give any text-only LLM the ability to see images via structured spatial text encoding. Registers the mm_vision tool.
One-click health check for a dsh deployment: a sidebar button runs the ops kit's check-health.ps1 (hidden PowerShell) through a plain HTTP route and renders a structured report. The route is independent of the tool registry, so the button still works when agent tool calls break.
Agent governance suite for DeepSeek Harness (enterprise companion): policy-based tool gating (allow/deny/ask), structured JSONL audit trail, and per-agent token quotas against the host token meter — state under $DSH_HOME/gov
DSH-Plugin: durable agent memory core — mem_save / mem_search / mem_health tools backed by the DSH storageDomain (durable, survives restarts), plus a 記憶 view tab.
类 Codex 自定义指令：在设置里编辑 ~/.dsh/AGENTS.md 全局指令，对本机所有会话、所有模型生效。Codex-style custom instructions panel for DeepSeek Harness.
DeepSeek Harness web plugin — upload files and folders straight into the conversation (no workspace copy needed): images attach as real image blocks, text content is written into the composer, folders land under ~/.dsh/uploads by directory structure
DSH-Plugin: structural observability layer — real tool/skill usage recording (tools/result), skill-catalog audit, and a watchdog with health/error events. No model self-reporting.