dsh-context-console
DSH context console with trajectory, prompt/skill/MCP/tool inventory, message forging, and conservative session-log recovery.
356 results
DSH context console with trajectory, prompt/skill/MCP/tool inventory, message forging, and conservative session-log recovery.
DeepSeek Harness 插件:Hermes 式跨会话持久记忆。MEMORY.md/USER.md 纯文本存储 + 冻结快照注入 system prompt + memory_* 工具(add/replace/remove/batch/show/refresh)
Source-aware prompt injection protection for DeepSeek Harness
DSH Web GUI 轻量记忆系统:四个大写 Markdown 文件(USER.md / PROJECT.md / WORKLOG.md / CONVENTION.md)+ 两个动作(append 流水 / distill 沉降)。零外部依赖,只用 Node 内置模块;文件可视化、可 diff、可 git 管理。
Minimal first-turn conditioning for DeepSeek Harness Web sessions, with a persistent UI toggle.
VS Code / IDEA-style run control for the DeepSeek Harness web GUI: run buttons, task run configurations (LLM prompt / background command), configuration CRUD, and an LLM-exposed configuration tool with an on-demand usage skill
DSH rules plugin: activate rule prompts / markdown documents by glob-matching the files an agent reads or edits (Claude Code rules.md style).
Inspect, measure, search, and compare the exact provider-neutral context assembled by DeepSeek Harness.
Prompt-cache observability and logical-input diagnostics for DeepSeek Harness
DSH web plugin: a yellow one-line cache-miss notice under the first assistant reply of each turn, when that turn's first request rebuilt the prompt cache.
Private, per-project system-prompt rules for DeepSeek Harness — matched by git remote URL, repo path, or cwd prefix; worktree-aware; never committed to the repository.
Local prompt-injection and secret-exfiltration firewall for DeepSeek Harness
Quick prompt templates for DeepSeek Harness: global and per-session templates, a browser panel, and a pure-TS node:sqlite persistence backend
Claude-Code style CLI scheduling bundle for DeepSeek Harness headless: --append-prompt, --resume, --continue, --output-format json, and model overrides.
Obsidian-style [[wikilink]] mentions for the DeepSeek Harness web GUI: type [[ in the composer to fuzzy-search note titles and attach their contents to the prompt
需求锻造:需求澄清、提示词提炼与经验沉淀。把模糊的编程需求锻造成可执行规格,并在每次任务完成后沉淀为可自动复用的个人提示词模板库。
Multi-provider image, video, and speech generation, transcription, visual understanding, and prompt optimization with an integrated Iris workbench for DeepSeek Harness.
Conversation timeline dock bar for DeepSeek Harness: a turn-level timeline embedded above the composer, with user-prompt hover tooltips and click-to-jump back to the exact chat position.
DeepSeek Harness (DSH) plugin: removes the queued prompts a fork child inherits from its parent, so a new branch runs the prompt you type instead of the parent's next one.
面向 DeepSeek Harness 的科研 Agent 工作台:317 条工作流、86 个技能条目、122 个科学数据源,支持公开 API 直查与 DSH Agent/MCP 查询回退。
NoAtMark text hygiene as a DeepSeek Harness (dsh) plugin — sanitize untrusted text, scan invisible characters, clean LLM formatting, and escape CSV formula injection.
LLM auto-review approval answerer for DeepSeek Harness — decides sandbox escalations without a human prompt via a deterministic filter and a clean-context LLM safety review. REQUIRES a patched harness core (see core-patches/)
DSH multimodal input plugin: route file attachments (images, video, audio, text) through per-preset model chains and feed the results to the session model as prompt tokens. Adds a Multimodal settings page.
Image2 (gpt-image-2) generation plugin for DeepSeek Harness with simple relay settings, in-conversation previews, a chat-dock studio (text-to-image / image-to-image / multi-view character consistency) and a reusable prompt/flow preset library. Community fork of JuneLearn/dsh-image2-draw with gateway compatibility fixes.