216 results
DeepSeek Harness LLM User-Agent/header injector with key pool round-robin: keeps the official llm-pi-ai adapter, re-injects user-agent, and supports multi-key rotation per provider. | DeepSeek Harness LLM 请求头注入器 + Key 轮询：保留官方适配器，补回 User-Agent，支持按提供商多 Key Round-Robin 轮询。
Cross-session self-learning memory for DeepSeek Harness, ported from XT-AGENT packages/memory. BM25 relevance injection + background extraction (sanitize/dedupe/merge) + lifecycle archive + memory_read/memory_search/memory_write tools.
Control which tool schemas are injected into the DeepSeek Harness model context. Registers a tool_visibility manager tool AND a settings-page UI (Settings → 工具注入控制) with per-tool toggles; backed by the framework-native tools.restrict filter and persisted to a JSON state file.
DSH plugin that injects an editable section into the global system prompt, with a settings page to customize it.
DSH plugin that forces the agent's chain-of-thought and reasoning to stay in Chinese via a per-step system-prompt injection — 让 Agent 的思考过程也自动使用中文
Inject a user-configured custom prompt at the very top of every session's system prompt; editable live from the web settings page
Deterministic two-level memory injection for DeepSeek Harness: global and project MEMORY.md plus today's notes, auto-loaded into every new session.
DeepSeek Harness (dsh) plugin: manage named roles, each with a preset system prompt. The active role is injected into the system prompt (replacing it before the conversation starts, appending afterwards). Ships a host service plus a Web client UI.
Secure credential vault for DeepSeek Harness: store GitHub/npm/API tokens (secrets never leave the host), run gh/npm/npx/node/git with the token injected in the environment, and manage tokens from a Settings page.
Codex-style text annotation for DeepSeek Harness conversations: select text, add a quote with your comment, inject it into the composer, and expand sent annotations as a pill. / Codex 风格对话文字批注：选中原文加注释、引用进对话、发送后以「N 条注释」胶囊展开。
Declutter the DeepSeek Harness chat: hide agent execution-log rows (Think / context injection / tool calls), tighten message spacing and font sizes, wrap messages in rounded-corner bubbles, and inject an editable "reply concisely" instruction into the system prompt.
Static trust audit for DeepSeek Harness plugins: capabilities, injected prompts, token cost, provenance, and a reproducible 0-100 trust score
Ponytail (lazy-senior-dev) as an always-on DSH plugin: injects the spec every response and mirrors the five companion skills into ~/.dsh/skills. Attribution: github.com/DietrichGebert/ponytail (MIT).
Inject a neofetch-like device info block (host, OS, kernel, arch, CPU, memory, uptime, timezone, locale, shell, node) into each brand-new DeepSeek Harness session once; existing sessions are untouched.
Restyle pwsh tool-call cards in DSH session replies (CSS-injection + optional DOM decoration), modeled on dsh-file-mentions
在每次会话开头固定注入一段用户配置的文本上下文（设置页输入框可编辑），作为模型可见的 instructions 注入第一轮请求。 | Injects a user-configured text block as model-visible instructions context at the start of every DSH session (editable from the settings page).
Inject Context for DeepSeek Harness (DSH): persist your own context entries and inject them as a standalone 'Remember:' row — right after your message — per turn or once per session (per-entry 'Every turn' switch). Simple/Advanced datasets, native Settings editor, standalone manager page.
会话注入门控：给 DeepSeek Harness (dsh) 加一个会话级上下文裁剪闸门，按会话取消/恢复插件贡献的 skill、tool、系统提示词段落——3 条影子通道、5 条本地路由、零依赖零配置。Per-session injection gate for DeepSeek Harness (dsh): trim skills, tools and prompt sections per session. Zero-config, zero dependencies.
Hindsight long-term memory for DeepSeek Harness: auto-recall context injection before each agent step (agent/pre-step) and auto-retain of each finished turn (session/event).
Fix the DeepSeek Harness Web GUI over plain HTTP on a LAN: injects a crypto.randomUUID polyfill (getRandomValues-backed) before dsh bundle code runs. No official source changes needed.
DSH bundle: re-inject KEY/PASSWORD/SECRET/TOKEN variables from the launching environment into dsh bash subprocesses under their original names
Custom CSS injection for DeepSeek Harness — a Settings section with an on/off toggle and a CSS textarea injected live into the Web GUI
Glob-activated rule prompts for DeepSeek Harness (DSH): when the agent reads or edits a matching file, the rule activates and is injected into the conversation (Claude Code rules.md / # Path: style).
Add mood-aware Japanese kaomoji to DeepSeek Harness (dsh) replies; prompt-injection plugin with a curated library from kaomojiya.org.