dsh-kaomoji
Add mood-aware Japanese kaomoji to DeepSeek Harness (dsh) replies; prompt-injection plugin with a curated library from kaomojiya.org.
217 results
Add mood-aware Japanese kaomoji to DeepSeek Harness (dsh) replies; prompt-injection plugin with a curated library from kaomojiya.org.
DeepSeek Harness (Cordis) 插件:提供「自定义上下文」设置页并注入到模型上下文,支持落盘持久化。
Ponytail (lazy-senior-dev) as a mode-switchable, always-on DSH plugin: injects the COMPACT ruleset every step (off empties it) and mirrors the full ruleset + five companions into ~/.dsh/skills. Attribution: github.com/DietrichGebert/ponytail (MIT).
DSH plugin: mint issue tracking integration — session context injection, event reminders, plan binding, a zero-approval `mint` tool, and a session tab.
dsh-plugin: quality-first topic memory for dsh — a topic keeps the starting question, conclusion, impact and dependencies, not the process; local-first git-traced OKF bundle, budgeted LLM-free injection
DSH compatibility guard: repairs compaction limits, fail-safe sandbox escalation, and missing tool descriptions for third-party models; capability lookups are cached and the deprecated prompt-injection path is off by default.
Fix DSH web_search through OpenCode Go / Zen: auto-inject x-opencode-session. Drop-in patched fork of @deepseek-ai/dsh-web-search-deepseek (DeepSeek Harness).
mycel session state as a plain-text notebook: add_state / read_state / compact_state plus a focus task stack over per-session files under <cwd>/.mycel/state/<sessionId>/; survives compaction and resume, never auto-injected, writes zero session events
Browse archived DSH sessions and re-invoke them: view the transcript, inspect what a session touched, restore to the sidebar, inject into the current conversation, or fork a new session.
Auto-inject user-chosen skills into DeepSeek Harness sessions and harvest skills from other agent tool dirs (~/.claude, ~/.codex, ...) as extra providers.
User-only instruction memory for DSH: long-term instructions maintained in the settings UI and auto-injected into every conversation — the model has no write access. 指令记忆:只由用户在设置页维护的长期指令,自动注入此后每轮对话;模型没有任何写入口。
Multi-Agent collaborative skill forging system for DeepSeek Harness — distill conversational experience into verifiable, reusable skills with evolutionary optimization.
Keyboard shortcut that injects an encouraging message into the running dsh-TUI conversation: steer when a tool is in flight, interrupt-and-deliver when the model is only streaming text
NPM registry management for DeepSeek Harness: query package info, list versions, search packages, and publish/deprecate packages — registry info via HTTP API, publish via the npm CLI with optional token injection, plus a web settings panel
Inject Cursor-aligned project rules from .dsh/rules into DeepSeek Harness sessions
超级模组注入器:运行时注入任意本地 DSH 插件包(junction 链接 + loader.create,不碰 patch/package.json/不重启),热重载全家桶 + 开发侧挂区一键转正 + 一键卸载 + 路由自愈 + 插件管理 UI(设置页:列表/卸载/拖入内化),清单持久化重启自动恢复——DSH 生态的 BepInEx 式模组注入入口
One-click, cross-platform restart button for the DSH web GUI. The loopback-only host route relaunches the exact current DSH invocation; the browser half injects the button.
Layered, approval-gated, auditable cross-session memory for DeepSeek Harness — a capability seam (ctx.memory service + local SQLite provider + memory tool + frozen snapshot injection), not another memory warehouse
Order DSH-injected user-role context before the current human message
Third-party DeepSeek Harness plugin: per-workspace custom prompt configured from a slash command and injected into the model context at session start.
DSH plugin: inject a one-line hint naming skills that match the current turn, so installed-but-forgotten methodology skills actually get used. Deterministic matching, no LLM calls, fail-open.
DSH memory plugin gated by the TypeSafe Jev decision model: mem_* tools whose every read/write is a typed judgement (choice/noul) — write gate, recall gate and a fail-closed injection gate with budget, audit log and restore/merge.
Plugin dependency graph for DeepSeek Harness: which plugin provides the services every other plugin injects, read from the live Cordis runtime.
Frontend-injected per-model reasoning-effort (thinking strength) configuration for custom pi-ai providers. Registers a per-model 思考强度 editor into the Settings -> Models provider card and persists reasoningEfforts through the settings Remote.