99 results
Read-only security & compliance toolkit for DeepSeek Harness: prompt-injection detection (rule engine with a pluggable model classifier), Chinese-PII redaction, and a local configuration security audit that emits redacted, reproducible risk reports.
System tray support for DSH Desktop: tray icon plus settings to hide the main window on minimize or close, with self-healing boot-time injection and an injection management panel.
Cross-session project memory for DeepSeek Harness: seven-layer SQLite memory, first-turn snapshot injection, per-message keyword hits, memory_remember/search/project tools, automatic reflection with reflection-fold UI, and idle-triggered dream consolidati
Native Context Graph and budget-aware context injection plugin for DeepSeek Harness
Indirect prompt-injection guard for DeepSeek Harness: taints tool output by origin and gates privileged tool calls that follow untrusted content
Agent observability plugin for DSH — behavior audit, cost tracking, anomaly detection
DSH plugin: a codex-style apply_patch tool (*** Begin Patch / *** Update File / *** Add File / *** Delete File) injected into the model toolset through DSH's built-in sandbox, with a settings card to choose injection scope (off / GPT models only / all models).
Global and workspace rules for DeepSeek Harness agents: configurable storage paths, system-prompt injection and a rules_read model tool.
对角巷 · 角色面具 — 一键切换AI人格，定制专属对话角色
Mem0 persistent memory for the DeepSeek Harness web profile — automatic recall injection, tidal-coalesced memory writes, and mem0_search/add/update/delete tools against a self-hosted Mem0 server (X-API-Key). Zero-intrusion bundle plugin; no dsh source changes.
OpenViking memory integration: Web Settings plugin card + automatic memory-context injection
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.
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
Deterministic two-level memory injection for DeepSeek Harness: global and project MEMORY.md plus today's notes, auto-loaded into every new session.
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.
Restyle pwsh tool-call cards in DSH session replies (CSS-injection + optional DOM decoration), modeled on dsh-file-mentions
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).
Custom CSS injection for DeepSeek Harness — a Settings section with an on/off toggle and a CSS textarea injected live into the Web GUI
Add mood-aware Japanese kaomoji to DeepSeek Harness (dsh) replies; prompt-injection plugin with a curated library from kaomojiya.org.
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.