dsh-memory-search-plus
Local, storage-bounded cross-session search for DeepSeek Harness conversations with SQLite FTS5, Chinese segmentation, and message-level jump targeting
1041 results
Local, storage-bounded cross-session search for DeepSeek Harness conversations with SQLite FTS5, Chinese segmentation, and message-level jump targeting
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.
RTK command rewriting suggestions + tool output compaction for DSH. Suggests rtk-rewritten bash commands (deny-mode under rewrite) and compacts noisy tool output (bash/grep/read) to reduce context usage. Port of pi-rtk-optimizer for the Pi coding agent.
Curated Irmia DevKit tools ported to the DeepSeek Harness: safe_edit / safe_rollback / multi_edit / http_get / http_post / code_index / code_explore / code_diff_impact / db_query.
Browsable, searchable, stats-driven directory of GitHub DSH plugin repositories, rendered inside the DSH Web GUI settings.
Vision + Android UI automation plugin for DeepSeek Harness: gpt-5.6-luna screenshot understanding and real-tap mobile app testing via adb
DSH web plugin: theme customization placed under the built-in Appearance (外观) settings. It reuses the Appearance light/dark switch and lets you adjust accent / background / foreground / contrast for the active theme, applied live through DSH theme token overrides.
Multi-agent orchestration and LLM model routing for DeepSeek Harness (DSH): semantic AI agent Specialists, exact model routes, declarative Cohorts and Strategies, and bounded subagent delegation.
General APEX preset with a Minimal Pro anchor, role-bounded PTC implementation, verified handoffs, and evidence convergence
Model-facing typed tools wrapping the frozen, reviewed underseal adapter for the DeepSeek Harness
Zero-dependency scientific computing tools for DeepSeek Harness: physical-unit conversion, CODATA physical constants, and Runge-Kutta ODE/dynamical-system simulation. No core changes.
Token usage statistics for the DeepSeek Harness Web UI: captures per-request LLM usage from the llm/stream waterfall, persists it, and renders animated charts grouped by API (provider), model, and date.
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.
Retrieved ≠ injected: CBDC-gated memory for DeepSeek Harness — decides how memory is USED (use/verify/ignore decisions, feedback learning, full audit); local SQLite + FTS5, bounded, no extra model call
QuickJS/WASM-isolated WorkflowEngine for running model-written DeepSeek Harness orchestration with bounded resource controls.
Privacy-safe local activity scanner and agent preset recommender for DeepSeek Harness
AntV Infographic renderer for DeepSeek Harness: render AI-generated infographic fences inline with streaming, editing, and SVG/PNG export.
Background stream listeners that wake the DeepSeek Harness agent — put a watch on a command or file and receive new lines as in-session notices. Ships a daemon host so a watcher can run unattended for weeks.
DSH web plugin: per-workspace background, chat font size, line height, block spacing, and Retina font rendering.
梁文谷提醒:按 DeepSeek API 定价高峰/空闲时段(北京时间)提醒——峰前喊快跑、峰走喊开谷。右下角卡通弹窗 + 浏览器系统通知 + 提示音。
Content-addressed audit indexes across independent DeepSeek Harness evidence producers
Self-maintaining handoff.md per working directory + git branch for DeepSeek Harness, stored under ~/.agent/agent-handoff (shared with pi-handoff).
DSH session completion notifier: appends a plugin system message to the session log on turn/end and pushes browser notifications (Web Notification + toast) with custom per-reason image/icon/alert-sound, plus a fully customizable official settings panel (presets, 5-language templates, cache-hit rate & tok/s from official projections).
Keep Think reasoning rows visible and auto-expanded, and always force Chinese thinking and replies. 保持 Think 思考行可见并自动展开,并始终强制中文思考与回复。