dsh-session-pruner
会话生命周期管理:one-shot 完成归档/删除、可续与主会话闲置归档、容量保底、连带清理 projcache——全类型生命周期管理。
98 results
会话生命周期管理:one-shot 完成归档/删除、可续与主会话闲置归档、容量保底、连带清理 projcache——全类型生命周期管理。
Cost dashboard for DeepSeek Harness - model spend, tokens and cache usage across all sessions (settings section). DSH 费用看板:汇总全部会话的模型输入/输出/缓存 token 用量并按价格表计费。
DSH web plugin: pick skills from a sidebar tab — list every installed skill with global/local badges, LLM-generated descriptions (cached, never touching skill files), and inject the /skill gesture into the current session composer on check.
In-place three-decimal cache-hit percentage plus a widened composer stats line for DSH Web.
DSH 插件:把 Kimi WebBridge 浏览器控制能力封装成原生模型工具(webbridge_*)。官方 bundle 插件,dsh plugin --profile web add 安装。
Cache-stable progressive tool discovery and dispatch for DeepSeek Harness
Cache-aware Harness Alliance Mode for DeepSeek Harness with DSH-routed Claude Code, Codex, and Kimi Code execution.
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。
DSH recap plugin: distills every model request (turn:step) of a session into one sentence, appended incrementally with a cache-friendly prompt (history sentences first, new delta last). Side-effect-free for the agent loop.
Full wigolo integration for dsh: WebSearch/WebFetch providers with configurable takeover, 7 wigolo_* agent tools (search/crawl/extract/research/find_similar/cache/watch), a sidebar config panel, and cordis-managed provider routing.
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.
Remote multi-server GPU status board for DeepSeek Harness Web: read-only nvidia-smi over SSH with ControlMaster-muxed connections, a host-side cached snapshot, per-server selection, and gpu_overview / gpu_refresh agent tools.
Agent FinOps / token analytics for DeepSeek Harness: usage collection, time-aware cost engine, cache analysis, and session drill-down
Reasonix-style cache-aware compaction backend for DeepSeek Harness (DSH). Replaces/enhances compaction-basic with compact_ratio, one structured summary checkpoint, and a stable recent tail.
DeepSeek Harness (cordis) client plugin: a right-side session stats panel showing average cache-hit rate, session cost, runtime, request count and cumulative tokens (DeepSeek pricing).
为 DSH read 工具提供版本令牌校验的进程内结果缓存:未变更文件的重复读取跳过文件 I/O 与重渲染,并附带 readcache 工具查看统计与清空缓存。
Auditable usage, cost, token, cache, balance and pricing analytics for DeepSeek Harness.
Prompt-cache observability and logical-input diagnostics for DeepSeek Harness
Adaptive Reversible Context (ARC) for DeepSeek Harness — provider-aware, cache-conscious context governance with reversible recovery.
LLM cost tracker for the DeepSeek Harness: bills every model call from provider token usage (cache hit/miss included), shows per-call cost in the conversation stats line, a per-session summary, and a CC-Switch-style usage statistics dashboard
A DeepSeek Harness plugin: model-facing reload_plugin tool that restarts one Cordis Loader entry (by entry id, module name, or MCP serverName) without touching sibling entries — respawns mcp-client server processes and hard-reloads in-process plugin code (ESM/CJS cache bust + fiber swap)
DSH web plugin: a 技能 (Skills) tab in the dsh-better-sidebar right panel that lists all locally readable skills with short Chinese descriptions. Persists a cache so the list appears instantly on startup, auto-adds newly installed skills, and re-scans all skills every Monday.
Cache-prefix stabilization and evidence-based cache metrics for DeepSeek Harness
Token usage / cache-hit / duration report cards for DeepSeek Harness sessions, with optional cost estimation.