dsh-context
A DeepSeek Harness plugin for context insight and management, with context dashboard and context command, for understanding how the context is made of, and how it evolves.
32 results
A DeepSeek Harness plugin for context insight and management, with context dashboard and context command, for understanding how the context is made of, and how it evolves.
DSH 上下文注入审计插件:统计 AGENTS.md 指令链 / 技能目录 / 工具 schema / MCP 工具的 token 成本,检测重复与冲突;原生 Context Doctor 面板 + context_audit 工具。
Context7 up-to-date library documentation for DSH: context7_search / context7_get_docs model tools backed by the Context7 Public API v2 (context7.com).
DSH context-window relief: knowledge base (ctx_index/search), routing enforcement (deny flood tools), sandboxed execution (ctx_execute/batch Think-in-Code), and session continuity (post-compaction restore).
Observe-only provenance ledger over public DeepSeek Harness runtime evidence
DSH context console with trajectory, prompt/skill/MCP/tool inventory, message forging, and conservative session-log recovery.
Inspect, measure, search, and compare the exact provider-neutral context assembled by DeepSeek Harness.
Thin on-demand context-retrieval layer for DeepSeek Harness: context_query / context_slice / context_grep tools over the sessionQuery and subprocess seams.
DSH plugin for semantic code search via Milvus vector database
上下文工程:按层级(规则文件→规格→源码→错误输出→对话历史)主动策划 agent 看到的信息,提升输出质量。受 addyosmani/agent-skills(88k★ MIT)启发。
DSH 会话上下文统计面板:统计每个会话的消息数、轮次、工具调用、字符数与预估 token,生成全量/按项目上下文报告,帮你看清上下文消耗大户。Context usage dashboard for DeepSeek Harness — per-session message/token statistics and context reports (zstd + plaintext logs).
会话上下文分诊插件:为 DeepSeek Harness (dsh) 自动筛查过期与冗余的上下文内容,以判决式处理节约 token 预算。
Native Context Graph and budget-aware context injection plugin for DeepSeek Harness
Context compression for small-context models on the DeepSeek Harness Web GUI: one click condenses the whole conversation into a few sentences, opens a fresh session in the same workspace, and re-injects the summary as the first message so a small model keeps working with a clean, compact context.
Deterministic privacy-aware repository context packs for DeepSeek Harness
Token-efficient tool-result pruning policy for DeepSeek Harness presets.
Real-time context occupancy meter for DSH Web: draggable compact/detail panel, per-tool usage, settings-editable cost table (CNY/USD, flat or peak/off-peak), per-provider usage and token totals
Structured context for DeepSeek Harness: split the conversation into typed sub-contexts (reasoning / tool calls / replies) and index them with a table of contents. 结构化 dsh 上下文:按类型拆分小上下文(思考/工具调用/正式回复),以结构化目录为索引。
Model-driven context-window rollover bundle for the DeepSeek Harness: fresh working context, durable model-managed notes, a small verbatim recent tail, and targeted history recovery — no summarization.
Windowed, reversible context management for DeepSeek Harness; replaces Basic compaction.
对话上下文面板:在布局左/右区域展示当前对话用到的技能、规则、文件
Reusable trajectory-tree context, exact-turn forks, and bounded cross-session recall for DeepSeek Harness
Keeps a local model's context at a size the GPU handles well: measured prefill speed, hard ceiling, early compaction for DeepSeek Harness
DSH plugin for AST context compression, test log filtering, and token budget guard