context 75

OpenViking memory and context bundle for DeepSeek Harness

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.

ThoughtDAG for DeepSeek Harness: turn the current DSH session into an editable thought graph on an infinite canvas. Source, releases and issues: github.com/chenxiachan/thoughtdag

A bilingual floating pet for DeepSeek Harness with runtime status, context and lifetime token usage, trends, and optional completion sounds.

One-install context-compression selector bundle for DeepSeek Harness

Gives DeepSeek Harness three automatic Jev judgments — prune oversized tool output, screen fetched pages for injected instructions, suggest which skill to use — plus the jev_ask and jev_gate tools, a persistent judgment ledger, and a /jev-status diagnosis

A live context-window donut for DeepSeek Harness: token usage, compaction savings, and cost at a glance

Lossless context folding for DeepSeek Harness: the oldest span is replaced by a brief, and the originals stay in the session log.

Manage MCP servers, skills, and tools for your DeepSeek Harness agent — true in-context state (loaded/truncated/evicted) and per-session switches for every capability.

Claude Code-style @path imports for DSH: expands @imports in AGENTS.md/CLAUDE.md and injects the referenced files into model context at session start

Context compaction that keeps its receipts: a five-section handoff summary, a durable segment index, review tools that read compacted text back, optional working notes, and a read-only extraction exit. Mounts as the compaction-basic row's replacement; cha

dsh-plugin-appshot — a DeepSeek Harness plugin for macOS and Windows context screenshot capture.

User-side undo/redo for DeepSeek Harness (dsh): the /undo command rolls the transcript back to before the last message and /redo restores it.

Shows which graft index a dsh session is serving and whether it still matches the code, and gives the model graft_ask, graft_grep, graft_callers, graft_skeleton and graft_map as native tools.

In-process graph memory for DeepSeek Harness, backed by TriviumDB.

Progressive long-term memory for DSH: sharded markdown bodies under ~/.dsh/memory/topics/, with only a live-generated index (shard · count · path · per-entry line numbers) injected into the system prompt — so the prompt cost stays flat however large the m

会话级自动上下文压缩插件：回合中每步前 + 回合结束检测上下文用量，超过会话阈值自动 compact，摘要注入上下文后自然继续（DeepSeek Harness / DSH）

Per-message delete for DeepSeek Harness: remove a user message, one reply step, or a whole assistant reply from the derived model context through the official surface-replace contract, and hide it from the visible transcript without rewriting the append-o

DSH plugin for semantic AST code skeletonization and test/build log compression

DeepSeek Harness plugin: tells the model its real, host-measured context occupancy every turn — and keeps compaction summaries from carrying false "context is nearly exhausted" claims.

Minimal date line for the DeepSeek Harness runtime-context snapshot: 'Current date: 2026-09-08 Asia/Shanghai Tuesday' (46 chars, ~12 tokens) - a cordis host plugin, no dsh source changes, no PR required

Curate tool output before it enters the model's context: keep error/warning lines and head/tail, spill the full text to disk with a pointer. Faster turns, smaller context, sharper attention — for every tool, not just bash.

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.

Session context governor for DeepSeek Harness: prompt size and per-step cost in dollars (cache-read/cache-write aware), cache-hit, context bands, a per-session compaction threshold derived from the model window, DeepSeek balance and peak/off-peak tariff,

Manual context compaction for DeepSeek Harness: keep the latest N conversation items with stop or batch mode and a per-session compaction archive — embedded in the context meter popup when the meter panel slot exists, or a composer button otherwise.

Logical-call context taxonomy for the DeepSeek Harness Web profile

把 git 状态与仓库规范动态注入 system prompt：分支/脏文件数/最近提交 + 仓库规范指引（官方 system-prompt section/context/variable 缝隙插件）

Personal dsh preferences: a tunable companion to the official compaction engine (threshold, retention, summarization model/reasoning, turn-end compaction), llama.cpp model import for the Models page, and tab/notification helpers (status-light favicon, bro

Native knowledge context for DeepSeek Harness

Manual budget-targeted context compression for DeepSeek Harness: the conversation model picks ranges, a cheap flash-tier route writes the checkpoint summaries.

Jev-scored context compaction for DeepSeek Harness -- keep the messages that matter, compact the ones that do not

dsh 插件 · 上下文剃刀：把当前会话上下文逐条列出（角色/预览/≈token/占比，cl100k 估算），类型筛选与超阈值标红一眼锁定大头，勾选后精确裁剪——不经 LLM 总结，删了什么一目了然。

DSH context-pressure guard: when a session's next request would carry a dangerously large prompt, tell the user at turn end to write the handoff and start a new session. Consumes the official token-meter contextPressure projection; injects no prompt, regi

Model-autonomous context compaction for DeepSeek Harness: mind_map surveys the agent's own context surface (seqs, token weights, clear-boundary markers and the clear-mind playbook), clear_mind replaces a chosen span with a model-written checkpoint through

DSH plugin: mark messages as invalid so an operator annotation digest steers what a compaction checkpoint absorbs. Cache-preserving: appends after the cached prefix, never rewrites history.

Manual context compaction for DeepSeek Harness: keep the latest N conversation items with stop or batch mode and a per-session compaction archive — embedded in the context meter popup when the meter panel slot exists, or a composer button otherwise.

Sidebar meters for DeepSeek Harness Web: a DeepSeek account balance bar (orange, with a low-balance alarm) and a conversation context-usage bar (blue), rendered above the plugin store with a hover detail popover.

DeepSeek Harness 长会话守卫：检测思考循环和输出复读，按本地日志建议何时交接，并生成无需额外模型调用的交接文档

Model-free /trim for DeepSeek Harness — drop the oldest, least valuable span of context on demand (the `/trim` command) or automatically when a request hits the model's context wall, without any model call.

Focus board for DeepSeek Harness agents: durable, model-maintained notes in the session workspace that pin the objective, constraints, and decisions across compaction and sessions — with structured entry tags (kind/status), a grouped summary view, automat

DeepSeek Harness plugin: trims the oldest images from outgoing chat requests and, when the provider rejects the image count with HTTP 400, parses the limit from the error and retries with fewer images. · DSH 插件：裁剪即将发出请求中的历史图片，并在上游因图片数量返回 400 时解析该上限并按更少的图片

High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.

OpenViking memory and context bundle for DeepSeek Harness：自动召回、会话捕获、viking:// 保护与记忆工具，可在 DSH 设置中配置。

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).

DSH 插件：上下文构成诊断、重复/遮蔽检测、Token 排名与可回滚优化补丁预览

DeepSeek Harness plugin for bounded, provenance-linked context steady state with recoverable raw history

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。

在上下文监控卡片内直接调节自动压缩的触发阈值。host 半在运行时替换 @deepseek-ai/dsh-compaction-basic 已挂载引擎的 thresholdRatio 并持久化，client 半把滑块画进卡片面板。

Read-only DeepSeek Harness plugin that surfaces Claude Code's project memory, redacted and byte-budgeted

Context compression skill for DeepSeek Harness -- intelligent conversation summarization