67 results
Full session management for the DSH web UI: delete (with trash/restore/purge), restore archived sessions, activity stats, continue/pause, fork to a new chat, unread markers, and open log folders. Plus a global context compaction threshold. No harness changes.
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.
Terminal-style input history for the DeepSeek Harness web composer: edge-first arrows with exact draft/caret restore, browser-local persisted history, Ctrl+R reverse search, workspace-scoped recall, and fully configurable keys — plus sliding-context awareness (compaction summaries join recall/search, a compaction notice with one-click /compact fill) layered on the ordinary composer draft only.
Langfuse observability for DeepSeek Harness: OpenTelemetry traces, compaction, feedback Scores, and fork lineage
VCC-style instant, near-lossless deterministic compaction engine for the DeepSeek Harness — a drop-in replacement for @deepseek-ai/dsh-compaction-basic
One DeepSeek Harness Codex capability bundle for ChatGPT login, LLM access, Web Search, and durable Image Creation
A live context-window donut for DeepSeek Harness: token usage, compaction savings, and cost at a glance
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）
Third-party DSH WebUI enhancement plugin: custom backgrounds, theme colors, prompt presets, token visibility, and manual context compaction.
Context Assembler DSH V0.99 — Context Assembler plugin for DeepSeek Harness (dsh): context compaction, cache-friendly topic-block management, water-pressure topic splitting, tool trace/rewrite, handoff planning and reality recall injection.
DeepSeek Harness plugin that uses configured model providers for image analysis and context compaction.
Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph eviction (0-LLM) + byte-exact recall from an append-only log. 压缩率精确兑现，历史永不销毁。
为 DeepSeek Harness 极简模式增加自动上下文压缩、/compact、/context 和模型主动压缩，解决极简模式长任务无法持续工作的问题。
Context compression tool (context_compact): the agent writes the replacement checkpoint itself and hands it to the host compaction engine, which skips the LLM summarizer call; automatic compaction stays on the official engine.
Agent-driven long-term memory for DeepSeek Harness: scoped memory (global + per-workspace), layered entries (fact/knowledge/episodic), time-bucket compaction (day→week→month→year), associative recall (related chains) + memory_relate navigation (multi-hop BFS closure), auto recall injection on user messages (CJK bigram search, tail append), agent-decided content.
Windows minimal agent preset for DeepSeek Harness: a one-line fixed persona, gitbash + str_replace_editor + web_search, no runtime context, no compaction. Installs the preset into the user's agent-presets root.
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).
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 上下文自动压缩、手动压缩与溢出恢复插件
Agentic Surface Compaction (ASC) for DeepSeek Harness: the model decides when and what to compact, committed as durable session-log replacements with full replay, search, and degradation
Model-authored context pruning for DeepSeek Harness through the official compaction API.
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 automatic context injection, an archive on clear, and an optional read-only web panel
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）
元压缩：模型自己决定何时、如何压缩自己的上下文——列 surface、选区间、以自写文本替换；替换走官方 compaction 事务（检查点、配对平衡、可重建）。Meta-compaction: the model directs its own context compaction through the official compaction seam.