dsh-clear-tool-results
DeepSeek Harness host plugin: archive raw tool results into the session folder, clear them from the visible conversation at round boundaries, and let the model recall them through a read_tool_result_log tool.
120 results
DeepSeek Harness host plugin: archive raw tool results into the session folder, clear them from the visible conversation at round boundaries, and let the model recall them through a read_tool_result_log tool.
Manual budget-targeted context compression for DeepSeek Harness: the conversation model picks ranges, a cheap flash-tier route writes the checkpoint summaries.
Tiered micro-clear layer for DeepSeek Harness compaction: clears whitelisted re-runnable tool results to placeholders before the official summarization tier, freeing context with no model call.
Compact, searchable, tag-based agent preset management for DeepSeek Harness
DeepSeek Harness plugin: multi-tier memory management, semantic retrieval, structured memory, and model-context awareness for infinite context.
File-defined subagent roles for DeepSeek Harness: project (.dsh/roles) and global (~/.dsh/roles) role files, a compact role catalog, and real per-role tool filtering.
官方回合折叠模式为 Compact 时,打开会话自动加载全部历史,让官方原生回合折叠立即生效:不新增折叠行、不接管官方设置、数据完整无偏差。When the official turn-folding mode is Compact, auto-loads the full conversation history on session open so the official native per-turn folding engages — no extra fold rows, no takeover, always data-complete.
Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.
Pure-incremental directive-driven compaction for DeepSeek Harness: /compact-directive <requirement> summarizes the session middle per your requirement, /trim-directive <requirement> trims the whole conversation per your requirement
Visual percentage and token settings for official DeepSeek Harness compaction
Token-efficient tool-result pruning policy for DeepSeek Harness presets.
AgentFrame compaction backend for DeepSeek Harness: semantic + physical KV compression (28.4x) replacing LLM summarization
Browser-style UI zoom for DeepSeek Harness and DSH Desktop — Ctrl +/−/0, Ctrl+wheel, and a compact zoom widget with a saved level.
Replace the DSH Web reasoning-effort chooser with a compact animated FX slider that scales with effort level.
Adaptive task and risk routing, loop budgets, and progressive tool-result pruning for DeepSeek Harness
High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.
DSH Web plugin: per-turn cost beside the native turn-usage pill, plus a per-reply Cost-stats settings page with calendar day/month pickers, fed by a host route that folds every stored session log (replies and context compactions alike). Official DeepSeek price tables (CNY + USD), peak/off-peak aware.
A compact DSH model and reasoning quick-switcher showing the last three choices.
Document-review modal for DeepSeek Harness web: design documents and plan reviews open in a full rendered-markdown modal instead of the compact composer card.
Model-scoped DSH plugin: GPT Responses lifecycle, Native V2 compaction and Hosted/Alpha Search; Grok native Web/X Search
提问面板折叠:agent 提问时把问答面板折叠成一条紧凑条(保留标题与取消),展开后回答草稿不丢。Collapse the DSH question panel into a compact strip; the unsent answer draft survives expand.
Idle-triggered context compaction for DeepSeek Harness: compact a session once it has gone quiet past a token floor
Per-route context window, compaction threshold, and per-model thinking-effort controls for DSH models. · DSH 模型上下文窗口、压缩阈值与思考强度设置。
Session health for DeepSeek Harness: real token-meter data, configurable continue-vs-new decision model. Reactive header badge (compaction-aware), /compass command, context_compass tool.