dsh-process-fold
Fold each DSH Web turn's thinking, tool calls and context into compact expandable process boxes cut at every piece of model text, and reuse the shipped turn-process disclosure row as the toggle whenever it exists.
120 results
Fold each DSH Web turn's thinking, tool calls and context into compact expandable process boxes cut at every piece of model text, and reuse the shipped turn-process disclosure row as the toggle whenever it exists.
Token-efficient tool-result pruning policy for DeepSeek Harness presets.
Codex OAuth provider with native compaction and image input support for DeepSeek Harness.
Web sidebar indicator: API key context headroom, account balance, and estimated turns until compaction
Save and load a compact, Git-tracked handoff for DeepSeek Harness sessions
Dual-pipeline compaction for DeepSeek Harness: official server-side Responses compaction v2 for OpenAI-routed targets, with a deterministic VCC-style local compiler (zero model calls) as the default fallback and for every other provider.
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.
Compact conversation turn navigation for the DSH Web client
Complete mobile PWA for DeepSeek Harness (DSH): secure LAN/Tailscale remote access gateway + install-to-homescreen (manifest), offline-capable service worker, touch-first gestures, agent-done notifications, and dark compact mobile UI. 移动端 PWA 完整方案 for DeepSeek Harness.
Auto-compact a DSH conversation after the current task finishes, at a user-set context threshold. Settings-page switch + slider included.
Routes manual /compact summarization to the frontend's currently selected model in DeepSeek Harness.
OpenAI Responses adapter and durable server-side compaction bundle for DeepSeek Harness.
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
DeepSeek Harness 会话健康度提醒插件:可拖动悬浮按钮,三因子健康度评分(上下文占用/压缩/缓存命中率)、token/耗时/步骤/压缩分析、亚健康一键生成 handoff
Context compression for DeepSeek Harness: engineer-handoff-note summarization backed by dsh-compaction-basic.
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, automatic context injection, an archive on clear, and an optional read-only web panel
DSH plugin: fixes compaction failure on local qwen3.8-27b gateways — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters
Minimal epoch bootstrap, full-tool promotion, and hard handoff compaction for DeepSeek Harness
High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.
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.
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
DSH /compact-and-branch command: canonical compaction into a fresh continuation session.
DeepSeek Harness 侧边栏用量/余额插件:在设置按钮上方显示简洁「用量/余额」标签行,悬停右侧展开玻璃详情卡(运行时长/Token/估算金额/官方账户余额),滑杆开关控制详情常驻。Sidebar usage/balance plugin: a compact label row above Settings with a glass details card (runtime, tokens, estimated cost, official balance) and a slide-switch pin.
Deterministic, recoverable tool-result compression and cache-aware compaction for DeepSeek Harness