115 results
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
Post-compaction premise-drift guard plugin for DeepSeek Harness: after a compaction summary drops a critical literal anchor (path, value, error code) it injects a one-shot notice telling the model what it may have lost and how to recover it from the log
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.
Web sidebar indicator: API key context headroom, account balance, and estimated turns until compaction
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.
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
OpenAI Responses adapter and durable server-side compaction bundle for DeepSeek Harness.
Codex OAuth provider with native compaction and image input support for DeepSeek Harness.
Minimal epoch bootstrap, full-tool promotion, and hard handoff compaction for DeepSeek Harness
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.
侧边栏模式外部插件：紧凑模式 + 右侧边栏 + 收起窄条（对话/Trajectory 竖排），三态持久化，收起/展开动画右锚定无漂移。
Token-efficient tool-result pruning policy for DeepSeek Harness presets.
Context compression for DeepSeek Harness: engineer-handoff-note summarization backed by dsh-compaction-basic.
High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.
Deterministic context-pruning compaction backend for dsh (DeepSeek Harness) — zero-LLM summaries, /dcp command, works out of the box. Design references Opencode-DCP/opencode-dynamic-context-pruning.
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
Windowed, reversible context management for DeepSeek Harness; replaces Basic compaction.
DeepSeek Harness host plugin: archive raw tool results into the session folder, clear them from the visible conversation at round boundaries (or per-step in overclock mode), and let the model recall them through a read_tool_result_log(turn, step) tool.
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.
Keeps long coding-agent sessions lean: wrap work in named tasks and, when one is done, fold its whole span into a short titled summary. The conversation stays readable, context costs stay low, and every fold's original content can be read back on demand. 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.
Compact, searchable, tag-based agent preset management for DeepSeek Harness
Compact conversation turn navigation for the DSH Web client
dsh-memory — cited memory over DSH's lossless session log: post-session distillation into human-auditable markdown files, a compact recall index, memory_read/memory_expand tools, and a dsh-memory CLI