65 results
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.
Keeps a local model's context at a size the GPU handles well: measured prefill speed, hard ceiling, early compaction for DeepSeek Harness
Workspace History: journals every compaction summary to <workspace>/.dsh/history/<unix-ts>.<short-session-id>.md, and adds a History subtab to the Workspace Overview tab for reading the journal. Per-session toggle lives in the granular Settings tab — requires dsh-granular-settings (hard dependency).
Chat branch tree plugin for DeepSeek Harness: mind-map of conversation branches, group folders, archiving and compaction preview.
Durable DeepSeek Harness bundle: the local-model performance tuning carried as a re-installable plugin layer (compaction, tool-result pruning, time context, cloud title routing, text-toolcall guard) — survives dsh updates
High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.
自动上下文策展：tool 输出瘦身 + 无效日志清理 + 工作流/记忆钉扎保护 + 先归档后压缩
Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.
Adaptive task and risk routing, loop budgets, and progressive tool-result pruning for DeepSeek Harness
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.
DeepSeek Harness plugin: aggressive token optimization without affecting task quality. Trims tool results, manages context window pressure, optional LLM-summary compaction, stable prompt-cache layout.
Persistent task state and context-aware compaction for DeepSeek Harness coding sessions.
Composer control for DeepSeek Harness auto-compaction: set a percent (30–80) or absolute token threshold that persists in settings.yaml.
DSH plugin: Codex-style context management — token-budget notice, model-facing new_context, and handoff reset instead of summary compaction.
Keep native vision, drop historical images before they hit relay providers. Global DeepSeek Harness bundle for every agent.
Idle-triggered context compaction for DeepSeek Harness: compact a session once it has gone quiet past a token floor