dsh-plugin-langfuse
Langfuse observability for DeepSeek Harness: OpenTelemetry traces, compaction, feedback Scores, and fork lineage
28 results
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
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)
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.
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
Model-authored context pruning for DeepSeek Harness through the official compaction API.
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.
DSH plugin (NInfer engine only): fixes compaction failure on local qwen3.8-27b gateways served by NInfer — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters; the same idea applies to other launch methods
dsh-plugin: OMP-style ingress shaping plus optional local /fast-compact. Can replace DSH /compact and auto-compaction with a mechanical fold.
Token-efficient tool-result pruning policy for DeepSeek Harness presets.
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.
Auto-compact a DSH conversation after the current task finishes, at a user-set context threshold. Settings-page switch + slider included.
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.
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.
Windowed, reversible context management for DeepSeek Harness; replaces Basic compaction.
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.
Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.
High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.