dsh-context-clean
DeepSeek Harness 插件：可由模型调用的上下文压缩器，可从转录文本中去除重复词语、重复行和重复段落，同时不会丢失重要信息（数字、路径、代码、决策）。
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add dsh-context-clean@0.1.1Context Clean 以 dsh-context-clean 发布，当前版本为 0.1.1。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
English | Česky
A DeepSeek Harness plugin that exposes a model-callable context compressor:
context_clean. It strips bloat from a conversation or thinking transcript
while keeping the information that matters — numbers, paths, code, decisions.
Public, MIT-licensed. No runtime dependencies beyond the DSH tools peer.
| Bloat removed | Preserved |
|---|---|
Adjacent repeated words (the the the → the) | All first occurrences |
Consecutive duplicate lines (collapsed to a [… N×]… marker) | First line of each run |
| Repeated paragraphs/blocks (later copies dropped) | First paragraph of each block |
| Runs of blank lines (collapsed to one) | Section structure |
The compressor is deliberately conservative: it only drops exact duplicates (case- and whitespace-insensitive for paragraphs), so numbers, code lines, and decision text are never rewritten.
context_clean(text?, path?) — clean a transcript and return the compacted
text plus a one-line before/after summary.
text — inline transcript text (required unless path is given).path — absolute path to a text file to clean instead.The engine is a small Python script (scripts/clean_context.py) that ships
inside the plugin, so it works regardless of the session's working directory.
Python 3 is the only prerequisite.
dsh plugin --profile web add dsh-context-clean
After restarting the session, context_clean appears in the tool catalog.
python3 scripts/clean_context.py transcript.txt # file → stdout + stats on stderr
cat transcript.txt | python3 scripts/clean_context.py
MIT.