DeepSeek Harness Plugin Hub
← Plugins

dsh-qwen38-ninfer-compaction-fix

Qwen38 Ninfer Compaction Fix

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

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:zhubaohi/dsh-qwen38-compaction-fix#8ee6e7ba85d7db02fe2308c2ec0c4a90aac089b9

Compatibility and provenance

Qwen38 Ninfer Compaction Fix is published as dsh-qwen38-ninfer-compaction-fix and currently resolves to version 1.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
github
Registry updated

Versions

1.1.0stable

Related plugins

More verified plugins in models-usage.

Whale Widgetdsh-whale-widgetA small DeepSeek balance whale widget in the bottom-right corner of the DSH Web interface, featuring today’s usage, peak/off-peak pricing, random lines, sound effects, and per-round usage statisticsDeepseek Harness Walletdeepseek-harness-walletLocal-first DeepSeek Harness control center for balance monitoring, usage accounting, custom third-party API pricing, a 365-day local token ledger, Z.ai Coding Plan quotas, official pricing sync, encrypted multi-account switching, reminders, recharge, andUsage Stats@ychris12138/dsh-usage-statsToken usage heatmap, provider balances, and subscription quotas for the dsh web GUICodex Connectdsh-codex-connectChatGPT OAuth and Codex models for DeepSeek Harness.