zhubaohi/dsh-qwen38-compaction-fix
Compaction fix for NInfer-hosted qwen3.8-27b gateways: disables thinking on dsh context-compaction and session-title calls so xhigh reasoning stops burning the whole output budget; the same idea applies to other launch methods, this package targets NInfer only.
About this plugin
Fix for a local qwen3.8-27b gateway running on the NInfer engine that fails to compact. The model thinks at xhigh, spends the entire output token budget on reasoning before reaching a conclusion, and the compaction checkpoint comes back truncated. This DeepSeek Harness (dsh) plugin disables thinking for compaction calls only and applies, to those calls, the sampling parameters the model recommends when thinking is off.
$ dsh plugin --profile web add dsh-qwen38-ninfer-compaction-fix$ dsh plugin --profile web add github:zhubaohi/dsh-qwen38-compaction-fixHealth breakdown
57 / 100Score reflects license, community signals, documentation and distribution. It is not a code audit — review the source before installing.
Security
Key metrics
Related
Related plugins
Adds /pua to steer the agent to try another approach and verify results before claiming completion, with 15 company styles, persona modes, global and per-conversation settings, and an optional loop that continues until a verification command passes, the iteration limit is reached, or the user cancels.
Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.
Adds a summonable domain-expert roster that runs as subagents while the parent session keeps the task and final answer.
Layered memory for DSH whose agent-facing surface is 10 tools: high-privilege writes (memory_add, memory_delete, memory_import), rumination controls (memory_ruminate, _cancel, _status), and a memory graph (memory_search_graph, memory_expand_graph_node), built over an L0-L3 distillation pipeline that recalls and injects relevant memories before each model step.
White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.
Shared real browser for DSH: a native Electron window the human can watch and take over, driven by the agent over CDP with 20 browser_* tools (open/snapshot/execute/fill/screenshot/download/auth), per-task session isolation, cookie persistence, CAPTCHA detection; self-hosts on plain dsh web without a desktop shell.