Plugins

Context window auto-management for DeepSeek Harness: when the window fills up it rolls over to a fresh one with zero summarization model calls, archiving the old window verbatim for line-by-line recall; handoff anchors carry task orientation, working notes survive compaction, and a stale-notes gate warns instead of vouching for outdated notes. The trigger follows the provider budget equation (window - max_tokens) and the real routed model even after a mid-session switch. One-click composer button plus /smart-compact, three-band automatic rollover, mandatory anchor sanitization; works out of the box.

Model-autonomous context compaction for DeepSeek Harness: a mind_map tool surveys the agent context surface (stable seq ids, roles, token weights, clear-boundary markers, the clear-mind playbook), a clear_mind tool replaces a chosen conversation-history span with a model-written checkpoint through the native compaction transaction, call and result pairs self-collapse into one-line tombstones, and a proactive reminder nudges the model when the context grows long or a turn runs too many steps.

Forces context compression when running low-context llama.cpp models such as Qwen3.8-27B, improving model efficiency and usage smoothness, together with well-refined compaction prompts.

Tool-call discipline for DeepSeek Harness with behavior prompts, failure-driven concurrency reduction and retry guidance, post-write checks with backup rollback, high-risk command gates, change summaries and verification reminders, advisory project-memory checks, configurable project-discipline reminders after compaction or at intervals, and compliance statistics.

Auto-resume for interrupted agent sessions: an ordered rule table routes by failure type (rate limit, quota, auth, context overflow, crashed orphan) to automatic backoff retry, model switch, resume after context compaction, or a stop-loss notification, with a visual rule editor and a full activity log.

Replaces the dsh compaction backend with a Codex-style window reset: the checkpoint is a handoff assembled from the session log by code, not a model-written summary, so a reset costs no summarization calls. A task ledger with a two-check gate keeps intent, next steps and the files still in play across resets, and a new_context tool lets the model reset on its own. Re-declares the four built-in agent presets (standard, ptc, minimal, cordis) exactly as shipped in dsh 0.2.2-rc.1, so re-run sync-presets.mjs after a dsh upgrade; idle cache keepalive is on by default and sends real requests that use quota (keepalive: false turns it off).

QQ (NapCat / OneBot 11) bridge for DeepSeek Harness: chat with your harness from QQ, with persona presets and custom personae, a grouped sticker library plus web sticker search, edge-tts or custom HTTP TTS voice notes, pluggable lookup engines, periodic memory compaction, an owner-only relay mode, and an eleven-tab management panel with live monitoring and per-turn cost tracking.

Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.

DeepSeek Harness plugin that aggressively saves tokens without affecting task quality: lossless head/tail truncation of tool results (default), grep-result folding, pressure-triggered dsh-compaction-basic delegation, and an LLM-summary CompactionEngine subclass for the aggressive mode. Saves 97.6% of input tokens on an 8-scenario synthetic suite, with all reductions routed through dsh event flow so model-visible = logged stays intact.

Vision for text-only DeepSeek via Doubao Web by default (zero-cost, no API key — drives your logged-in Chrome through a Windows CDP bridge), with Antigravity IDE quota (flash/pro) or Gemini fallback; auto detail escalation, vision evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

Import claude-code / codex / reasonix / zcode chat history into dsh sessions: workspace binding, tool calls preserved, oversized-session protection, zcode compaction restore.

Splits New Session in the DSH web sidebar into two modes: a 日常聊天 row opens a session on the `daily` agent preset the plugin installs into the harness home (persona, web search and fetch, ask-user and compaction — no files, shell, plan mode or subagents), inside its own daily-chat workspace whose sidebar region lists only those chats, while 开始工作 keeps the shipped coding agent; the built-in New Session button is hidden and every other New Session entry point follows the active mode, which is remembered in localStorage.

Lossless context folding for DeepSeek Harness: the oldest span is replaced by a brief, and the originals stay in the session log.

LLM-free lossless* compaction engine for DeepSeek Harness

Takes over the compaction threshold on every mounted engine: forces headroomTokens to -1e6 so the ratio is the only term in the trigger, keeps retention below it on every write path, reroutes the compaction call to a chosen model, and adds a panel with a one-click compaction button and a per-session compaction log.

Make your dsh ready for serious coding. (Tools x Schemas)^REPL. `skill://`, `ctx://`, `agent://`, `dvc://`, `dsh://`, IPython REPL, Context as Variables, cross compactions recallable, full context revive. `hash-edit`, `dvc://browser`, subagent as function, workflow as function.

Reads the files that AGENTS.md references with @path imports and injects their content into model context, with byte budgets, compaction re-seeding and a six-language settings card. v0.5.x expands the imports of every instruction file the harness loaded (including a project AGENTS.md picked up mid-session, needs DSH 0.2.0+) and offers an opt-in live mode (off by default) that watches injected files and re-injects them on change, with settings-page controls; use 0.2.x on DSH 0.1.7.

Make your dsh ready for serious coding. (Tools x Schemas)^REPL. `skill://`, `ctx://`, `agent://`, `dvc://`, `dsh://`, IPython REPL, Context as Variables, cross compactions recallable, full context revive. `hash-edit`, `dvc://browser`, subagent as function, workflow as function.

Context Assembler plugin for DeepSeek Harness: topic-block context assembly, water-pressure topic splitting, tool trace/rewrite, reality recall injection and handoff planning.

Automatic context compaction: a background observer distills early history into summary blocks, and when usage crosses the trigger line the engine commits whole blocks until it is back under the target line, with no model call on the commit path. Blocks merge into higher tiers as material runs out, and decompress or search_context reads any block back at its original length. The background observer spends model tokens: it uses the session's provider and model unless you pick another, with up to 10 distillations at once by default.

DSH 长期记忆插件：上下文超过阈值时把最早的一段对话归档进 memory/ 回忆文件夹，之后按关键词与重要性概率自动回忆。 · DSH long-term memory: archives the earliest context into memory/ folders and recalls it by keyword probability.

Replaces the built-in DSH compaction summarizer with a five-section handoff summary and keeps every shadowed message readable in a segment directory.

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.

Session handoff & context management: structured handoff documents (export/resume/status) so a fresh session can continue seamlessly, plus active context pruning (acp_* tools via the official compaction API with model-authored summaries).