Plugins

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

Proactive associative memory for DSH: zero-prompt recall injected at a fixed boundary, three-layer auto-consolidation, skill crystallization, and Astra-style context management - handoff ledgers and a PLAN whiteboard that survive context-window switches, water-level sensing with an auto-detected model window. Local Markdown storage, model-agnostic, zero deps; lexical 0GB floor with optional semantic tiers.

Filters tool outputs, prunes stale context and discloses skills on demand for DSH 0.2.1-alpha.1.

Context engineering and token optimization plugin for DeepSeek Harness (DSH): tool output filtering, context pruning and progressive skill disclosure for LLM coding agents

Connects Qoder (China and Global) subscriptions to DSH through personal access tokens, keeping each variant on its own credentials and catalog, with saved-token switching, sidebar quota cards, per-model toggles, a context-window preference and a daily check-in.

Match context windows for configured DSH models in one click, show capacity sources, and support selective bulk configuration, manual editing, and continuous synchronization.

Per-round thinking-level (reasoning_effort) control for DeepSeek Harness: pick Auto and it schedules low/high/max from the recent tool-call history, or fix a wire level (off/on/minimal/low/medium/high/xhigh/max) manually, with custom wire mapping, a model-aware capability guard, and context-window presets (64K–1M); its per-model capability card pairs with a separate plugin, [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (installable from dsh-market), so custom OpenAI-compatible gateways (vLLM / LM Studio / self-hosted) can try reasoning — the card writes llm-pi-ai capabilities, the adapter drives the wire (compat.thinkingFormat), and this plugin auto-maintains the takeover list.

Terminal-style input history for the web composer: edge-first arrow-key recall with exact draft/caret restore, browser-local persisted history, Ctrl+R reverse search, and sliding-context awareness; 0.5.0 adds a smart input layer — cross-session snippets (/save, /load), prompt templates with variables, reuse insights, and compaction-summary highlighting.

DeepSeek Harness plugin that turns Jev judgments into three automatic actions — pruning oversized tool output to the segments relevant to the request, screening fetched pages for instructions aimed at the model, and picking which skill fits the next step — plus the jev_ask and jev_gate tools, a judgment ledger that survives restarts, and a /jev-status report. Needs a TypeSafe API key; without one it is inert and sends nothing.

Progressive-disclosure MCP gateway that searches large remote catalogs through `mcp_search`, then invokes exact schemas through `mcp_call` with lazy connections and bounded caches.

Wraps work in named tasks and, once a task closes, folds its whole span of messages into one summary at the next step boundary; the original content can be restored on demand.

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.

DeepSeek Harness adapter for Context Mode: in-process ctx_* tools for sandboxed code execution and an FTS5 knowledge base, plus context-window routing guidance.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

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

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.

Hierarchical Claude Code-style memory: user + project scopes (project memories committed to git for the team), MEMORY.md index auto-injected at session start, context-window guards, pure files.

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.

A biomimetic memory plugin for DSH that folds context into token clues and reconstructs memories on-demand.

Context indicator for the DeepSeek Harness composer: segmented occupancy, compression points, and the native auto-compaction line (flashes red when crossed). Supports preview-then-confirm compaction (/bc), seamless handoff (the old session becomes "History N" while the new one keeps the name; a relay bar above the composer shows the full handoff chain with two-way jumps), and message pinning with stale-pin labels. Thresholds, colors, and auto-archive after handoff are configurable in Settings.

Forgetting-curve in-place dialogue compression for DeepSeek Harness: recent turns stay verbatim, middle turns are structurally dehydrated (zero-LLM), ancient turns fold into a bounded summary pair — unbounded conversations on a bounded memory budget.

Adds a squeeze tool: the agent hands a long web page, a batch of pages, a text file or a text PDF (via pdftotext) plus one question to a helper model and gets back only the answer, so the material never enters the chat. A settings page picks up to three helper models from the DSH model list, each with a nickname, a fixed thinking level and a "when to use" note, with optional fallback and size limits taken from each model's context window.

Community-maintained WorkBuddy and WorkBuddy AI model provider using local desktop sign-in, with model discovery and credit display. Version 0.1.17 supports per-model context-window selection and DSH 0.2.1-rc.2, rc.3, rc.5 and 0.2.2-rc.1; its CN compatibility layer differs from the functy23 fork. Derived from corrinehu/dsh-workbuddy-connect (MIT), it registers the same workbuddy / workbuddy-ai provider ids, so it cannot be enabled together with the original or other WorkBuddy bridges. Version 0.1.12 requires authenticated Host owner access for status and control routes.

Stops DeepSeek Harness from compacting (summarizing) your conversation far too early. Without it, compaction fires around half-full on smaller context windows; with it, compaction waits until the window is as full as you want (80% by default), settable per provider/model. It only changes when compaction happens — what a summary keeps is still DSH’s decision.