Plugins

Context compression for small-context models: visually configure the compressed context budget, default to an 8k handoff + 16k recent context, and keep full history searchable.

Compaction fallback for compaction-basic: when its LLM summary throws, comes back empty or cannot fit the window, the span is compiled deterministically with a seq pointer on every line (vendored dsh-compaction-instant compiler). Adds recall and search tools, /recall and /context commands, an idle trigger at 45% of the window and an on-disk span archive. The engine mounts as one row in the agent preset (docs/dsh-integration.md).

Distills session work into background observations and reflections to preserve context across compaction.

Per-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md, DECISIONS.md and SESSIONS.md — are auto-created on the first step of any session in that workspace, re-read from disk and re-injected only when they change (and re-injected if compaction dropped them), and written back by classification through a memory_checkpoint tool, with a bounded end-of-turn nudge when a turn did work but recorded nothing. memory_read and memory_search read the live log and the archive, the latter over a zero-dependency BM25 index. The session log is capped at 200 entries with the overflow moved to SESSIONS-archive.md — never injected, but visible, readable and searchable, and restorable one entry at a time. Settings page: a workspace list with a path filter, read-only tabs for the three memory files plus the archive, reload, export/import of one workspace's memory as a JSON bundle, a two-step clear, a panel that rewrites or removes the AGENTS.md instruction block, and a PROJECT.md staleness reminder. A composer status chip shows that workspace's sync state and creates the files on click. Zero dependencies — no vector store, no embeddings, and no model calls.

人脑式上下文压缩逻辑，大幅减少长任务上下文占用以及token消耗

Plugin development toolkit for DeepSeek Harness with scaffolding, contract checks, plugin vetting, impact analysis, and upstream compatibility tracking.

Split-screen workspace for the DeepSeek Harness web GUI - chat with several agents side by side in panes that look and behave exactly like the stock conversation: drag-to-split, live sessions with queued messages and in-pane ask_user/approval cards, per-pane view tabs (Chat/Trajectory/plugin views), a compact TUI composer mode (Alt+T) and pane-focus shortcuts. Requires DSH 0.1.5+.

Project+global long-term memory for the dsh web GUI: split POST /items endpoints, tool-call context merged into memory items as compact summaries, with deduplication and session-scoped persistence.

Decision-and-goal memory with lineage: explicit commands and a model tool record decisions deterministically, a status card re-anchors them across compaction, a lossless event stream with BM25+jieba retrieval backs it, and a scenario-level fidelity regression suite gates releases.

Token attention management panel for DeepSeek Harness: per-task/day/week/month token usage and cost tracking (input hit/miss, output, reasoning), DeepSeek peak/off-peak pricing, task-type recognition, and advice on when to switch sessions, write a hand-off, or compact context.

Mobile adaptation for the DSH Web UI: compact typography, full-width composer with caret fix, drawer sidebar with overlay-close, two-page settings flow, responsive tables and stats, safe touch targets.

Vision toolkit for text-only DeepSeek: model-invokable `vision` tool, wrapper adapters for deepseek/opencode-go (v4 flash/pro), Antigravity IDE quota (default, flash/pro) / any OpenAI-compatible VLM / Gemini / local Ollama channels, evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

DSH context-compression backend with a go game record (kifu) DAG: node = position, edge = attempted move + result. Incremental fold (each span summarized once), failure memory that survives compaction, transposition detection (chess-engine style), and a t

Two chibi Genshin Impact desktop pets (Columbina and Nahida), 22 transparent animations each, with desktop wandering, drag-and-throw physics, click reactions, idle chatter and chat through DSH models. A fan pack derived from PC2005-cloud/dsh-pet (MIT) — it reuses upstream's /dsh-pet-7340 route and ~/.dsh/dsh-pet data directory, so install it instead of dsh-pet, not alongside it; the character art is not MIT-licensed.

Long-conversation memory for DeepSeek Harness (DSH): keeps settled decisions, user corrections and exact numbers, with their conditions and sources, available across compaction and restarts in 100-1000+ turn sessions; one small budgeted evidence block per model step, with enabled skill rules re-applied in the same block.

Columbina mascot for DeepSeek Harness: a 2D live pet on the desktop and inside the web panel, with four sprite sets, 76 official voice lines in Chinese, Japanese and English, weather reports, sticker moments, idle whispers, and a right-click menu for the sprite switch interval, sprite set, language and scale. Also includes quiet hours, volume with one-click mute, a searchable idle-action picker, and a power-save mode. It is a 2D-only fork of PC2005-cloud/dsh-pet (MIT) with upstream's 3D skin switching removed; it uses its own plugin id and can be installed alongside dsh-pet.

Replaces the summarizing context compactor with a handoff note the model writes itself and a fresh window that keeps only the system prompt, the note, and the current turn.

Composer control for the automatic context-compaction threshold. A 20%-80% slider rewrites the running BasicCompactionEngine config per step, shows current usage, context window and the effective trigger line, and compacts immediately when the threshold drops below current usage and the agent is idle.

Adds handoff, context-decision and context-diagnose skills, self-contained context_pressure/context_history tools (peak tokens, compaction stats), per-route realWindows with windowSource evidence, routeKey, handoffAt forced-handoff line, and slash commands.

Jev-scored context compaction for DeepSeek Harness -- keep the messages that matter, compact the ones that do not

Reads one Genshin Impact account (characters, talents, weapons, artifacts, wish history) into a single snapshot, then exposes it as six agent tools and a six-tab panel. Artifact substats come from the public in-game character showcase; scoring ships both CV and per-character weight models with six grade tiers; wish analysis covers pity, luck tiers and per-pool progress. Needs a Miyoushe QR login to read characters, weapons and wish history; showcase data is public by UID.

Warns the session to flush what matters before context compaction kicks in, and rolls a long-term ledger into a frozen archive with a digest of title plus up to three lines per moved section. The roll-up stays off until home is set.

Compact interface with borderless messages, a light queue, composer controls, and adjustable corners. Built for DSH 0.2.1-rc.2 only; while enabled it replaces the stock sidebar module, and removing it restores the original.

File-defined command hooks across the session, prompt, tool, permission, Stop and PostCompact seams, with an approval-only GUI: no unapproved command runs, and approval binds the exact definition, canonical working directory and pinned watchFiles. Commands run as the DSH OS user without a hook sandbox, so the trust ledger is explicit.