Plugins

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.

A context usage ring with configurable character-based automatic compaction, manual compaction, protected user requirements and recoverable original history for DSH 0.2.0-rc.2.

Long sessions get expensive, and the platform compacts the context on its own. This plugin adds an occupancy badge (hover to see how it is computed), writes a handover draft into HANDOVER.md from 45% — files changed, money spent, what recent turns were about — and reminds you once at 60% to wrap up. On compaction it records the reading from just before, so you can check it later. No model calls, nothing added to the conversation; it does not prevent compaction.

A persistent multi-step task stack for DeepSeek Harness agents: focus_task / focus_complete / read_focus plus a /focus command, with zero automatic prompt injection

Context fullness bands, the per-session compaction threshold derived from the model window, per-step cost computed from cache read and cache write rates, cache-hit, DeepSeek balance with the peak/off-peak tariff, and a one-click handoff. It never calls a model and spends no tokens.

DeepSeek Harness plugin: tells the model its real, host-measured context occupancy every turn — and keeps compaction summaries from carrying false "context is nearly exhausted" claims.

Counts completed compactions per session in a floating window and warns only after repeated compactions plus extra token spend or high context occupancy, with all three thresholds adjustable in Settings.

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

Keeps DSH agents from forgetting your requirements during long tasks. It saves important conditions and completion evidence locally, brings them back after context compaction or session resume, and stops partial work from being reported as the whole task done.

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.

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.

Configurable context compaction with three independently switchable sections — whole-context checkpoint, reasoning compression and tool-output pruning — each with its own pressure threshold and method. Mechanical modes make no model calls; model modes summarize fragments in batches with a configurable provider and prompt. A left-sidebar panel exposes switches, method cards and editable parameters that save without a restart, and every rewrite is archived with its original text.

Context control for DeepSeek Harness: inspect token usage across request and conversation; switch skills, MCP servers and plugins between loaded, brief and hidden per session; toggle prompt sections and tools; compact on demand or at a configurable 5–95% threshold.

Context handoff sentinel for DeepSeek Harness: three behavioral recall tests (constraints / changed files / next step) run after every compaction or on /guard check, cross-checked against the session log, returning a green/yellow/red verdict plus an optional handoff document.

A session auto-compaction plugin that is friendly to local models: the trigger point is configurable, compaction does not make the local engine re-read the whole history, and the model writes a structured handoff summary from the prefix that is already cached. Trigger ratio, summary template, display style and per-preset scope are configurable. Installing and restarting DSH takes over; uninstalling restores native DSH compaction.

Precomputes the compaction summary in the background and commits the held result when pressure compaction fires, removing the foreground model round-trip. Registers itself as the session compaction engine, pins the span it summarised so the payload fingerprint still matches at commit time, prunes tool results before committing, and falls back to the stock foreground path on payload drift or context overflow.

A durable, user-owned session charter for DeepSeek Harness, designed to survive context compaction.

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.

Take over context compaction on both the manual and the automatic path, each runnable by a compaction model (falling back to a second model, or used directly) or by a mechanical fold that builds the summary card locally with no model call; the fold goes through the same official compaction transaction, so the replaced events stay in the append-only session log under their sequence numbers. It adapts code from dsh-compact-saviour and takes the mechanical fold from dsh-ledger-compact (both MIT) — install it instead of dsh-compact-saviour, not alongside it.

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.