Plugins

Context-Insight-Panel: zeigt, woraus das Kontextfenster des Modells besteht und wie es sich entwickelt — Zusammensetzung im Verhältnis zur Fenstergröße, Verlauf je Anfrage, Kompressions-/Injection-Ereignisse und Token-Statistiken je Nachricht.

Profile-wide DSH governance and routing bundle with configurable compaction calls and scoped local semantic memory; compatible with DSH 0.1.0-rc.6 and 0.1.0-rc.7.

DSH session manager: delete with trash/restore/purge, restore archived sessions, recent-activity stats, continue/pause, open log folder, unread markers, fork into a new chat, workspace grouping and sorting, context compaction threshold.

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.

LLM-freie, verlustfreie* Kompaktierungs-Engine für DeepSeek Harness.

Eingabeverlauf im Terminal-Stil für den DeepSeek-Harness-Web-Composer: Pfeiltasten mit Rand-Priorität und exakter Wiederherstellung von Entwurf/Cursor, browserlokal gespeicherter Verlauf, Rückwärtssuche mit Strg+R, arbeitsbereichsbezogener Abruf und vollständig konfigurierbare Tasten — plus gleitkontextbewusste

Importiert Chat-Verläufe aus claude-code / codex / reasonix / zcode in dsh-Sitzungen: Workspace-Bindung, erhaltene Tool-Aufrufe, Schutz vor übergroßen Sitzungen, Wiederherstellung der zcode-Kompaktierung.

Dedicated model routes, tools, and system guidance for vision, compaction, reviews, subagents, titles, and image generation.

Native Vision-Bridge für LLM-Anbieter: In den Chat eingefügte Bilder werden von einem Vision-Modell (Qwen3-VL über pi-ai/llama.cpp) beschrieben, und die Textbeschreibung wird zur Antwort an das rein textbasierte DeepSeek weitergegeben — Bildaufnahme, Routing und Kompaktierung laufen vollständig über harness-native Mechanismen, mit LRU-Beschreibungscache und 503-Retry.

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.

Routes chat images to a fixed OpenAI-compatible vision model, returns factual observations to the selected main model, and reuses session-scoped observations across replay, compaction, and restarts.

Enhanced auto-compaction defaults for DeepSeek Harness agent presets: apply tuned threshold/retention budgets and per-model policies with one command, idempotent with backups and rollback.

Model-authored context pruning for DeepSeek Harness through the official compaction API.

Deterministic context compaction: prunes conversation atoms in reference-graph topological order with no LLM calls during compaction, and keeps pruned atoms recallable by marker.

Deterministic context-pruning compaction backend for dsh (DeepSeek Harness) — zero-LLM summaries, /dcp command, works out of the box. Design references Opencode-DCP/opencode-dynamic-context-pruning.

Read-only performance diagnostics for DeepSeek Harness: session load (open/restore) timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via the /fas

Visual percentage and token settings for official DeepSeek Harness compaction

File-based self-evolving memory for DeepSeek Harness v2: compression & extraction over official compaction, daily episodic layer, dream consolidation to semantic files (user/agent/memory/dream + project), catalog disclosure injection, no confidence machin

Pure-incremental directive-driven compaction for DeepSeek Harness: /compact-directive <requirement> summarizes the session middle per your requirement, /trim-directive <requirement> trims the whole conversation per your requirement

The pet that grows with your agent: 5 evolution stages earned from real signals (verified rules, completed sessions, tool calls, compactions), agent-state mirroring, and one-click growth share cards. Zero dependencies, 100% local.

One-command bundle of the three AgentFrame plugins: memory-director, compaction, and aura-scheduler together.

Compaction backend replacing LLM summarization with a deterministic semantic extractor (keeps code/paths/commands, drops chatter) plus 28.4x KV-compression accounting.

Session context triage for long DeepSeek Harness sessions: deterministic screeners trim stale, duplicate, failed, and oversized content through the official ctx.compaction seam.

Focus board for DeepSeek Harness agents: durable, model-maintained notes in the session workspace that pin the objective, constraints, and decisions across compaction and sessions, with automatic context injection, archive on clear, and an optional web panel.