Plugins

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.

Cross-session plaintext memory: deterministic BM25 keyword recall (no embeddings), memory_save/list/search/confirm/forget tools behind a human-confirm gate, and global + project-scoped JSON stores that follow your git repo.

Cross-session event-cue memory for DeepSeek Harness: auto-extracts task/conversation cues and user language habits from every turn into a persistent global cue bank, then re-injects remembered context on topic-switch detection (keyword or vector matching).

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

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.

Minimal-compatible first turn for Web root sessions: starts with persistent bash and str_replace_editor, removes automatic workspace and skill context, then restores the selected preset after the first tool call or reply; includes a persistent composer toggle.

Ollama Cloud native chat adapter: direct NDJSON translation of the Ollama /api/chat wire format, model discovery with context windows and capabilities, and web search/fetch providers under the ollama-cloud id, plus a Web settings card.

Vendor-based usage dashboard: per-provider token/cache/output KPI, a 53-week heatmap, trend chart with hourly "today" view, model drilldown, cost estimation, CSV export, and health cards (TTFT, generation speed, peak context, error rate).

Floating API-balance badge for DeepSeek Harness: live balance for DeepSeek, Moonshot, OpenAI and custom endpoints; draggable, resizable, frosted-glass look, with text color adapting to the content beneath.

Adds a removable quote banner above the web chat composer for text selected from an AI reply, included in the next message.

Auto-saves large pasted text as an attachment file in the DeepSeek Harness web input box.

Interactive terminal chat app for dsh: streaming conversation, tool cards, jobs panel, full-text search, trajectory replay, multi-session tabs, and A2A dispatch (Ink-based).

Voice for DeepSeek Harness（dsh） — speech-to-text input + read-aloud TTS for text-only DeepSeek, zero API key.

GPU-aware execution layer for DeepSeek Harness: gpu_status / gpu_exec / gpu_run_bg tools, per-step GPU context injection, automatic CUDA_VISIBLE_DEVICES card selection

Context compression skill for DeepSeek Harness -- intelligent conversation summarization

DeepSeek Harness plugin bundle: qwen_vision (Qwen-VL image understanding) and qwen_generate (Qwen-Image text-to-image) tools for text-only models

Persistent long-term persona memory for DeepSeek Harness: MEMORY.md/USER.md storage, memory + memory_search tools, per-request context injection, and secret scanning. Ported in spirit from pi-hermes-memory.

Logical-call context taxonomy for the DeepSeek Harness Web profile

Vision toolkit for DeepSeek Harness -- glance, ground, detect, crop CLI tools for text-only agents to understand images

A DeepSeek Harness plugin that integrates claude-mem: query, context injection, manual save, and session lifecycle over a local claude-mem worker's HTTP API

Request Context Profiler for DeepSeek Harness — see what changed between model requests, and how cache reuse changed with it.

Plug-in vision for text-only DeepSeek Harness (dsh) models: a `vision` tool with built-in cheap/free VLM presets, multi-image batch analysis, paste-to-hint image admission, and a web settings page with hot-reload.

Thin on-demand context retrieval: context_query / context_slice / context_grep tools that read already-persisted history back with replay-safe citations.

Text hygiene as a dsh plugin: sanitize untrusted text, scan invisible characters, clean LLM formatting, and escape CSV formula injection.