Plugins

Per-plugin usage budgets and cost caps on the llm/stream waterfall: per-model usage accounting, session and monthly budgets with warn/block transitions, latency windows, and a carbon-footprint estimate.

DSH Mini TUI: a minimalist terminal interface plugin for DeepSeek Harness

Replaces the chat composer with an editor-style input panel on CodeMirror 6: line numbers, edit + markdown-preview split, a floating window mode and a full-height sidebar tab — one input surface at a time. Drafts ride the official input machine; the official voice-input button is rendered when the host provides one, and the stats row and context meter read the same data as the official dock.

Windows only: the agent edits documents inside the Word, Excel and PowerPoint (Microsoft Office or WPS Office) windows you have open, through the applications' automation interface, so changes appear live and you can edit alongside; it reads structure, applies batches of edits, renders pages to images to check layout, and saves or exports PDF.

Adds an edit action to finalized assistant replies in DeepSeek Harness, letting you rewrite the reply text or reasoning chain; the edit is saved as a surface replacement.

Auto-resume for interrupted agent sessions: an ordered rule table routes by failure type (rate limit, quota, auth, context overflow, crashed orphan) to automatic backoff retry, model switch, resume after context compaction, or a stop-loss notification, with a visual rule editor and a full activity log.

Security scanner for DSH plugins: static and semantic passes over plugin source, DSH-specific attack-surface rules, npm audit, batch scanning, and an HTML report with per-finding severity and evidence.

SearXNG search and Crawl4AI fetch providers for DeepSeek Harness

Adds two UI surfaces: a composer image editor (numbered edit marks with per-mark instructions, solid-background removal, brush-mask erase, resize and crop presets; results return to the composer as attachments plus a manifest capsule) and a Settings → vision/generation provider panel (three priority tiers, drag reordering, per-channel model fallback chains, arrears-aware balance probing, ChatGPT-web account store) that writes the resolved providers back to the skills .env files.

Six-player no-limit Texas Hold'em for the dsh Web GUI. One human plays against five LLM agents that each see only their own hole cards. Adds a dedicated tab plus a draggable mini-window over the conversation area, per-browser sessions with CSRF protection, pot-relative raise sizing, three rebuys before elimination, and showdown reveals with board-card deal animations.

Long-term cross-session markdown memory with an LLM-Wiki structure and a SOUL.md persona, injected at session start (by default only after the first user message and only in the active session), plus remember/recall/consolidate/forget workflows, an embedded memory skill, pack/unpack migration tooling, and an idle-time first-person recall nudge that surfaces real memories in a companion voice. Also gives the store observability and upkeep it lacked: a per-file boot-block budget that keeps the index routing table from being truncated, automatic last_access stamping so salience decay actually works, a read-only memory health dashboard (size, freshness, lint-parity checks), a declarative index compiler (pages declare summary:, one command re-lines the index), an interactive memory graph (page links plus shared tags, draggable, wheel zoom), structured queries (tag/type/salience/hot/stale filters), cross-link suggestions for pages that have no relationship yet, and a `checkup` report that ends in a prioritised action list. The boot payload was also cut by ~23% by moving operational detail into the on-demand skill. Its settings section now carries its own navigation mark (a brain half wired to a node cluster, since the shell offers no icon slot to plugins) and a feedback entry that opens this repository. Requires DSH session format v4 (official DeepSeek Harness 0.1.7+): injected messages declare the producer-owned source kind plugin:memory.

Cross-session memory plugin for DSH (v0.6.1, npm @asherliner/dsh-memory-connect): auto-extraction, SQLite FTS5 indexing, RRF semantic recall injected into the system prompt every turn, scheduled maintenance, LLM-powered consolidation via ctx.llm, context explosion prevention, and global Soul identity via ~/.dsh/soul.md. v0.5.0 added temporal context graph (valid_from/valid_until/supersedes, append-only corrections via reviseMemory), trust model (recalled history injected as untrusted reference, current instruction always wins), turn-end summarization. v0.6.0 added local semantic embeddings (BAAI/bge-small-zh-v1.5 via embed_server.py, cosine + RRF fusion with FTS5, no cloud calls, ~232 msgs/sec on CPU). v0.6.1 fixed ~ expansion in path config. Zero-config install.

Custom background image for the DSH Web UI: upload a picture or paste an image URL behind the whole app surface, with opacity, theme-aware scrim, panel transparency, frosted-glass and wallpaper blur, live preview and persisted settings, plus an optional DeepSeek-style timeline rail with per-question bookmarks for long conversations.

HTTPS + login gateway for the DeepSeek Harness web surface: access your DSH Web UI securely from another machine on your LAN, or from the internet via port forwarding. Fail-closed defaults (loopback-only, no accounts until configured); setup and security notes in the README.

Chinese localization for DeepSeek Harness: translates all system prompts, tool descriptions, and runtime contexts into Chinese at runtime via the system-prompt/assemble waterfall (1788 entries, zero source modification, uninstall restores English).

Neumorphic DSH Web theme with light and dark palettes, ambient lighting, material shadows, grain texture, frosted-glass surfaces, and micro-interactions.

Fan-made wallpaper plugin themed on the streamer Zhang Shunfei: full-screen high-definition rotating colorful pegasus GIF wallpaper with theme blending and prominence control, plus a Bilibili music player (add songs by pasting a link, delete, volume, seek, single/list/shuffle loop, and a sidebar mini player).

AI can write resume text, but templates may still look wrong, pages may overflow, whitespace may remain, and small edits can destabilize the layout. dsh-resume provides an end-to-end DSH workflow for truthful content refinement, template selection, A4 layout tuning, visual review, and tailored resume versions for different job-search scenarios.

A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.

Sidebar weather panel: current conditions, 5-day and 24-hour forecasts, an hourly rain chart, temperature history, CMA alerts with graded reminders and county-level matching, a radar mosaic, FY-4B satellite imagery, typhoon tracks, and ECMWF / NW Pacific sea surface temperature charts.

Cross-session persona and diary for DeepSeek Harness: a local gate decides whether a turn is worth remembering, then one extra model call turns it into a first-person diary entry plus an impression of the user, where every impression carries the specific moment that produced it. Later conversations inject about 2000 tokens of that as a self-memory block in three registers: a persona core, a section for judgements the model wrote itself, and the diary. There is a tool for the model to record a judgement in its own words, and a plain markdown hand-note file the human can write into which the plugin only ever reads. A sidebar panel lets you read, forget or export the archive, and forgetting demotes an entry rather than deleting it, so an old one still surfaces on a strong topical match. Local-only, secrets are stripped before anything is sent, and the archive is a plain folder you can read, edit or carry to another account. Zero runtime dependencies, no build step.

Per-message delete for DSH: remove a user message, one reply step, or a whole assistant reply from the derived model context through the official surface-replace contract, and hide it from the visible transcript without rewriting the append-only log.

Model-autonomous context compaction for DeepSeek Harness: a mind_map tool surveys the agent context surface (stable seq ids, roles, token weights, clear-boundary markers, the clear-mind playbook), a clear_mind tool replaces a chosen conversation-history span with a model-written checkpoint through the native compaction transaction, call and result pairs self-collapse into one-line tombstones, and a proactive reminder nudges the model when the context grows long or a turn runs too many steps.

A font plugin for the DeepSeek Harness Web GUI: the conversation gets its own font, size, line height, weight, tracking, word gap, paragraph gap and first-line indent, the interface font follows it, code keeps its own axis with ligature control; light and dark can each hold their own set, whole setups save as presets, and a floating panel puts every axis a dot away.