Plugins

Message timeline rail for DeepSeek Harness web chat: evenly spaced ticks for each user message on the right edge, click to jump, hover to preview.

Falsification-driven correction loop for agent sessions: risky work commits an evidence-checkable claim first, deterministic gates verify it, falsified claims force mutually exclusive replacement hypotheses with discriminating experiments, and every event lands in an append-only evidence ledger.

A per-conversation visual slide editor for DeepSeek Harness with AI annotations, workspace files, and shared knowledge guidance.

Right-edge turn navigation for dsh web: one dash per user turn, hover to expand an outline panel, click to jump

Self-healing runtime layer: a resource control loop with strategy switching and repair escalation, error-storm and fiber-failure insight, cross-session knowledge carry-over, a self-healing dashboard and 7 tools.

Registers the remove-pdf-background-gray skill for DSH: whitens gray/off-white scan backgrounds in image-based PDFs while preserving resolution, page geometry, and anti-aliased text edges (lossless Flate write-back), via a single Python script (pypdf + Pillow + numpy).

CDP bridge to an already-running Chrome/Edge for DSH: screenshots, pixel assertions, DOM/CSS checks, and page JS evaluation over HTTP + WebSocket, with zero child processes, zero npm dependencies, and zero per-use approval.

Qichacha (企查查) enterprise data source as a dynamic Cordis plugin: 5 agent tools (auth with QR login, company search, knowledge search, tool search, tool execute) covering 100+ data dimensions (business registration, shareholders, judicial, IP), plus a settings-page account manager; network/file IO via DSH subprocess spawning node -e, credentials interop with the local BizOwl client.

Connects DSH to local Beav for Xiaohongshu (RED/RedNote) and social-media AI operations: topic research, knowledge, copywriting, image, audio, and short-video workflows with approval and artifact tracking.

Auto-supplement QMD semantic search when the model greps/globs a knowledge-base directory: zero-dependency DSH plugin, async injection via next-step, no manual invocation.

Long-term memory injected at session start: preferences/facts/summaries/knowledge in global and per-project scopes, budgeted recall via `agent/pre-step`, durable JSON store.

Brings your existing Claude / ChatGPT history into DSH: instant zero-token import of the memories.json inside a Claude export, local Claude Code transcripts with no export needed, and conversations distilled through the model you already configured in DSH. Every memory carries verbatim evidence checked against the source by code — a paraphrase is dropped and counted, and evidence found only in the assistant turns is always routed to review rather than stored.

DSH WebUI session query navigation with a faint conversation-edge rail, a hover list of real user queries, and click-to-jump back to the matching bubble.

DeepSeek API quota panel collapsed into a left-edge handle for the Web UI: click to expand balance, official today's consumption (with platform token) and live conversation cost; fork of dsh-deepseek-quota.

Left-edge turn-marks strip in chat: one bar per user message, click to jump to that message, hover for a preview, active bar turns white.

Cross-tool session migration plugin for the DeepSeek Harness (dsh): high-fidelity ingest, continue, knowledge extraction, bidirectional export, privacy redaction.

Hosted tool server over MCP: invoice and bank-statement extraction with in-code arithmetic checks, ledger reconciliation in integer cents, PDF and table conversion, SQL dialect transpiling, and mainland-China reachability probes run from a China Mobile network vantage point.

Browser Web Speech API voice input: zero server, zero keys, zero model downloads (Edge=Azure, Chrome=Google speech).

Turn a feature that actually runs into a trustworthy delivery demo video: real screen recordings, edge-tts narration with word-clock subtitles, a self-contained ffmpeg pipeline, and a deterministic quality gate (spec, audio, loudness, black/freeze/silence scans) that refuses to pass a fake or broken demo. Preflight and artifact verification included. Requires Python 3.9+, ffmpeg/ffprobe on PATH, and `pip install edge-tts Pillow`; narration calls the public edge-tts endpoint.

Memory for DeepSeek Harness with five sections (memories, tree, profile, graph, inbox), a rule-based capture policy that decides what to keep and what to drop, and hybrid BM25 plus vector retrieval over parent and child chunks, backed by twelve agent tools that read and write the same local files.

Unified rules/guidelines layer for DeepSeek Harness. Keeps every agent guideline in one local rule library with default (always-on) vs local (task-domain) coverage, syncs the effective set into the AGENTS.md managed section, and adds semantic routing, a classification tree, a management page / right-sidebar panel, an in-panel assistant that can collect existing guidelines, calibrate pending rules, re-classify them, and report an issue ledger grouped by owner, rule copies (right-click move/copy, folder copy, jump to origin), decision points with branch conflicts, and per-session branch choice.

Turns the promises a chat quietly drops into an interest-bearing ledger: every “later” becomes a card, older ones rank higher, and each card jumps back to the conversation where it was said.

A status bar for the DSH sidebar. While a session runs, its row becomes a green card with a progress bar driven by an estimate of how long the turn will take (drifting dotted track), plus a live percentage on the leading edge that switches to elapsed mm:ss once the estimate is exceeded. When the turn finishes the row turns orange and stays lit until you actually open that conversation. Pure client-side, no extra services, a few localStorage keys.

Local-first research toolkit for DSH: registers kb_grep, kb_list, and kb_save model tools. kb_grep searches the markdown knowledge base with ripgrep when present and falls back to grep, while kb_list and kb_save go through the scoped ctx.fs filesystem service; the KB defaults to ~/dsh-kb. The repo also ships two skills (local-first-research and session-memory) that must be copied into a DSH skills directory yourself; they are not installed by the plugin bundle. The plugin is pure Node ESM with no npm runtime dependencies and ships a framework-free node test harness. Installable via plugin_manager install_bundle; no client UI is bundled.