Plugins

Prove that a local image edit left every pixel outside its mask untouched. Original, generated and mask PNGs go in; a greppable `MASK_PIXEL_LOCK=PASS|FAIL|EMPTY` verdict, a difference heatmap, per-channel statistics, a bounding box and the largest changed pixels come out, plus a self-contained HTML report and `report.json` with a SHA-256 file hash, a canonical protected-pixel digest and a proof digest binding both to the policy. Supports edit and lock mask polarities, a mask threshold, tolerance and alpha-ignoring; PNG color types 0/2/3/4/6, bit depths 1-16, all five filters and Adam7. Zero dependencies, local only — no model call, no network, no upload.

Auditable token-cost ledger for DeepSeek Harness: wraps the llm/stream waterfall and records every call with provider, model, input/output/cache-hit/cache-write tokens, usage source and integer nano-CNY cost from an explicit price table. Aggregates by hour, day and session; exports JSON or CSV with a no-write dry-run preview; keeps a manually entered official platform bill in a parallel column with actual-minus-estimate diff. Unknown provider/model routes stay explicitly unpriced. Zero runtime dependencies; no balance query, notifications or animations.

Agent preset with adaptive tool presentation and environment-aware shell routing. Ports modules from yjh051108/dsh-routing-suite and xiaobright/dsh-anchored-standard (the former is listed here), so do not enable it alongside those presets.

Change impact analysis plugin that lifts a code change into an evidence-backed impact and verification plan (CHANGE-IMPACT.md + change-impact.json): affected modules, entry points and public exports, risk levels with factors and confidence, and recommended verification commands (read-only, never runs repository commands). Only read-only git queries (rev-parse, diff, status) are run; suggested verification commands are never executed.

For DSH plugin AUTHORS: run this after you finish writing a plugin and it audits the entire publish path, then hands you the exact GitHub + npm + market commands. Pre-publish gate for DSH plugins. Turns every silent failure in the publish path into a deterministic check: package.json completeness (missing exports\["."], files omitting lib/ so the tarball is empty, no "type": "module", client declared without a ./client export), UTF-8 BOM, JSON/YAML parse errors, cordis.patch.yml insert rows written at the wrong indent (the bug that makes a plugin install and never mount), insert name mismatches, missing entry exports, require() inside ESM, missing LICENSE or README install line, missing tests, unscoped npm names that return a 403 no granular token can diagnose, versions already on the registry, and missing GitHub repos. Six agent tools; every finding carries its fix. Read-only, no LLM.

Audit what context compaction actually lost. Reads the raw session event log and checks session-constraint survival (the standing instructions the user gave — do-not-X, must-Y, only-in-Z — and whether the summary still carries them; arXiv 2608.11242 measured ~17% survival across compactors), summary hallucination (paths, versions, ports and identifiers the summary invents that were never in the history it replaced), ghost references ("see above" pointing at removed text), token accounting (a summary nearly as large as what it claims to free), and unaccounted prunes. Four agent tools including a cross-session sweep that ranks conversations by how much compaction hurt them. Deterministic — no LLM, so a wrong answer is a rule bug with a name.

Format checker for theses and lab reports: verifies body font size, first-line indent, line spacing, Chinese font, header student ID and name, page margins, and figure/table caption numbering against a JSON rules preset, then reports each problem with its paragraph location and the concrete fix. Read-only, zero dependencies (Python standard library only), and it refuses to report a pass when no check actually ran. Requires Python 3.8 or newer on PATH.

Syntax-highlighted code for reports via one highlight_code tool: 68 languages, 15 themes, 11 output formats (inline HTML, Word-ready SVG/PNG, LaTeX), incl. the classic SyntaxHighlighter themes. PNG output needs Python 3 with Pillow; other formats need no external runtime.

Extracts deadlines, deposit, validity, ceiling, bid composition and copy counts from a tender document, and reports the items it did not find rather than omitting them.

Converts tables in .docx, .xlsx, .xlsm, .csv and .tsv files into the table JSON consumed by the rule checkers, and reports when it could not rather than guessing.

Joins two spreadsheets on a declared key and compares declared fields within declared tolerances, producing a Markdown report, a JSON result and a diff workbook. It reports differences; it does not adjudicate them.

Offline LAN chat inside DSH: direct chats, group chats and file transfer between machines running the harness on the same network, with UDP auto-discovery, CIDR scanning to add contacts, an optional access code (unset by default), local-only contact aliases, per-message and per-conversation deletion, and a configurable per-file limit. The host opens its own HTTP/WebSocket port for peers, and the plugin imports only node built-ins.

Bailian (DashScope / Model Studio) model catalog in the DSH settings page: lists every model the configured API key can reach, groups them by model family, probes whether a model is actually callable (an unopened model answers 403, which DSH reports as an invalid key), refuses to add models that fail the probe, and shows the active session's context window and remaining budget. An sk- key has no balance endpoint, so quota here means context quota.

Imports wallpapers newly downloaded by the Hao Wallpaper app into the DSH wallpaper engine on startup, incrementally and idempotently. Requires the Hao Wallpaper app, Python 3.8+ and the dsh-plugin-wallpaper-engine plugin (elysia395/dsh-wallpaper-engine) installed first. Supports macOS and Windows.

Draws the sidebar navigation as a compact two-column grid at every viewport; on narrow, short or coarse-pointer screens it additionally caps the navigation at 34vh with scrolling so the workspace and session history keep a 38vh floor. Also repairs dsh-resource:// records whose protocol the browser URL parser reports as empty.

SOLIDWORKS for DeepSeek Harness: dsh reads, edits, rebuilds, renders and exports the models in a SOLIDWORKS 2016 or later, on the same Windows PC or in a Windows VM on your Mac. Read-only by default; the Windows side decides what may be written.

Registers /daily, which sends the model to read the newest bili-scroll report and say what it understood instead of repeating the text; a sidebar panel runs the same command. Needs the dsh-bili-scroll plugin to have written reports into ~/.dsh/bili-duty/out, otherwise /daily finds none.

Brain-shaped relationship graph viewer for DeepSeek Harness with a Markdown knowledge-base pipeline that imports documents and builds the graph. The viewer ships demo data and needs no Python; rebuilding the graph from your own notes needs Node.js 20+ and Python 3.8+ and runs from the command line.

A greeting card that speaks — 156 prebuilt voice clips with a one-click mute — plus per-turn completion reports, long-run companionship notes and a takeover approval panel in the DSH conversation area.

Registers one agent tool, plugin_guard, that statically scans a DSH plugin package before it is installed and reports a verdict with the reasons: a missing or broken dsh.bundle.patch, a missing dsh.permissions block, install scripts, dangerous APIs and obfuscation, dependency risk, and source that is not indexed and therefore cannot be verified. Read-only: the scanned code is never imported, installed, evaluated or run.

Registers one `doc_ocr_sign_fix` tool for DeepSeek Harness: on macOS it diagnoses and repairs the condition where the bundled Python cannot load native extensions (onnxruntime, cv2, pypdfium2) because of the hardened runtime and library validation, by injecting the disable-library-validation entitlement and re-signing the interpreter, then verifying the imports. Operations are idempotent and the original binary is backed up first. It never touches the enclosing application bundle.

Client-side performance HUD and always-on recorder for DeepSeek Harness: FPS and worst frame, long tasks with four-leg attribution (React fiber / subtree / DOM writes / scheduler), per-plugin callback rate and sync time, DOM growth and writers, JS heap, host event loop and link RTT, plus a night-watch recorder that keeps the worst stalls and exports incident packs for replay.

Outbound route pool for DeepSeek Harness. Ships 15 seed routes plus a 20-entry candidate pool covering 7 target kinds (GitHub raw/codeload/main, npm registry, PyPI index, HuggingFace, general). Routes are verified before use: upstream IP lists go through a TLS handshake with full certificate-chain validation (a bare TCP check can be answered locally and report dead IPs as healthy), and failures advance a cooldown ladder of 2/5/15 minutes with the fastest healthy route picked per target kind. Routes are applied by rewriting the URL with one of four rules (prefix, registry, index, host-replace), reaching git, pip, npm, pnpm, gh, curl and wget through three paths: the shell seam (download commands the model runs through the bash tool are intercepted and rewritten automatically; commands wrapped by the pwsh tool, and fetches made by the host itself or the renderer, are not covered), two registered tools the model can call directly (line_pool_status, line_pool_run), and child-process spawn. Multi-line commands keep their line breaks and only the download segment is touched. URLs carrying credentials (user:token@host) are never rewritten, so tokens are not forwarded to third-party mirrors. No global config is modified. A sidebar panel lists every route with latency, failure reason and cooldown countdown, supports per-route retest and enable/disable, and shows live TUN/proxy status from network-adapter and loopback port checks. The candidate pool is re-verified every 24 hours so newly usable routes are added and dead ones dropped. 570 tests, 87% line coverage.

Plugin diagnostics for the dsh web GUI: finds plugins that failed to load, bundle rows that never started and broken file links, then reports the findings. Read-only: it does not repair, journal or undo anything.