プラグイン

Compiles a Windows .bat/.cmd launcher into a real .exe from inside DSH: renders an icon from a built-in bitmap font, emits a C# wrapper that runs the batch file next to it, compiles with csc.exe (or dotnet build), and can write Start Menu / Desktop shortcuts.

Diagnose DSH home, leftover processes, ports, and oversized sessions, then write a paste-ready /doctor report.

Image and video production toolkit for DeepSeek Harness - background removal with quality tiers, local inpainting retouch, headline and logo compositing, batch platform-size exports and image QA reports; for video, AI subject matting with background replacement (RVM ONNX, plus a chroma-key path), animated titles with fade/slide/typewriter/karaoke presets, 53 transitions with stylized variants, and light-effect and grading presets with LUT support, alongside footage inventory, accurate cutting, subtitle burn-in, music mixing and platform-spec exports; it provisions its own local Python runtime through a bundled bootstrap script.

Embeds external AI chat sites in a DSH side panel through the same-origin reverse proxy with per-site DOM adapters, and adds a composer button that either rewrites the draft with the host model or runs a two-round loop: compress the conversation, optimize, send to the embedded site, capture the reply, then finalize it into the composer.

Live token cost for every chat in the DSH Web UI: the chat, its subagents and the whole session tree, priced from a bundled models.dev snapshot of seven providers and 139 priced models, with cache read and write rates wherever the provider publishes them and DeepSeek from its own peak and off-peak table. Every finished answer carries its own price in the transcript, and a chat that is not currently open is priced from the log instead of disappearing. Spend is costed per interval from an append-only JSONL ledger in the project folder, so logged work keeps the tariff it was billed at. On top of it: budget-aware work plans packed against a money limit, routing scenarios that show which models are worth connecting, a generated plan document in English, Chinese or Russian, and a warning when spend belongs to no plan unit.

Generate and format Chinese Word (.docx) documents from a simple markup file, using built-in heading styles, SimSun and Times New Roman fonts, and per-chapter figure and table captions.

Adds /dev/dxg and /proc read-write grants to the DSH Landlock sandbox on WSL2, so CUDA is available inside a confined agent bash session.

A ✨ button left of the send button: reads the draft and recent turns, asks the configured model for three suggestions each pairing an issue with a patch, lets you tick them individually with a live preview of the merged prompt, and writes the result back to the composer without sending.

Adds a Long text button to the composer tool row: write or paste the body in an editor overlay, and on save it is written to <workspace>/.dsh-longtext/<timestamp>_<title>.md and an @ path reference to that file is appended to the composer, leaving the conversation free of the long text itself.

Tiered persistent memory (user/env/project) with per-tier char budgets and semantic query routing; full layers refuse writes instead of silently evicting.

Polaris Memory: local-first project memory plugin for DeepSeek Harness. Uses per-project .dsh-memory.json; provides memory_read/recall/write/update/delete tools, /memory command and settings UI, with tiered injection (resident user profile + scene-triggered memories with P1/P2/P3 importance), semantic recall (IDF + synonym layer), and a hard-guard mechanism for bottom-line memories (detect deny-semantics -> authorize -> block AI deletion; user can confirm-override).

Measures what an llm-pi-ai endpoint really accepts — context window from its own model list, output-token limit and reasoning levels read out of its own range errors, image support from a generated test image — then reports declared values that contradict that evidence and rewrites them only after confirmation.

Settings section that reports token usage: totals for input, output, cache read, cache write, reasoning and call count, with breakdowns by model, day, month and project plus a per-day trend chart for the last 30 days; history is rebuilt once on a worker thread and then kept current from live session events.

Declare whether a configured third-party model accepts image (multimodal) input; writes the modality into the owning provider settings and verifies it through runtime model resolution.

Adds a workspace-write++ permission that keeps file tools inside the workspace while skipping the Windows process sandbox for wildcard-allowlisted executables such as Git Bash.

Multi-role parallel argumentation for DeepSeek Harness: runs the real Codex and Claude CLIs in parallel, has the DSH model (Judge) write a third-party verdict back into the conversation, plus Obsidian-style single-agent direct chat and per-role model config.

Rolling, integrity-verified backups of each session at turn boundaries: verifies the log still loads before promoting a snapshot, never overwrites the last good one when a turn ends corrupt, and restores in one command even when dsh will not boot.

Prevents concurrent-write session corruption: takes a per-session advisory lock on session start and every step, so a second dsh process fails loudly instead of writing a duplicate-seq gap; dead owners are taken over automatically.

Force the model to write all replies in a chosen language (Simplified Chinese by default) via a system-prompt section, switchable anytime with a tool.

Local token usage and cost dashboard for DeepSeek Harness: four-segment token breakdown (miss/cache-hit/cache-write/output), cache savings estimate against the miss/hit price gap, per-session drill-down with context-growth curves and anomaly flags, global filters with shareable URLs, monthly budget progress with month-end projection, and day/month aggregate fast-path queries (O(days)) with incremental rescan.

一个给 DeepSeek Harness（dsh）用的 Agent Skill，负责写 / 优化 GitHub 项目 README.md。

Restore syntax highlighting of read/write tool envelopes inside run_code (PTC / Code Mode) result cards

Cross-session knowledge for DeepSeek Harness: ctx.knowledge service + knowledge_* tools, SQLite FTS5 trigram retrieval (CJK substring) with L1 query expansion. V1.11 contract (write/update/search/list/delete + budget + events + error codes).

Real AST-based scan of installed plugins for malicious-intent patterns (dynamic eval, cross-plugin writes, exfiltration-shaped network calls), with an optional periodic schedule and auto-quarantine on critical findings.