Plugins

Answers Dark Souls III questions from your own Windows PC save (default `%APPDATA%\DarkSoulsIII\*\DS30000.sl2`): level and stats, current area, bonfires/rings/spells/covenants counted by family, kill state for the 24 bosses, and Steam achievements when Steam is installed - exposed as model tools plus a progress pill beside the composer and a 19-area sidebar page with next-step suggestions. The save stays read-only and is parsed locally by a bundled Python 3 script; Python 3 and the `cryptography` package must be installed, and the game data ships with the plugin.

Publishes and reads QQ Zone posts through SnowLuma's OneBot qzone_* actions (SnowLuma 2.2+ signed in to QQ), and lets the agent understand images with a local vision model (OpenAI-compatible gateway) or Windows OCR.

Compiles LaTeX with the TeX Live installed on the machine: one `latex` tool typesets a formula into an SVG, PNG or PDF and a whole document into a PDF (Chinese text switches to xelatex with ctexart), writes the file into the workspace and returns a Markdown reference to it. A system-prompt section asks the model to write `$...$` and `$$...$$` instead of code fences, and when no TeX Live is found a banner above the composer offers a one-click BasicTeX or TinyTeX install.

Read-only knowledge gateway over a local Markdown vault, in four tools: `wiki_recall` returns the matching section in full with page-level citations plus vault health checks and a page skeleton for writing a good answer back; `wiki_context` returns one evidence pack with per-page excerpts, a support verdict and an explicit list of gaps; `wiki_verify` re-checks a drafted answer against that pack and reports claims the evidence cannot back, including unsupported numbers; `wiki_observe` reports how often answers needed correcting. The settings page and sidebar panel share the same query path as the model, so a search you run by hand cannot disagree with what the model was given. The three knowledge-gateway tools (`wiki_context`, `wiki_verify`, `wiki_observe`) need a local Python 3 bridge — `bridge.python` plus `bridge.toolsRoot` containing `wiki_bridge.py`; without it they return `E_PYTHON_UNAVAILABLE`.

Self-narrative memory in five budgeted segments (800 chars, not a full context): a first-person note the model writes to itself, a profile of you aggregated from approved facts, environment facts kept separate from who you are, heat-ranked conclusions, and habits. Every injected fact is traceable to a fact id and can be retired; the profile can be edited by hand, and self-notes stay plain lines you can clear. Facts fade by use and time without ever changing their credibility. Preference-like lines you say are auto-detected as candidates (never auto-approved), with conflicts kept side by side. Recall over past conversations with citations, an incremental index that only decodes newly appended frames, a pointer-required warm layer, a doctor that says which part is broken, a heartbeat proving injection is alive, and export/import so the whole thing moves to another machine.

Claude Code-compatible persistent memory: the host injects the MEMORY.md index at session start, the model maintains memory files with plain read/write/edit tools, and a Settings page lists saved memories. Same on-disk format as Claude Code; claude mode shares the exact memory directory.

Precomputes the compaction summary in the background and commits the held result when pressure compaction fires, removing the foreground model round-trip. Registers itself as the session compaction engine, pins the span it summarised so the payload fingerprint still matches at commit time, prunes tool results before committing, and falls back to the stock foreground path on payload drift or context overflow.

Rewinds a finished turn in place — a button next to your own message withdraws that message and everything after it from the model context, puts its text back in the composer for editing, and optionally restores the files the turn changed through the DSH filesystem service.

Turns the composer's model menu into a two-level list (provider first, then that provider's models), shows the current model together with its provider name, asks for a reasoning effort after a model is picked, and adds settings switches that hide whole providers or single models from the picker.

Provider-first model picker for the composer. Every provider is listed in the left rail and its models in the right pane. Providers, models within a provider, and pins reorder by drag or Alt+Arrow; providers take a local display alias; one provider can be the panel default; a model's reasoning levels expand inline; search matches model names, provider names and aliases. Switching goes through the shipped model directory service, so the /model popup and this panel always agree.

Deep-sea tidal-blue theme for the DeepSeek Harness Web client with a single accent color and matte (non-glass) surfaces in light and dark modes. Same-token UI additions: a single-line dock HUD reading real session projections (context usage vs. window, TPS, cache-hit rate, elapsed time), per-turn subagent delegation cards showing token usage and an optional cost estimate from OpenRouter public prices, sidebar pagination with pinned sections and type-to-filter, and model / reasoning-effort / permission controls under the composer. Each addition can be toggled in the plugin settings.

Adds a /context slash command to DeepSeek Harness: shows how much of the session context window is used, how much is free, and a per-category breakdown (system prompt, memory files, skills, messages, tool results). Read-only, local, no model calls.

Agent enhancements for DeepSeek Harness Desktop: prompt history, one-click optimize with undo, next-prompt prediction, conversation and tracked-file restore, model bill, context details with compact, Auto routing, and per-provider DeepSeek balance.

Sidebar leaderboard for DeepSeek Harness (DSH): LMArena blind-test ratings, Artificial Analysis intelligence index, LiveBench 2.0 capability, OpenRouter weekly/monthly usage and market share, price, speed and context — plus a local token-usage dashboard built from your own session logs (tokens, estimated cost, per-model ranking), model detail drawers and CSV export. Daily snapshot, instant open, no API key; locally configured models are highlighted.

Adds a prompt-refine button to the DSH composer and, when auto mode is on, refines the prompt before the agent starts by rewriting the text with recent session context through a side-channel model call, asks on the native question card when the rewrite cannot be decided, reports each stage as a command card in the chat, and keeps the original text when analysis fails.

DSH-SOLO desktop plugin for its companion app. Pair by QR code to view sessions, send tasks, switch models, transfer attachments and approve operations with end-to-end encryption; official cloud relay preconfigured, no server setup required. Download the App APK at https://github.com/wudidiandian/dsh-solo/releases/latest/download/dsh-solo.apk (GitHub Releases).

Use SSH hosts and WSL distributions as remote DSH workspaces, with environment setup, model configuration porting, and the remote interface embedded locally.

Provider logos and model IDs in the DSH model picker, registered as a label decorator on the official conversation.input.model.label slot; providers match by token, display name, model ID and explicit override, falling back to a letter monogram when unknown.

官方 subagent 的默认策略包：装上一次配好「什么时候自己干、什么时候派出去、派给谁」。

Inline visualizer for DSH: the model loads a design contract first, then renders an SVG or a sandboxed HTML card in place inside the conversation, with light/dark tokens and a source/download toggle.

Persistent cost ledger for the DeepSeek Harness: every priced model call lands in a monthly JSONL file; /ledger renders monthly reports, /ledger-export writes CSV, and the agent can query its own spend via ledger_query.

Delegate subtasks to Herdr-managed coding agents from DeepSeek Harness: pick the model, keep the pane, harvest the exact result, review in DSH.

DeepSeek Harness (DSH) plugin: edit a finalized assistant reply and its reasoning/thinking chain right in the conversation. A pencil action opens a single-message editor; edits become a plugin message projection, so the model and the UI only ever see your

Decision layer for dsh: provider-agnostic typed judgments (Jev first) behind tool guardrail, model routing, result judging, and machine approval seams