Plugins

Workspace memory for DeepSeek Harness ported from ZCode: one Markdown memory directory per workspace (a MEMORY.md index plus one file per fact), injected into each main session and refreshed by a background extraction request after completed turns; a sidebar page browses the stored files read-only.

Tide Memory: a long-term memory that forgets on purpose. It keeps what matters and lets the rest fade. Whether an entry enters the context is decided by an evidence score C = s/(s+2): below the threshold (0.35 by default) it never enters. Events decay by half-life (30 days, or 7 days when they carry emotion); facts never decay; superseded entries are kept and marked stale instead of deleted. Recalled lines do enter the context and therefore do consume tokens — small, but real. No embeddings, no network calls, no cloud.

Reads a local Hermes Agent session store read-only and imports sessions into the current conversation as bounded, untrusted background context: a composer button opens a searchable list across every profile, plus the hermes_sessions_list and hermes_session_import tools.

Adds job-role prompts to the DSH composer: type - at the start of the input to pick a role, which becomes a reference chip in the draft and is then injected as a system prompt section on every turn of that conversation, so the instruction keeps applying without showing up in the transcript. Roles are added and edited on a Settings page and stored in ~/.dsh/dsh-role-prompts.md.

A lightweight plugin that decompresses and reads past sessions, so a new session can read what an earlier conversation contained, in milliseconds per read. `/recall` lists the sessions of the current project with title, last activity, turn count and first prompt; `/recall <number>` reads back the turns of that session; `/recall all` covers every project; the model can also be asked in natural language to query with the `recall_sessions` tool.

Delete a DSH conversation from its sidebar menu or the conversation header, optionally cascading into that conversation's associated memory nodes when you tick the box (the confirmation dialog shows the hit count before you commit); deletes land in a plugin recycle bin with restore, every action is appended to an audit log, and batch deletes are rate-limited with per-conversation rollback.

Prepares context summaries in the background and applies them at safe step boundaries, with native compaction fallback and a per-conversation history of summaries, application status, timings, and token usage.

Per-turn checkpoints of the whole workspace: every turn ends with a snapshot, the files it changed are listed under that turn in the chat, and any turn can be restored — files, the conversation, or both. Capture is a whole-tree scan rather than a hook on write/edit tools, so edits made by shell commands, external editors or git leave a record too. Restoring the conversation forks it from that turn instead of cutting the original, and a restore can itself be undone. History sits in a shadow git repository under DSH_HOME and never touches your project .git. Requires Git >= 2.20 and Node.js >= 20.

Self-hosted chat room where the owner and coding agents share one room: a local Node server (SQLite, REST, SSE) that the plugin starts when it is not running, a DSH sidebar entry that opens the room in a panel, five tools (room_join, room_send, room_read, room_status, room_leave) that push an incoming message into the session as a user message labelled with its sender before flushing it to the session log, and a Codex CLI connector that forwards room messages through `codex queue`. Every message carries a server-assigned author, platform and seq, and messages from anyone other than the owner are delivered as data with the sender named. Requires Node.js 24+.

Replaces the harness identity block with its own prompt pack: three system-prompt sections (identity, rules, footer) in full, concise and dev presets, a per-turn rule card appended as a real user message, a remote announcement feed that falls back to a bundled copy offline, a GitHub Releases update check with an apply command, five `sunder_*` tools, and a read-only status section in Settings.

Answers model calls by driving your own logged-in chatgpt.com session in a local Chrome, so inference spends the ChatGPT web quota rather than Codex quota, and adds a JSON tool-call protocol so the web model can run DSH tools.

Model failover for DeepSeek Harness: pick one or more providers and the pool becomes every model inside them; when a request fails (rate limit, quota, timeout, server or transport error) the next untried model in the pool retries automatically, and the original error surfaces once the pool is exhausted. Configure from a seat beside the composer model picker or the model_failover tool, with no restart needed.

Registers the workbuddy model provider by mounting dsh-llm-workbuddy, supervises the local wb2api gateway, and runs a bundled Responses-to-chat-completions bridge so Codex CLI can use the same gateway. Skips work that is already running or already registered, and reports each part through a status tool. Requires a local wb2api gateway and a WorkBuddy account.

Two-level model routing: pick the best model group first, then the best channel within that model; a failure switches channel before switching model. Preference mode pins one model across its channels, a status bar under the composer shows the live model, channel health and the day's token usage, and a speed/intelligence report can be imported as the routing prior. Exposes a model_orchestrator tool and a /route command.

Registers local Qoder, QoderCN, OpenCode, Pi and CodeBuddy CLIs as DSH subagent backends, with ordered model fallback, live progress, per-run credit display, a settings page, and slash commands. Requires the corresponding CLI installed and logged in.

Minecraft-styled theme for the DSH web GUI: blocky pixel components, a photo wallpaper library with auto-rotation and local uploads, Minecraft UI sound samples, and a BGM player with a local track library.

Adds an appearance settings page to DeepSeek Harness: five eye-comfort light themes, each with its own accent and link colours, plus controls for the accent and background colours, UI and code fonts and sizes, font styles, content width, contrast and reduced motion.

Cross-session usage panel for DeepSeek Harness: an always-on usage ring plus a draggable panel that aggregates token usage, cache-hit rate, cost and balance from local session logs, with per-tool cost attribution, iOS-style tile layout editing and an optional animated companion face.

Alibaba Cloud / Qwen balance card above the Settings row in the DSH web sidebar: account available and cash balance, coupon balances with expiry dates (student vouchers included) read through the BSS OpenAPI, and OpenAI-compatible relay quota. An official DashScope sk- key has no balance endpoint at all, so real money and coupons require an Alibaba Cloud AccessKey with bss:DescribeCoupons + bss:DescribeAcccount (AliyunBSSReadOnlyAccess is enough); secrets stay in the host process, the browser only sees a masked AccessKey ID, and /api/dsh-qwen-balance/* is loopback-only.

Composer pill with the DeepSeek account balance, the live peak/off-peak pricing phase, and this session's spend priced request by request at the rate in effect when each request was sent. Subagent sessions' costs are aggregated into the parent session; Search and Fetch fees are charged only for DeepSeek's search engine, while third-party engines (Tavily, Bing, Exa, …) are counted but free. The balance refresh interval is configurable.

Buckets every model call by local date, provider and model, then shows the totals in a sidebar card, a per-chat pill under the composer and a settings page, alongside each provider's account balance and subscription windows.

DeepSeek Harness plugin that trims tool output (head/tail plus grep folding), adds optional prompt shaping (Caveman and Ponytail), instant local responses, RTK command-output compaction, context-pressure handling, optional LLM-summary compaction, stable prompt-cache layout, a Web settings UI, and persisted savings telemetry.

Fork of dsh-effort-slider that splits the composer model seat into two buttons: the model name opens the model list, the effort label opens the Claude-style slider with WebGL fire.

One-click thumbs up/down feedback UI that injects rating summaries into model context.