Plugins

Creates and edits Feishu and Lark cloud content through ten tools - Bitable databases and their records, documents with Markdown converted to native blocks, spreadsheets, wikis, drive files and messages - plus Base V3 dashboard charts and server-side aggregate queries.

Turns guard denials, gate failures and human thumb-downs into project lessons, and injects only the rules a human has armed into each new session of that project; it registers no model tools and is reviewed through its settings card.

Write guard for the Akasha Book store: blocks tool calls that write into the memory data directory, and injects the store usage contract and self-layer sections into the system prompt. Companions: Hindsight (repo memory), OpenViking (user memory), and the built-in session search (see repo README). Setup: clone the repo, copy core/ aside, then replace <AKASHA_DIR> in cordis.patch.yml with its absolute path (or set the AKASHA_DIR env var); plugins fail loudly while the placeholder remains.

Exposes every model of every provider configured in DeepSeek Harness through one OpenAI-compatible endpoint on a fixed loopback port, with a sidebar page for the base URL, key, port and model ids.

Tiers free-channel models into three 1M fallback chains plus a custom chain; orders them by measured throughput, drops models below throughput or error-rate thresholds, and rotates accounts. Requires an OpenAI-compatible gateway (default :8326).

Free Egg credits panel for the DSH sidebar: WorkBuddy / Qoder account balances, daily budget, check-in state and per-turn spend (WorkBuddy credits priced per input / cache / output token type where rates are known), with one-click switching of the platform whose credits are spent first when new-api is configured. Requires a local WorkBuddy2API or Qoder gateway.

Local-first usage analytics for DSH: subscribes to session events and aggregates tool calls, turns, errors, latency and capability usage into daily tables, shown in a sidebar panel (6 KPIs, 14-day trend, top tools, capability breakdown) and served over a fenced local HTTP API with 18 JSON-RPC methods. Zero runtime dependencies, local mode makes no outbound requests, and no message bodies are collected.

Reads the local Codex CLI ChatGPT-plan quota (5-hour and weekly windows), defaults to gpt-6.1-sol at high reasoning, falls back to gpt-5.6-sol when a window has 10% or less left, and delegates tasks through codex exec with an explicit opt-in for the expensive gpt-6-astra model. Requires a signed-in Codex CLI (`codex login`).

Adds F5 / Ctrl+R page reload to the DeepSeek Harness desktop web UI, which production builds lack by default (the "Reload Page" menu item and bare-F5 accelerator are development-gated). Binds soft reload (F5, Ctrl+R) and cache-busted hard reload (F5 with a modifier, Ctrl+Shift+R, appending a _dsh_refresh timestamp) through a capture-phase client key listener.

A file editor in the DSH web GUI right sidebar: open any text file, edit it, and save in place, with a version gate on every save — if the file changed on disk during the edit it stops and asks instead of overwriting. The document preview gains an edit button and a two-step delete button, and a separate File editor sidebar tool brings its own file tree for create, rename or move, copy, cut and paste (including a file taken from the system clipboard), delete and drag to reorganize. Two renderer bands cover 107 plain-text, config and source extensions; the second is offered only as an open-with choice, leaving the shipped Markdown and highlighted-code views as the default. All mutations run through the plugin's own trusted host routes, behind the connection trust fence, the workspace containment check and the sandbox policy.

Give DeepSeek Harness its own persistent computer: a bundled microVM with shell, browser, live view and approval gates

Operate the Chrome or Edge tab you are already in, through the unpacked extension: hover, coordinate clicks, drag, batched actions, whole-page screenshots, file upload, image addresses and switching between connected browsers — with approval-gated actions

A social deduction game played against your own model configurations. A table has N seats (six by default, one of them yours) and some of the rest are played by agents bound to different provider, model, temperature, system prompt and disguise settings; you interrogate them and cross-check the answers to work out which seats are not human. Seat identity and each agent model configuration stay hidden in the host state until a seat is judged, then the disguise parameters are revealed. Every round exports a per-seat conversation JSONL plus the judgment record, and the same seed with the same move script replays byte-identical, so runs with different models or disguise strengths can be diffed.

Adds a local phone pairing, gateway control, and diagnostic panel for Pocket Bridge in DSH Settings.

System-prompt surface drift gate: every section any plugin or preset contributes to the assembled system prompt is hashed and baselined; a silent rewrite of what the model is told fails loud.

Deterministic write gate: scope policy denies out-of-scope write/edit calls before they touch the disk, residue rules scan the written text, and every decision lands in a content-hashed JSONL ledger; can reuse the repo's agent-pr-gate.yaml so CI and session enforce one policy.

Tool-surface snapshot and drift gate: baselines the full visible tool registry (name/description/parameters, MCP tools included) into a committable JSON file and warns loudly when an upgrade adds, removes or reshapes a tool.

Deterministic network egress gate: web fetches and searches are checked against a destination allowlist in tools/pre-execute and denied before they run; shell fetch-verbs are observed (enforcement opt-in).

Adversarial review gate for tool calls. It hooks `tools/pre-execute`: a local regex pass over destructive commands (`rm -rf`, `git push --force`, `git reset --hard`, `DROP TABLE`, `format`, disk writes) and sensitive paths (`.env`, `id_rsa`, `.ssh`, `.git/`, `$DSH_HOME`) runs first with no latency, and only a hit is escalated to one review-model call that returns allow or deny. Plain reads and ordinary writes never enter that path, so everyday work pays no added delay. Every verdict is shown live in the Web GUI.

A resident assistant for DeepSeek Harness that is deliberately not another chat box: one floating window plus one standing conversation, both independent of every other session. The heartbeat is held back by four gates — an authority grant, a daily turn budget, quiet hours and a pacing cooldown — and it keeps working across restarts through a lease it has to hold. Each wake is decided by a model that must answer SKIP or a short message, so silence is a decision rather than a failure. The window shows the standing conversation's real message flow, read from the host session store, or from the on-disk session log when the host does not publish that session, and it can send into that conversation directly. den carries the same reach as the person it stands in for, with one limit: read-only. It may read every session, this machine and work channels such as GitHub, but it does not write, send or publish, it never asks anyone for permission, and it never gates another session's tool calls. `npm run digest:github` turns GitHub notifications and your own open pull requests into three Chinese sections — waiting on you, waiting on your review, and yours — with reply drafts that are explicitly marked as unsent.

Removes the model-capability gate that blocks image prompts: patches llm.resolveModelInfo results and adapter model tables to declare image input, so routes with no declared input modality can send and read images. No app.asar or config-tree edits.

OpenAI-compatible web search provider for the built-in web_search tool: one baseURL/apiKey/model config powers Qwen Token Plan, OpenAI and any Responses API gateway.

Token statistics for every stored DSH session: a Host service folds the durable session logs into a persisted checkpoint and serves them over one read-only HTTP route, and the Usage settings page paints the saved aggregate immediately, then updates it in the background. Days are bucketed by hour behind a date picker, next to a trailing window with per-model breakdowns, request and web-search counts; no cost or pricing model.

Adds two visual pages to DSH Settings. MCP servers are kept as a JSON source of truth that rewrites the profile patch managed block, with YAML validation and timestamped backups, plus import of a pasted mcpServers JSON that first lists what will be added or overwritten. Thinking unlock probes each OpenAI-compatible gateway for the reasoning efforts it really declares and writes the per-level config back while leaving other hand-written YAML byte ranges untouched; the available model list syncs from a separate button that previews additions and removals, then writes levels and models in one atomic pass, and can also run on the page schedule.