Plugins

Circuit breaker for idle agent turns: watches agent/assistant-stream and cancels a turn that produces only reasoning — no text and no tool call — after 45s, after 80000 reasoning characters, or on a degenerate repetition pattern (exact repeat unit, sentence-template repeat, sparse repeat, or 6-gram density). On trip it injects a continue instruction that requires the next action to be a tool call, and ships 11 regression cases plus per-gate tuning.

Edit any user turn in DeepSeek Harness and re-run it: an inline editor on the message row rolls the conversation back to just before that turn through the official surface-replace contract, then re-prompts the agent with the revised text. The append-only

Behavior-drift reports for DSH sessions: compares two session logs and reports tool-sequence alignment, tool mix, reasoning volume, timing, retries and file targets, with an optional CI threshold gate. Zero dependencies.

TypeSafe Jev (System One decision model) as the jev_decide tool for DeepSeek Harness: noul, choice and score questions return calibrated probabilities; credentials reuse the DSH credential seam; 429/529 backoff retry built in.

Pairs two DeepSeek Harness machines with a one-time code - directly on a LAN, or across networks through an end-to-end-encrypted relay with a zero-config official default - so one agent can run tasks and exchange files on the other while each machine keeps its own files in place.

Connects seven Wind financial MCP domains and Wind Alice to DSH while resolving WIND_API_KEY only inside the host credential boundary.

A judgment core for DeepSeek Harness: a cognition loop that gives every decision a source and attribution and drives planning to a close, hippocampus memory that condenses running experience into reusable knowledge, and a customizable persona card (name, personality, communication style). Requires DSH ^0.1.0-rc.7.

Persona engine for DeepSeek Harness: one config.json drives the AI's self-name (per model, per tier), how it addresses you, relationship stance, character text, per-item work contracts with individual toggles, thinking-chain language, appearance and reply tone (both opt-in and per-model overridable), and long-term memory gated by human confirmation - the AI can only append proposed candidates, a human confirm line flips them into effect, and the log is physically append-only and replayable. Confirmed entries are injected as a quoted data-not-instructions block; entries tagged with a kind can instead be routed to arbitrary files on confirmation and never reach the prompt. Three prompt sections re-evaluate from disk on every assembly, so edits apply on the next step with no restart. Persona presets are shareable JSON snapshots (imports and exports SillyTavern character cards, v2/v3 read, v2 written) and deliberately never carry memory. Zero runtime dependencies, no network, no shell; any error degrades to an empty section rather than a broken session. Ships blank - installing changes nothing until you write something.

WeChat article typesetting workbench: renders Markdown into inline-styled HTML you paste into the WeChat editor, with a right-sidebar panel and five model tools for block-level revision.

Cross-session memory for DeepSeek Harness: agents save, search and update user preferences, facts and project decisions; important entries are injected into later sessions, and a Settings section lists, edits, archives or deletes them.

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.

Controls user-authorized Chrome tabs from DeepSeek Harness through a local native-messaging broker, with semantic page reads, actions, screenshots, and explicit handoff.

Per-model appearance for the DSH Web UI: an ordered rule list matched against the current session model name, each rule carrying its own wallpaper, theme colour, layout mode, framing and wallpaper opacity and blur, plus per-surface opacity and frosted-glass blur for the main background, left panel, right panel, cards and panels, input and controls, settings panel, conversation text frame and trajectory view.

Zero-config lint feedback loop for JS/TS, Python, Go and Rust: lint_diagnostics / lint_workspace_errors / lint_fix tools driven by the repo's own eslint / biome / ruff / golangci-lint / cargo clippy (auto-detected from config files, repo-local node_modules/.bin resolved first, nothing bundled), plus an auto-injected post-edit findings delta on the harness fs/observed event and a bounded completion gate — edit → lint → auto-repair with one lint_fix call for dsh agents.

Auto-fills reasoning-efforts, context windows, output limits and image modality fields for models from unofficial (custom) providers (with data from models.dev), and provides user experience improvements such as compatibility enhancement and remembering reasoning effort.

TickTick (Dida365) task bridge: a session-header task panel and curated agent tools over the official TickTick MCP endpoint.

Models+ settings page for the DSH web UI: per-model reasoning-effort tables, input modalities and compat flags saved through the official settings pipeline, with models.dev metadata prefill and API key management.

QQ Official Bot adapter for C2C single chat, interactive action boards, workspace session management, and real-time Web UI sync.

Six-stage WeChat Official Account content-publishing workflow with quality-gate tools and a bundled skill.

A DeepSeek Harness Skill built on the official command-line tool maa-cli for MaaAssistantArknights (MAA), enabling direct control of MaaCore to automate daily tasks in Arknights.

Native-feel DSH attachments: official PNG/JPEG/WebP/GIF thumbs plus 64px cards for other files via drag, paste, or paperclip; non-images land in .dsh-uploads and sent cards sit on the user bubble.

Agent discipline guard for DeepSeek Harness: four gates enforced at the harness boundary — loop circuit-breaker, token-cost fuse, route-switch warning, plan approval — where prompt-level reminders can't reach, so an agent can no longer burn a weekly quota in minutes; one-click 🛡 chip, hot-reloadable thresholds, and presets from invisible-but-armored to warn-only.

Live2D companion for DSH: a floating Cubism model with state-driven expressions and mouse tracking; config-driven geometry (size/position from the plugin config); official Haru sample bundled (© Live2D Inc.).

DeepSeek Harness peak/off-peak pricing gate: during peak hours (weekdays 09:00-12:00 / 14:00-18:00 Beijing time) every send asks for confirmation, with an option to mute the reminder for the current peak segment, or to queue the message for off-peak (half