Plugins

Results-only conversation toggle for the Web GUI: hides thinking and tool-call process rows, keeps one live status line while the agent works, restores working animations under prefers-reduced-motion, zh-CN/en localized. Works in the stock composer and inside dsh-split-screen panes; verified on DSH 0.1.1 and 0.1.5.

Diagnose, unstick, and read DSH sessions: list sessions with agent status, read conversations, diagnose stuck agents, recover them with cancel+keepInbox, and send messages to other sessions.

DeepSeek Harness (DSH) plugin: live conversation cost and DeepSeek account balance in the composer stats row — RMB in Chinese UI, USD in English UI

Draggable grid-aligned workbench of 28 mini-cards in the margins of the conversation (API balance, token usage, cost, context pressure, todos, goal, usage heatmap, GitHub repo, image relay), with S/M/L/XL size tiers.

Tree view of a DSH conversation: editing an old message forks the thread, every version lives in one tree while the sidebar keeps a single entry, branches can be renamed, and a branch can be promoted to a session of its own.

Brings the models included in the Xiaomi MiMo desktop app (free during beta) into DeepSeek Harness, with zero configuration in the DSH conversation window.

Element annotation and review panel for the DeepSeek Harness web client: pick UI elements in a live app preview, write notes, and send them to the conversation as one structured block

Native side-by-side chat beside the main conversation: an independent archived DSH session with full native UI, on-demand parent-context retrieval, selection quoting, and a keep-or-delete lifecycle.

TypeSafe Jev (System One decision model) for DeepSeek Harness, end to end: jev_decision (choice/score/noul, parallel, typed answers + confidence), a Settings > Plugins card for the API key and switches, inline tool views showing every decision in the conversation (answer, confidence, latency, cost), an auto-guard (deterministic + Jev risk/loop checks), a local /jev dashboard, and an online verification benchmark (96.3% on 27 labeled questions, median ~283 ms on jev-latest, 2026-09-21). Honest by design: real API only, no mock fallback.

Shows a DSH session as a conversation canvas — every turn is a node, any turn forks a real child session, and a compacted context folds into one green node you can keep talking from; the left rail groups canvases by DSH workspace and renames them in step with the session titles.

DeepSeek Harness bundle for GitHub PR monitoring, readiness, and conversation reports

Fork companion for DSH: on any official fork, copies every direct subagent child of the source session onto the forked conversation (recursively, whole subtrees) through the official agent API, leaving each copy as a cold session the official resume path can wake — so the new conversation keeps its subagent panel and can keep messaging those children, while the originals stay with the old branch.

Reformats dsh session titles as "date | type | topic" (type and topic are summarized by a model from the full conversation), and hides unused sessions from the sidebar without deleting them.

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.

Adds a Quick Chat entry to the Web UI sidebar that opens a floating chat window with its own model and reasoning-effort picker, optionally seeded with the current session's transcript, and keeps every side conversation in a resumable, renamable, deletable history.

Settings section for archived sessions: browse by workspace, search, batch unarchive with the sidebar updating live, and optional auto-archive rules (idle days, keep-last-N per workspace) with a dry-run preview — plus a left-edge turn rail for jumping between turns of long conversations and ↑/↓ input history in the composer.

Canvas task board ported from CodexFF: hierarchical parent/child tasks with boundaries, snap-aligned draggable panels in a conversation view tab, plus `board_*` / `task_*` agent tools and a sync skill.

Side-ask drawer opened from a completed answer's action row: follow-up questions run in an independent, auto-archived session seeded with the prior conversation text (read-only, capped at 48,000 characters), leaving the main session untouched. The side session inherits the main session's model, switchable inside the drawer, with a context-usage ring.

给每次 AI 对话装一根 Token 保险丝：为每条用户消息设置独立总预算，统一约束输入、缓存、思考与回答。A per-conversation total-token safety fuse for DeepSeek Harness, with a whale slider and automatic reset on the next user message.

Drag-and-drop file upload into the conversation composer, token usage pill with quota tracking, and session archive management — a three-in-one daily-driver addon.

Codex-style message navigator for the DeepSeek Harness Web UI: a tick per user message along the conversation edge, hover or click to preview and smooth-jump to the message, with full history auto-loading.

One-click standalone two-column code review page for Git diffs in the conversation: line numbers, add/delete coloring, character-level highlight, hunk-aware per-file sections, a file nav sidebar and a stats bar; line comments submit back to the DSH composer, and the UI follows the DSH locale.

A Codex-style conversation navigator for the DeepSeek Harness Web GUI.

Select a range of a DeepSeek Harness conversation and share it as a branded PNG long image, with draggable magnetically snapping range markers.