Plugins

Agent config packer for DeepSeek Harness: pack local agent assets (skills/sessions/profiles/settings/memory) into a zip for migration or sharing, with privacy scanning, diff-based restore, pack management, and a settings UI; memory ships as a read-only Markdown mirror, not the live database.

Conversation history recall for DSH: three-layer (literal/fuzzy/semantic) retrieval over every past session's original text, fully local & offline — AI never forgets what you told it. One-command install via `dsh.bundle.patch`, semantic layer runs in a worker thread.

Export sessions to Markdown/JSON for review, replay, and per-session cost summaries.

Import Claude Code sessions, skills and plugin assets into DSH as native resumable sessions, and export or sync DSH sessions back to Claude Code JSONL.

Incognito sessions: a standalone ephemeral sub-agent with its own preset (no parent context) and full toolset, draggable floating window, burned to zero traces on close.

Writes live provider model lists into DSH settings and shows 5h/7d plan windows or metered balance for the current session model.

Settings usage dashboard: tokens, requests, output tokens, and cache-hit rate from session logs, with a stacked chart and a breakdown table by provider, model, or workspace.

Session cost estimate in a status bar at the bottom of the conversation (per-model token pricing, CNY) plus the live DeepSeek account balance via the official balance API.

Mobile UI for the Web GUI on narrow screens: full-width responsive layout, overlay session drawer, 44px touch targets, safe-area support, and reading enhancements with zero desktop impact.

DSH Web right-side output dock: session-scoped tabs for reports, images, data, video, and audio, with inline previews, output quality checks, and a searchable per-turn history.

Offline diagnostic for DSH: 19 checks across env, profile, and session state, with a settings "Doctor" panel and a read-only JSON API.

Zero-touch runtime telemetry for DSH: every session auto-writes task, model tier, tools, failures, duration, status into a human-readable journal with a stats section (pure observer — no tools, no LLM calls, no injection).

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 会话管理设置面板：列出本机全部会话（运行中/空闲/已归档），支持继续会话、预览大纲、删除会话 | Session management settings section for dsh web: resume, outline, and delete any session

用于监控当前会话额度消耗、预估费用及当前API余额/Used to monitor the current session's quota consumption, estimated costs, and current API balance.

DSH 一键复活：重启后给所有被打断的会话自动发送「继续」指令（/revive 命令 + revive_sessions 工具 + 浏览器一键按钮）

Superpowers (obra/superpowers) for DeepSeek Harness: the software-development methodology skills plus their session bootstrap, as a dsh plugin

Shows DeepSeek balance and estimated daily spend, merges external vision-call JSONL records, and adds a per-session dashboard with model statistics, TTFT, cache rate, call logs, cost estimates, filters, and CSV export.

Appends local hash-chained JSONL receipts for tool results and session events without storing prompts, tool arguments, result text, or raw session IDs.

Agent trajectory governance and anomaly diagnosis: rebuilds flat session logs into multi-branch trajectory trees, detects loop deadlock, invalid retry, and goal drift, alerts with cost attribution, one-click interrupt and breakpoint fork via official APIs, independent GUI tab.

Session execution analytics: steps, tool calls, failures, repeated actions, token usage and verification signals, rendered as text/Markdown/JSON reports.

Export the current session to portable, schema-versioned Markdown and JSON files via the `session_export` tool and slash commands, with cross-platform-safe filenames.

Deep links: open a specific session or workspace via `?session=` / `?workspace=`.

Search and insert workspace file and directory paths with `@`, plus a `/h` menu for reusing prompts from the current session.