Plugins

A living memory workbench for DeepSeek Harness: watch the Hindsight bank grow (7-day curve, recall heat, timeline) and manage knowledge pages and background tasks, with the local daemon auto-started by the plugin.

Session management for DSH: archive or delete one session, archive/delete all sessions in a workspace, and restore archived sessions from the settings page — archiving backs up workspace metadata and restoring recreates deleted workspace registrations automatically.

Auto-wakes the main agent after a DSH service restart: compares last-run timestamps, posts a recovery notice with humanized downtime, and delivers it so interrupted work picks itself back up. Runs on plain cordis ctx, packaged-DSH-Desktop ready.

One-click/auto sync provider model lists against /v1/models endpoint.

DSH Web 任务面板插件：把需求、队列、子 agent 执行、自动复核、验收返工和定时执行做成一个可视化闭环。

Fail-closed network recovery, recommended answers, and safe unattended continuation for DeepSeek Harness.

autodsh —— 基于 DeepSeek Harness 的自动化任务插件：触发器 + 自动化内容 + 结果通知，由任务面板统一管理。An automation-task plugin for DeepSeek Harness: triggers + automation content + result notification, managed from a task panel.

Type /tabs to pick a browser tab (via chrome-devtools-mcp) and auto-fill its URL into the composer.

Three-layer local memory for DeepSeek Harness: L1 snapshot memory (MEMORY.md/USER.md) read on demand through the memory_* tools + L2 searchable knowledge base (facts + SQLite FTS5, Chinese search via sliding-window tokenization) + L3 import from Hermes/Claude Code/Codex/WorkBuddy and from approved Agent Hub documents (memory/global, memory/projects, accepted decisions) with content-hash dedup. v0.2.0 removed every automatic injection: memory enters the context only when the model calls one of the 12 memory_* tools, and data stays on the local drive.

Real DeepSeek account balance and official spend tracker in the session header, with peak/off-peak badge, monetary alert with auto-stop, and one-click top-up.

Expand button for the DSH Web UI composer — appears at 3+ lines, stretches to near-fullscreen height, auto-collapses on send, and Enter inserts newlines in expanded mode.

DSH plugin: auto-import local AI CLI conversations (Claude Code, Codex CLI, Cursor Agent) as real DSH sessions

DSH plugin: auto-upload conversation progress to Tencent IMA (daily note + Work knowledge base), mirroring the local Claude Code ima-upload workflow

View local Skills and edit automatic and /name invocation policies from DSH Web settings, with bundled and symbolic-link entries kept read-only.

A pouch of practical micro-plugins for DSH: per-turn wall-clock time injection, safe restart, session ID header badge, Tavily search provider, configurable LLM request-header routes, and an MCP server console managing the official @deepseek-ai/dsh-mcp-client at runtime — add/edit/enable/disable/reconnect, per-tool switches, live status over SSE, mcpServers JSON import, and auto-migration of profile-YAML MCP entries.

Composer stats strip for the DSH Web UI: official CNY pricing with auto-synced peak/off-peak tiers, per-model accounting, live timers, subagent-tree merging, DeepSeek account balance, budget alerts, and streaming cost estimation.

Antigravity-style run_command for DSH: short commands return inline within a configurable wait window (default 10s) while longer ones auto-promote into ctx.jobs for later collection and completion notices — executed via ctx.shell under the session sandbox and approval pipeline.

Transparent multimodal routing for text-only models: every image in every model call is fully transcribed (verbatim OCR, data, uncertainty zones, injection-hardened) by your own multimodal understander, with focused re-look via vision_relook and automatic retry on image-related failures. No bundled endpoints, no borrowed logins.

Mnemosyne memory for DeepSeek Harness: remember / recall / forget / stats / sleep tools, embedded skill, auto-setup, optional auto-sync/prefetch, and a Settings panel. Data lives under ~/.dsh/mnemosyne.

Dual-ledger cross-session memory: auto-extracts lasting facts from conversations into MEMORY.md and maintains a PROGRESS.md project ledger, recalling both into every new session.

Question index: an ordered, collapsible list of your asked questions floating on the right side of the conversation; click a question to jump the session to that point. Auto-indexes each session's full history on open, persists it locally, and jumps to older questions by growing the window on demand.

Workflow One - Visual AI workflow orchestrator for DeepSeek Harness (dsh), with multi-agent DAGs, live execution, recovery, and Feishu integration

Instance manager for DSH Web: a Mini Utility Dock panel that lists every local dsh web instance the machine can see (port, PID, uptime, live session count, resident memory, version), starts a new instance on an automatically picked free port in 3080-3129 or on a port you name, opens a row in a new tab, and stops one or all of them through that instance’s own graceful shutdown (appExit). Rows also show what each instance is serving, and read-only instance logs and session summaries are one click away. Where a peer is configured, the same panel lists and queries instances on other machines over a bearer-authenticated link. Every route is loopback-guarded, and a browser-facing action must additionally pass the host’s own browser authentication.

Dual-model auto-routing plugin: low-cost direct / high-cost upgrade with an escape-learning closed loop (wrong direct answers auto-learn fingerprints, force-upgrading the same fingerprint next time), persisted and interoperable with the Python ModelRouter.