Plugins

Long-form novel writing plugin: each book is a git repository of frontmatter files, with 39 DSH domain tools and a web writing UI. Deep import drafts candidates, AI adoption into canonical assets requires DSH approval, and deterministic continuity checks ship with a report-only benchmark. Independent open source (MIT), not an official DeepSeek product; requires Node >= 24.11.0 and currently targets DSH 0.1.2-rc.1.

WeChat Official Account channel for DSH — WeChat messages run agent turns and the answers are pushed back through the customer-service message API, with signature-checked callbacks and an openid allowlist.

Dynamically trusts every Host header that actually arrives and flips the default web binding to 0.0.0.0: wildcard or unenumerable entry domains work without editing the start command, the authentication layer is untouched, and hosts are evicted by LRU beyond a capacity cap.

Manage VPS servers over SSH key login: 21 zero-token /vps- commands (status queries, recipe installs with a plan and /vps-yes confirmation, reboot that waits for the machine to come back), an in-conversation terminal (xterm.js over ssh -tt) for interactive programs, 5 agent tools with risk-tiered confirmation, file backup with automatic restore and a firewall/SSH safety net, 29 built-in recipes, and a settings page for adding machines.

Read-only DSH/Cordis composition doctor for plugin conflicts and upgrade rehearsal: scan profile manifests and patches, find duplicate rows, hook-order and UI ownership conflicts, compare redacted snapshots, diff plugin/row/hook changes, and preflight target DSH releases with explicit evidence boundaries — without mutating a real profile.

A GitHub-connected visual git manager for DeepSeek Harness: guided GitHub-Flow steps, commit graph with PR/CI badges, one-click GitHub login, PR and issue management, and structured git tools for the agent. Renamed from gitcompass in 2.0.0.

Per-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md, DECISIONS.md and SESSIONS.md — are auto-created on the first step of any session in that workspace, re-read from disk and re-injected only when they change (and re-injected if compaction dropped them), and written back by classification through a memory_checkpoint tool, with a bounded end-of-turn nudge when a turn did work but recorded nothing. memory_read and memory_search read the live log and the archive, the latter over a zero-dependency BM25 index. The session log is capped at 200 entries with the overflow moved to SESSIONS-archive.md — never injected, but visible, readable and searchable, and restorable one entry at a time. Settings page: a workspace list with a path filter, read-only tabs for the three memory files plus the archive, reload, export/import of one workspace's memory as a JSON bundle, a two-step clear, a panel that rewrites or removes the AGENTS.md instruction block, and a PROJECT.md staleness reminder. A composer status chip shows that workspace's sync state and creates the files on click. Zero dependencies — no vector store, no embeddings, and no model calls.

Layered memory for DSH whose agent-facing surface is 10 tools: high-privilege writes (memory_add, memory_delete, memory_import), rumination controls (memory_ruminate, _cancel, _status), and a memory graph (memory_search_graph, memory_expand_graph_node), built over an L0-L3 distillation pipeline that recalls and injects relevant memories before each model step.

Model capability editor: edit each model reasoning-effort levels and image-input (multimodal) declarations inline in the official model page, written back to settings.yaml as a whole group, with a floating entry as fallback when the anchor breaks.

Session-affinity routing for LLM gateways: injects the session ID into every request sent to NewApi-style gateways so the gateway can pin requests per session and raise prompt-cache hits; takes over the official pi-ai routing on install and restores it on uninstall.

Session usage statistics panel: token and request stats at day/hour/minute granularity, an activity heatmap, bottom-bar session info takeover with per-turn cost chips, and cost estimation under multi-condition time-segmented pricing. Re-implemented from HaoyueQin/dsh-usage-statistics-panel with extensions.

Agent billing and usage observability for dsh web: session-log direct-scan recording (zstd, per-event timestamps, watermark + lastSeq double dedup), multi-account rate profiles per provider and model, per-window live badge reading the window session id via React fiber, full glassmorphism dashboard with 14-day sparkline, budget alerts, relay-station balance queries and a 332-model official price library.

Section icons for the settings navigation: replaces the uniform gear icons with per-section glyphs and fills the plugin-market card avatar slot with each plugin icon; a page reload after uninstall restores the official icons.

Literature search for DeepSeek Harness over the official PubMed NCBI E-utilities API (esearch/esummary/efetch/elink) and Google Scholar (SerpApi engine, or direct HTML parsing because Google publishes no Scholar API). Zero runtime dependencies.

Per-command proxy for DeepSeek Harness: the agent decides which shell commands leave through a proxy, backed by a kernel the plugin installs and supervises itself.

输入卡底部工具行的计费时段徽标，附倒计时。高峰为北京时间周一至周五 09:00-12:00、14:00-18:00；周末全天算空闲，周五 18:00 后显示距下周一 09:00 还有 63 小时。

Biomedical research plugin for DeepSeek Harness (dsh): biomcp MCP server tools, scientific plotting skills, and deep-research subagent

Cross-session long-term memory for the DeepSeek Harness: a two-phase extraction/consolidation pipeline over a file-based memory workspace, recall injection, a citation feedback loop, lease-based job semantics, plus a settings page, a sidebar status panel

Keeps an unfinished task list visible across turns. DSH clears the todos projection at the start of every turn and expects the model to rewrite the whole list, so when a turn is interrupted the plan is durably in the session log but permanently gone from the UI — and todo_write is write-only, so neither the user nor the model can read it back. This plugin registers one ordinary session/event listener, remembers the last list per session, and when a turn/start arrives whose remembered list still has unfinished work, re-appends that list so the projection stops reporting an empty plan. No fork of tool-todo and no waterfall: a plugin cannot replace the projection (the registry throws on a stateVersion mismatch), so appending the event the fold reacts to is the reachable seam. Deliberately narrow — only unfinished lists, at most one event per turn start, fails open. Verified by a controlled A/B on real sessions: identical runs differing only in whether the plugin was installed, folded through the real projection definition. Zero dependencies.

Keeps one reasoning-only turn from making an entire session unusable. When a turn produces no visible text and no tool call, the assistant message is persisted empty, the gateway then rejects every later request in that session with 'content or tool_calls must be set', and the session is dead with no way back through chat. This plugin registers a single llm/stream waterfall listener and, only when the turn carried nothing visible, injects a small text block immediately before the terminal finish, so the persisted message is never empty. Ships the fixture DSH's own mock cannot express (a strictly reasoning-only SSE server, since llm-mock-server forbids an empty successText and always appends text after reasoning), plus an end-to-end reproduction that replays a real persisted session through DSH's own serializeMessages. Preventive, not a repair. Zero dependencies, one file, no process or filesystem access.

FreeDSH — free-first multi-model routing, safe core updates and pt-BR/Windows support for DeepSeek Harness. Installable as a DSH bundle (dsh plugin add). Unofficial project.

File-defined subagent roles for DeepSeek Harness: roles live in project and global .dsh/roles files, a delegating agent sees one catalog line per role, and each role's tool policy decides which tools its child can see.

Composer readouts for the DeepSeek Harness: CJK-weighted draft token count, session spend at official peak/idle rates, context occupancy, and what the same usage would have cost on the costliest other model; client-only, with no host half and no credential access.

Live token cost for every chat in the DSH Web UI: the chat, its subagents and the whole session tree, priced from a bundled models.dev snapshot of seven providers and 139 priced models, with cache read and write rates wherever the provider publishes them and DeepSeek from its own peak and off-peak table. Every finished answer carries its own price in the transcript, and a chat that is not currently open is priced from the log instead of disappearing. Spend is costed per interval from an append-only JSONL ledger in the project folder, so logged work keeps the tariff it was billed at. On top of it: budget-aware work plans packed against a money limit, routing scenarios that show which models are worth connecting, a generated plan document in English, Chinese or Russian, and a warning when spend belongs to no plan unit.