Plugins

Profile-wide DSH governance and routing with a Web Control Center for responsibility and evidence inspection, plus compaction, scoped semantic memory, safety continuity, and verified delivery; compatible with DSH 0.1.5-rc.1.

Novel-writing guardrails: 20 novel_* tools enforce fact-ledger consistency, phase and chapter gates, machine audit with deterministic metrics, and proposal-only revisions; a right-panel workbench covers reading, TTS playback, polish, proofread, continuity checks and batch drafting, and a bypass engine runs internal steps off the main conversation.

Adds an optimize button beside the composer that analyzes and rewrites the prompt draft with SSE streaming, conversation-context awareness (template vs intent-polish strategies), an edit-continuity memory chain, undo, and model routing with fallback and a connectivity test.

Chinese long-form screenwriting skill: two input blocks (background + character bible) feeding a causal-value engine, anti-AI-flavor review, and a continuity ledger; works on Codex / Claude Code / dsh / zcode.

Evolving memory infrastructure for DSH — evidence, time, context, and correction for long-term continuity — backed by a local Python 3.11+ memory service (fastapi/uvicorn/pydantic, started automatically as a python3 subprocess).

Local-first fiction workspace that links outlines, chapters, characters, timelines, writing rules, and continuity checks to the conversation.

Injects a small continuity pointer at the start of a new session, naming the previous session and any handoff file, and reuses DSH's own compaction summary when there is no handoff file.

Local image, voice, music and SFX generation plus transcription, with pinned identity: characters, animals, objects and actor voices are defined once and reused on every later call, degenerate output (a near-flat image, silent audio) is rejected instead of returned as success, and a generated line can be read back as text so a clone that swallowed its ending becomes visible. The engines unload when idle, and image generation and transcription can each be pointed at an OpenAI-shaped API instead of the local Vulkan backend.

Multilingual writing, chunked long-form collaboration and continuity review, with on-demand DSH delegation discovery. Requires Python 3.9+ on PATH.

Explicit cross-session work state for DeepSeek Harness: goals, decisions and next steps captured automatically from host events or via a model-visible work_state tool, inspectable with /checkpoint.

Adds two audit tools and four skills for Chinese medium-to-long texts (fiction among them) and document review — seven-dimension AI-flavor scoring with line-numbered blocking findings, plus file-backed continuity state for long manuscripts. Do not install with the older dsh-deai-audit from the same author, which registers the same tool names.

Telegram and WeChat bridges plus handoff continuity for DeepSeek Harness (DSH)

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.

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.

Keep conclusions alive across context compaction: the model writes a task checkpoint and the plugin re-injects it into the system prompt's first node — the span compaction never touches, so it survives any number of compactions. Four-tier injection (0/95/175/≤12000 chars) scales with session relatedness; checkpoints live in the plugin's own folder, never in your workspace.

Cross-model continuity for DeepSeek Harness: memory, skills and rules live in local files, so judgement survives session and model changes. Not about storing more memory — about using it well after the model changes.

Checks supervision logs for cross-day continuity and for on-site supervision coverage, against GB/T 50319-2013 and other published documents. Reports gaps and coverage differences for a human to review.

Restart your ongoing agent sessions once on server restart in DeepSeek Harness.