Plugins

Adds file-backed Chinese web-fiction planning, chapter writing, consistency review, rollback, and style-profile skills.

Conversation outline panel for the DSH web surface: user questions as root nodes (index, time, tool count and text volume per turn) with the Markdown headings of assistant replies hanging beneath them, plus level slider, search scope, bookmarks, copy and export as Markdown, section jump, keyboard navigation, a right-edge density rail and per-session reading-position memory. Read-only UI: it never touches prompts, tool results or provider traffic, and writes nothing outside its own localStorage keys.

Filesystem permissions for shell calls, granted per path and capability rather than per command name. The command line is parsed for the read, write, create, delete and execute effects it needs, a capability it lacks raises the approval card instead of a flat refusal, and the same rules are compiled into the macOS Seatbelt profile the process, its children and the code its arguments never showed all run under. An Approvals tab in the conversation reads the audit log back and shows which rule, automatic reviewer or person answered each call.

Session cleanup for the DSH sidebar: drag a conversation row onto the balance widget's whale and it eats the row — the session directory goes to a recycle bin, not to rm. Deletion asks one short question first (how many tokens it burned, and that prompt can be turned off in Settings). Undo from the persistent toast or the 12-entry log in Settings. Clicking the whale jumps straight to the plugin's Settings, where you can swap the avatar, drag the mouth into place and rewrite all 17 UI strings; blank, currently-open and running sessions are refused in place with a reason.

Prompt-polish template injector for DSH: click ✨ in the composer to inject a "polish my prompt" template (current draft auto-embedded), no send, no network, no model — the main agent rewrites with full context. Replaces narrative-prompt-polish (2026-09-14 migration).

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 cross-session memory for DSH that pushes only what changed - the first round injects every active entry, later rounds push only added / updated / removed ones, and nothing at all is injected when nothing changed, with keys that merely repeat an entry id left out of the text so the baseline is about 26% smaller. Facts and decisions carry semantic keys (one active truth per key), the model may only write to an inbox that a human promotes, an entry can carry a review date that raises a one-time reminder when due, and search is relevance-ranked with journal lines down-weighted and Chinese matched by bigram. A sidebar tab tells the lifecycle story instead of listing files - entries are grouped by stage (awaiting confirmation / in use / archived) along four axes (topic - one level, human-assigned, type, tag, date), each group can be ticked for batch promote / withdraw / archive / restore / delete / assign topic, and topics can be renamed store-wide or searched on their own. The archived stage reads in three levels - the category says why an entry left (distilled into the docs / useless for good / not needed right now, the first two being defaults you can add to), below it the entry topic stays collapsed until you click it, and entries with no topic sit right under the category. The tab also shows the global and workspace instruction files plus the current injection size. A zero-dependency CLI ships with it, so the store is usable without DSH.

DSH plugin: read and write DingTalk AI Tables through the official dws CLI, adding ten DingTalk AI Table tools (nine `dingtalk_aitable_*` plus `dingtalk_sync_job`), a settings panel, and scheduled CSV export.

Model-visible SSH file tools read_remote, write_remote and edit_remote: read a remote UTF-8 file with line-numbered paging, create a new remote file (an existing target is refused, there is no overwrite branch), and apply literal replacements with unique-match checking — all addressed through a single "alias:path" field whose alias comes from ~/.ssh/config.

Cloud workspaces for DeepSeek Harness: pick "Cloud (SSH)" in the workspace chooser and the agent's bash/read/write/edit/glob/grep tools transparently run on your Linux server over SSH. Includes ssh_* agent tools, an SSH host settings card, jump-host suppo

Codex-style per-session memory draft for DeepSeek Harness: one session one draft (rollout_summaries), restrained & passive (write only on explicit user request), layered disclosure (summary + registry), idempotent integration watermark. / 一会话一草稿记忆插件。

Image and video production toolkit for DeepSeek Harness - background removal with quality tiers, local inpainting retouch, headline and logo compositing, batch platform-size exports and image QA reports; for video, AI subject matting with background replacement (RVM ONNX, plus a chroma-key path), animated titles with fade/slide/typewriter/karaoke presets, 53 transitions with stylized variants, and light-effect and grading presets with LUT support, alongside footage inventory, accurate cutting, subtitle burn-in, music mixing and platform-spec exports; it provisions its own local Python runtime through a bundled bootstrap script.

Generate and format Chinese Word (.docx) documents from a simple markup file, using built-in heading styles, SimSun and Times New Roman fonts, and per-chapter figure and table captions.

Writes a Windows shortcut and tray launcher to start dsh web in WSL, with Health/Restart and the :3081 launch-token URL.

A dsh web plugin that wraps the running Harness in a native Windows desktop window: it bundles a Wails v3 desktop client (so installing the plugin is enough), probes the web port and writes the ~/.dsh/dsh-web-port.json protocol file for the client, registers a system tray, desktop/Start Menu shortcuts and a startup autostart toggle, and the client can start dsh itself if it is not running.

Draggable ring gauge showing live model output speed (tok/s) with an expandable per-step detail panel (exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).

Model visibility manager for DeepSeek Harness: hide or show any model in the conversation model selector from a dedicated settings page. Per-model switches, search, provider-level batch actions, reset-all. Zero intrusion - writes only its own hidden list, never the provider config; hiding a model in use never interrupts a running session.

Read-only Odoo tools over JSON-RPC: server info, model field introspection, and a restricted search_read limited to an allow list of models whose domain field names may not contain dots, so related-record traversal is not possible. A draft-create tool is registered only when allowWrite is enabled, and is limited to sale.order and project.task with the draft state enforced by the plugin.

Renders edit and write tool calls as always-expanded side-by-side diffs styled like git diff, with optional syntax coloring and word-level highlighting.

A document preview / edit / management plugin for DeepSeek Harness. It provides a VSCode-style "Document Center" workbench inside the DSH Web GUI: a file tree on the left, click-to-preview, editable code & Markdown with Ctrl/Cmd+S save; and exposes three document tools (doc_read / doc_edit / doc_create) to agents, letting models read and write workspace documents through natural language.

Fourth permission preset for dsh: unconfined, GPU-capable sessions (danger-full-access) with per-operation user approval for writes outside the workspace or to protected paths (.git/**, .env*); implemented purely as a bundle over the official tools/pre-execute ask hook, no core edits.

IDE-style run configurations for DSH: save LLM prompts and shell commands as reusable run configs (global or per-workspace), run them from the session header or the new-session page, and manage them via the task_run_config tool with approval-gated writes.

Vets local, npm, and GitHub plugin source before installation, blocks configured high-risk tool calls at runtime, audits output secret patterns, and writes HMAC-chained local audit logs.

Safe, audited SQLite/PostgreSQL/MySQL access for dsh agents: schema introspection, enforced read-only queries, a write approval gate, and a durable JSONL SQL audit trail.