プラグイン

Observes consecutive identical tool failures and optionally pauses before the next model step, preserving original results and successful repeats, with an in-chat report in DSH Web.

Mounts the hosted Reaudit MCP server (https://mcp.reaudit.io/mcp) through the in-box @deepseek-ai/dsh-mcp-client bridge with a REAUDIT_API_KEY bearer token: 238 mcp__reaudit__* tools for brand visibility in AI answers (ChatGPT, Perplexity, Gemini, Google AI Overviews), competitor and citation analysis, site audits, content generation and social scheduling.

Offline Wikipedia and ZIM lookups through your own kiwix-serve: the wiki_search, wiki_read and wiki_books tools run full-text search with snippets, read an article by exact title, and list the local ZIM library.

Low-token web search that returns only {title, url, snippet} per hit — vendor extras such as answer, score and raw_content never enter the context. Five interchangeable backends (Tavily, Brave, SearXNG, Google CSE, Exa) with automatic failover to the next usable one in fallback / chain order when the primary fails, deduplicating repeated providers. Returned URLs and snippets are sanitized of tracking parameters.

Connects DeepSeek Harness to the AdWhispr remote MCP server through mcp-remote with browser OAuth sign-in, adding tools for competitor ad research, ad creative cloning, and launching and managing Meta, Google and TikTok campaigns. Requires an AdWhispr account.

SQLite-backed long-term memory for DeepSeek Harness: add, search, update and archive entries with categories and tags, automatic conversation logging, tiered compression, and a project dimension that scopes retrieval to the current workspace plus global facts.

Persists scoped user corrections and method candidates for DSH with bounded recall and restart-safe completion settlement.

Cross-session and cross-project long-term memory: a non-blocking silent sedimentation dispatch on turn/end writes into a local SQLite store (FTS5 trigram full-text index with insert/update/delete sync triggers) that later turns recall from; entries are scoped per project alongside a global tree, and the plugin ships its own embedded web dashboard (it starts the HTTP server itself, no separate process) for browsing, graphing and controlled deletion.

Adds Copy session ID and permanent deletion of a Conversation's log, projection cache and workspace references to the session row's ⋯ menu, behind a two-step confirm.

Invites people into one conversation through single-use links with no account: up to 20 guests discuss together and ask the AI, the shared fork runs read-only, and the owner can remove guests or end the share at any time.

Per-task disk-space ledger in the sidebar with opt-in reclamation of unowned junk; session logs are never trimmed.

Inspect conversation context and apply configurable compaction with usage history.

Turns a DSH session into a self-contained interactive HTML mind map of its topics, conclusions, decisions, todos and open questions, and reports what changed since the previous run.

Export the current session to clean Markdown from a button in the session header, through the native save dialog, with a CLI and an HTTP route over the same renderer; reads session logs directly (formats v0, v3 and v4) and declares no @deepseek-ai peer dependencies.

Adds a red "Delete session" row beneath Archive in the sidebar session menu and permanently deletes that one session - its stored logs and its workspace account entry, written through the workspace registry itself. A second click confirms and the row leaves the list immediately; sessions opened this run are disposed from memory first so nothing resurrects them, and a session running work shows one extra warning whose click stops the task before deleting.

Project-less chats for dsh: a session created without a workspace gets its own directory under ~/Documents/DSH/<date>/chat-NN, reused whenever the chat is reopened and left in Ungrouped rather than made a sidebar project; the new-session hero gains a hover clear badge and a "work without a project" row, and a client-only sentinel workspace keeps that hero and its composer usable.

Copies a session log path (or a paste-ready handoff block) and turns the multi-frame zstd log into a readable file another session can continue from.

Registers a configurable prompt variable so an agent preset whose persona uses complete: true can still receive an injected text block; the plugin ships no content of its own and reads the text from its config.

Replaces the composer model seat with a search-first picker and adds a model management page: create and edit llm-pi-ai channels, choose which of an endpoint's models exist, and declare per-model thinking ladders and capabilities.

Reuses the local model proxy of a logged-in XiaoyiWork desktop app (Windows only) so its models appear in DeepSeek Harness without a separate API key.

Adds a thinking-depth slider mapped to declared model levels, configuration guidance, and optional inline model settings.

Adds a one-click switch to every provider row in Settings - Models: turn a provider off and it leaves the model picker, turn it back on and it returns. It works by wrapping the model catalog call, so it affects the catalog and the picker only, never routing, keys or provider config; existing sessions that already use such a model keep working.

Per-model enable/disable and renaming for every provider in DeepSeek Harness: a panel at the bottom of Settings - Models with a search box, status chips with counts, a provider filter, collapsible provider groups with group-level switches, and batch actions scoped to the current view. Disabled models leave the model picker and custom names replace the built-in ones. Preferences persist in the profile and apply immediately, without reloading the page or restarting DSH.

Client theme plugin for the DSH Web GUI: a fluid background, frosted glass panels and quantised shader effects, with 100 adjustable parameters persisted to a JSON file.