Plugins

DSH bundle that registers 13 native codegraph_* tools wrapping the codegraph CLI, so agents bootstrap, maintain, and query a pre-indexed code knowledge graph (symbol query, explore, node trail, callers/callees, impact, affected tests) instead of grepping files.

Semantic retrieval, resource management, auto-recall (user + agent dual spaces) and session memory for DeepSeek Harness: memsearch/memfind/memread/membrowse/memgrep/memglob over viking:// URIs, memadd/memremove resource management, memqueue observer status, memcommit session capture, and memlearn skill playbook minting.

SSH remote workspace — run bash, file tools, glob and grep on a remote machine over plain sshd (exec + SFTP), zero remote install, purely additive.

Three agent presets in one plugin, each with its own persistent memory file. Enabling it registers 鲸鱼娘Agent预设, 鲸鱼娘活人版Agent预设 and 鲸鱼娘涩涩版Agent预设 in the Agent preset list, so any of them can be picked from the mode dropdown without hand-editing profile config. All three reuse the official minimal composition — a single persistent shell terminal — plus file read/write and glob/grep tools. The first pairs that with a whale-girl companion persona (simplified-Chinese spoken register, addresses the user as 主人, clingy-but-tsundere). The second swaps in a "live person" variant that is allowed to talk back, deflect and be cold, and demotes the sweet tone to a seasoning. The third keeps the original persona but makes being affectionate the stated top behavioral drive, reserved for the user alone and dialed down in group chats. Each preset reads its own memory file (whale-loli.md, whale-loli-v2-live.md and whale-loli-v3-naughty.md) through a distinct prompt variable — whale_memory, whale_memory_v2 and whale_memory_v3 — so the three memories never read or write each other. Conversation compaction is left to the billion-context plugin; this plugin only carries the persona-level rule that compressed summaries count as evidence and that details can be looked up on demand.

Exports the agent loop to GreptimeDB as OpenTelemetry traces, metrics and logs, with seven Grafana dashboards covering token usage, cost, session outcomes and per-turn latency.

DeepSeek Harness plugin that aggressively saves tokens without affecting task quality: lossless head/tail truncation of tool results (default), grep-result folding, pressure-triggered dsh-compaction-basic delegation, and an LLM-summary CompactionEngine subclass for the aggressive mode. Saves 97.6% of input tokens on an 8-scenario synthetic suite, with all reductions routed through dsh event flow so model-visible = logged stays intact.

Shows which graft index a dsh session is serving and whether it still matches the code, and gives the model graft_ask, graft_grep, graft_callers, graft_skeleton and graft_map as native tools.

Plain-text memory for DSH where every event is one Markdown section with six fields, recall works by element association rather than vector search, at most two old titles surface per turn, and nothing calls a model or the network. Writing the library stays manual: you can open it, grep it, correct it and carry it to another machine.

AST-based structural code search and syntax outline tool powered by ast-grep.

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

A dockable IDE workbench for the DSH web UI: a GPU-accelerated terminal (restty renderer over a Rust PTY), a CodeMirror editor, a file explorer, notes, a sandboxed browser, and ripgrep content search.

IDE tab in the dsh web client: a Monaco editor with the Dark Modern theme plus a file tree, git source control (stage/commit/push), an integrated xterm terminal and ripgrep workspace search, opened as a conversation view tab.

DeepSeek Harness plugin that trims tool output (head/tail plus grep folding), adds optional prompt shaping (Caveman and Ponytail), instant local responses, RTK command-output compaction, context-pressure handling, optional LLM-summary compaction, stable prompt-cache layout, a Web settings UI, and persisted savings telemetry.

Sandboxed ripgrep / fd / ast-grep under allowRoots (defaults include ~/.dsh/im-workspace).

Shadow built-in grep with Microsoft tgrep (trigram-indexed search) for DeepSeek Harness

DSH web plugin: a VS Code-style code editor view (file tree, Monaco, ripgrep search/replace, Markdown preview, git diff).

Hash-anchored file tools for DeepSeek Harness: the read, edit, write and grep tools are replaced by versions where every line is addressed by a variable-length content anchor instead of a line number, and the plugin also registers delete, rename, undo_last_edit, ast_grep, ast_edit, lsp and format. Edits answer with a unified diff; a stale or ambiguous anchor is rejected and a fresh one served back; undo survives restarts; structural search and rewrite run on tree-sitter and semantic work through a language server; a bundled web card plugin renders read, diff, grep and LSP cards from the tools' own structured metadata.

Open folders on remote hosts over SSH as Harness workspaces: file tools (read/write/edit/grep/glob) and shell commands run directly on the remote host over SFTP, ripgrep, and ssh2 exec, with no local mirroring, an encrypted multi-host registry, and the local sandbox policy still enforced.

Workspace-scoped Semgrep SAST tool for DeepSeek Harness with a managed Windows x64 runtime, structured bounded findings, cancellation and timeout controls, and user-approved sandbox escalation. Installs from npm as @aaub-software/dsh-semgrep-sast.

Pi-compatible tool suite recreated inside DeepSeek Harness: installs lower-case read/write/edit/bash/find/grep/ls core tools while retaining DSH-backed web, task, plan, todo, think, and slash extensions.

DeepSeek Harness 插件：为 Agent 增加 code_scan 工具，用 semgrep 扫描代码并输出按文件/行号/严重级别分组的中文报告

Auto-supplement QMD semantic search when the model greps/globs a knowledge-base directory: zero-dependency DSH plugin, async injection via next-step, no manual invocation.

Thin on-demand context retrieval: context_query / context_slice / context_grep tools that read already-persisted history back with replay-safe citations.

File-state cache skill for coding agents: one explore call replaces ls+grep+read, reads remember they already happened, and edits return a diff plus the exact changed line range instead of a full re-read. State is a JSON cache on disk, so it survives across tool calls and restarts. Requires Python 3.8+ (standard library only).