Plugins

macOS menu bar app for the DSH web server, plus the host plugin it reads: the plugin writes the running server's port, PID and tokenized URL to ~/.config/dsh-launcher/runtime.json and removes it on shutdown, so start, open, restart and stop work from the status bar even for a server started from a terminal.

Tiered persistent memory (user/env/project) with per-tier char budgets and semantic query routing; full layers refuse writes instead of silently evicting.

Polaris Memory: local-first project memory plugin for DeepSeek Harness. Uses per-project .dsh-memory.json; provides memory_read/recall/write/update/delete tools, /memory command and settings UI, with tiered injection (resident user profile + scene-triggered memories with P1/P2/P3 importance), semantic recall (IDF + synonym layer), and a hard-guard mechanism for bottom-line memories (detect deny-semantics -> authorize -> block AI deletion; user can confirm-override).

Settings section that reports token usage: totals for input, output, cache read, cache write, reasoning and call count, with breakdowns by model, day, month and project plus a per-day trend chart for the last 30 days; history is rebuilt once on a worker thread and then kept current from live session events.

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.

Search, read and write an Outline knowledge base from conversations, with whitelist-guarded approval for every document write.

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.

DSH GitHub connector: review PRs, triage issues, debug CI, prepare changes (18 tools, gh-first + REST fallback, approval-gated writes).

Local token usage and cost dashboard for DeepSeek Harness: four-segment token breakdown (miss/cache-hit/cache-write/output), cache savings estimate against the miss/hit price gap, per-session drill-down with context-growth curves and anomaly flags, global filters with shareable URLs, monthly budget progress with month-end projection, and day/month aggregate fast-path queries (O(days)) with incremental rescan.

Mandatory cross-review for design proposals and lessons-learned: auto-detects design doc writes and enqueues them (tier=review) into the task queue, delivers the external reviewer verdict back to the initiating session, and appends approved preventive measures to OPS-GUARDRAILS.md (append-only, conflict-checked).

Codex-shaped coding tools and agent presets for GPT models on DeepSeek Harness: exec_command, write_stdin, apply_patch and view_image, plus OpenAI Chat Completions and Responses API routes, bridged to DSH-native plan, ask, approval and compaction. Long-running commands become DSH background jobs with bounded head/tail output readable through job_output, and each subagent type can be pinned to its own preset, provider, model and reasoning effort.

Cross-app project memory for DeepSeek Harness with role-separated writeback, a visual knowledge workspace, confirmed corrections, session controls, local Writer and organizer settings, and an account-free Windows local installation preview.

Browse and govern the skill library from a floating-ball panel with three tabs — skills, call ledger and quick start. You choose the skill root yourself through a native directory chooser (defaults to ~/.dsh/skills, no path is shipped with the plugin); skills are grouped into two levels of categories, with manual, keyword-based and AI grouping available and a tree or flat view toggle, and grouping is purely visual so no skill file is ever moved. Descriptions are read from each SKILL.md frontmatter, search filters by skill name, description or original text, and a card opens the full SKILL.md. Skills can be switched on and off per card, per category or for the whole library — the toggle rewrites disable-model-invocation in that SKILL.md and writes a SKILL.md.bak-toggle-<timestamp> backup before saving, rolling back if the write fails; disabled cards grey out until restored. The call ledger separates automatic from manual entries, records skill successes and failures by listening to tools/result events, and reports call counts, success rate, trend and a ranking, reusing an existing ledger file found in the library. Hot reload picks up skill edits without a restart. The DSH settings page gains a floating-ball section that shows or hides the three balls, offers one-click restore of a ball dragged off-screen, and picks the shared 130-skin catalogue for all three balls.

In-session "Files" tab (conversation.view, order 20) for dsh Web that browses the active session's workspace directory with breadcrumbs and previews files inline — sanitized Markdown (marked + DOMPurify), images, line-numbered text and PDF — served by read-only /dsh-files host routes registered on ctx.webServer; no write endpoints. Bilingual zh/en.

Reads and writes the Windows clipboard from WSL.

DSH tools for operating a self-hosted Talebook library: search, download, upload and manage books and audiobooks, manage Legado book sources, and admin operations, with approval-gated writes.

Per-profile settings overlay for DeepSeek Harness: global settings.yaml stays the baseline while each profile overrides any namespace through its own profiles/<name>/settings.patch.yml — object sections merge recursively, scalars and arrays replace wholesale, and !unset masks an inherited value. The overlay is transparent to existing plugins (they keep reading ctx.settings unchanged), writes land in the profile overlay only, and official schema validation, revision semantics, expectedRevision conflicts, watchers and events are untouched. Ships a settings command family (get/set/unset/mask/unmask/promote/demote/migrate/diff/layers) plus a Profile Settings section in the web Settings panel over a loopback RPC channel.

LLM approval answerer for sandbox escalations beyond workspace-write: a deterministic regex filter first, then a clean-context reviewer model; humans are asked only when it is unsure. Requires the bundled core patches.

A microphone button for DeepSeek Harness that writes browser speech recognition into the composer draft.

Publishes a project plan the agent writes: ordered steps in a panel docked to the right of the frame, and the framework graph as an auto-laid-out diagram in its own centre tab, downloadable as SVG or PNG. Charts are rebuilt from the session log, so they survive restart and resume.

Reliable todo panel that survives restarts (official panel only re-renders on write — fixed via projection pre-warm) with three-state completion verification: evidence exists → verified, fake evidence → blocked, no evidence → unverified badge; settings toggle to fall back to official behavior.

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.

Persistent memory for DeepSeek Harness: memory read/write/retrieve tools, per-turn auto-recording, project-scoped recall injection and a management UI, with non-destructive Claude Code memory import.

Permission mode between workspace-write and full access: shell commands are checked by deterministic rules and a subagent review; irreversible or system-level actions require explicit approval.