Plugins

Settings section for archived sessions: browse by workspace, search, batch unarchive with the sidebar updating live, and optional auto-archive rules (idle days, keep-last-N per workspace) with a dry-run preview — plus a left-edge turn rail for jumping between turns of long conversations and ↑/↓ input history in the composer.

After official llm-retry (n/5) gives up, keep retrying transient API failures (timeout, transport, rate-limit, 5xx, dropped SSE) on the same open step until success, cancel, or pause; AUTH, QUOTA, and user Stop are never retried.

Tri-channel task notifications: in-page toasts with chimes, browser OS banners, and host-direct OS toasts that keep working with the browser closed, plus a bell panel with persistent history.

Vision bridge for text-only DeepSeek: send images (alone or mixed with text) and a fast tiny vision model describes them behind the scenes — the chat keeps the picture, DeepSeek sees only text. Pure plugin: uninstall restores everything.

Adds a Reading tab to the DSH web client that shows process steps and live reasoning in source order, collapses successful turns to the final answer, and keeps the original tabs, composer, and tooling intact.

Native side-by-side chat beside the main conversation: an independent archived DSH session with full native UI, on-demand parent-context retrieval, selection quoting, and a keep-or-delete lifecycle.

Cursor-style New Session: every click creates a fresh blank draft session (persisted before the first message) instead of reusing the workspace's single one, plus a sidebar Drafts switcher to keep several empty chats open at once.

Bot Mode for DeepSeek Harness: a roster of named bots with avatars, personas and per-bot chats, each backed by one durable continuable subagent session that keeps memory across turns.

Keeps a local task-outcome ledger for DSH, verifies acceptance criteria from deterministic evidence, records user disposition and token usage, and supports digest-bound export.

Smart form skill: structured record-keeping for bills, ledgers and logs with auto-categorization and periodic reports.

Tracks DSH's file reads, image views, and code edits in WakaTime, including exact counts of lines added and deleted by AI. Keeps activity tracking running while DSH responds, batches updates across files, and coordinates per-project reporting limits across parallel DSH processes. Automatically installs and updates wakatime-cli.

Settings section for archived sessions: browse by workspace, search, batch unarchive with the sidebar updating live, and optional auto-archive rules (idle days, keep-last-N per workspace) with a dry-run preview — plus a left-edge turn rail for jumping between turns of long conversations and ↑/↓ input history in the composer.

Vision provider route that transcribes attached images to text through a configurable model (15+ OpenAI-compatible and Anthropic vendors) while DeepSeek keeps answering.

Agentic Control Plane for DeepSeek Harness — check every tool call against your policies before it runs, and keep a durable record of what was allowed and why.

Project-scoped cross-session memory: PROJECT.md snapshot injected into the first user message, a memory_remember tool, and auto-reflection after ReAct tasks; each project keeps its own memory file.

Keeps a project's documentation in step with its decisions on DeepSeek Harness: the same append-only decision log and derived design snapshot, kept fresh in-process instead of by a hook process.

Configuration UI for the official OpenViking memory plugin: connection and user-key setup, local connection diagnostics, a per-session memory toggle in the composer, memory isolation that keeps recall inside the current topic, and recall tuning for score threshold, injected item count, query expansion and excluded URIs.

Token usage dashboard in the DSH settings page: nine metric cards (total, today, yesterday, peak day, longest session, active-day streak, active days, sessions, subagent tokens), a GitHub-style daily/weekly/cumulative heatmap, and an activity insight list, aggregated locally from session logs and projection caches, keeping token history after a session is deleted.

On-demand skill tools for DeepSeek Harness: registers skill_search / skill_load / skill_ref so the model searches a staged skill library first and loads a skill body only when it needs it, keeping the library out of the resident session catalog and out of every turn's context; adds a Skills tab to the conversation view ring that reads back the whole session and lists which skills were actually loaded, and in which turn. Zero dependencies, and the records render client-side only, never entering the model's context.

DSH plugin that registers the ai-eight-honors-eight-shames skill: eight checkable working rules for coding agents (verify before calling, confirm ambiguity, cite evidence, reuse before creating, test before claiming done, follow local conventions, separate fact from inference, keep changes reversible) plus a ninth rule that logs each user request and the change made in two fixed report files at the workspace root.

Bridges a WSL dsh agent to a Windows Obsidian vault on NTFS: status/list/search/read/write/append, wikilink resolve, write/append require confirm=true, plus obsidian:// open. Keep the vault under /mnt/<drive>/; Linux-disk vaults via \\wsl$ are unreliable.

Compresses older DSH context into a structured handoff, retains recent messages, and keeps session history searchable.

Skill that fact-checks a claim against the open web rather than model memory: it splits the claim into independently checkable fact points, routes each point to the primary-source ladder for its domain (policy, academic, medical, financial, disaster and accidents, food safety, science, education, sports, entertainment, judicial, and more), searches domestic and international ecosystems in parallel, fetches primary pages, grades sources by type, re-searches with debunking keywords, and reports conclusion-first with a full URL and citation position behind every statement, keeping unverified and undecidable points separate from confirmed ones. Three factual judgements can be routed to a TypeSafe Jev (System One) decision model when a key is configured, falling back to the skill's deterministic rules when it is not; a model verdict can only lower a confidence tier.

Blocks an agent from reading, searching, writing, or editing chosen files and directories, keeping their contents out of the conversation — including sensitive-word files whose text can make later provider requests fail with a 400. Rules are picked from a file/directory browser on the plugin page.