Plugins

Lets the agent inject one turn into a chosen session on its own when the host has been idle. Daily cap, active hours, weighted action lottery, per-activity budget, and a policy file re-read on every check. Disabled by default; sends no network requests.

Registers Brave as the web_search provider, resolving the API key from the DSH credential store, $DSH_HOME/.credentials.yaml, or the environment. No settings card and no fallback engine: one request to Brave's Web Search API per search.

Long-term memory kept as plain Markdown plus git: each session opens with a generated memory-context block assembled from a global store and per-project books (role card, user profile, current focus, routing table, recent logs), the plugin records which memory files the agent read and reminds it to extract conclusions while the day's log is unextracted, personas live in roles/<role>/SOUL.md role cards, and it ships a seven-tab settings page in the sidebar plus four skills. Requires Python 3.10+.

Static-context audit for a DSH home: a six-layer baseline (rules, memory, skills, tool surface, sessions, KB), broken-path checks for a markdown capability map, memory duplicate/stale/over-limit reports, SKILL.md description compression, and tool-surface plus cold-start static-context estimates recovered from session logs. Four read-only DSH tools; writes require --apply and are backed up first. Requires Python 3.10+ on the host (stdlib only; all four tools shell out to the bundled CLI).

Replaces the summarizing context compactor with a handoff note the model writes itself and a fresh window that keeps only the system prompt, the note, and the current turn.

Per-workspace session defaults for DeepSeek Harness: save the Agent preset, permission preset, model, reasoning effort, Chat work-details level and collapse timing per workspace; new or reused blank sessions in that workspace start from them.

Edit a sent message in place and resend it as a forked chat, keeping the original: change the text, remove, reorder or add images and files, with session image limits checked before sending (the first message opens a new chat in the same workspace). Also @-references pending images by file name, drag-reorders composer attachments, copies messages together with their images, and adds copy, download and drag-to-composer for images in the conversation.

Ships the Codex UI 1.1.49 sidebar inside the plugin itself, so no upstream release can change the interface, and adds a real delete to the session menu: it provides the remote.workspaceRegistry.deleteSession service, unhides the per-session ... button, and permanently removes the session log, workspace records and projection cache, with subagent and forked conversations selectable in a family-tree dialog. Bundles the Codex UI 1.1.49 sidebar from MichengAI/dsh-codex-ui (Apache-2.0) — do not install both; the delete engine is adapted from Lzcdebear/better-dsh-session-deletetool (MIT).

Read, message and live-follow local DeepSeek Harness sessions from inside an agent: four tools (session_list, session_read, session_send, session_chat) plus a matching Python CLI, over the desktop app local RPC; transcripts also read offline. Requires Python 3.10+; offline transcript reads also need the zstd CLI.

Registers a QwenWork (千问办公) model provider that reuses the desktop client's local sign-in, runs a loopback OpenAI-compatible bridge on 127.0.0.1, and translates DSH model requests into the ACP-style control-envelope conversation protocol the upstream actually speaks.

Registers the workbuddy model provider by mounting dsh-llm-workbuddy and supervises the local wb2api gateway, then bundles two protocol bridges onto that same gateway: Responses for OpenAI Codex CLI, and Anthropic Messages for Claude Code and Claude Desktop, which see the gateway models under generated claude-wb-… ids. Skips work that is already running or already registered, and reports each part through a status tool. Requires a local wb2api gateway and a WorkBuddy account.

Remembers the reasoning effort you explicitly chose for each provider and model and restores it when you switch back, without replacing DSH's own model picker.

Qoder supplier plugin for dsh-router, covering both the CN and international regions. Uses a personal access token for authentication, signs requests to the Qoder cosy gateway and converts upstream SSE to OpenAI SSE; the model list reports the upstream display name alongside the key, while account selection and cooldown stay in dsh-router core.

EVA armor HUD theme skin for DSH, with startup animation and sequential UI entrance animation.

DeepSeek balance and token usage panel for DSH, with official platform billing, a daily usage calendar, and local session-log estimates for all providers using editable per-model pricing.

Token spend panel for DeepSeek Harness: today and 7/30-day totals, natural month/quarter/year sums, cost split by cache-hit input, cache-miss input and output, per-model and per-session detail, daily and monthly budgets with a projected day-end spend, peak/off-peak pricing, CSV and JSON export, and a zero-dependency CLI report. Also prices GLM (Zhipu) and Kimi models shipped through third-party routes. Maintained fork of olimc2016/dsh-token-meter-panel (MIT, 0.6.7) with a rewritten panel; it uses its own row, route and slot ids, so it installs alongside the upstream entry rather than replacing it.

A read-only overview tab beside the conversation: what this round asked, what was observed, what still needs checking, and a bounded history you can step through round by round.

Prompt enhancement for the DSH Web GUI composer: pick a style before generating (logic-only, structured, or concise), or supply or clear a custom system prompt in settings; a sparkle button or Shift+Tab rewrites the current draft through the harness model, streams the result into an inline preview (original vs enhanced) with a live thinking timer, fills it back with one click, keeps an undo bar, and offers settings for model route, temperature, length limits, context awareness, undo-bar behavior and shortcuts.

Native generation-time Mixture-of-Agents: every turn, reference models run the same session context in parallel as pre-run drafts and one aggregator executes with full tooling; config-as-model recipes, F mirror / R trimmed views, enforced subagent gating (dual-shape session indexing), derived per-recipe vision (vision refs relay image reads to text-only aggregators), tiered cadence with separate steering and patrol rosters plus frozen reuse between beats, degeneration guard dropping degenerate reference output, anonymized model face (failure notices carry no provider identity), and cache-friendly guidance placement (the rehearsal record is pinned where it was produced instead of appended to every request, so the cached prefix covers it and each step pays only for what was added since - on by default across every cadence).

A Telegram bot plugin for DeepSeek Harness, with shared sessions, image input, and interactive agent conversations

Give your DeepSeek Harness agent an addressable visual memory: revisit any image, inspect any region, and read exact pixels.

The shared UI foundation for DSH plugins, with a live component preview: design tokens, common controls, workspace browsing and notifications maintained in one place — install it to preview every component in a real host.

Route implementation work from the main model to executor models and collect their reports.

DeepSeek Harness plugin: a Sourcetree-style Git workspace — branches, diff, history, fetch/pull/push, AI-written commit messages and AI-assisted conflict resolution, with pinned and usage-ordered repositories.