Plugins

OpenCode Go usage bar in the composer dock: rolling/weekly/monthly quota rings, DSH-session token & cost stats priced with live official rates, per-model and current-session scope breakdowns with live per-session updates, one-click API key copy.

DSH 模型 Pro:为 DSH WebUI 提供将 pi-ai 预设或任意已配置提供商的模型上下文、输出上限、推理档位与兼容开关一键应用到目标提供商,并集中查看、新建、编辑、复制与删除各提供商模型条目的能力。

Extensible animated response pet with blue-whale, orange-cat, and silver-shaded-cat themes, per-session progress, model and tool-call traces, token counts, output speed, elapsed time, and collapsible multi-session status cards.

Every night generates the companion character's schedule for the next day with DSH's configured model, from the persona (AGENT.md by default) and a weighted day type (work, rest, outing, home, overtime, slacking, or your own); injects the date, time, current activity and what comes next into the system prompt, with a speaking-style note so the character does not recite a timetable; adds schedule_view and schedule_adjust tools and a /life command that turns the injection on or off per session. With aa1355721445-lgtm/dsh-image-studio installed, each entry gets an outfit, scene and props from its libraries. A settings page shows today's and tomorrow's timelines and edits day types.

Agent-team orchestration sidecar for DSH: teams with a configurable member cap, real sub-agent members with per-member model routing, task DAGs that dispatch automatically when their dependencies finish, a broker that enforces fs/exec/net/env permissions, and a live web panel over SSE.

Switchable backends behind the native web_search and web_fetch, chosen per session from a composer menu or /setup-search and /setup-fetch: DeepSeek, Exa, Firecrawl, Tavily, Tinyfish, OpenAlex, Semantic Scholar and server-side model search for search; local HTTP with a private-network allowlist, the DeepSeek Fetch API, Exa, Firecrawl, Tavily and Tinyfish for fetch.

Shows a card in the sidebar footer with the DeepSeek account balance (read from the official /user/balance endpoint with the API key DSH already stores) and the unit prices of the active model — input, cache read and output — taken from a built-in snapshot of the official price table. A dot marks the current billing window and a countdown shows the time left until it flips: peak is Mon–Fri 9:00–12:00 and 14:00–18:00 Beijing Time, excluding Chinese public holidays, and everything else is off-peak. Prices and the dot appear only for official DeepSeek models; for any other model the card shows the balance alone. The card refreshes every 30 seconds, on click, and when the model changes, and follows the app theme and the DSH language.

Reusable Agent Team presets for DeepSeek Harness: a Settings page stores named Teams — a captain with its own prompt and tool allow-list, plus members carrying their own provider/model route, reasoning effort, prompt and tools — and a composer control applies one Team to the current Session, installing the captain prompt and registering the spawn_team_member, get_team_preset and update_team_preset tools.

Magpie gateway provider for DSH: syncs gateway models into the picker with visibility control, image input and thinking levels.

Codex-style context window auto-management for DeepSeek Harness: a lossless rollover engine with zero summarization model calls, task-oriented handoff anchors, working notes that survive compaction, verbatim recall of archived windows, and a stale-notes gate that downgrades to an explicit warning instead of vouching for outdated notes. One-click composer button plus /smart-compact command, three-band automatic rollover, mandatory anchor sanitization; works out of the box with zero configuration.

Read-only Git and SVN code review using the current DSH agent model, with change previews, explicit context and approval-gated model requests.

Reports which skills each turn invoked (loaded by the model, typed as /name, or none) and manages the local skill directory: install from a pasted repository, folder, SKILL.md or zip address, set a Chinese display name in the skill meta.yaml, and remove a skill while keeping a backup.

Model-autonomous context compaction for DeepSeek Harness: a mind_map tool surveys the agent context surface (stable seq ids, roles, token weights, clear-boundary markers, the clear-mind playbook), a clear_mind tool replaces a chosen conversation-history span with a model-written checkpoint through the native compaction transaction, call and result pairs self-collapse into one-line tombstones, and a proactive reminder nudges the model when the context grows long or a turn runs too many steps.

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models. Within a turn it supports skeletonized information compression with a low original-text retrieval rate; at the tail of a turn it supports a turn-tail intent summary implemented purely by content substitution; context content stays safe, and the whole process runs inside the official JSONL compression.

Supervises a local workbuddy2api gateway process and exposes its models as an LLM provider, reading context windows and reasoning efforts from the gateway's own model endpoint.

Auto-resume for interrupted agent sessions: an ordered rule table routes by failure type (rate limit, quota, auth, context overflow, crashed orphan) to automatic backoff retry, model switch, resume after context compaction, or a stop-loss notification, with a visual rule editor and a full activity log.

Configures provider and model reasoning-effort mappings for DeepSeek Harness, with a grouped model picker and composer slider.

A self-healing layer for tool calls: missing params, wrong fields and out-of-range paths are fixed before they reach the model. Measured visible error rate fell from 7.95% to 2.20%.

Control a HarmonyOS phone from the DSH web UI with AI: live H.264 screen mirroring, mouse touch and system keys, hilog streaming, and agentic tools that let the model read the screen, locate UI controls, then tap, long-press, press keys, or type.

Model high-availability failover (quarantine, circuit breaking, probe recovery) and subagent orchestration (fanout/pipeline/supervisor) with bilingual settings UI.

Literary DSH plugin: one session is one book. Cover-card /new opens one of 19 realms, a prose-only 诸天万界DSH preset keeps the model writing fiction, keyword worldbook entries ground each turn, and /export-story typesets the session into a Markdown novel.

A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.

Ollama Cloud native chat adapter: direct NDJSON translation of the Ollama /api/chat wire format, model discovery with context windows and capabilities, and web search/fetch providers under the ollama-cloud id, plus a Web settings card.