Plugins

Two-level model routing: pick the best model group first, then the best channel within that model; a failure switches channel before switching model. Preference mode pins one model across its channels, a status bar under the composer shows the live model, channel health and the day's token usage, and a speed/intelligence report can be imported as the routing prior. Exposes a model_orchestrator tool and a /route command.

Reads the API balance or subscription quota behind the current DSH route — including OpenDesign (AMR) wallet and Design Plan windows via the control plane — and never guesses a figure: a miss reports its cause (the raw response is echoed only when parsing fails). OpenDesign needs `vela login` or a desktop `controlKey` in `~/.amr/config.json`.

A Usage page in DSH settings that folds every model call into a local ledger and reports requests, tokens, and estimated cost by day, route, and model, with editable unit prices and CSV export.

Local-only, read-only DSH token dashboard: provider-reported usage across all backends, all-time totals, a 365-day heatmap, input+output and cache read/write details, turn/step counts, average tok/s, and durable history after sessions are archived.

Select text in a conversation to attach a numbered highlight with a colour stored per note, keep every mark in an outline panel that jumps back to its quote, and let a corner self-check badge report style, selector and saved-key problems without opening dev tools.

Keeps quotes out of the message body: quoting any passage from an assistant turn opens an editable quote tray above the composer, the quotes are injected into the next turn as system-prompt context (attributed with source and time), and an expandable quote row under that turn shows exactly which quotes were used. Quotes persist across page reloads and are claimed per turn; the host and client halves hand-shake on version and report a compatibility verdict.

Adds a draggable restart button and a plugin panel to the DeepSeek Harness desktop app: it prompts when the profile plugin list changes, records additions and removals per profile, tracks trials, reports host startup state, and offers rollback, minimal boot and recoverable cleanup.

A conversation-style layer that rephrases trade-off warnings: when a shortcut is cheap but has a catch, the reply may say the fast road is the rival shop and the slow one keeps its rules. Ships a rewrite engine that turns any text into a fixed-format dialogue with five independent knobs (act count, catchphrase density, ending turn, seed, preset), a slider for four on/off intensity levels, and a /bushaoxin command that reports a joke "heartburn index" from the session tool-call log. Every rewrite ends with a real technical conclusion that cannot be disabled. Zero dependencies, no build step, engine is pure functions.

Conflict diagnosis and repair for DeepSeek Harness plugins. Builds a capability graph of the running Loader profile and of the on-disk cordis.patch.yml layers, comparing imports, peer ranges and config against the host that is ACTUALLY running rather than the profile's possibly-stale copies, and reports the conflicts that fail silently: a fiber stuck PENDING on a service no plugin provides, a browser half injecting a client module nothing provides, a tool id two plugins both register, duplicate Loader entry ids, a row disabled by one layer and re-inserted by another, an import of a host subpath the running host does not export, and a cycle among inject declarations. Every finding carries its evidence, a confidence grade for who owns a name, and a repair with a risk grade — verify it with a dry-run difference table, or take the individual .patch.yml files that --fix-out writes (never auto-loaded, so picking wrong breaks nothing).

An agent preset (Hermit/小寄) that turns DSH into an always-on personal hub: a scoped butler persona, a dispatch tool that delegates multi-step tasks to background sub-agents with per-task model routing, async completion reports woven back into chat, plus a credit budget gate, a P/M confirmation chain and an M1 event log.

C++ audit skill: detects the target project's actual C++ standard before making any recommendation, then reports findings across RAII and ownership, move semantics, exception safety, performance and memory, containers and algorithms, concurrency, templates and compile-time, standard boundary, and type safety, ABI and interface design, each with a checkpoint, a reason, a bad-to-good example and the minimum standard.

Tsundere mesugaki persona pack: dialect replaces whole sentence skeletons instead of sprinkling dialect words, stays on as the default voice even through work talk and delivery reports, and ships a temper system, banter mode and silent file handling.

Compiles an LLM persona in DSH from six dimensions (identity, tone, creative habits, feedback style, boundaries, run parameters), injects the compiled text into the system prompt at the end, ships six built-in templates plus a drop-in templates folder, and drafts a persona from your own past messages — either by counting patterns in them or by having the current model read them and report its rationale. Adds a panel next to the composer and a /persona command.

Deep-space theme for the Harness Web GUI: two fully designed light and dark palettes over a seamless cross-dissolve nebula wallpaper, plus a model probe that reports which configured models actually answer and their real context window.

A composer switch between running always and running only in off-peak hours, set per session: a task is judged by the session that owns it, so changing one session no longer changes the others, and a session without its own choice follows a default. In off-peak mode every task, including one already running, is held at its next agent step or tool dispatch when a Beijing peak window starts (Monday to Friday 09:00-12:00 and 14:00-18:00, statutory holidays excluded), and one timer releases it at the boundary; weekends and holidays are idle all day. The holiday calendar lists every statutory day off in 2025 and 2026 from the State Council notices, and a year with no data is reported as unknown rather than assumed to be a workday.

Read-only clinic for DSH session logs: 22 named diagnostics (token waste, retry and failure loops, context bloat, cross-session amnesia, idle MCP servers and skills), each reported with a replayable evidence locator such as session.v4.jsonl.zstd#L101-L110, and each finding turned into an executable prescription — a profile-patch YAML snippet or a command with current to suggested values, risk, verification and source — plus a feedback command that retires a prescription you reject, after which the report states it was removed by your feedback. Zero dependencies, default zero egress, session files are never written.

A download-progress indicator for the DSH session header: it reads the background-job roster and parses what downloaders already print — curl --progress-bar, wget, aria2, or a JSON progress file — into a progress ring, animated bars, transfer speed and ETA. Jobs that report nothing show as unknown progress instead of being hidden. A finished file opens with one click, or reveals in the file manager. No third-party plugin required; the package ships zero runtime dependencies.

Token usage panel for DeepSeek Harness: a bar above the composer opens billing token totals, trend charts, per-model and per-project breakdowns and a custom date range, read from local session logs of DSH, Codex, Claude Code, Trae and WorkBuddy. With a self-hosted portal URL and an app key it also reports usage events to that portal; with neither configured it collects nothing. It exposes token_usage tools plus a ctx.tokenReport service, and never collects conversation content.

Sidebar panel for a weekly, human-curated Chinese ranking of the DSH ecosystem: 31 tracked projects (17 installable plugins plus tools/skills) ranked by live GitHub stars with week-over-week deltas, and a real-call availability survey of the "free" models. Sponsor slots are labelled and sit outside the ranking.

Replaces the composer model selector with a "model · reasoning level" trigger: a slider across every level a model reports, three switchable modes (the DSH native selector, a gradient particle rail, an energy-charge track), and a per-provider one-click fill for models that declare no reasoning levels.

Cross-workspace worker fleets: one orchestrating session spawns named worker sessions in other project workspaces, queues or steers tasks into them, watches them in the background via a real host job, and collects their reports. Worker completions deliver themselves to the orchestrator's session rather than needing to be polled, so an idle orchestrator still reacts. Escalations and failed workers deliver by steer when the orchestrator is mid-turn and by queue when it is idle; a turn that ends without a report counts as a failure and the worker is replaced after a configurable limit. The roster persists to disk and each worker session carries a durable title, so a restart neither loses the fleet nor spawns duplicate sessions. Ships five agent presets at full plugin parity with the standard preset.

Dispatches coding tasks to local Orca-managed agents and reports completion to DSH; documented for DSH 0.1.5-rc.2.

Permission-wall-immune file search for DeepSeek Harness (DSH): the find_file agent tool skips unreadable directories, reports them with errno, and never lets a failed walk pose as an empty result.

Per-turn and per-session estimated cost in the DSH Web UI, computed from provider-reported token usage in four buckets with the built-in official DeepSeek CNY peak/off-peak card — peak hours are Monday-Friday 9:00-12:00 and 14:00-18:00 Beijing time, weekends and Chinese statutory holidays are off-peak all day. An optional local JSON rate table overlays prices for other or self-hosted models, and models without a price show tokens only.