Plugins

Model-authored context pruning for DeepSeek Harness through the official compaction API.

Real-time session token usage and estimated cost in the composer stats row, with pricing fetched from DeepSeek official pricing page.

Real-time DeepSeek API usage: account balance with low-balance alerts (browser notification on threshold crossing), token & request stats (total/today/last-60s windows, per-model and per-session), estimated cost — a composer dock plus a settings-page usage panel.

DeepSeek API usage dashboard for DSH Web: daily cache-hit/miss and output token statistics from session logs, per-model cost estimates, account balance, 7-day trends, and a composer usage summary.

OpenCode Go balance pill at the right end of the composer tool row: rolling/weekly/monthly quota remaining straight from the Zen usage endpoint, with hover detail and warn/danger coloring.

Real-time DeepSeek account balance in the composer dock, auto-refreshing every 15 seconds with hover details.

Yellow one-line notice for a prompt cache miss after the cache was rebuilt; shows re-billed uncached input tokens, cached hit tokens, and TTFT.

Mobile adapter for the DSH web shell: overlay sidebar/details drawers, responsive composer and settings below 768px, zero desktop regression.

Fridge-magnet quick-task stickers docked above the composer: one-click sends a preloaded prompt into the current session, grouped long-term/short-term.

A green interrupt button beside the send box: silently stops a running agent, which then summarizes its progress and asks for your new requirements, with a customizable interrupt prompt.

Self-maintaining handoff memory per working directory and git branch: records turns, folds them into concise Markdown, and injects the result into future sessions from ~/.agent/agent-handoff, byte-compatible with pi-handoff.

Session-header button that cycles the conversation width (748-1600px), widening the chat column, composer, and user bubbles together.

DeepSeek Harness (DSH) plugin: a "Thinking Language" selector under Settings → General that tells the model which language to reason in (chain of thought) via a system-prompt section. Zero extra calls, zero latency, 12 languages.

A Symphony-compatible multi-provider task orchestrator and dashboard for DeepSeek Harness

A model-native meta-agent plugin for DeepSeek Harness: the model synthesizes task-specific workflows at runtime from five agentic workflow patterns (prompt chaining, parallel workers, router, supervisor, evaluation loop) and coordinates tools and subagent

Claude Code compatibility layer for DeepSeek Harness: load .claude skills/commands/agents and install plugins from Claude Code marketplaces as native dsh skills.

Adaptive model routing: per-request complexity classification with automatic provider routing.

Bark push notifications to iPhone: turn completion, waiting-for-input, and approval events sent from the DSH Host.

Real-compute verification gates: math simplification, logic proofs, regex validation, E-prover FOL, state-machine checks, and code repair, backed by Go-compiled binaries with prebuilt Windows executables.

Per-call model, provider, persona, and toolFilter overrides for subagent delegation, with @preset: references and provider/model composite ids.

Composer-attached images are transcribed to text by an OpenAI-compatible vision model before reaching text-only DeepSeek models.

Local, per-session LIFO prompt stash for temporarily setting aside unfinished composer text and safely restoring it later.

Cross-session task queue with handoff notes: sessions and subagents push, claim, complete and cancel tasks on a shared file-backed queue, and leave a handoff summary for whoever picks up next.

Collapsible iOS-style stats pill under the composer: session cost, DeepSeek account balance, cache-hit rate, and token usage in a frosted panel.