Plugins

Hana-style assistant manager for DSH: visual preset management (cards, yuan personalities, avatar cropping) plus a full Hana memory stack (rolling summaries, layered compilation, SQLite fact store, deep memory).

Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an OpenRouter-like gateway plus cfgpu.com/llm/square, dispatches each via in-process subagents or direct LLM calls, and tracks per-model token consumption with a feedback-driven ranking.

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.

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

File-browser web app for DSH: React frontend and REST API served by the host webserver, a /dsh-agfs command that opens at the current session workspace, and a browse_files model tool.

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.

Command Code Go provider adapter for dsh: scan the Go-plan model catalog dynamically and serve /alpha/generate through the harness LLM seam

Structured, safe Git tool family for DeepSeek Harness: status/diff/log/branch/stage/commit/stash/show/fetch/pull/remote/checkout with a destructive-command guard.

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

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

Automated unit-test generation: a /testgen command and generate_tests tool that scaffold, run, and fix tests until they pass (LLM + offline template generators; vitest/jest/mocha/node:test).

Claude-Code-style lifecycle hooks: configured shell commands run before/after model tool calls with a JSON payload on stdin; a non-zero pre-tool exit blocks the call.

First-class Git tools for the model: status / diff / log / commit / branch with validated messages and paths - no bare-shell git calls.

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.

Bounded, privacy-safe local scanner for Codex, Claude Code, WorkBuddy, and CodeBuddy metadata: atomically aggregates keyed evidence and deterministically advises built-in DSH presets and optional capabilities—without content retention, network access, or preset mutation.

Bounded local memory with CBDC authority gating: SQLite + FTS5 claims, scoped recall with explainable use/verify/ignore decisions and a full audit trail, /memory commands, ≤3-claim/1200-char injection per call, no extra model call.

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