Plugins

Multi-bot workbench for DeepSeek Harness: bridges the sdk-bots orchestration gateway (group chats, single bots) into the dsh web shell with official-styled UI.

Explains which layer killed a failed turn: times every model request (first byte, longest silence, total) and combines that with the error to name the culprit (dsh idle watchdog vs Node undici timers vs SDK timer vs server crash, context overflow, gate queue, tool timeouts, failed compactions) and the exact setting to change; verdicts in the DSH terminal plus a /why command, subagents included.

Audits every plugin HTTP route in a profile for a browser-trust fence: plugin routes win the web server's longest-prefix match ahead of the /api gateway, so they never see its trust check and must pin the Host to loopback themselves. Grades PASS/WARN/FAIL per route and fails a fence that compares Origin to Host without pinning it (bypassable by DNS rebinding). Ships as a CLI for CI and a route_fence_scan tool.

Hands DSH reset requests to an external ops agent via a versioned JSON protocol: preflight snapshot, pre-restart maturity gate (no pending approvals, free disk, cooldown), restart, health check, and interrupted-work recovery, with the result delivered back to the requesting session.

Realtime Avatar (realtimeavatar.ai) for agents: the developer API key held by the harness credentials store, the public docs as five on-demand skills, rta_* tools over the public REST API (balance, avatars, clips, sessions, usage) with approval-gated credit spending, and a /rta command that walks a developer from no key to a live avatar call.

Cloudflare D1 tools for agents: d1_list/query/exec/schema/stats/health over the D1 HTTP API, read-only by default with a SQLite-accurate lexical guard, LIMIT row cap, CSV/JSON query output and an approval-gated write path.

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

Decision log for DeepSeek Harness: record key decisions (chosen option + why) into a versionable DECISIONS.md via decision_log / decision_list / decision_audit tools, and auto-inject the summary into future sessions so decisions stay traceable and are never re-litigated.

Model Capability Manager for DSH Web: thinking levels, context window, output caps, input modalities, gateway compat presets, EN/中文 UI.

Agent discipline guard for DeepSeek Harness: four gates enforced at the harness boundary — loop circuit-breaker, token-cost fuse, route-switch warning, plan approval — where prompt-level reminders can't reach, so an agent can no longer burn a weekly quota in minutes; one-click 🛡 chip, hot-reloadable thresholds, and presets from invisible-but-armored to warn-only.

dsh plugin: keep llm-pi-ai provider routes' model lists in step with the pi.dev gateway, written through the official settings seam

Mobile remote pairing for DSH with QR offers, a loopback Host Gateway, encrypted Relay or Quick Tunnel transport, same-LAN WebRTC Direct, and revocable Device Tokens for the Android client.

Source-filtered HTTP/SSE/WebSocket gateway for using the DSH Web UI behind an authenticated reverse proxy, with loopback trust adaptation, in-app host directory selection, and an allowlisted health endpoint.

Auto-switch the DeepSeek route to the vision model on demand: flash main session switches (A), pro keeps deep reasoning and delegates image reading to a vision subagent (B), subagents always switch, with fatal-failure fallback. No manual model switching.

CPA account-pool status panel for DeepSeek Harness: sidebar health light, quota bars, success-rate ticks, and gateway key endings

Dynamic LLM provider gateway latency and health pulse probe for DeepSeek Harness

DSH provider preset for the Memorax DeepSeek V4 Flash gateway

Reversible context slimming for DeepSeek Harness: TOON-style lossless tabular re-encoding of uniform JSON arrays, stride-sampled table windows with line numbers, and cross-turn dedup for repeated tool output; every replacement passes a byte-plus-token gate (≤72% bytes, strictly fewer estimated tokens) and the original is spilled to disk behind a `[save-token #id]` notice retrievable in one call via the `save_token_expand` tool, with billed and avoided token metering on a settings dashboard.

DeepSeek Harness provider plugin that delegates ChatGPT subscription access and agent execution to the locally authenticated Codex app server.

Danus-native DSH plugin suite: verifier-gated mathematical proof-search orchestration (fact graph, role-gated tools, cold-start verifier, worker swarm, orchestration tools, heartbeats).

DSH web plugin: a better-sidebar tab that embeds the VS Code web workbench opened at the current session workspace, behind the gateway's /vscode subpath or any configured editor base URL. Editor selections land as atomic reference chips whose canonical me

Compaction fix for NInfer-hosted qwen3.8-27b gateways: disables thinking on dsh context-compaction and session-title calls so xhigh reasoning stops burning the whole output budget; the same idea applies to other launch methods, this package targets NInfer only.

Offline BM25 knowledge base for the Conjugate Spectral Geometry (CSG) corpus: 208 articles / 3833 chunks / 871 verified truths, 5 geo_* tools (list / search / read / calc / truth) with LaTeX→Unicode rendering, truth→article citation chains and single-character query support, zero runtime deps, `dsh plugin add geometry-knowledge`.

Paired experiments and promotion gates for DSH plugins.