by dongsheng123132

Content-addressed readiness proof for sanitized DeepSeek Harness observations on managed Windows hosts

by shuang-ying

Reads each third-party endpoint's own model listing and keeps llm-pi-ai's per-model reasoningEfforts in sync, so the composer offers the thinking levels a model actually has.

by wefio

Notify when a cache miss occurs. The plugin isn't broken, so it probably won't update.

by Mutx163

Reasoning-effort tier manager for custom API models plus cross-session preference memory: inline low/medium/high/max toggles inside Settings → Models, with atomic settings writes.

by fishlikewater

MCP Server Manager: Configure MCP servers on the DSH settings page; the host side hot-mounts/unloads mcp-client instances according to the configuration

by hpfs0

A plugin that makes providers route through the proxy

by minyang-chen

Resolves a company name or ticker to a verified stock symbol via SEC EDGAR, then fetches a live quote with price, P/E, EPS, market cap, 52-week range, and dividend yield from yahoo-finance2.

by ChrisZhangWG

Adds a Settings Usage dashboard for DeepSeek API balance, official token and cost analysis, trends, context warnings, and live API activity.

by yishengdaxiaonengjihui

Budget-LLM pool router for DeepSeek Harness: ledger, health tracking, Thompson-sampling failover across free-tier models. Broke Router

by Storm-Starlight

MCP server and skill management for DeepSeek Harness: a sidebar panel and a plugin-page config section with search, status lights, per-row switches, expandable details, and an add-server form followin

by JasperPengC

MCP server and skill management for DeepSeek Harness: a sidebar panel and a plugin-page config section with search, status lights, per-row switches, expandable details, and an add-server form followin

by GeekRicardo

Composer-dock balance/usage readout for DeepSeek, Kimi Coding, OpenCode Go, Zhipu, MiniMax, OpenRouter and OpenAI Codex — provider-based, 2s polling, 5min cache.

by uckkk

Minimal peak/valley meter for DeepSeek Harness: balance badge above the composer + hover 24h peak/valley timeline, 5s live balance refresh, independent spend metering, 10 color presets. Peak/valley meter: balance badge + hover

by penguin-oo

Automatic Flash/Pro routing for DeepSeek Harness subagent calls: light tasks go cheap, heavy tasks stay strong — with /delegate overrides.

by 66rapper

Model channel auto-enricher for DeepSeek Harness: eliminates manually configuring contextWindow, maxTokens, [text, image] multimodal input, and {low, high, max} reasoning effort tiers model by model a

by haochi72

Automatically sends "continue" to recover from RATE_LIMIT (429) and QUOTA (insufficient_quota) errors. Per-session consecutive-failure counter (default 20, configurable 1-100), a toolbar on/off switch

by LuminariSoftwares

Your MCP servers for ~300 tokens instead of ~28,000. MCP server + native DeepSeek Harness bundle.

by dongsheng123132

Evidence-first token cost ledger and budget checks for DeepSeek Harness

by zoumutou

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

by w2327644822-png

Personal usage analytics & activity dashboard for the DeepSeek Harness (dsh) web GUI: token totals, contribution heatmap, model share, insights. Local-only, metadata only.

by Ztyss

Fully take over model services, and provide an intuitive configuration approach with quota display

by linziyanleo

Configure custom LLM providers in DeepSeek Harness.

by dyuan311

ChatGPT subscription OAuth for the openai-codex provider in DeepSeek Harness

Token usage statistics by model, session and date in a sidebar panel, plus OpenCode Go quota, DeepSeek balance and Z.ai quota monitoring.