Adds a colored status line under the DSH conversation stats showing live DeepSeek API cost, usage and account balance, with on/off-peak pricing indicators.

by phungthien269

Token usage dashboard for the DSH web GUI — today/week/month totals, per-model breakdown and a stacked 30-day chart, with a 4-language UI.

Single-model disable gate: hides denied models from DSH catalogs, blocks direct dispatch with an in-protocol error chunk, and exposes a settings UI for the denylist.

Per-model reasoning effort declarations for GPT, Gemini and OpenAI-compatible providers in DeepSeek Harness

DeepSeek Harness plugin: join ACN so this agent can discover, message, and collaborate with other agents. Defaults to the China region.

by xxvk

Floating cost crystal for the Web UI: balance card, real-time tok/s, peak/off-peak billing countdown, last-24h spend, and a 🔮 next-message cost forecast, all timezone-aware.

by EasyTZ

Balance and Cost: DeepSeek balance, daily/weekly/monthly spend, per-model usage, and real-time unit pricing.

Bottom-right balance badge for the DSH Web UI: on expand it fetches the currently-selected provider's OpenCode Go plan limits or DeepSeek prepaid balance, plus local token usage and pricing-based spend est

Exposes the models already configured in DeepSeek Harness through an OpenAI-compatible gateway, so other local projects can call them with any standard OpenAI client. Multiple provider candidates shar

by david0702

DSH (DeepSeek Harness) Chat Footer Cost Display Plugin: Batches billing by request time + model, time-period breakdown, model attribution, image-reading cost, and balance.

by dongsheng123132

Content-addressed proof for body-free DSH tool-result retention and spill custody

by hualuo520-h

Brings the models of the SCNet (Supercomputing Internet) Computing Service desktop client into DSH by reusing the API key that client already wrote, with a 30-model catalog and a per-model default thinking level.

A balance and cost widget for the DSH web GUI: a sidebar footer card shows the account balance, a remaining-ratio bar and today costs; clicking opens a four-tier cost breakdown (last prompt / this ses

by HB00

Automatic provider failover on rate limits or quota exhaustion: switch between providers with configurable per-provider models, a cooldown, and a permanent last-entry fallback.

Registers external ACP (Agent Client Protocol) agents such as Codex, Claude Code and Gemini CLI as DSH model providers: maps each agent's thought_level options to the reasoning-effort selector, forwar

by Willmylife

Adds a connection-test panel under Settings -> Models: reads the deployment's model catalog and probes each configured model with one minimal chat round-trip (a short "ping" with a small output cap) t

DSH Model Center Plugin: Free Model Directory / Verified Free in Practice / Pricing & Balance / One-Click Switch / Usage Statistics — Model center plugin for DeepSeek Harness

by lj100886

Configure model providers by probing their endpoint, check DeepSeek Harness health, and repair what can be fixed - from a standalone settings page.

by xtd1145

Real-time DeepSeek API balance (official endpoint) and today-spend estimate (this DSH instance session-log usage x per-model price table) for the DSH web: composer dock strip, always-on floating badge

Reuses stored Responses IDs for continuation, with retry and branch isolation and verified history replay.

Fork of dsh-reasoning-effort with a two-level model picker in the composer: a provider list, a model pane that slides out beside it, search, and compact rows, alongside the reasoning-effort slider and

by ct-jyjntc

Declare whether a configured third-party model accepts image (multimodal) input; writes the modality into the owning provider settings and verifies it through runtime model resolution.

Shows DeepSeek API account balance and Volcengine Ark Coding/Agent Plan quota windows (5h/weekly/monthly with reset countdowns) in the settings panel, composer dock, and a draggable floating refresh b

Conversation Usage Receipt: Display each conversation's token usage, call count, time consumed, and cost by model (receipt-style per-conversation usage and cost)