by TuringCorp-net

Generic stateless dialogue compression that mimics human memory. LLM conversations stay bounded forever — no session management, no context overflow. Ships a ready-to-use adapter for DeepSeek Harness

by john-walks-slow

Per-agent model switching for DeepSeek Harness: set_model / list_models agent tools with provider whitelist and token-budget guardrails, plus plan-mode model staging and cache-safe active-model contex

by GaoHu1997

Third-party model settings for DeepSeek Harness: pick a provider and a model in the composer menu, gate a model's thinking level with one switch on the official Models page card, and configure per-rou

by KIDLi1412

DSH web plugin: conversation status bar with per-session token cost estimate (per-model CNY pricing) and live DeepSeek API balance; display mode configurable (standalone bar or merged into the stats l

by ericw0315

Sidebar panel for account balances and local token usage, with provider/model breakdowns and a 27-week daily heatmap.

by vinyumao

DSH plugin: OpenCode Go Plan Usage Display (rolling/weekly/monthly usage percentage and reset countdown + Agent tool opencode_go_usage). Official bundle plugin, install: dsh plugin --profile web add github:vinyumao/dsh-opencode-usage#<ref>

by Jesse-njx

dsh-polyglot — the model switch for DSH: generic OpenAI-compatible ctx.llm adapter, curated free/cheap DeepSeek presets, automatic provider fallback on rate limits

by jiay98528-dev

Writes live provider model lists into DSH settings. Composer rings show 5h/7d plan windows or metered balance for the current session model. / Write the live model list into settings; the composer ring shows the current session's 5h/7d plan windows or pay-as-you-go remaining balance.

by activeing123

DSH plugin bundle that mounts mcptoon as an MCP server: compresses MCP tool discovery from 71,929 to 581 tokens across 255 tools (-99.2%, measured).

by ljsysfurryACE

Proactive scheduling for DeepSeek Harness: Aura heartbeat + value network (official is model-driven only)

by jiekesu967

Shows OpenCode Go subscription usage (rolling, weekly and monthly used and remaining percentage with reset times) in a floating panel anchored to the bottom-left of the session window.

by xohmai

DeepSeek Harness Plugin: CLIProxyAPI Account Pool Status Panel — Quota, Health Gauge, Traffic Overview / CPA status panel for DSH

by liaoyuqing

LLM request retry plugin for DeepSeek Harness: when a model request fails with a configured HTTP status code, machine code, or provider field=value match, it sleeps for the per-rule delay and re-issue

by NOirBRight

Command Code Provider API chat for DSH with a Host-held API key, discovered model catalog, effort defaults, an optional zero-data-retention header, quota meters, and per-model OpenAI or Anthropic prot

by kikomaotu

Sync cc-switch provider balances and track token usage & cost by day/month/total with relay-aware currency settings.

by jiay98528-dev

Weak-network adaptor: transparent long-backoff model-stream retries (10-min cap), local response replay cache, heartbeat auto-reconnect, and degraded-mode token economy, with a bilingual (zh/en) setti

by victorzhong0110

DeepSeek Harness (DSH) Task Outcome Ledger & Acceptance Plugin: evidence-backed verification, zero extra model cost, user-owned sidecar data. Local-first task outcome ledger & acceptance plugin: evidence-backed verification, zero extra model cost, user-owned sidecar data.

by xiaweiliang060035

DSH (DeepSeek Harness) web plugin — floating widget showing real-time OpenCode Go subscription usage (rolling / weekly / monthly) for every API key. Floating real-time display of opencode-go per-key usage.

by zhangjunjesse

Run the main session model on a local Claude Code subscription through the official Claude Agent SDK, taking over the llm/stream route for the claude-code provider, with token-level streaming, session

by rayadesune

DeepSeek account balance, this session's billed spend, and today's total spend in the session-header badge; a turn-cost row in the message actions strip, a detail panel with per-model pricing and a to

by dfycaly98931680

Agent trajectory governance and anomaly diagnosis: rebuilds flat session logs into multi-branch trajectory trees, detects loop deadlock, invalid retry, and goal drift, alerts with cost attribution, on

by loyalchiiina

Groups the model picker by provider: the menu lists sources first, and each source opens its models in a slide-in side panel (default) or inline below the title, switchable by double-clicking the sour

by GodD6366

Connect a sub2api gateway to DeepSeek Harness: OpenAI-compatible multi-provider routes (OpenAI / Claude / Grok / Gemini) behind one base URL, with per-key model discovery, usage lookup, and global vis

by moon09300731

Auto-switches the agent to ultra-compressed caveman-style output during DeepSeek peak-pricing hours (Beijing 09:00–12:00 / 14:00–18:00, price x2) and shows a status badge plus transition toasts.