Model pricing for the DSH settings page: per-1M-token prices from models.dev with the harness catalog overlaid, capability tags, cross-provider comparison, and a community promotion feed.

LLM provider adapter that routes model calls through any ACP (Agent Client Protocol) server — Claude Code, Codex, Gemini CLI, Devin and more — with a registry browser, per-server settings UI, lazy aut

Role-based LLM retry & fallback strategies.

Model switching, model capability configuration, fixed compaction models, subagent routing, and input history enhancement.

One-click/auto sync provider model lists against /v1/models endpoint.

OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-mod

Tiered model routing for DeepSeek Harness: think/build model tiers, vision delegation (the vision model only describes images; the working model acts), image generation, and a high-impact guard.

xAI Grok subscription chat: SuperGrok or X Premium+ OAuth, a displayed model subset, Responses through the Grok CLI proxy, and always-on server-side web_search and x_search.

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.

Command Code LLM provider plugin adapted for DSH-Desktop 0.7.1: registers a commandcode route, with a live model catalog, reasoning-effort support, and real-time plan usage display.

Per-model system prompt injector for DeepSeek Harness: append custom prompt text to the END of the system prompt for locally configured models, matched by exact provider/model route or a provider-wide

Adds CC Switch providers and models to DeepSeek Harness, with provider filtering and model-name search.

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.

Global Alt+M model command palette for DeepSeek Harness Web: fuzzy search over models and providers, favorites and recents, per-model reasoning effort, provider and model configuration, request retrie

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