Badakonpro/dsh-llm-volcengine

README excerpt

dsh-llm-volcengine Volcengine Ark Agent Plan and Coding Plan providers for DeepSeek Harness (DSH), with verified thinking-effort compatibility. A DSH profile bundle that registers two LLM provider routes through a self-contained pi-ai-backed LlmAdapter , so model catalogs and compatibility switches reach pi-ai without depending on the dsh-llm-pi-ai settings compat schema . Thinking levels low / medium / high / xhigh / max are exposed where the endpoint honors them. Why A hand-declared Volcengine Ark route in settings.yaml runs into several gotchas that this bundle resolves once and for all: Gotcha What breaks This bundle Agent Plan must be reached over openai-responses at /api/plan/v3 The Anthropic-style /api/plan path does not expose a thinking-effort control Uses the community-verified Responses path; reasoning.effort maps natively Coding Plan gateway rejects the OpenAI developer role (HTTP 400) Every request with a system prompt fails once reasoning is enabled compat.supportsDeveloperRole: false on every Coding Plan model Coding Plan gateway rejects store and needs max tokens (not max completion tokens ) Mis-shaped requests are 400'd compat.supportsStore: false , maxTokensField:…

Category