dsh-llm-opencode-go
OpenCode Go models, mixed Completions/Responses/Messages chat, and subscription usage for DeepSeek Harness
27 results
OpenCode Go models, mixed Completions/Responses/Messages chat, and subscription usage for DeepSeek Harness
Improve web search in Deepseek Harness, use server-side search service.
ChatGPT Codex, xAI Grok, Zhipu GLM, AWS Kiro, Google Antigravity, Cursor, Ollama Cloud, Kimi, and GitHub Copilot subscription OAuth for DeepSeek Harness — PKCE / device-code / Google login, local Responses proxy, llm-pi-ai sync.
DeepSeek Harness plugin: gzip /api responses — fixes history loading failures over slow links
DeepSeek Harness bundle for Google Generative AI and third-party OpenAI Responses providers.
Open Eyes for DeepSeek Harness: delegate images to a configurable multimodal model through OpenAI Responses, Chat Completions, or Anthropic Messages.
DSH harness bundle/plugin: tolerate OpenAI-compatible providers whose streaming responses omit finish_reason (e.g. the Snowflake Cortex gateway) so turns complete instead of failing with a TRANSPORT error.
DeepSeek Harness plugin: run subagents on a local llama.cpp model via the OpenAI Responses (/v1/responses) protocol, with a subagent delegation skill
DSH plugin for static OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages providers
DeepSeek Harness Cordis plugin for free ChatGPT Web (GPT 5.6 Luna) pure chat and zero API fees.
OpenAI Responses API-backed web search provider for dsh: registers into ctx.web (web_search tool with server-side retrieval), plus a Web settings card for endpoint/model/key. Hot-pluggable — mounted via profile bundle patch, no dsh source changes.
DSH model management, synchronized model visibility, and OpenAI Responses web search.
dsh WebSearchProvider over the OpenCode Zen Go Responses API server-side web_search tool
OpenAI Responses adapter and durable server-side compaction bundle for DeepSeek Harness.
DSH ctx.web search provider that reuses the conversation model's OpenAI Responses web_search tool
Dual-pipeline compaction for DeepSeek Harness: official server-side Responses compaction v2 for OpenAI-routed targets, with a deterministic VCC-style local compiler (zero model calls) as the default fallback and for every other provider.
Configurable OpenAI Responses-compatible native web search provider for DeepSeek Harness, with a Settings UI
Token Rhythm (OpenAI Responses web_search) search provider for the DeepSeek Harness web capability seam (ctx.web)
Normalize undersized Grok Responses images with Sharp while leaving supported large images unchanged.
TokenLab provider bundle for DeepSeek Harness with native Responses, Messages and Chat routing plus full multimodal and async tools.
Dedicated AnyRouter Claude Code and Codex Responses adapter for DeepSeek Harness
Volcengine Ark (火山方舟) web-search provider for the DSH web seam: calls the Ark Responses API with the native web_search tool and maps url_citation annotations to search sources.
Inspect raw LLM requests and responses in DeepSeek Harness Web
Processes tab for DeepSeek Harness: a live per-process console (main agent and every subagent) with raw tool requests, responses and timing, installed as one profile bundle.