631 results
Vision for text-only DeepSeek Harness agents: delegate image reading to a one-shot subagent on a configurable vision route (MiniMax / Kimi / any OpenAI-compatible provider), keeping image bytes and the vision model's context out of the main session.
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.
Daily token-consumption stats for the dsh web surface: aggregates provider-reported usage from every session log by local day, serves a /token-stats report page and /api/token-stats JSON, and adds a Token 用量 settings section to the web GUI
Engineering-discipline skill pack for DeepSeek Harness — code review, simplification, plan-then-execute, test-first, and conflict resolution, delivered as a bundled skill provider plugin.
dsh plugin: live USD cost badge (whole-session + per-turn) from provider token usage and a configurable pricing table.
NeevSandbox execution providers for DeepSeek Harness
OpenSpec (spec-driven development) as a DeepSeek Harness plugin: ships the OpenSpec agent skills as a bundled skill provider and resolves the openspec CLI from the plugin's own dependency, so no global install and no per-project .agents/skills copy is required.
Multi-provider quota, balance and Token-cost dashboard for DeepSeek Harness Web, with a draggable widget, usage analytics, local pricing and route diagnostics.
LongCat (LongCat-2.0) adapter for the DeepSeek Harness LLM seam — 1M context, thinking mode, tool calling
Use OpenCode models inside DeepSeek Harness without a separate provider API key.
Dify agent and knowledge-base capability for the DeepSeek Harness — the ctx.dify Service Definition, an HTTP Service Provider, and the model-facing dify_chat and dify_retrieve tools
OpenAI Codex (ChatGPT Plus/Pro) provider for DeepSeek Harness, with Web UI and CLI device-code OAuth login.
CodeBuddy (Tencent IOA) as a native DeepSeek Harness llm provider: browser OAuth login, token auto-renewal, credential storage, and /v3/config model sync.
Independent DeepSeek Harness plugin that adds Grok subscription as an LLM provider
Timesheet for DeepSeek Harness (dsh): turn-based time tracking from session logs — totals, per-day, per-project, per-provider, per-source rollups, tool-call counts, failure rates, and time-to-first-token. CLI + agent-callable timesheet tool, zero runtime dependencies.
Register AllRouter as a DSH provider: one base URL and one key for Kimi K3, Claude, GPT, Grok, GLM, DeepSeek, MiniMax-H3. Switch models without managing separate providers; every call reports real cost.
DSH plugin for static OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages providers
Volcengine Ark Agent Plan and Coding Plan providers for DeepSeek Harness
Academica scientific, healthcare, SEC, provider-market, reimbursement, and market-access MCP bundle for DeepSeek Harness and Pi.
DeepSeek Harness plugin: text-to-image output with in-chat image cards, download button, history gallery, and provider selection tabs
DeepSeek Harness bundle for Google Generative AI and third-party OpenAI Responses providers.
Provider-folded model selector for the DSH Web composer with catalog-driven reasoning effort choices.
DeepSeek balance & token-cost plugin for DeepSeek Harness (dual-face): query official balances of every DeepSeek provider (multi API key), compute costs (last question / session / today-project / today-all) from token usage with a user-editable price table. Unified modal UI, bilingual (zh/en)
Claude Code subagent provider with configurable CLI executable path, forked from @deepseek-ai/dsh-subagent-claude-code