dsh-llm-capabilities
DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.
57 results
DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.
OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", enable_thinking / chat_template_kwargs / reasoning_effort driven by the llm-pi-ai model config, and a </think> split on the receive side — no pi-ai behavior guessing.
dsh plugin: keep llm-pi-ai provider routes' model lists in step with the pi.dev gateway, written through the official settings seam
DeepSeek Harness Web plugin: per-model input-modality selector on the Models settings page for third-party (pi-ai) providers
dsh plugin: sync the pi.dev model catalog into llm-pi-ai provider routes through the official settings seam, including mixed-protocol routes such as OpenRouter that in-place sync cannot address.
Reuse the Codex CLI ChatGPT OAuth login in DeepSeek Harness through pi-ai's openai-codex provider.
Installable OpenAI Codex device-login provider for DeepSeek Harness pi-ai routes
ChatGPT Plus/Pro OAuth model provider for DeepSeek Harness, backed by pi-ai's openai-codex route.
Sync CC Switch (cc-switch) providers and models into DeepSeek Harness custom providers (llm-pi-ai)
DeepSeek Harness LLM User-Agent/header injector with key pool round-robin: keeps the official llm-pi-ai adapter, re-injects user-agent, and supports multi-key rotation per provider. | DeepSeek Harness LLM 请求头注入器 + Key 轮询:保留官方适配器,补回 User-Agent,支持按提供商多 Key Round-Robin 轮询。
DSH plugin: exposes per-provider balance / coding-plan usage (5h window + weekly) in a status bar pinned to the native session-stats row.
Per-route context window, compaction threshold, and per-model thinking-effort controls for DSH models. · DSH 模型上下文窗口、压缩阈值与思考强度设置。
dsh web 插件:自动配置模型思考档位与能力,并按 provider+model 记住最后选择的思考档位
DSH 模型视觉开关:设置页「模型视觉」行,为 llm-pi-ai 自定义路由下手写声明的模型切换 input 视觉模态(settings.mutate 官方通道,热生效)。
Rebuild DSH's pi-ai model catalogues at runtime: fetches the live model lists from OpenRouter, OpenCode Zen, Fireworks, Groq, Together and DeepSeek and patches the harness's installed pi-ai MODELS registry, so the model picker and discovery show fresh models without hand-adding custom models.
Persistent DSH model-account authorization UI for ChatGPT, Claude, and other llm-pi-ai login flows
Per-model and per-route image-input (vision) checkboxes on the Models page's custom-provider cards, writing through the llm-pi-ai settings namespace.
DeepSeek Harness bridge plugin: exposes the newest Zhipu/Z.AI coding-plan models (e.g. glm-5.3) on the zai-coding-cn route before the bundled pi-ai catalog catches up.
DeepSeek Harness 推理强度与网关增强插件:自动为 llm-pi-ai 下所有模型补齐推理强度档位(off→max 全七档),并自动为 OpenCode Go 网关注入必需的 x-opencode-session 路由 Header,写入 settings 由 dsh 原生解析生效。
DSH 插件:提供文本 / 图像 / 视频 / 语音 / 音乐 五个生成工具,模型从 llm-pi-ai 自动发现,含 Settings UI (llm-multimodal namespace)。
Probe local model servers (llama.cpp / Ollama) for the real runtime context window and keep llm-pi-ai's contextWindow in sync automatically — tighter before overflow, wider when the server grows. Zero-config profile plugin for DeepSeek Harness.
Volcengine Ark provider plugin for DeepSeek Harness (DSH): registers Agent Plan, Coding Plan, and postpaid routes on the native pi-ai adapter so Ark models appear in the model picker.
Personal dsh profile bundle: disables the shipped agent presets, builds generated standard / ptc presets into dist, and declares personal llm-pi-ai provider routes.
Grant official-style reasoning-effort selection to hand-declared pi-ai models (DeepSeek relays and the like) in the chat box