dsh-model-context-catalog
One-click context window matching and selective bulk configuration for DeepSeek Harness models, with source references and manual management.
14 results
One-click context window matching and selective bulk configuration for DeepSeek Harness models, with source references and manual management.
Model Capability Manager for DSH Web: per-model thinking levels, context window, output caps, input modalities, gateway compat, route defaults, one-click presets, EN/中文 UI.
DSH web plugin: 为自定义模型(OpenAI-compatible pi-ai provider)增加思考强度(reasoning effort)配置 —— 设置页新增「思考强度」分区,按模型配置思考级别与线格式、按 provider 配置默认思考强度,直接写入 llm-pi-ai 设置,composer 模型选择器随即生效。
Sync opencode-go models from https://models.opencode.ai/api.json into llm-pi-ai provider opencode-go-autosync (one-click create/update in settings).
DSH Web GUI 模型能力配置:在「设置 → 模型」的模型目录编辑器内,为每个已配置的模型直接设置思考等级(reasoning efforts),并按 models.dev 预设/批量同步思考等级与上下文容量,写入 llm-pi-ai 设置命名空间。
Persistent DSH model-account authorization UI for ChatGPT, Claude, and other llm-pi-ai login flows
DSH 插件:提供文本 / 图像 / 视频 / 视觉理解 / 语音 / 音乐 六个生成工具,模型从 llm-pi-ai 自动发现,含 Settings UI (llm-multimodal namespace)。
DSH plugin: context-aware per-step reasoning-effort routing. Classifies each step (trivial/standard/engineering/hard) from the task brief and live session evidence, escalates on tool errors, stabilizes with hysteresis, clamps to the target model's advertised efforts, and injects an 'Auto' mask into the native model selector. Fills default reasoningEfforts for hand-declared llm-pi-ai custom models. All user-facing options live in the plugin config file (no settings UI); the GUI surfaces (composer badge, trajectory hoisting) are read-only displays.
A dsh plugin that replaces the built-in llm-pi-ai and llm-deepseek adapters, the model selector and the Models settings page with self-maintained versions, tracks upstream @earendil-works/pi-ai, and adds quota/balance lookups plus a provider management UI
dsh plugin: shows the model name the upstream actually reported for each assistant step, backfilling pi-ai replay metadata from a non-invasive fetch observer when the adapter omits it
Frontend-injected per-model reasoning-effort (thinking strength) configuration for custom pi-ai providers. Registers a per-model 思考强度 editor into the Settings -> Models provider card and persists reasoningEfforts through the settings Remote.
DeepSeek Harness Web GUI 插件:在设置面板为 llm-pi-ai 提供方按模型配置思考开关/思考等级(reasoningEfforts),为官方 DeepSeek 配置思考开关(thinking)与思考等级(reasoningEffort),并为各提供方模型配置输入类型(llm-pi-ai 写 input、官方 DeepSeek 写 inputModalities)。
Reorder the model list of any llm-pi-ai route from Settings > Models; the composer model menu follows the same order.
DSH 错误分类修正插件:把 pi-ai 适配器一律判成 AUTH 的提供方失败改写为 PROVIDER_ERROR,让网关原文原样显示,而不是被 UI 替换成「API 密钥无效」。