dsh-vision-opencode
DeepSeek Harness plugin: configurable vision model with vision_read_image tool, composer-bar vision-model selector, and automatic image-to-text conversion for text-only main models.
36 results
DeepSeek Harness plugin: configurable vision model with vision_read_image tool, composer-bar vision-model selector, and automatic image-to-text conversion for text-only main models.
Free models leaderboard for DeepSeek Harness: paginated sidebar panel, one-click custom-provider setup (you only paste your free API key), powered by your own PHP 7.4 + SQLite backend.
A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, live per-task cost, prices and context windows.
Write live provider model lists into DSH settings. Composer rings show 5h/7d plan windows or metered balance since the last top-up for the current session model.
基元律动费用中心:账户余额与限时额度、按分类筛选的模型价格卡(含折扣价)、官方同款服务状态与平台密钥管理;凭据只存本机 host。
CodeBuddy (copilot.tencent.com) provider bundle for DeepSeek Harness (dsh): 18 models (DeepSeek, GLM, Kimi, MiniMax, Hunyuan, auto) with adjustable reasoning efforts, CodeBuddy web search / web fetch backends for the stock dsh tools, and a settings card in the Web UI.
Composer-attached images are auto-described by an OpenAI-compatible vision model and handed to text-only models (DeepSeek) as text.
Explicit model input-modality selection for the DeepSeek Harness Web UI
Read-only insight panel for a DeepSeek Harness profile: where every plugin, service, tool and model came from, which config layer inserted or disabled it, and what is running right now.
Adds an 'Invert selection' button to the fetch-models dialog of the Models settings section
DeepSeek Harness plugin for local GGUF models without Ollama
DSH plugin: view OBJ/STL/STEP models in the web UI and translate them into a standardized, LLM-readable JSON
Model capability radar for the DeepSeek Harness web GUI: a Settings tab that charts codexradar crowd-benchmark scores per model tier — task-composition bars, 7-day IQ trend, efficiency badges
DSH web plugin: DeepSeek balance & platform usage monitoring, integrated into the Models settings provider row and the composer tool row (left of the model name). Replicates the DeepSeekMonitorWindows backend.
DeepSeek Harness client plugin: adds an 'Invert selection' button to the fetch-models dialog of the Models settings section, so only the rows that are already in the model list stay checked on a second fetch + add pass.
DeepSeek Harness plugin: content-aware PDF reading tools for vision models (pdf_scan / pdf_read_page / pdf_render_region). Detects figures (vector+raster), tables, math, and two-column layout per page, then routes text pages to extraction and figure/table/math pages to high-DPI region crops rendered for read_image — avoiding DeepSeek's ~800x800 whole-page token ceiling. Backed by PyMuPDF; returns a clear warning (with the exact install command) when Python or a dependency is missing.
DSH web plugin: splits the composer model selector into two independent controls — a searchable, favorite-marking model dropdown and a reasoning-effort slider — plus Ctrl+P (cycle favorite models) and Ctrl+T (cycle reasoning effort) shortcuts.
Context compression for small-context models on the DeepSeek Harness Web GUI: one click condenses the whole conversation into a few sentences, opens a fresh session in the same workspace, and re-injects the summary as the first message so a small model keeps working with a clean, compact context.
Model and reasoning-effort switcher: composer seat with an Off/Max effort slider over session.models / session.selectModel
Dense translucent-glass Universal Palette for DeepSeek Harness Web — federates Commands, Models, Sessions and Conversation Hits with deterministic ranking and verified public-contract interoperability.
DeepSeek Harness plugin: the Models+ settings page — a fully plugin-owned model/provider UI with per-model extension fields (reasoning efforts, input modalities, compat flags) and models.dev metadata prefill
DSH-native multi-AI group chat: the host (user) runs a chatroom of configurable AI agents with per-agent models, role cards, mute controls, and passive/active speaking modes — pure Node.js/Cordis, no Tauri/Rust
Model-facing analyze_image tool for the DeepSeek Harness: multi-modal image understanding via any OpenAI- or Anthropic-compatible vision API, with 8 analysis modes, local path / http(s) URL / data URL input, and a Web UI hint that guides image-incapable models to the reliable local-path route.
Single-model disable gate: hides denied models from every discovery path, blocks dispatch with an in-protocol error chunk, and exposes a settings-section UI for the denylist