dsh-always-status-bar
DSH Web UI plugin: keep the native per-message status line (date | time, run duration, TTFT, tokens/s) always visible without hovering
108 results
DSH Web UI plugin: keep the native per-message status line (date | time, run duration, TTFT, tokens/s) always visible without hovering
Text-to-image for DeepSeek Harness: a `draw_image` model tool, an input-bar 生图 button with a prompt popup (async generation, 4-grid results, download / keep / delete), an /imgdraw image route, and persisted history. Backends: DashScope wan2.7-image (free default) and SiliconFlow Qwen-Image.
Login gate for the DeepSeek Harness web GUI: username/password entry page (DeepSeek style), 12-hour session tokens, slash commands for user management. Background tasks keep running while logged out.
Drag and paste files into dsh Web with a unified preview rail; keep native images and add file references only when sending.
Semantic vector search over a ~6,000-skill local corpus. Ships a bundled `skill-router` skill that routes any task to the most relevant vetted playbook on demand, keeping the corpus out of the per-turn model catalog.
DSH vision bridge (DSH >= 0.1.2-rc.1): when the selected chat model is text-only, attached images are described by a local Ollama VL model (qwen3-vl:8b) with keep_alive VRAM cooling. Install-time patch of dsh-api-session-controller prompt admission + runtime status companion.
CodeBuddy-style deferred tool loading for DeepSeek Harness: keep tool schemas out of the model context until the model loads them on demand via tool_search / defer_execute_tool.
Model providers for DeepSeek Harness: sign in with OAuth or an API key, and keep every provider's model catalog current
On-demand vision for text-only LLMs in DeepSeek Harness: keep pasted/attached images in the backend, and let the model call view_image to look at them anytime via any OpenAI-compatible vision endpoint — as if the model were natively multimodal.
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 plugin: pick configured model providers, and when a model fails with a model-related error the request automatically falls through the provider group's models (then the next selected provider) until one works, so the unfinished task keeps going. Adds its own Settings tab.
Keeps long coding-agent sessions lean: wrap work in named tasks and, when one is done, fold its whole span into a short titled summary. The conversation stays readable, context costs stay low, and every fold's original content can be read back on demand. For DeepSeek Harness.
DSH plugin: auto-tiles oversized chat images into labelled grid pieces (row/col metadata, overlap-aware, multi-image group isolation) so the DeepSeek vision model keeps fine detail instead of the ~800px downsample.
Minimal-anchored agent preset for DeepSeek Harness: first request keeps the real Minimal tool pair, promotion unlocks the full Standard catalog with a one-shot background-jobs notice
Compatibility antidote for dsh-claude-ux: keep its risk-control UI visibly enabled while neutralizing the actual debuffs.
DeepSeek Harness web GUI: collapse the agent trajectory (tool calls, thinking, workflow steps) while always keeping the agent's final output. A setting controls whether the trajectory is default-collapsed after the final output completes (default on).
Monitor the system clipboard and keep a searchable persisted history with a Web panel and agent tools for DeepSeek Harness (DSH).
Token optimizer for DeepSeek Harness — condense your context, keep the essence
Work out how a web system actually works — once. Captures its real HTTP API and accessibility tree in a dedicated, fenced browser, then keeps a reusable playbook so later automation never pays to rediscover it.
Side-chat (旁会话) plugin for DeepSeek Harness: launch a fresh, continuable parallel session from the conversation header while the main session keeps running. · DSH 旁会话插件:主会话进行中也能一键新开一个独立会话并行提问。
DeepSeek Harness plugin: a deterministic UTF-8 byte cap on tool results, keeping the first N bytes and carrying a sha256 of the full original so a truncated result is never mistaken for a whole one
Multiple API keys per provider for DeepSeek Harness: keep a pool of keys with notes, switch the active key right from Settings → API 密钥, and every switch really takes effect on the next model call.
DeepSeek Harness plugin: route an agent request to a vision model (deepseek-v4-flash-vision-exp) when the user message contains an image, and keep the original model otherwise.
Ghost Refresh (鬼影提神) — a friendly ghost drifts across the page to keep you awake. Adjustable speed / opacity / size / frequency, persisted per browser.