121 results
Local OCR fallback for DeepSeek Harness (Web): when the routed model cannot accept image input, a pasted image is saved locally and its text read by PP-OCRv5 + ONNX Runtime — fully offline, no vision model required. / DeepSeek Harness 本地 OCR 兜底插件（Web）：当接入的模型不支持图片输入时，自动把图片存到本地并用 PP-OCRv5 读出文字，完全离线。
Provider fallback chain for the DeepSeek Harness LLM seam
DSH host plugin — smart outbound HTTP(S) routing: named proxies (http/https/socks4/4a/5/5h), per-host/provider/plugin rules, direct-first fallback with health memory (global fetch + node http/https).
DeepSeek Harness SSH remote workspaces with a versioned system-OpenSSH helper runtime and compatibility fallback.
Web chat entry for DeepSeek Harness (dsh plugin): a sidebar button (right below New Session) that opens chat.deepseek.com in a dedicated desktop window when running under dsh-desktop (Wails bridge), falling back to a NEW browser tab in plain web / official browser mode (never replacing the current harness page)
dsh plugin + agent preset that replicates opencode + oh-my-openagent (omo): opencode's toolchain and system prompt, omo's multi-role subagent orchestration, and browser-side omo role selection + per-role model/fallback settings.
dsh-polyglot — the model switch for DSH: one generic OpenAI-compatible ctx.llm adapter, curated free/cheap DeepSeek provider presets, and automatic provider fallback when a free tier rate-limits you
Native DeepSeek Harness plugin: gates every pwsh tool call against the PowerShell pitfalls from the blog post 'PowerShell 实战踩坑大全' via the official tools/pre-execute interception point, and bundles the powershell-check skill.
Web chat entry for DeepSeek Harness (dsh plugin): a sidebar button (right below New Session) that opens chat.deepseek.com in a dedicated desktop window when running under dsh-desktop (Wails bridge), falling back to in-webview navigation in plain web environments
DSH plugin: renders images inline in DeepSeek Harness Web chat and gives text-only models vision — cloud multimodal API first, local Qwen3-VL fallback.
Draggable animated floating companion for the DeepSeek Harness web GUI, with cat and dog breed skins that react to the current session
DSH web plugin: local offline FunASR voice input (paraformer int8 onnx sidecar, Web Speech fallback, LLM polish).
Free web search for DeepSeek Harness: Bing, DuckDuckGo, SearXNG, Exa, Tavily, Keenable — with automatic fallback, time filtering, and platform search
DSH 插件工作室 — 事件流 / 插件一览 / 插件管理 / 插件开发的 webUI 工作台
Two-level model circuit breaker with failover for DeepSeek Harness: trip a model or a whole provider after repeated request failures and route the next request to a configured fallback
Tiered auto-review for DeepSeek Harness (DSH): static-rule safety net + LLM reviewer + human fallback. Auto-approve safe actions, auto-deny irreversible ones, ask a human for the rest. PURE VIBE CODING - not audited, use at your own risk.
Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.
Two-tier model router for DeepSeek Harness — automatic execution/judgment routing with LLM Judge, multi-model fallback chains, and exponential-backoff runtime failover. A DSH adaptation of pi-shift-router.
One-click DSH background switcher backed by local Wallpaper Engine images/videos (WE Web API first, Steam workshop/myprojects directory scan fallback)
DSH 静默视觉增强：主模型照常选择，图片自动交给固定视觉模型后以隐藏上下文返回主模型。
Ask DeepSeek to falsify a file or gate a PR. Receipt: PASS / PASS_WITH_DEBT / BLOCK. Adjudicator, not a second opinion. Green lint is not a ship.
Popper: a falsification-driven correction loop for agent sessions — claim commitment, gate falsification, and mutually exclusive hypothesis revision, with an append-only evidence ledger
Unified ModelID routing for DeepSeek Harness: one logical model id over multiple providers, first-token failover with cooldown, health-aware ranking, fallback reasoning efforts, purpose-based simple/complex task split, per-tier reasoning effort, and a settings-page management panel.
Token usage statistics for the DeepSeek Harness Web UI: captures per-request LLM usage from the llm/stream waterfall, persists it, and renders animated charts grouped by API (provider), model, and date.