115 results
OpenCode Go subscription key rotator for DeepSeek Harness (dsh): per-request active-key routing, 429/quota cooldown rotation, cost accounting, dashboard quota scraping, and a web GUI settings section. Self-contained data dir under the plugin install folder — no machine-specific paths.
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
Adaptive model routing for DeepSeek Harness: per-request complexity classification with automatic provider routing.
Delegate light subagent tasks to cheaper models: automatic Flash/Pro routing for DeepSeek Harness subagent calls, with /delegate overrides, budget caps, and a routing-ledger panel.
Map & routing tools for DeepSeek Harness: driving/transit/walking/bicycling route planning, geocoding, reverse geocoding and POI search via Amap (高德) or free OSM/OSRM.
DSH context-window relief: knowledge base (ctx_index/search), routing enforcement (deny flood tools), sandboxed execution (ctx_execute/batch Think-in-Code), and session continuity (post-compaction restore).
Full wigolo integration for dsh: WebSearch/WebFetch providers with configurable takeover, 7 wigolo_* agent tools (search/crawl/extract/research/find_similar/cache/watch), a sidebar config panel, and cordis-managed provider routing.
Multi-agent orchestration and LLM model routing for DeepSeek Harness (DSH): semantic AI agent Specialists, exact model routes, declarative Cohorts and Strategies, and bounded subagent delegation.
Multi-route high availability, fault isolation and observability for DeepSeek Harness. Route groups fail over between authorized provider routes on rate limits (429 / Retry-After), transport errors and auth/quota failures, with per-route quarantine (exponential backoff) and disablement.
Evidence-first model control plane for DeepSeek Harness
DeepSeek Harness multi-model routing plugin: route tasks to custom specialist agents (vision / image generation / translation / speech / subagent) with per-agent providers & models, multimodal account sign-in, OAuth account pools, and realtime usage stats
DeepSee: DeepSeek Harness vision, multi-model routing, and Gemini visual self-checks before delivery
Reusable prompt profiles with per-turn model selection for DeepSeek Harness
DeepSeek Harness plugin: learning agentic router — rule + UCB + LinUCB + k-NN experts under an EXP3 meta-selector, with a durable quality-reward flywheel, REAL model switching via the session request-header precedence chain, and STEP-LEVEL routing (v1.5.0)
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.
Multi-model governance, routing, fallback, quota, and usage for DeepSeek Harness
OpenRouter Provider List — 在「插件 → 插件配置」填写 OpenRouter 请求使用的提供商列表与量化位数限制，作为 provider.only / provider.order / provider.quantizations 注入；设置通过 settings 服务持久化到 DSH 设置文档。
A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify-commit-push-review-close sequence.
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.
Capability-aware reasoning controls and provider-native Fast mode for the DeepSeek Harness web composer
Progressive capability routing for DeepSeek Harness.
智能路由：供应商自动路由，任何渠道报错自动切换下一家（含 4xx），对话栏一键启用/停用，多链管理。Provider auto-routing with fallback to the next channel on any error (incl. 4xx).
Automatic model routing for DeepSeek Harness: a virtual `smart` model classifies every request by difficulty (hard / normal / easy) and by vision need, then delegates to the models you already configured in Settings → Models. 内置智能路由：三级难度 + 视觉自动路由，模型从「设置-模型」已配置模型中选取，虚拟 smart 模型零配置接入。
Use ZenMux models in DeepSeek Harness with OAuth login, model search, and protocol-aware routing