dsh-pi-catalog-sync
The `dsh-pi-catalog-sync` plugin is designed to address the outdated model list for the `llm-pi-ai` provider in DeepSeek Harness (DSH). It synchronizes the real-time model catalog from pi.dev to DSH via the official API, with control through both the CLI and Web UI. It supports intelligent filtering, hybrid protocol handling (such as companion routing), and scheduled refreshes. The configuration is flexible, allowing customization of synchronization strategies and companion routing. The plugin runs only at startup or refreshes at defined intervals, and automatically skips when conflicts or specific configurations are encountered.
Read MoreDeepSeek Harness Plugin: Sync Cherry Studio Providers to DSH
This plugin reads Cherry Studio's SQLite database and synchronizes its configuration to DeepSeek Harness (DSH), resolving the issue of limited model discovery. Users must meet environment requirements, including Node.js 24, DSH 0.1.7-rc.2, and the expected database schema. Installation requires editing the configuration file and building the project; after restarting DSH, you can select providers and models in the interface. The plugin syncs changes every 5 seconds and securely stores API keys in DSH's local credentials. Uninstallation requires manually removing the routes and credentials from DSH.
Read MoreDeepSeek Harness Plugin: dsh-live-model-catalog
This is a DeepSeek Harness (DSH) plugin maintained by CN-WenYu, designed to automatically maintain the model catalog and reasoning tiers for the `llm-pi-ai` route. It syncs new models, capabilities, and reasoning information from endpoints via official APIs, fixes the "Get Available Models" button, is patch-free, supports safe uninstallation, and runs automatically after installation.
Read MoreDeepSeek Harness Model Sync Plugin: Monitor and Update Provider Models
The DeepSeek Harness (DSH) Model Sync plugin is designed to address the issue of missing new models when adding them manually. It supports fetching the latest model lists from various providers and offers features such as read-only inspection, selective adding, and search/filtering. It can also automatically set up multi-protocol routing and backup configurations. Users need to install and restart DSH, then sync models via the UI or the command line (`/model-sync`); all write operations are validated for safety and backed up.
Read MoreDeepSeek Harness Plugin: OpenCode Go Model Sync
dsh-opencode-models is a plugin for DeepSeek Harness that addresses stale server-side model lists. It uses live probing—text and image requests—to fetch the latest OpenCode Go models, verify availability and vision capability, and intelligently update the configuration. The plugin includes multiple safeguards, such as preserving manually added metadata, avoiding hard-coded context windows, and aborting updates when a large number of probes fail. It is easy to install, compatible with dsh ≥ 0.1.0-rc.7, and supports custom Provider configuration and thinking intensity.
Read Moredsh-better-model-select: Real-Time Model List Sync and Usage Badges
`dsh-better-model-select` is a DSH plugin designed to address delayed model list updates and the lack of usage monitoring. **Core Features:** 1. **Real-time model list synchronization**: By periodically reading the configuration and requesting the API, it updates the model list every 30 minutes. It supports merging remote and local definitions, ensuring that new models are immediately available. 2. **Usage monitoring and display**: It uses the RPC channel to fetch and display each Provider's usage in real time (such as GLM coding usage and DeepSeek balance), and applies color coding based on the remaining amount (>30%: green, ≤30%: orange, ≤10%: red). **Features:** * Supports manual synchronization and forced refresh. * Credentials are resolved through the DSH database to ensure security; failures are only logged.
Read Moredsh-model-sync: Automatic Synchronization of DeepSeek Harness Model Catalog
`dsh-model-sync` is an automation plugin for DeepSeek Harness, built around an "everything is a plugin" philosophy to eliminate the burden of manually maintaining model configurations. Maintained by GooDAnDReaDY, it can connect to 25+ upstream providers to automatically discover model lists, context windows, and pricing information, and supports quota monitoring, smart virtual aliases, and fallback chain management. It supports numerous platforms, including OpenAI, Anthropic, Groq, and Ollama, with audit logging. Installation requires Node.js 20+, and the plugin runs under DSH process permissions. It is ideal for administrators who need to efficiently manage multi-provider model catalogs.
Read MoreIntroduction to the DeepSeek Harness Model Sync Plugin
This plugin provides model list synchronization for DeepSeek Harness, addressing issues where provider endpoint changes cause outdated lists. It supports one-click manual sync and automatic sync when a conversation is opened (with debounce), queries the official API in real time to replace the existing list, and ensures that a single failure does not affect other providers. Users can install it via the `npx` command and view each provider's sync status in the settings panel, reducing maintenance costs.
Read Moredsh-model-sync: Integrate the latest model lists and quota readings from all Providers into DSH.
# Introduction If you use multiple providers—such as openai-codex, kimi-coding, and deepseek-official—simultaneously in DSH, you have likely encountered two issues: first, when a provider releases a new model, you have to manually add the model ID to `llm-pi-ai.providers.<id>.models` by referencing the documentation; and second, the quotas are scattered across different provider consoles, requiring you to switch pages to check how much remains in the 5-hour window or if your pay-as-you-go balance is sufficient. dsh-model-sync brings these two tasks into the DSH settings page: one page to synchronize the model list, one page to monitor quotas, and a ring indicator next to the input box that updates based on the current session model. Below, we introduce its features, installation, and usage.
Read More