跳到正文
cccskills
免费在 GitHub 公开

add-provider

Add an LLM provider to DeepChat by choosing a suitable API connection method, updating authentication and model configuration, and making focused source changes with tests for the affected behavior.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Add a DeepChat LLM provider through explicit reviewed source changes. Use when a developer asks Codex to add a provider, provider profile, upstream provider config, model catalog mapping, provider auth behavior, or a special provider adapter in this repository.

集成工具OpenAI
查看安装方法

适用场景

  • Adding an OpenAI-compatible provider
  • Connecting a provider through an existing transport
  • Implementing provider-specific authentication
  • Updating model discovery and connection tests

包含的文件(1)

  • SKILL.md4.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Add Provider

Goal

Generate DeepChat provider integration changes against the current provider architecture. Keep provider display data in PublicProviderConf, map runtime behavior to known transports, and use a special provider implementation only when the API behavior requires one.

Required Inputs

Collect or derive these before editing source:

  • Provider ID in kebab case.
  • Display name.
  • API type or known transport family.
  • Default base URL.
  • Auth type: API key, no auth, OAuth, profile credentials, or provider-specific credential.
  • Model metadata source: built-in config, provider-db, config-db, live model fetch, or custom only.
  • Test model ID and check strategy.
  • Official website, API key URL, docs URL, model list URL.
  • Request quirks: headers, endpoint suffixes, route rewrites, streaming shape, tool-call support, reasoning support, image/audio/embedding endpoints, or proxy requirements.

Supported Paths

OpenAI-Compatible API

Use this when the provider supports OpenAI Chat Completions or Responses-compatible HTTP APIs.

Typical files:

  • src/main/provider/defaults.ts
  • src/main/provider/providerId.ts
  • src/main/provider/providerRegistry.ts for runtime strategies and derived public catalog membership
  • test/main/** provider registry or creation tests

Existing Native Transport

Use this when the provider maps to an existing DeepChat transport such as Anthropic, Gemini, Vertex, Azure, Bedrock, Ollama, or ACP.

Typical files:

  • src/main/provider/defaults.ts
  • src/main/provider/providerRegistry.ts
  • Settings components only when the existing generic form lacks required fields
  • Focused tests for provider creation and connection checks

Special Provider

Use this when auth, request shape, streaming, discovery, or error handling differs from existing transports.

Typical files:

  • src/main/provider/providers/<providerName>Provider.ts
  • src/main/provider/<providerName>Adapter.ts
  • src/main/provider/managers/providerInstanceManager.ts
  • src/shared/contracts/routes/* and src/renderer/api/*Client.ts for interactive auth
  • src/renderer/settings/components/* for provider-specific settings UI
  • Main and renderer tests covering the new behavior

Guardrails

  • Do not introduce ProviderRuntimeDefinition, generated runtime manifests, or runtime package-name inference.
  • Do not install provider SDK packages automatically.
  • Do not execute provider logic in the renderer.
  • Do not store new OAuth credentials in provider API-key fields.
  • Do not add a special provider when a known transport and explicit config are sufficient.
  • Reject the request when the required inputs cannot identify a safe path.

Workflow

  1. Read docs/features/provider-runtime/spec.md when the provider work touches the provider runtime scope. Also read plan.md if it exists for an active provider-runtime goal. Treat any legacy tasks.md as migration input rather than another execution tracker.
  2. Inspect the current provider files before editing:
    • src/main/provider/defaults.ts
    • src/main/provider/providerId.ts
    • src/main/provider/providerRegistry.ts
    • src/main/provider/aiSdk/providerFactory.ts
    • src/main/provider/managers/providerInstanceManager.ts
    • src/renderer/settings/components/ProviderApiConfig.vue
  3. Classify the request into one supported path.
  4. Add the smallest explicit source changes for that path.
  5. After implementation, assess provider creation, auth handling, and model discovery for durable regression coverage; add only the smallest contract-level tests warranted.
  6. Update an active SDD plan.md as coherent implementation slices land, when one exists. For a legacy tasks.md, merge remaining work into the existing plan; without one, keep a single-slice complex bug checklist in spec.md and create plan.md for feature, architecture, or multi-slice bug work. Do not update or recreate the task file.
  7. Run:
pnpm run format
pnpm run i18n
pnpm run lint
pnpm run typecheck

Run focused main/renderer tests for any touched provider code.

Output Checklist

Report:

  • Provider ID and API type.
  • Selected path.
  • Files changed.
  • Runtime transport or special provider class.
  • Credential storage location.
  • Model metadata source.
  • Check strategy and test model.
  • Validation commands run.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Create original generative art with p5.js, using code to produce patterns and motion. Receive a written artistic concept and an interactive HTML viewer with adjustable parameters, reproducible random variations, seed navigation, and PNG downloads.

中文简介正在准备中。当前显示英语简介。

  • Create art from particle motion and flow fields
  • Explore patterns by adjusting sliders
  • Reproduce a favorite variation with the same seed
ThinkInAIXYZ/deepchat63702026年10月13日 更新

Review code for readability, maintainability, security, and performance. Receive an overview, issues grouped by severity, concrete improvements with code examples, and positive feedback on parts of the implementation that work well.

中文简介正在准备中。当前显示英语简介。

  • Reviewing an implementation before sharing it
  • Checking code for security weaknesses
  • Finding performance improvement opportunities
ThinkInAIXYZ/deepchat63702026年10月13日 更新

Operate desktop applications through DeepChat's built-in Computer Use tools. Inspect windows, click controls, enter text, use menus, and arrange windows, checking the visible result after each action.

中文简介正在准备中。当前显示英语简介。

  • Entering text and using controls in desktop apps
  • Opening files or URLs in an application
  • Arranging application windows
ThinkInAIXYZ/deepchat63702026年10月13日 更新

Use DeepChat's bundled command-line interface to compare models, generate media, transcribe audio, and extract text from images. Also inspect runtime status, artifact metadata, public settings, installed Skills, and MCP connections to external tools.

中文简介正在准备中。当前显示英语简介。

  • Comparing models and collecting benchmark results
  • Generating images, video, or speech
  • Transcribing audio and extracting text from images
ThinkInAIXYZ/deepchat63702026年10月13日 更新

Build third-party tools to inspect, extract, migrate, or analyze DeepChat's local settings and conversations. Work through data locations, database encryption, and table relationships while favoring read-only copies and redacted output.

中文简介正在准备中。当前显示英语简介。

  • Building an importer for another application
  • Inspecting provider, model, and MCP settings
  • Extracting conversations for analysis
ThinkInAIXYZ/deepchat63702026年10月13日 更新

Prepare and publish DeepChat releases through its project-specific workflow. Update versions and bilingual changelogs, run release checks, manage release branches and tags, and resume unfinished releases before publishing after release PR approval.

中文简介正在准备中。当前显示英语简介。

  • Prepare a version update and bilingual changelog
  • Check which release steps remain
  • Resume an unfinished release after metadata changes
ThinkInAIXYZ/deepchat63702026年10月13日 更新

查看 ThinkInAIXYZ 的全部技能

报告此技能的问题