ThinkInAIXYZ/deepchat / .agents/skills/add-provider
add-provider
VerifiedAdd 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.
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.tssrc/main/provider/providerId.tssrc/main/provider/providerRegistry.tsfor runtime strategies and derived public catalog membershiptest/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.tssrc/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.tssrc/main/provider/<providerName>Adapter.tssrc/main/provider/managers/providerInstanceManager.tssrc/shared/contracts/routes/*andsrc/renderer/api/*Client.tsfor interactive authsrc/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
- Read
docs/features/provider-runtime/spec.mdwhen the provider work touches the provider runtime scope. Also readplan.mdif it exists for an active provider-runtime goal. Treat any legacytasks.mdas migration input rather than another execution tracker. - Inspect the current provider files before editing:
src/main/provider/defaults.tssrc/main/provider/providerId.tssrc/main/provider/providerRegistry.tssrc/main/provider/aiSdk/providerFactory.tssrc/main/provider/managers/providerInstanceManager.tssrc/renderer/settings/components/ProviderApiConfig.vue
- Classify the request into one supported path.
- Add the smallest explicit source changes for that path.
- After implementation, assess provider creation, auth handling, and model discovery for durable regression coverage; add only the smallest contract-level tests warranted.
- Update an active SDD
plan.mdas coherent implementation slices land, when one exists. For a legacytasks.md, merge remaining work into the existing plan; without one, keep a single-slice complex bug checklist inspec.mdand createplan.mdfor feature, architecture, or multi-slice bug work. Do not update or recreate the task file. - 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.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |