Skip to content

feat(provider): add AGIone provider preset#1123

Closed
KaiShaoCheng wants to merge 3 commits into
ValueCell-ai:mainfrom
KaiShaoCheng:feat/agione-provider
Closed

feat(provider): add AGIone provider preset#1123
KaiShaoCheng wants to merge 3 commits into
ValueCell-ai:mainfrom
KaiShaoCheng:feat/agione-provider

Conversation

@KaiShaoCheng

Copy link
Copy Markdown

Summary

Adds AGIone as a built-in OpenAI-compatible provider preset.

The preset uses AGIone's Chat Completions-compatible endpoint:

https://agione.pro/hyperone/xapi/api/v1

Default model:

qwen/qwen3.5-plus/cec84

Related Issue(s)

None.

Type of Change

  • Bug fix
  • New feature
  • Documentation
  • Refactor
  • Other

Validation

pnpm exec vitest run tests/unit/providers.test.ts
pnpm run typecheck
pnpm run lint:check
git diff --check

Checklist

  • I ran relevant checks/tests locally.
  • I updated docs if behavior or interfaces changed.
  • I verified there are no unrelated changes in this PR.

Disclosure

Submitted by the AGIone team.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 61267cda80

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread src/lib/providers.ts
apiKeyUrl: 'https://aistudio.google.com/app/apikey',
},
{ id: 'openrouter', name: 'OpenRouter', icon: '🌐', placeholder: 'sk-or-v1-...', model: 'Multi-Model', requiresApiKey: true, showModelId: true, modelIdPlaceholder: 'openai/gpt-5.5', defaultModelId: 'openai/gpt-5.5', docsUrl: 'https://openrouter.ai/models' },
{ id: 'agione', name: 'AGIone', icon: '🧩', placeholder: 'ak-...', model: 'Multi-Model', requiresApiKey: true, defaultBaseUrl: 'https://agione.pro/hyperone/xapi/api/v1', showModelId: true, modelIdPlaceholder: 'qwen/qwen3.5-plus/cec84', defaultModelId: 'qwen/qwen3.5-plus/cec84', apiKeyUrl: 'https://agione.pro', docsUrl: 'https://agione.pro' },

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Add E2E coverage for AGIone provider UI

AGENTS.md's UI change validation rule requires user-visible UI changes to include or update an Electron E2E spec; this line makes AGIone appear in the Add Provider dialog, but the commit only adds unit coverage in tests/unit/providers.test.ts. Please add a Playwright/Electron E2E that covers selecting/adding the AGIone provider so the new visible flow is validated.

Useful? React with 👍 / 👎.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 43bc0ae515

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread tests/e2e/provider-lifecycle.spec.ts Outdated
if (request.action === 'list') return respond(request.id, []);

if (request.action === 'validateKey') {
expect(body.providerId).toBe('agione');

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Move assertions out of Electron main evaluate

When the renderer validates the key, this handler runs inside the Electron main process created by electronApp.evaluate, not in the Playwright test worker, so the imported Playwright expect symbol is not available there. The first validation request will hit this line, throw ReferenceError: expect is not defined, reject the host:invoke IPC call, and the new E2E will fail instead of adding AGIone; capture the request data in main and assert it back in the test process, or return explicit validation errors from the mock.

Useful? React with 👍 / 👎.

Comment thread electron/shared/providers/registry.ts Outdated
envVar: 'AGIONE_API_KEY',
supportedAuthModes: ['api_key'],
defaultAuthMode: 'api_key',
supportsMultipleAccounts: true,

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Keep AGIone single-account until runtime keys are unique

With this flag, the real add-provider dialog will allow multiple AGIone accounts and buildProviderAccountId will create agione-<uuid> ids, but the runtime mapping still collapses every registered non-custom/non-ollama provider back to the single OpenClaw key agione and ProviderService.listAccounts() keeps only one account per runtime key while deleting the rest. Adding a second AGIone account therefore overwrites/prunes the first account (and can clear the default if the first was default); either mark AGIone single-account here or add AGIone to the multi-instance runtime-key mapping.

Useful? React with 👍 / 👎.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 9714cbdeb8

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

},
},
{
id: 'agione',

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Add harness coverage for the AGIone provider scenario

AGENTS.md requires new user-visible OpenClaw scenarios to add or update the relevant harness task/scenario/rule specs, and this preset introduces a new provider flow that writes runtime provider config. This commit adds the provider and tests but no harness/specs change, so future AI-coding validation will not cover the AGIone provider/runtime behavior; please add the corresponding harness spec coverage for this scenario.

Useful? React with 👍 / 👎.

@su8su su8su closed this Jul 2, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants