Integrate Gatewayz provider extension and docs

[vdimarco]

Summary

• Adds Gatewayz provider extension for universal AI inference (10k+ models) with OpenAI-compatible API
• Includes provider code, tests, docs, and integration into implicit providers

Changes

Extensions

• Added Gatewayz extension package and code:
  • extensions/gatewayz/index.ts: Registers provider with id "gatewayz", label "Gatewayz", env var GATEWAYZ_API_KEY, api_key auth, and OpenAI-compatible models config
  • extensions/gatewayz/index.test.ts: Unit tests for plugin metadata, provider registration, api_key auth, and models config
  • extensions/gatewayz/package.json: Extension manifest
• Documentation:
  • docs/providers/gatewayz.md: New Gatewayz provider docs (quick start, env var, config, and models)
  • docs/docs.json: Routes /gatewayz to /providers/gatewayz
• CI/labels:
  • .github/labeler.yml updated to include gatewayz category

Core provider config

• Core integration:
  • src/agents/model-auth.ts: Added Gatewayz environment variable mapping (GATEWAYZ_API_KEY) for API key resolution
  • src/agents/models-config.providers.ts:
    • Built function buildGatewayzProvider() returning baseUrl, api, and models (gpt-4o, gpt-4o-mini, claude-3-5-sonnet/haiku, gemini-1.5-pro/flash, llama, deepseek, qwen, mistral, etc.)
    • resolveImplicitProviders() now includes Gatewayz provider when a key is available

Tests

• Updated tests to cover Gatewayz integration:
  • src/agents/model-auth.test.ts: Added test to resolve Gatewayz API key from env (GATEWAYZ_API_KEY)
  • extension tests verify provider metadata, registration, auth method, and OpenAI-compatible models config includes gatewayz models

Documentation and keys

• Documentation updated to reflect Gatewayz provider, including how to configure and use the key:
  • Quick start: onboard gatewayz with an API key
  • Environment variable: GATEWAYZ_API_KEY
  • Config snippet: example providers config including models and base URL
• pnpm-lock.yaml updated to account for new extension

Rationale

• Enables OpenClaw users to access Gatewayz’s universal AI inference API via a single provider, with OpenAI-compatible endpoints and a catalog of 10k+ models. Centralizes model definitions and authentication flow for Gatewayz within the existing provider framework.

Test plan

• Run unit tests for the gatewayz extension
• Verify environment-based API key resolution for Gatewayz in model-auth flow
• Validate OpenAI-compatible models config includes Gatewayz models

How to test locally

• Install and run tests: pnpm test
• Validate env var workflow:
  • Set GATEWAYZ_API_KEY in your environment
  • Run tests or trigger provider resolution to ensure the key is picked up and provider config is populated
• Try onboarding Gatewayz via OpenClaw CLI using your API key as documented in docs/providers/gatewayz.md

Notes

• The Gatewayz provider is registered with id "gatewayz", aliases include "gateway" and "gatewayz.ai", and uses the GATEWAYZ_API_KEY environment variable for authentication
• Default models include GPT-4o, GPT-4o Mini, Claude 3.5 Sonnet/Haiku, Gemini 1.5 Pro/Flash, DeepSeek, LLaMA, Qwen, Mistral, and others as defined in the provider config
• Documentation links and model catalog guidance are provided in the new docs/providers/gatewayz.md

🌿 Generated by Terry

---

ℹ️ Tag @terragon-labs to ask questions and address PR feedback

📎 Task: https://terragon-www-production.up.railway.app/task/72008ef3-5fb0-4c76-8462-ea032daefd46

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.

[coderabbitai]

Warning

Rate limit exceeded

@vdimarco has exceeded the limit for the number of commits that can be reviewed per hour. Please wait 18 minutes and 6 seconds before requesting another review.

⌛ How to resolve this issue?

After the wait time has elapsed, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout.

Please see our FAQ for further information.

✨ Finishing touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch gatewayz-code/integrate-gatewayz-provider-ujrc9h

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}