feat: Add SAP AI Core provider support

[jerome-benoit]

Summary

This PR adds support for SAP AI Core as a provider in OpenCode, enabling users to access 40+ AI models (GPT-4o, Claude, Gemini, Amazon Nova, etc.) through SAP Business Technology Platform.

Implementation Details

Provider Integration

• Uses @mymediset/sap-ai-provider (community Vercel AI SDK compatible package)
• Custom async loader pattern to handle OAuth2 authentication
• Follows existing OpenCode provider architecture patterns

Configuration

Users can configure SAP AI Core via:

1. Service Key: SAP_AI_SERVICE_KEY (JSON from SAP BTP Cockpit)
2. Deployment ID: SAP_AI_DEPLOYMENT_ID (default: d65d81e7c077e583)
3. Resource Group: SAP_AI_RESOURCE_GROUP (default: default)
4. Auth Storage: opencode auth add sap-ai-core

Features Supported

• ✅ OAuth2 authentication with automatic token refresh
• ✅ 40+ models (OpenAI, Anthropic, Google, Amazon, Meta, Mistral, etc.)
• ✅ Streaming responses
• ✅ Tool calling (function calling)
• ✅ Multi-modal inputs (text + images)
• ✅ Structured outputs
• ✅ Model parameters (temperature, topP, maxTokens, etc.)
• ✅ Data masking via SAP Data Privacy Integration (DPI)

Files Changed

• packages/opencode/package.json - Added @mymediset/sap-ai-provider@1.3.1
• packages/opencode/src/provider/provider.ts - Added custom loader for SAP AI Core
• packages/web/src/content/docs/providers.mdx - Added documentation
• bun.lock - Updated dependencies

Testing Status

• ✅ TypeScript compilation passes
• ✅ Build succeeds (all platforms)
• ⏳ Manual testing with real SAP AI Core instance (requires maintainer validation)

Documentation

Complete user-facing documentation added to providers.mdx including:

• Prerequisites (SAP BTP subscription)
• Service key acquisition steps
• Configuration examples
• Supported models list
• Model parameters guide

Conformity with OpenCode Standards

• ✅ Follows existing provider architecture (custom loader pattern like github-copilot)
• ✅ Uses Auth.get() for credential management
• ✅ Type-safe implementation with proper TypeScript types
• ✅ Documentation follows exact formatting of existing providers
• ✅ No style guideline violations

Why This Provider?

SAP AI Core is an enterprise-grade AI platform widely used in SAP ecosystem and beyond. This integration allows:

• Enterprise users to leverage their existing SAP BTP infrastructure
• Access to RAG (Retrieval-Augmented Generation) deployments
• Enterprise compliance (data masking, audit trails)
• Unified model access across OpenAI, Anthropic, Google, Amazon models

Questions for Maintainers

1. Should we create a GitHub issue first per CONTRIBUTING.md guidelines?
2. Any preferred approach for testing without exposing SAP credentials?
3. Is the default deployment ID acceptable or should we require explicit configuration?

---

Note: This PR is in draft status to allow for review and validation before final testing.

[jerome-benoit]

Closing to recreate with simpler description per guidelines