feat(dotAI): Dot AI LangChain4J - Anthropic

[ihoffmann-dot]

Summary

Adds Anthropic as a supported provider, talking directly to the Anthropic Messages
API with an API key — distinct from accessing Claude models through AWS Bedrock,
which requires AWS infrastructure and IAM credentials.

• Add langchain4j-anthropic dependency (version via langchain4j BOM)
• Add AnthropicModelProviderStrategy registered in LangChain4jModelFactory.STRATEGIES
• Chat + streaming chat via AnthropicChatModel / AnthropicStreamingChatModel
• Embeddings and image throw UnsupportedOperationException (Anthropic has no such APIs)
• endpoint config field overrides the default base URL (proxies/gateways)
• Add 8 unit tests in LangChain4jModelFactoryTest

Configuration

{
  "chat": {
    "provider": "anthropic",
    "model": "claude-sonnet-4-6",
    "apiKey": "sk-ant-...",
    "maxTokens": 4096,
    "temperature": 0.7
  }
}

Notes

• Model IDs use the Anthropic form: claude-sonnet-4-6, claude-opus-4-8, claude-haiku-4-5.
• maxRetries is not supported by the streaming chat model and is ignored with a warning (same behavior as the OpenAI provider).

Related Issue

This PR fixes #36135
EPIC: dotAI Multi-Provider Support #33970

[claude]

Claude finished @ihoffmann-dot's task in 36s —— View job

---

I'll analyze this and get back to you.

[github-actions]

🤖 dotBot Review (Bedrock)

Reviewed 5 file(s); 3 candidate(s) → 3 confirmed, 0 uncertain (unverified, kept for review).

Confirmed findings

• 🟡 Medium dotCMS/src/main/java/com/dotcms/ai/client/langchain4j/AnthropicModelProviderStrategy.java:55 — Negative timeout value not validated
  The code uses config.timeout() directly in Duration.ofSeconds() without validation. If the configured timeout is negative, this creates a negative duration which may cause unexpected behavior in the Anthropic client. The AIConfig's timeout value (likely from user-provided JSON) isn't validated here, and the client may not handle negative durations properly.
• 🟡 Medium dotCMS/src/main/java/com/dotcms/ai/client/langchain4j/ProviderConfig.java:58 — Missing configuration parameters in Anthropic Javadoc
  The Javadoc for Anthropic configuration in ProviderConfig.java lists only 'apiKey', 'model', and 'endpoint' as parameters, but the PR's example configuration includes 'maxTokens' and 'temperature'. This creates documentation inconsistency, as users may not realize these optional parameters are available for tuning the Anthropic model.
• 🟡 Medium dotCMS/src/test/java/com/dotcms/ai/client/langchain4j/LangChain4jModelFactoryTest.java:602 — Test does not validate custom endpoint configuration is applied
  The test 'test_buildChatModel_anthropic_customEndpoint_returnsModel' configures a custom endpoint but only asserts the model is non-null. It lacks an assertion to verify the AnthropicChatModel instance actually uses the configured endpoint URL, leaving a gap in test coverage for endpoint overrides.

---

_{us.deepseek.r1-v1:0 · Run: #28672626375 · tokens: in: 35391 · out: 9608 · total: 44999 · calls: 14 · est. ~$0.100}

[mergify]

Queued — the merge queue status continues in this comment ↓.

[mergify]

Merge Queue Status

• ✅ Entered queue — 2026-07-03 18:37 UTC · Rule: default · triggered by @ihoffmann-dot with the merge queue checkbox
• ❌ Checks failed · on draft merge queue: checking main (25a3bba) and #36138 together #36422
• 🚫 Left the queue — 2026-07-03 18:41 UTC · at ef24802e6239147b68a71c9c3da402021b8010b9

This pull request spent 3 minutes 52 seconds in the queue, including 3 minutes 34 seconds running CI.

Waiting for any of

• check-neutral = Finalize / Final Status
• check-skipped = Finalize / Final Status
• check-success = Finalize / Final Status

All conditions

• any of [🛡 GitHub branch protection]:
  • check-neutral = Finalize / Final Status
  • check-skipped = Finalize / Final Status
  • check-success = Finalize / Final Status
• #review-threads-unresolved = 0 [🛡 GitHub branch protection]
  • feat(dotAI): Dot AI LangChain4J - Anthropic #36138
• github-review-approved [🛡 GitHub branch protection]
  • feat(dotAI): Dot AI LangChain4J - Anthropic #36138
• github-review-decision = APPROVED [🛡 GitHub branch protection]
  • feat(dotAI): Dot AI LangChain4J - Anthropic #36138
• any of [🛡 GitHub branch protection]:
  • check-success = Initialize / Initialize
  • check-neutral = Initialize / Initialize
  • check-skipped = Initialize / Initialize

Reason

The merge conditions cannot be satisfied due to failing checks

• Finalize / Final Status
• Initialize / Initialize

Failing checks:

• ❌ Finalize / Final Status (job log)

Hint

You may have to fix your CI before adding the pull request to the queue again.
If you update this pull request, to fix the CI, it will automatically be requeued once the queue conditions match again.
If you think this was a flaky issue instead, you can requeue the pull request, without updating it, by posting a @mergifyio queue comment.

Tick the box to put this pull request back in the merge queue (same as @mergifyio queue).

• Requeue this pull request