Embeddings --max_length parameter - error message when value is grater then model's max length

[przepeck]

🛠 Summary

OVMS was silently failing when the --max_length parameter was grater then model's max length. Adding error message and OV_THROW to stop server.

🧪 Checklist

• Unit tests added.
• The documentation updated.
• Change follows security best practices.
  ``

[Copilot]

🟡 Changes recommended

The new failure path should provide a single, fully-informative exception message (including relevant values/context) and should be backed by a regression test for invalid max_length configurations.

Once you've addressed the issues Copilot identified, you can request another Copilot review.

Pull request overview

This PR hardens the embeddings servable initialization by validating that a graph-configured max_length does not exceed the model’s detected maximum length (from config.json), preventing previously silent/undefined failures.

Changes:

• Add a validation check for configuredMaxLength vs. detected maxModelLength.
• Emit an error and throw to stop initialization when the configuration is invalid.

File summaries

File	Description
src/embeddings/embeddings_servable.cpp	Adds a guard that rejects max_length values greater than the model’s detected maximum length during preprocessing setup.

Review details

• Files reviewed: 1/1 changed files
• Comments generated: 2
• Review effort level: Lite

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.