Skip to content

Nexus stopword list is English-only #104

@jaumforest

Description

@jaumforest

The Nexus stage's fallback token pruning uses an English stopword list. For multilingual content (common in international agent deployments), this means:

  • Non-English text gets almost zero compression from Nexus
  • Mixed-language content has inconsistent compression

Could the stopword list be extended to cover top 10 languages, or use a language-detection heuristic from Cortex to load the right list?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions