Fix/language output

[fujiajie666]

Description

Fixed a bug where the generated memories did not match the language of the input messages to be extracted.

Related Issue

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Refactoring (no functional changes)
• Performance improvement
• Test update

Changes Made

• The primary language in user_messages is used as the language determination criterion.
• Remove the bug where a single foreign language (besides Chinese and English) was used as a memorization language.

Testing

• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I have tested this on the following platforms:
  • Linux
  • macOS
  • Windows

Checklist

• My code follows the project's coding style
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• Any dependent changes have been merged and published

Screenshots (if applicable)

Additional Notes

[github-actions]

PR Reviewer Guide 🔍

Here are some key observations to aid the review process:

⏱️ Estimated effort to review: 3 🔵🔵🔵⚪⚪

🏅 Score: 85

🧪 PR contains tests

🔒 No security concerns identified

✅ No TODO sections

🔀 Multiple PR themes Sub-PR theme: Prefer user text over assistant text for language detection in SessionExtractContextProvider Relevant files: openviking/session/memory/session_extract_context_provider.py tests/session/memory/test_memory_react_system_prompt.py Sub-PR theme: Overhaul language detection logic with fallback, Latin script support, and system locale/timezone hints Relevant files: openviking/session/memory/utils/language.py tests/storage/test_semantic_processor_language.py Sub-PR theme: Update MemoryExtractor to use new language detection functions Relevant files: openviking/session/memory_extractor.py tests/session/test_memory_extractor_language.py

⚡ Recommended focus areas for review Use of private function from another module MemoryExtractor._detect_output_language imports and uses _detect_language_from_text, a private function (starts with underscore) from openviking.session.memory.utils.language. This couples the two modules unnecessarily; consider exposing a public API for language detection instead of relying on private functions. from openviking.session.memory.utils.language import _detect_language_from_text user_text = "\n".join( str(getattr(m, "content", "") or "") for m in messages if getattr(m, "role", "") == "user" and getattr(m, "content", None) ) if not user_text: return fallback return _detect_language_from_text(user_text, fallback)

[github-actions]

PR Code Suggestions ✨

No code suggestions found for the PR.