Change scanning.scanResolution recommended setting to character for agglutinative languages

[ImenaOphelia]

Source is this Wikipedia category.

Not sure what translation.searchResolution does; removed it completely for agglutinatives.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 8f867a37e8

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[chatgpt-codex-connector]

Restore word search resolution for agglutinative presets

This replacement removes the previous translation.searchResolution = "word" override for Finnish (and the same pattern appears in hu, id, mn, and tr), so these languages now fall back to the global default translation.searchResolution = "letter" (ext/data/schemas/options-schema.json). In letter mode, Translator._getNextSubstring truncates one character at a time (ext/js/language/translator.js), which substantially increases per-scan lookup attempts and introduces many partial-prefix matches compared with the prior word-boundary behavior, especially on long agglutinative words; keeping an explicit word search resolution avoids this regression.

Useful? React with 👍 / 👎.

[StefanVukovic99]

what translation.searchResolution does

Search resolution determines whether only whole words will be searched, or any prefix substring:

Some people are annoyed by having the prefix matches shown (e.g. cat for category) so they like it on 'word', and it can stay that way. For languages with lots of compound nouns like German, and probably agglutinative languages also, 'letter' is more useful.

scanResolution is 'aim assist', whether the text to be searched starts from the cursor or from the beginning of the word. So I think the description Scan text one character at a time. could be improved.