Tonic Textual release information

Learn about what’s in the latest Tonic.ai product releases.

Release Notes

v409

April 16, 2026

  • For zip codes, the synthesis configuration now includes options to truncate zip codes to the first 3 digits, and to replace foreign zip code values with zeroes.
  • Fixed a guided redaction issue where deleted files were not immediately removed from the file list.
  • For all entity types, the synthesis configuration now includes an option to provide a single constant replacement value. When you provide a constant value, Textual ignores any entity type-specific synthesis configuration. It does respect mappings of specific original values to replacement values.

v408

April 15, 2026

  • Fixed an issue with searching for a user to grant permission set access to.
  • For the Date of Birth entity type, when you choose to synthesize values, you can now select whether to use the Date Shift Generator, which was previously the only option, or the Date Truncation Generator. For the Date Truncation Generator, Textual always sets the month and day to January 1. If the original year is less than 90 years ago, then Textual keeps the original year. If the original year is 90 or more years ago, then Textual sets the year to the current year minus 89.
  • For the Age entity type, when you choose to synthesize values, you can now select whether to use the Age shift generator, which was previously the only option, or the Passthrough or group age generator. For Passthrough or group age, if the original age is less than 90, then Textual keeps the original age. If the original age is 90 or older, then Textual sets the age to 90+. This is to meet HIPAA Safe Harbor requirements.

v407

April 9, 2026

  • For the Snowflake integration, the redaction can now include model-based custom entity types. The custom entity types are created and configured in Textual.

v406

April 2, 2026

  • Improved accuracy for Spanish and Dutch when using multilingual deployment.
  • Changing the enabled custom entity types in a dataset is now included in the dataset version history.
  • When you download guided redaction files to a single PDF, you can now choose to add page numbers.

v405

March 31, 2026

  • Bug fixes and other internal updates.

v404

March 30, 2026

  • Users can now view a history of changes to a dataset, and restore the dataset to a previous version.
  • When you export files from a guided redaction project, you can now include:
    • Footer text
    • A watermark

v403

March 24, 2026

  • Bug fixes and other internal updates.

v402

March 20, 2026

  • Bug fixes and other internal updates.

v401

March 18, 2026

  • Bug fixes and other internal updates.

v400

March 18, 2026

  • Bug fixes and other internal updates.

v399

March 18, 2026

  • Improved PDF redaction stability so repeated processing produces consistent output.
  • Improved the LLM used to detect key-value pairs in PDF files.

v398

March 17, 2026

  • Bug fixes and other internal updates.

v397

March 16, 2026

  • Fixed complex HTML redactions so synthesized email and phone replacements preserve surrounding markup and no longer produce broken HTML fragments.

v396

March 14, 2026

  • For CSV files in a dataset, from the file preview, you can now configure entity type handling for entire columns. A column might be structured and sensitive, structured but not sensitive, or unstructured. Structured columns contain a single consistent type of value, such as a name, date, or number. For unstructured columns, such as a description or notes, the values can contain multiple entities of different types, and must be scanned individually. Note that this only applies to CSV files that are added to a dataset after this release. Existing CSV files are not affected.
  • Fixed HTML replacements so that inline breaks such as `` do not pull adjacent text into phone and email replacement values.
  • Fixed HTML report mappings so that spanning HTML replacements keep their surrounding markup in report values.
  • Added an optional phone metadata flag to preserve US prefixes such as `(855)` or `1 (234)` during synthesis.

v395

March 13, 2026

  • Bug fixes and other internal updates.

v394

March 13, 2026

  • Improved accuracy for Italian when using multilingual deployment. Added an environment variable TEXTUAL_MULTI_LINGUAL_XLM_ONLY to optionally only run multilingual model, instead of English + multilingual model, when Textual detects non-English languages.

v393

March 12, 2026

  • Added a new endpoint to retrieve dataset entity mappings grouped by file. From the Python SDK, to retrieve the entity mappings, use Dataset.get_entity_mappings(). The results include original, redacted, synthetic, and final output values. When available, the results also include tabular row, column, and score metadata. The results respect dataset entity type handling configuration. When none of the entity types are active, it can return empty per-file entity lists.

v392

March 12, 2026

  • Fixed an issue that prevented Textract from being used to process standalone documents submitted through the SDK.

v391

March 12, 2026

  • Improved filtering and sorting on the Datasets page.
  • Changed entity linking from an LLM-based model to a BERT-based model, which increases throughput and decreases the deployment footprint without decreasing accuracy.

v390

March 10, 2026

  • Redesigned Textual pages to accommodate the new left navigation menu. Options and tabs that were previously to the left of the page are moved to the top of the page.

v389

March 6, 2026

  • Bug fixes and other internal updates.

v388

March 3, 2026

  • For self-hosted customers only, for model-based custom entity types, added annotation support with Gemini on Vertex AI.

v387

March 2, 2026

  • For Textual built-in entity types, regular expression patterns for excluded values can now reference the surrounding context.

v386

February 27, 2026

  • Bug fixes and other internal updates.

v385

February 27, 2026

  • Bug fixes and other internal updates.

No items found.