v3.9.1

3.9.1 – 2025-11-05

Fixed

• catch errors in model fetch during migration @kyteinsky #289

v3.9.0

3.9.0 – 2025-11-04

Fixed

• correct app version release

3.8.0 – 2025-11-04

Added

• add chunking to ChangeTone, ContextWrite, ProofreadProvider, ReformulateProvider, TopicsProvider, and TranslateProvider @lukasdotcom #240
• implement auto detection for task types and toggle for analyze image @lukasdotcom #252
• add notification when quota exceeded @lukasdotcom #254
• add monthly quota periods @lukasdotcom #256
• implement quota rules @lukasdotcom #255
• add quota report download @lukasdotcom #257
• add config for how long to store usage @lukasdotcom #257
• add AI app category @janepie #275
• specify language for AudioToText @lukasdotcom #266
• add user preference to set default language for AudioToText @lukasdotcom #266

Changed

• update context needed for the quota reset day @lukasdotcom #265
• add openai api info in the readme @kyteinsky #268
• lazy load most app config values, store them as lazy too @julien-nc #246
• bump max NC version to 33
• hint about the v1 in the custom service url info text @kyteinsky #279
• change default completion model to 4.1 mini @lukasdotcom #271

Fixed

• use admin specified max tokens as default for all tasks it makes sense for @lukasdotcom #239
• admin settings style and quota fixes @kyteinsky #241
• fix default tts model selector for vue3 @lukasdotcom #247
• fix empty argument gets encoded as [] instead of {} @lukasdotcom #243
• fix custom unreachable service handling, store the model list in the DB @julien-nc #277

v3.8.0

3.8.0 – 2025-10-06

Added

• add chunking to ChangeTone, ContextWrite, ProofreadProvider, ReformulateProvider, TopicsProvider, and TranslateProvider @lukasdotcom #240
• implement auto detection for task types and toggle for analyze image @lukasdotcom #252
• add notification when quota exceeded @lukasdotcom #254
• add monthly quota periods @lukasdotcom #256
• implement quota rules @lukasdotcom #255
• add quota report download @lukasdotcom #257
• add config for how long to store usage @lukasdotcom #257
• add AI app category @janepie #275
• specify language for AudioToText @lukasdotcom #266
• add user preference to set default language for AudioToText @lukasdotcom #266

Changed

• update context needed for the quota reset day @lukasdotcom #265
• add openai api info in the readme @kyteinsky #268
• lazy load most app config values, store them as lazy too @julien-nc #246
• bump max NC version to 33
• hint about the v1 in the custom service url info text @kyteinsky #279
• change default completion model to 4.1 mini @lukasdotcom #271

Fixed

• use admin specified max tokens as default for all tasks it makes sense for @lukasdotcom #239
• admin settings style and quota fixes @kyteinsky #241
• fix default tts model selector for vue3 @lukasdotcom #247
• fix empty argument gets encoded as [] instead of {} @lukasdotcom #243
• fix custom unreachable service handling, store the model list in the DB @julien-nc #277

v3.7.1

3.7.1 – 2025-07-16

Fixed

• Prefer using the old message format in the chat history: content is a string. Use the new format when there is audio @julien-nc #237

v3.7.0

3.7.0 – 2025-07-11

Added

• Implement audio chat provider @julien-nc #227

Fixed

• update composer with php8.1 @kyteinsky #233
• Invalidate all cache with a prefix instead of deleting one key that we don't use anymore @julien-nc #234

v3.6.0

3.6.0 – 2025-07-09

Added

• Add support for text to speech @lukasdotcom #210
• Add Analyze Image Task Type @lukasdotcom #226

Changed

• update README.md @edward-ly @jospoortvliet #46
• update summary prompt @edward-ly #214
• migrate to vue3 and @nextcloud/vue 9 @julien-nc #220
• use outline icons instead of solid ones @kyteinsky #228
• update personal settings basic auth @kyteinsky #228

Fixed

• do not add /v1 twice to the service url @kyteinsky #207
• Fix some mistakes in phpdoc @lukasdotcom #211
• fix English source string @edward-ly #212
• improve 401 error message @kyteinsky #218
• Update all workflows and fix bootstrap.php @lukasdotcom #221
• fix content type identification @lukasdotcom #225
• separate user and admin cache, and allow taskproc without userId @kyteinsky #230

v3.5.0

3.5.0 – 2025-03-11

Added

• Add support for together ai @kyteinsky #197

Changed

• Enable use_max_completion_tokens_param by default for OpenAI, disable by default for non-OpenAI @julien-nc #184
• Add admin setting to toggle authentication in the image retrieval request @julien-nc #186
• Add a warning in the admin settings if the assistant app is not installed @julien-nc #185
• Raise the default image size for compatibility @Rello #193
• Bump max NC version to 32

Fixed

• Prevent browser autocomplete for API key inputs and credentials @julien-nc #187
• Do not attempt to update local quota if chat/completion response does not have usage.total_tokens set @julien-nc #189
• Prevent error log flood when not configured @kyteinsky #199

v3.4.0

3.4.0 – 2025-01-22

Changed

• Use max_completion_tokens instead of deprecated max_tokens @julien-nc #176

Added

• Add reuse compliance @AndyScherzinger #173
• Make image generation work with base64 responses (e.g. IONOS) @julien-nc @janepie #177
• Mention IONOS as service with an OpenAI-compatible API @julien-nc #178
• Support chatting with o1 models @julien-nc #179

New Contributors

• @AndyScherzinger made their first contribution in #173

Full Changelog: v3.3.0...v3.4.0

v3.3.0

What's Changed

• fix: English headlines for English text with OpenAI by @janepie in #162
• Feat: add change tone provider by @janepie in #163
• chore(i18n): Fixed grammar by @rakekniven in #165
• Add ChatWithTools provider by @julien-nc in #167
• feat: add input chunking to summarize task by @edward-ly in #157
• Feat: add proofread provider by @janepie in #169
• Feat: use server tasktype for changing tone if available by @janepie in #172
• prepare 3.3.0 by @julien-nc in #171

New Contributors

• @janepie made their first contribution in #162

Full Changelog: v3.2.0...v3.3.0

v3.2.0

What's Changed

• Add admin setting to set the default image size by @julien-nc in #135
• Encrypt api keys and basic passwords for app config and user settings by @julien-nc in #136
• Switch to IAppConfig by @julien-nc in #139
• Remove old providers by @julien-nc in #140
• Add warning: Mainly tested with OpenAI by @julien-nc in #142
• feat: add ability to customize API root path in service URL by @edward-ly in #143
• enh: update readme and info.xml by @kyteinsky in #144
• Fix: Use correct userId in most provider by @julien-nc in #153
• Move request timeout input out of "text processing" section by @julien-nc in #151
• Fix: Use api key in image retrieval request by @julien-nc in #147
• Cache the models for 30min in distributed cache by @julien-nc in #152
• Choose stt model in admin settings by @julien-nc in #154
• Prepare 3.2.0 by @julien-nc in #155

Full Changelog: v3.1.2...v3.2.0