Commit graph

5 commits

Author SHA1 Message Date
Danny Avila
2e1874e596
🔧 fix: handleError import path to use '@librechat/api' (#8415)
* 🔧 fix: Update handleError import path to use '@librechat/api' in middleware files

* chore: import order

* chore: import order

---------

Co-authored-by: Atef Bellaaj <slalom.bellaaj@external.daimlertruck.com>
2025-07-11 13:29:51 -04:00
Danny Avila
8263ddda3f
🤖 feat(Anthropic): Claude 3 & Vision Support (#1984)
* chore: bump anthropic SDK

* chore: update anthropic config settings (fileSupport, default models)

* feat: anthropic multi modal formatting

* refactor: update vision models and use endpoint specific max long side resizing

* feat(anthropic): multimodal messages, retry logic, and messages payload

* chore: add more safety to trimming content due to whitespace error for assistant messages

* feat(anthropic): token accounting and resending multiple images in progress

* chore: bump data-provider

* feat(anthropic): resendImages feature

* chore: optimize Edit/Ask controllers, switch model back to req model

* fix: false positive of invalid model

* refactor(validateVisionModel): use object as arg, pass in additional/available models

* refactor(validateModel): use helper function, `getModelsConfig`

* feat: add modelsConfig to endpointOption so it gets passed to all clients, use for properly validating vision models

* refactor: initialize default vision model and make sure it's available before assigning it

* refactor(useSSE): avoid resetting model if user selected a new model between request and response

* feat: show rate in transaction logging

* fix: return tokenCountMap regardless of payload shape
2024-03-06 00:04:52 -05:00
Danny Avila
8bef084bfc
🧩 fix(Plugins): Keep User agentModel and Model Validation (#1972)
* fix: do not override model

* temp fix for secondary model validation
2024-03-04 17:07:30 -05:00
Danny Avila
dd8038b375
🛠️ refactor: Model Loading and Custom Endpoint Error Handling (#1849)
* fix: handle non-assistant role ChatCompletionMessage error

* refactor(ModelController): decouple res.send from loading/caching models

* fix(custom/initializeClient): only fetch custom endpoint models if models.fetch is true

* refactor(validateModel): load models if modelsConfig is not yet cached

* docs: update on file upload rate limiting
2024-02-20 12:57:58 -05:00
Danny Avila
a8a19c6caa
🛡️ feat: Model Validation Middleware (#1841)
* refactor: add ViolationTypes enum and add new violation for illegal model requests

* feat: validateModel middleware to protect the backend against illicit requests for unlisted models
2024-02-19 22:47:39 -05:00