👤 feat: AWS Bedrock Custom Inference Profiles (#11308)

* feat: add support for inferenceProfiles mapping

* fix: remove friendly name since api requires actual model id for validation alongside inference profile

* docs: more generic description in docs

* chore: address comments

* chore: update peer dependency versions in package.json

- Bump @aws-sdk/client-bedrock-runtime from ^3.941.0 to ^3.970.0
- Update @librechat/agents from ^3.0.78 to ^3.0.79

* fix: update @librechat/agents dependency to version 3.0.80

* test: add unit tests for inference profile configuration in initializeBedrock function

- Introduced tests to validate the applicationInferenceProfile setting based on model configuration.
- Ensured correct handling of environment variables and fallback scenarios for inference profile ARNs.
- Added cases for empty inferenceProfiles and absence of bedrock config to confirm expected behavior.

* fix: update bedrock endpoint schema reference in config

- Changed the bedrock endpoint reference from baseEndpointSchema to bedrockEndpointSchema for improved clarity and accuracy in configuration.

* test: add unit tests for Bedrock endpoint configuration

- Introduced tests to validate the configuration of Bedrock endpoints with models and inference profiles.
- Added scenarios for both complete and minimal configurations to ensure expected behavior.
- Enhanced coverage for the handling of inference profiles without a models array.

---------

Co-authored-by: Danny Avila <danny@librechat.ai>

api/server/services/Config/loadConfigModels.js

@@ -28,6 +28,11 @@ async function loadConfigModels(req) {
     modelsConfig[EModelEndpoint.azureAssistants] = azureConfig.assistantModels;
   }
 
+  const bedrockConfig = appConfig.endpoints?.[EModelEndpoint.bedrock];
+  if (bedrockConfig?.models && Array.isArray(bedrockConfig.models)) {
+    modelsConfig[EModelEndpoint.bedrock] = bedrockConfig.models;
+  }
+
   if (!Array.isArray(appConfig.endpoints?.[EModelEndpoint.custom])) {
     return modelsConfig;
   }