🔀 feat: update OpenRouter with new Reasoning config (#11993)

* fix: Update OpenRouter reasoning handling in LLM configuration

- Modified the OpenRouter configuration to use a unified `reasoning` object instead of separate `reasoning_effort` and `include_reasoning` properties.
- Updated tests to ensure that `reasoning_summary` is excluded from the reasoning object and that the configuration behaves correctly based on the presence of reasoning parameters.
- Enhanced test coverage for OpenRouter-specific configurations, ensuring proper handling of various reasoning effort levels.

* refactor: Improve OpenRouter reasoning handling in LLM configuration

- Updated the handling of the `reasoning` object in the OpenRouter configuration to clarify the relationship between `reasoning_effort` and `include_reasoning`.
- Enhanced comments to explain the behavior of the `reasoning` object and its compatibility with legacy parameters.
- Ensured that the configuration correctly falls back to legacy behavior when no explicit reasoning effort is provided.

* test: Enhance OpenRouter LLM configuration tests

- Added a new test to verify the combination of web search plugins and reasoning object for OpenRouter configurations.
- Updated existing tests to ensure proper handling of reasoning effort levels and fallback behavior when reasoning_effort is unset.
- Improved test coverage for OpenRouter-specific configurations, ensuring accurate validation of reasoning parameters.

* chore: Update @librechat/agents dependency to version 3.1.53

- Bumped the version of @librechat/agents in package-lock.json and related package.json files to ensure compatibility with the latest features and fixes.
- Updated integrity hashes to reflect the new version.

packages/api/src/endpoints/openai/config.spec.ts

@@ -861,7 +861,7 @@ describe('getOpenAIConfig', () => {
       expect(result.provider).toBe('openrouter');
     });
 
-    it('should handle OpenRouter with reasoning params', () => {
+    it('should handle OpenRouter with reasoning params (no summary)', () => {
       const modelOptions = {
         reasoning_effort: ReasoningEffort.high,
         reasoning_summary: ReasoningSummary.detailed,
@@ -872,10 +872,11 @@ describe('getOpenAIConfig', () => {
         modelOptions,
       });
 
+      // OpenRouter reasoning object should only include effort, not summary
       expect(result.llmConfig.reasoning).toEqual({
         effort: ReasoningEffort.high,
-        summary: ReasoningSummary.detailed,
       });
+      expect(result.llmConfig.include_reasoning).toBeUndefined();
       expect(result.provider).toBe('openrouter');
     });
 
@@ -1205,8 +1206,9 @@ describe('getOpenAIConfig', () => {
         model: 'gpt-4-turbo',
         temperature: 0.8,
         streaming: false,
-        include_reasoning: true, // OpenRouter specific
+        reasoning: { effort: ReasoningEffort.high }, // OpenRouter reasoning object
       });
+      expect(result.llmConfig.include_reasoning).toBeUndefined();
       // Should NOT have useResponsesApi for OpenRouter
       expect(result.llmConfig.useResponsesApi).toBeUndefined();
       expect(result.llmConfig.maxTokens).toBe(2000);
@@ -1480,13 +1482,12 @@ describe('getOpenAIConfig', () => {
           user: 'openrouter-user',
           temperature: 0.7,
           maxTokens: 4000,
-          include_reasoning: true, // OpenRouter specific
           reasoning: {
             effort: ReasoningEffort.high,
-            summary: ReasoningSummary.detailed,
           },
           apiKey: apiKey,
         });
+        expect(result.llmConfig.include_reasoning).toBeUndefined();
         expect(result.llmConfig.modelKwargs).toMatchObject({
           top_k: 50,
           repetition_penalty: 1.1,