🪙 refactor: Collected Usage & Anthropic Prompt Caching (#11319)

* 🔧 refactor: Improve token calculation in AgentClient.recordCollectedUsage

- Updated the token calculation logic to sum output tokens directly from all entries, addressing issues with negative values in parallel execution scenarios.
- Added comments for clarity on the usage of input tokens and output tokens.
- Introduced a new test file for comprehensive testing of the recordCollectedUsage function, covering various execution scenarios including sequential and parallel processing, cache token handling, and model fallback logic.

* 🔧 refactor: Anthropic `promptCache` handling in LLM configuration

* 🔧 test: Add comprehensive test for cache token handling in recordCollectedUsage

- Introduced a new test case to validate the handling of cache tokens across multiple tool calls in the recordCollectedUsage function.
- Ensured correct calculations for input and output tokens, including scenarios with cache creation and reading.
- Verified the expected interactions with token spending methods to enhance the robustness of the token management logic.

package-lock.json

@@ -60,7 +60,7 @@
         "@googleapis/youtube": "^20.0.0",
         "@keyv/redis": "^4.3.3",
         "@langchain/core": "^0.3.80",
-        "@librechat/agents": "^3.0.66",
+        "@librechat/agents": "^3.0.77",
         "@librechat/api": "*",
         "@librechat/data-schemas": "*",
         "@microsoft/microsoft-graph-client": "^3.0.7",
@@ -12660,9 +12660,9 @@
       }
     },
     "node_modules/@librechat/agents": {
-      "version": "3.0.66",
-      "resolved": "https://registry.npmjs.org/@librechat/agents/-/agents-3.0.66.tgz",
-      "integrity": "sha512-JpQo7w+/yLM3dJ46lyGrm4gPTjiHERwcpojw7drvpYWqOU4e2jmjK0JbNxQ0jP00q+nDhPG+mqJ2qQU7TVraOQ==",
+      "version": "3.0.77",
+      "resolved": "https://registry.npmjs.org/@librechat/agents/-/agents-3.0.77.tgz",
+      "integrity": "sha512-Wr9d8bjJAQSl03nEgnAPG6jBQT1fL3sNV3TFDN1FvFQt6WGfdok838Cbcn+/tSGXSPJcICTxNkMT7VN8P6bCPw==",
       "license": "MIT",
       "dependencies": {
         "@langchain/anthropic": "^0.3.26",
@@ -12686,6 +12686,7 @@
         "https-proxy-agent": "^7.0.6",
         "mathjs": "^15.1.0",
         "nanoid": "^3.3.7",
+        "okapibm25": "^1.4.1",
         "openai": "5.8.2"
       },
       "engines": {
@@ -34310,6 +34311,12 @@
         "url": "https://github.com/sponsors/ljharb"
       }
     },
+    "node_modules/okapibm25": {
+      "version": "1.4.1",
+      "resolved": "https://registry.npmjs.org/okapibm25/-/okapibm25-1.4.1.tgz",
+      "integrity": "sha512-UHmeH4MAtZXGFVncwbY7pfFvDVNxpsyM3W66aGPU0SHj1+ld59ty+9lJ0ifcrcnPUl1XdYoDgb06ObyCnpTs3g==",
+      "license": "MIT"
+    },
     "node_modules/ollama": {
       "version": "0.5.18",
       "resolved": "https://registry.npmjs.org/ollama/-/ollama-0.5.18.tgz",
@@ -43169,7 +43176,7 @@
         "@google/genai": "^1.19.0",
         "@keyv/redis": "^4.3.3",
         "@langchain/core": "^0.3.80",
-        "@librechat/agents": "^3.0.66",
+        "@librechat/agents": "^3.0.77",
         "@librechat/data-schemas": "*",
         "@modelcontextprotocol/sdk": "^1.25.2",
         "@smithy/node-http-handler": "^4.4.5",