🚀 feat: Agent Cache Tokens & Anthropic Reasoning Support (#6098)

* fix: handling of top_k and top_p parameters for Claude-3.7 models (allowed without reasoning)

* feat: bump @librechat/agents for Anthropic Reasoning support

* fix: update reasoning handling for OpenRouter integration

* fix: enhance agent token spending logic to include cache creation and read details

* fix: update logic for thinking status in ContentParts component

* refactor: improve agent title handling

* chore: bump @librechat/agents to version 2.1.7 for parallel tool calling for Google models
This commit is contained in:
Danny Avila 2025-02-27 12:59:51 -05:00 committed by GitHub
parent 34f967eff8
commit 9802629848
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 187 additions and 40 deletions

View file

@ -45,7 +45,7 @@
"@langchain/google-genai": "^0.1.9",
"@langchain/google-vertexai": "^0.2.0",
"@langchain/textsplitters": "^0.1.0",
"@librechat/agents": "^2.1.3",
"@librechat/agents": "^2.1.7",
"@waylaidwanderer/fetch-event-source": "^3.0.1",
"axios": "1.7.8",
"bcryptjs": "^2.4.3",