LibreChat/packages/api/src
Danny Avila 723acd830c
🎚️ feat: Add Thinking Level Parameter for Gemini 3+ Models (#11994)
* 🧠 feat: Add Thinking Level Config for Gemini 3 Models

- Introduced a new setting for 'thinking level' in the Google configuration, allowing users to control the depth of reasoning for Gemini 3 models.
- Updated translation files to include the new 'thinking level' label and description.
- Enhanced the Google LLM configuration to support the new 'thinking level' parameter, ensuring compatibility with both Google and Vertex AI providers.
- Added necessary schema and type definitions to accommodate the new setting across the data provider and API layers.

* test: Google LLM Configuration for Gemini 3 Models

- Added tests to validate default thinking configuration for Gemini 3 models, ensuring `thinkingConfig` is set correctly without `thinkingLevel`.
- Implemented logic to ignore `thinkingBudget` for Gemini 3+ models, confirming that it does not affect the configuration.
- Included a test to verify that `gemini-2.9-flash` is not classified as a Gemini 3+ model, maintaining expected behavior for earlier versions.
- Updated existing tests to ensure comprehensive coverage of the new configurations and behaviors.

* fix: Update translation for Google LLM thinking settings

- Revised descriptions for 'thinking budget' and 'thinking level' in the English translation file to clarify their applicability to different Gemini model versions.
- Ensured that the new descriptions accurately reflect the functionality and usage of the settings for Gemini 2.5 and 3 models.

* docs: Update comments for Gemini 3+ thinking configuration

- Added detailed comments in the Google LLM configuration to clarify the differences between `thinkingLevel` and `thinkingBudget` for Gemini 3+ models.
- Explained the necessity of `includeThoughts` in Vertex AI requests and how it interacts with `thinkingConfig` for improved understanding of the configuration logic.

* fix: Update comment for Gemini 3 model versioning

- Corrected comment in the configuration file to reflect the proper versioning for Gemini models, changing "Gemini 3.0 Models" to "Gemini 3 Models" for clarity and consistency.

* fix: Update thinkingLevel schema for Gemini 3 Models

- Removed nullable option from the thinkingLevel field in the tConversationSchema to ensure it is always defined when present, aligning with the intended configuration for Gemini 3 models.
2026-02-28 16:56:10 -05:00
..
acl 🏗️ feat: Dynamic MCP Server Infrastructure with Access Control (#10787) 2025-12-11 16:38:37 -05:00
agents 🪙 feat: Add messageId to Transactions (#11987) 2026-02-27 23:50:13 -05:00
apiKeys 🛸 feat: Remote Agent Access with External API Support (#11503) 2026-01-28 17:44:33 -05:00
app 🧬 fix: Backfill Missing SHARE Permissions and Migrate Legacy SHARED_GLOBAL Fields (#11854) 2026-02-18 12:48:33 -05:00
auth 🛡️ fix: Implement TOCTOU-Safe SSRF Protection for Actions and MCP (#11722) 2026-02-11 22:09:58 -05:00
cache ⚛️ refactor: Redis Scalability Improvements for High-Throughput Deployments (#11840) 2026-02-18 00:04:33 -05:00
cdn 🪣 fix: S3 path-style URL support for MinIO, R2, and custom endpoints (#11894) 2026-02-21 18:36:48 -05:00
cluster 🐛 fix: Redis Cluster Bug + 🧪 Enhance Test Coverage (#10518) 2025-11-16 11:58:52 -05:00
crypto 🧵 refactor: Migrate Endpoint Initialization to TypeScript (#10794) 2025-12-11 16:37:16 -05:00
db 🔧 refactor: Centralize Collection Checks for Permissions Migration (#9565) 2025-09-10 20:40:58 -04:00
endpoints 🎚️ feat: Add Thinking Level Parameter for Gemini 3+ Models (#11994) 2026-02-28 16:56:10 -05:00
files 🧩 feat: OpenDocument Format File Upload and Native ODS Parsing (#11959) 2026-02-26 14:39:49 -05:00
flow 🌊 feat: Resumable LLM Streams with Horizontal Scaling (#10926) 2025-12-19 12:14:19 -05:00
mcp 🪣 fix: Prevent Memory Retention from AsyncLocalStorage Context Propagation (#11942) 2026-02-25 17:41:23 -05:00
memory 🛂 feat: Payload limits and Validation for User-created Memories (#8974) 2025-08-10 14:46:16 -04:00
middleware 🚦 fix: 404 JSON Responses for Unmatched API Routes (#11976) 2026-02-27 22:49:54 -05:00
oauth 🔒 fix: Secure Cookie Localhost Bypass and OpenID Token Selection in AuthService (#11782) 2026-02-13 10:35:51 -05:00
prompts 🧵 refactor: Migrate Endpoint Initialization to TypeScript (#10794) 2025-12-11 16:37:16 -05:00
stream 🪣 fix: Prevent Memory Retention from AsyncLocalStorage Context Propagation (#11942) 2026-02-25 17:41:23 -05:00
tools 💎 fix: Gemini Image Gen Tool Vertex AI Auth and File Storage (#11923) 2026-02-24 08:21:02 -05:00
types 🪨 feat: AWS Bedrock Document Uploads (#11912) 2026-02-23 22:32:44 -05:00
utils 📌 fix: Populate userMessage.files Before First DB Save (#11939) 2026-02-26 09:16:45 -05:00
web 🔍 feat: Add Serper as Scraper Provider and Firecrawl Version Support (#9984) 2025-10-05 20:34:05 -04:00
index.ts 🪣 fix: Prevent Memory Retention from AsyncLocalStorage Context Propagation (#11942) 2026-02-25 17:41:23 -05:00