Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2025-12-16 16:30:15 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

✨ feat: Add OpenAI Verbosity Parameter (#8929)

Browse source 
* WIP: Verbosity OpenAI Parameter

* 🔧 chore: remove unused import of extractEnvVariable from parsers.ts

* ✨ feat: add comprehensive tests for getOpenAIConfig and enhance verbosity handling

* fix: Handling for maxTokens in GPT-5+ models and add corresponding tests

* feat: Implement GPT-5+ model handling in processMemory function
This commit is contained in:
Danny Avila 2025-08-07 20:49:40 -04:00 • committed by GitHub
parent 486fe34a2b
commit 7147bce3c3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 989 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

2
client/src/locales/en/translation.json
View file

@ -231,6 +231,7 @@
"com_endpoint_openai_prompt_prefix_placeholder": "Set custom instructions to include in System Message. Default: none",
"com_endpoint_openai_reasoning_effort": "Reasoning models only: constrains effort on reasoning. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. 'Minimal' produces very few reasoning tokens for fastest time-to-first-token, especially well-suited for coding and instruction following.",
"com_endpoint_openai_reasoning_summary": "Responses API only: A summary of the reasoning performed by the model. This can be useful for debugging and understanding the model's reasoning process. Set to none,auto, concise, or detailed.",
"com_endpoint_openai_verbosity": "Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.",
"com_endpoint_openai_resend": "Resend all previously attached images. Note: this can significantly increase token cost and you may experience errors with many image attachments.",
"com_endpoint_openai_resend_files": "Resend all previously attached files. Note: this will increase token cost and you may experience errors with many attachments.",
"com_endpoint_openai_stop": "Up to 4 sequences where the API will stop generating further tokens.",
@ -269,6 +270,7 @@
"com_endpoint_prompt_prefix_placeholder": "Set custom instructions or context. Ignored if empty.",
"com_endpoint_reasoning_effort": "Reasoning Effort",
"com_endpoint_reasoning_summary": "Reasoning Summary",
"com_endpoint_verbosity": "Verbosity",
"com_endpoint_save_as_preset": "Save As Preset",
"com_endpoint_search": "Search endpoint by name",
"com_endpoint_search_endpoint_models": "Search {{0}} models...",