-
-
Notifications
You must be signed in to change notification settings - Fork 594
refine reasoning level options #1247
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
PR Compliance Guide 🔍Below is a summary of compliance checks for this PR:
Compliance status legend🟢 - Fully Compliant🟡 - Partial Compliant 🔴 - Not Compliant ⚪ - Requires Further Human Verification 🏷️ - Compliance label |
||||||||||||||||||||||
PR Code Suggestions ✨Explore these optional code suggestions:
|
|||||||||||||||||
PR Type
Enhancement
Description
Refine reasoning model settings with optional temperature and parameters support
Inject conversation state service into ChatCompletionProvider for cleaner dependency management
Extract reasoning parsing logic into dedicated method for better maintainability
Expand reasoning effort level options to include "minimal", "none", and "xhigh"
Add gpt-5 model variants with configurable reasoning parameters to settings
Diagram Walkthrough
File Walkthrough
LlmModelSetting.cs
Make reasoning temperature optional and add parameters supportsrc/Infrastructure/BotSharp.Abstraction/MLTasks/Settings/LlmModelSetting.cs
Temperatureproperty from required float with default 1.0f tonullable
float?Parametersdictionary property to support flexible modelparameter configuration
defaults
ChatCompletionProvider.cs
Refactor reasoning parsing and inject conversation state servicesrc/Plugins/BotSharp.Plugin.OpenAI/Providers/Chat/ChatCompletionProvider.cs
IConversationStateServiceas constructor dependency insteadof resolving it inline
ParseReasoningmethod thathandles temperature and effort level
ParseReasoningEffortLevelto support additional effort levels:"minimal", "none", "xhigh"
_statefield throughoutthe class
injection
appsettings.json
Add gpt-5 model variants with reasoning configurationssrc/WebStarter/appsettings.json
gpt-5.2
configurable effort level parameters