fix reasoning effort

[iceljc]

PR Type

Bug fix

---

Description

• Fix reasoning effort level fallback logic

• Only use agent config when model matches current model

• Prevent incorrect reasoning effort from being applied

---

Diagram Walkthrough

flowchart LR
  A["Get reasoning_effort_level from state"] --> B{"Is level empty AND<br/>model matches agent config?"}
  B -->|Yes| C["Use agent config<br/>ReasoningEffortLevel"]
  B -->|No| D["Use state value<br/>or null"]
  C --> E["Parse reasoning effort level"]
  D --> E

Loading

File Walkthrough

Relevant files

Bug fix

ChatCompletionProvider.cs Add model matching check for reasoning effort fallback      src/Plugins/BotSharp.Plugin.OpenAI/Providers/Chat/ChatCompletionProvider.cs Changed reasoning effort level fallback logic from unconditional to conditional Added model matching check before using agent config value Only applies agent config reasoning effort when current model matches agent's configured model +6/-2

---

[qodo-code-review]

PR Compliance Guide 🔍

Below is a summary of compliance checks for this PR:

Security Compliance
🟢	No security concerns identified No security vulnerabilities detected by AI analysis. Human verification advised for critical code.
Ticket Compliance
⚪	🎫 No ticket provided Create ticket/issue
Codebase Duplication Compliance
⚪	Codebase context is not defined Follow the guide to enable codebase context checks.
Custom Compliance
🟢	Generic: Comprehensive Audit Trails Objective: To create a detailed and reliable record of critical system actions for security analysis and compliance. Status: Passed Learn more about managing compliance generic rules or creating your own custom rules
	Generic: Meaningful Naming and Self-Documenting Code Objective: Ensure all identifiers clearly express their purpose and intent, making code self-documenting Status: Passed Learn more about managing compliance generic rules or creating your own custom rules
	Generic: Robust Error Handling and Edge Case Management Objective: Ensure comprehensive error handling that provides meaningful context and graceful degradation Status: Passed Learn more about managing compliance generic rules or creating your own custom rules
	Generic: Secure Error Handling Objective: To prevent the leakage of sensitive system information through error messages while providing sufficient detail for internal debugging. Status: Passed Learn more about managing compliance generic rules or creating your own custom rules
	Generic: Secure Logging Practices Objective: To ensure logs are useful for debugging and auditing without exposing sensitive information like PII, PHI, or cardholder data. Status: Passed Learn more about managing compliance generic rules or creating your own custom rules
	Generic: Security-First Input Validation and Data Handling Objective: Ensure all data inputs are validated, sanitized, and handled securely to prevent vulnerabilities Status: Passed Learn more about managing compliance generic rules or creating your own custom rules

Compliance status legend

🟢 - Fully Compliant
🟡 - Partial Compliant
🔴 - Not Compliant
⚪ - Requires Further Human Verification
🏷️ - Compliance label

[qodo-code-review]

PR Code Suggestions ✨

Explore these optional code suggestions:

Category	Suggestion	Impact
General	Compare model names case-insensitively Perform a case-insensitive comparison for model names to prevent mismatches due to casing differences. src/Plugins/BotSharp.Plugin.OpenAI/Providers/Chat/ChatCompletionProvider.cs [600] -if (string.IsNullOrEmpty(level) && _model == agent?.LlmConfig?.Model) +if (string.IsNullOrEmpty(level) && string.Equals(_model, agent?.LlmConfig?.Model, StringComparison.OrdinalIgnoreCase)) Apply / Chat Suggestion importance[1-10]: 7 __ Why: This suggestion correctly points out that model names are often case-insensitive. Using a case-sensitive comparison could lead to the fallback logic not being applied due to simple casing differences, so this change improves the correctness of the logic.	Medium
	Remove redundant null-conditional access Improve code clarity and safety by adding an explicit null check for agent?.LlmConfig and removing redundant null-conditional operators within the if block. src/Plugins/BotSharp.Plugin.OpenAI/Providers/Chat/ChatCompletionProvider.cs [600-603] -if (string.IsNullOrEmpty(level) && _model == agent?.LlmConfig?.Model) +if (string.IsNullOrEmpty(level) && agent?.LlmConfig != null && _model == agent.LlmConfig.Model) { - level = agent?.LlmConfig?.ReasoningEffortLevel; + level = agent.LlmConfig.ReasoningEffortLevel; } Apply / Chat Suggestion importance[1-10]: 6 __ Why: The suggestion correctly identifies that the null-conditional access inside the if block can be improved. The proposed change with an explicit agent?.LlmConfig != null check makes the code more robust and readable by ensuring objects are not null before they are accessed.	Low
	Treat whitespace-only state as empty Replace string.IsNullOrEmpty with string.IsNullOrWhiteSpace to handle cases where the level variable from the state contains only whitespace characters. src/Plugins/BotSharp.Plugin.OpenAI/Providers/Chat/ChatCompletionProvider.cs [600-603] -if (string.IsNullOrEmpty(level) && _model == agent?.LlmConfig?.Model) +if (string.IsNullOrWhiteSpace(level) && _model == agent?.LlmConfig?.Model) { level = agent?.LlmConfig?.ReasoningEffortLevel; } Apply / Chat Suggestion importance[1-10]: 5 __ Why: This is a good suggestion for improving robustness. Using string.IsNullOrWhiteSpace handles edge cases where the state might contain a string with only whitespace, which should likely be treated as an empty value, thus correctly triggering the fallback logic.	Low
More