remove temperature

[iceljc]

No description provided.

[qodo-code-review]

PR Summary by Qodo

Stop setting temperature for OpenAI Responses requests

🐞 Bug fix 🕐 Less than 10 minutes

AI Description

• Stops sending temperature through OpenAI Responses API requests.
• Preserves token and reasoning settings while using model-default sampling behavior.

Diagram

graph TD
    A["Agent request"] --> B["Response options"] --> C["Responses client"] --> D["OpenAI Responses"]
    E["Token state"] --> B
    F["Reasoning settings"] --> B

Loading

High-Level Assessment

Removing temperature from the Responses-specific options builder is the most targeted approach because it avoids unsupported or model-sensitive parameter combinations while preserving temperature behavior in the separate Chat Completions path. Conditional removal only for reasoning modes was considered but would retain compatibility risk for other Responses models.

Files changed (1) +0 / -7

Bug fix (1) +0 / -7

ChatCompletionProvider.Response.csRemove temperature from Responses API options +0/-7

Remove temperature from Responses API options

• Removes temperature state parsing and assignment when constructing 'CreateResponseOptions'. Also removes the now-unnecessary reasoning-specific temperature reset, allowing Responses models to use their default sampling configuration.

src/Plugins/BotSharp.Plugin.OpenAI/Providers/Chat/ChatCompletionProvider.Response.cs

[qodo-code-review]

Code Review by Qodo

🐞 Bugs (1) 📘 Rule violations (0) 📜 Skill insights (0)

1. Responses ignore requested temperature 🐞 Bug ≡ Correctness

Description

Removing CreateResponseOptions.Temperature makes the Responses API ignore the documented
MessageConfig.Temperature value stored by the conversation controller. Because UseResponseApi is
enabled by default in WebStarter, callers can request a sampling temperature but receive output
generated with the provider default instead.

Code

src/Plugins/BotSharp.Plugin.OpenAI/Providers/Chat/ChatCompletionProvider.Response.cs[448]

-            Temperature = temperature,

Evidence

The public request model documents temperature as a generation control, and the conversation
controller stores it under the exact temperature state key. OpenAI requests are routed through the
Responses implementation when UseResponseApi is enabled—which WebStarter enables by default—but
the changed options construction now only sets max tokens and reasoning options; the sibling Chat
Completions implementation still reads and applies temperature.

src/Infrastructure/BotSharp.Abstraction/Models/MessageConfig.cs[23-26]
src/Infrastructure/BotSharp.OpenAPI/Controllers/Conversation/ConversationController.cs[538-540]
src/Plugins/BotSharp.Plugin.OpenAI/Providers/Chat/ChatCompletionProvider.cs[37-46]
src/WebStarter/appsettings.json[44-46]
src/Plugins/BotSharp.Plugin.OpenAI/Providers/Chat/ChatCompletionProvider.Response.cs[441-459]
src/Plugins/BotSharp.Plugin.OpenAI/Providers/Chat/ChatCompletionProvider.Chat.cs[612-639]

Agent prompt

The issue below was found during a code review. Follow the provided context and guidance below and implement a solution

## Issue description
The Responses API path no longer propagates the caller's temperature, so the public temperature control is silently ignored and generation uses the provider default.

## Issue Context
`MessageConfig.Temperature` is documented as controlling completion creativity and is stored in conversation state. WebStarter enables the Responses API by default, while the sibling Chat Completions path still reads and applies the same state. Preserve temperature for compatible non-reasoning requests while omitting it only for models/options that reject it.

## Fix Focus Areas
- src/Plugins/BotSharp.Plugin.OpenAI/Providers/Chat/ChatCompletionProvider.Response.cs[441-459]
- src/Plugins/BotSharp.Plugin.OpenAI/Providers/Chat/ChatCompletionProvider.Chat.cs[612-639]
- src/Infrastructure/BotSharp.Abstraction/Models/MessageConfig.cs[23-26]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

---

Context sources

Review mode: ⚖️ Balanced

Tip of the day

💡 Did you know, you can add REVIEW.md to your repo root and Qodo follows it on every PR

More tips ↗ | Customize Qodo ↗ | Qodo docs ↗

[qodo-code-review]

1. Responses ignore requested temperature 🐞 Bug ≡ Correctness

Removing CreateResponseOptions.Temperature makes the Responses API ignore the documented
MessageConfig.Temperature value stored by the conversation controller. Because UseResponseApi is
enabled by default in WebStarter, callers can request a sampling temperature but receive output
generated with the provider default instead.

Agent Prompt

## Issue description
The Responses API path no longer propagates the caller's temperature, so the public temperature control is silently ignored and generation uses the provider default.

## Issue Context
`MessageConfig.Temperature` is documented as controlling completion creativity and is stored in conversation state. WebStarter enables the Responses API by default, while the sibling Chat Completions path still reads and applies the same state. Preserve temperature for compatible non-reasoning requests while omitting it only for models/options that reject it.

## Fix Focus Areas
- src/Plugins/BotSharp.Plugin.OpenAI/Providers/Chat/ChatCompletionProvider.Response.cs[441-459]
- src/Plugins/BotSharp.Plugin.OpenAI/Providers/Chat/ChatCompletionProvider.Chat.cs[612-639]
- src/Infrastructure/BotSharp.Abstraction/Models/MessageConfig.cs[23-26]

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools