feat: integrate thinking level support across agent and UI components

- Enhanced the agent service and request handling to include an optional thinking level parameter, improving the configurability of model interactions.
- Updated the UI components to manage and display the selected model along with its thinking level, ensuring a cohesive user experience.
- Refactored the model selector and input controls to accommodate the new model selection structure, enhancing usability and clarity.
- Adjusted the Electron API and HTTP client to support the new thinking level parameter in requests, ensuring consistent data handling across the application.

This update significantly improves the agent's ability to adapt its reasoning capabilities based on user-defined thinking levels, enhancing overall performance and user satisfaction.
This commit is contained in:
Shirone
2026-01-02 15:22:06 +01:00
parent 81d300391d
commit 8c04e0028f
11 changed files with 211 additions and 231 deletions

View File

@@ -1422,7 +1422,8 @@ export class HttpApiClient implements ElectronAPI {
message: string,
workingDirectory?: string,
imagePaths?: string[],
model?: string
model?: string,
thinkingLevel?: string
): Promise<{ success: boolean; error?: string }> =>
this.post('/api/agent/send', {
sessionId,
@@ -1430,6 +1431,7 @@ export class HttpApiClient implements ElectronAPI {
workingDirectory,
imagePaths,
model,
thinkingLevel,
}),
getHistory: (