Skip to content

fix: preserve content integrity in VS Code LM provider #2427

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.

Sign up for GitHub

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

Merged
mrubens merged 2 commits into from
Apr 11, 2025
Merged

fix: preserve content integrity in VS Code LM provider #2427

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ae43cd5
lang: translate Russian comments to English in vscode-lm.ts
Apr 9, 2025
7538e12
fix: preserve content integrity in VS Code LM provider
Apr 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 3 additions & 45 deletions src/api/providers/vscode-lm.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -282,54 +282,13 @@ export class VsCodeLmHandler extends BaseProvider implements SingleCompletionHan
return this.client
}

private cleanTerminalOutput(text: string): string {
if (!text) {
return ""
}

return (
text
// Нормализуем переносы строк
.replace(/\r\n/g, "\n")
.replace(/\r/g, "\n")

// Удаляем ANSI escape sequences
.replace(/\x1B(?:[@-Z\\-_]|\[[0-?]*[ -/]*[@-~])/g, "") // Полный набор ANSI sequences
.replace(/\x9B[0-?]*[ -/]*[@-~]/g, "") // CSI sequences

// Удаляем последовательности установки заголовка терминала и прочие OSC sequences
.replace(/\x1B\][0-9;]*(?:\x07|\x1B\\)/g, "")

// Удаляем управляющие символы
.replace(/[\x00-\x09\x0B-\x0C\x0E-\x1F\x7F]/g, "")

// Удаляем escape-последовательности VS Code
.replace(/\x1B[PD].*?\x1B\\/g, "") // DCS sequences
.replace(/\x1B_.*?\x1B\\/g, "") // APC sequences
.replace(/\x1B\^.*?\x1B\\/g, "") // PM sequences
.replace(/\x1B\[[\d;]*[HfABCDEFGJKST]/g, "") // Cursor movement and clear screen

// Удаляем пути Windows и служебную информацию
.replace(/^(?:PS )?[A-Z]:\\[^\n]*$/gm, "")
.replace(/^;?Cwd=.*$/gm, "")

// Очищаем экранированные последовательности
.replace(/\\x[0-9a-fA-F]{2}/g, "")
.replace(/\\u[0-9a-fA-F]{4}/g, "")

// Финальная очистка
.replace(/\n{3,}/g, "\n\n") // Убираем множественные пустые строки
.trim()
)
}

private cleanMessageContent(content: any): any {
if (!content) {
return content
}

if (typeof content === "string") {
return this.cleanTerminalOutput(content)
return content
}

if (Array.isArray(content)) {
Expand All @@ -352,16 +311,15 @@ export class VsCodeLmHandler extends BaseProvider implements SingleCompletionHan
this.ensureCleanState()
const client: vscode.LanguageModelChat = await this.getClient()

// Clean system prompt and messages
const cleanedSystemPrompt = this.cleanTerminalOutput(systemPrompt)
// Process messages
const cleanedMessages = messages.map((msg) => ({
...msg,
content: this.cleanMessageContent(msg.content),
}))

// Convert Anthropic messages to VS Code LM messages
const vsCodeLmMessages: vscode.LanguageModelChatMessage[] = [
vscode.LanguageModelChatMessage.Assistant(cleanedSystemPrompt),
vscode.LanguageModelChatMessage.Assistant(systemPrompt),
...convertToVsCodeLmMessages(cleanedMessages),
]

Expand Down