Skip to content

fix(provider): mark DeepSeek models as BYOK #162

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
Vizards merged 1 commit into from
Jun 16, 2026
Merged

fix(provider): mark DeepSeek models as BYOK #162

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 4 additions & 1 deletion src/provider/models.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,8 @@ import { toModelCostInfo, type ModelCostInformation } from './pricing/costs';
* NOTE: Non-public API surface.
*
* The fields below (`configurationSchema` on chat info, cost metadata,
* `modelConfiguration` on response options, plus `isUserSelectable` / `statusIcon`)
* `modelConfiguration` on response options, plus `isBYOK` / `isUserSelectable` /
* `statusIcon`)
* are not part of the stable `vscode.LanguageModelChat*` typings yet. They are
* the same shape currently consumed by GitHub Copilot Chat to render model picker
* metadata and per-model configuration controls.
Expand All @@ -25,6 +26,7 @@ type ThinkingEffortConfigurationSchema = ReturnType<typeof buildThinkingEffortSc
export type ModelPickerChatInformation = vscode.LanguageModelChatInformation &
ModelCostInformation & {
readonly isUserSelectable: boolean;
readonly isBYOK: true;
readonly statusIcon?: vscode.ThemeIcon;
readonly configurationSchema?: ThinkingEffortConfigurationSchema;
};
Expand All @@ -46,6 +48,7 @@ export function toChatInfo(
statusIcon: hasApiKey ? undefined : new vscode.ThemeIcon('warning'),
maxInputTokens: m.maxInputTokens,
maxOutputTokens: m.maxOutputTokens,
isBYOK: true,
isUserSelectable: true,
capabilities: {
toolCalling: m.capabilities.toolCalling,
Expand Down
Loading