Vision model support for Qwen-OAuth (#525)

* refactor: openaiContentGenerator

* refactor: optimize stream handling

* refactor: re-organize refactored files

* fix: unit test cases

* feat: `/model` command for switching to vision model

* fix: lint error

* feat: add image tokenizer to fit vlm context window

* fix: lint and type errors

* feat: add `visionModelPreview` to control default visibility of vision models

* fix: remove deprecated files

* fix: align supported image formats with bailian doc
This commit is contained in:
Mingholy
2025-09-18 13:32:00 +08:00
committed by GitHub
parent 56808ac210
commit 761833c915
41 changed files with 4083 additions and 5336 deletions

View File

@@ -53,6 +53,17 @@ import { FolderTrustDialog } from './components/FolderTrustDialog.js';
import { ShellConfirmationDialog } from './components/ShellConfirmationDialog.js';
import { QuitConfirmationDialog } from './components/QuitConfirmationDialog.js';
import { RadioButtonSelect } from './components/shared/RadioButtonSelect.js';
import { ModelSelectionDialog } from './components/ModelSelectionDialog.js';
import {
ModelSwitchDialog,
type VisionSwitchOutcome,
} from './components/ModelSwitchDialog.js';
import {
getOpenAIAvailableModelFromEnv,
getFilteredQwenModels,
type AvailableModel,
} from './models/availableModels.js';
import { processVisionSwitchOutcome } from './hooks/useVisionAutoSwitch.js';
import {
AgentCreationWizard,
AgentsManagerDialog,
@@ -248,6 +259,20 @@ const App = ({ config, settings, startupWarnings = [], version }: AppProps) => {
onWorkspaceMigrationDialogClose,
} = useWorkspaceMigration(settings);
// Model selection dialog states
const [isModelSelectionDialogOpen, setIsModelSelectionDialogOpen] =
useState(false);
const [isVisionSwitchDialogOpen, setIsVisionSwitchDialogOpen] =
useState(false);
const [visionSwitchResolver, setVisionSwitchResolver] = useState<{
resolve: (result: {
modelOverride?: string;
persistSessionModel?: string;
showGuidance?: boolean;
}) => void;
reject: () => void;
} | null>(null);
useEffect(() => {
const unsubscribe = ideContext.subscribeToIdeContext(setIdeContextState);
// Set the initial value
@@ -590,6 +615,75 @@ const App = ({ config, settings, startupWarnings = [], version }: AppProps) => {
openAuthDialog();
}, [openAuthDialog, setAuthError]);
// Vision switch handler for auto-switch functionality
const handleVisionSwitchRequired = useCallback(
async (_query: unknown) =>
new Promise<{
modelOverride?: string;
persistSessionModel?: string;
showGuidance?: boolean;
}>((resolve, reject) => {
setVisionSwitchResolver({ resolve, reject });
setIsVisionSwitchDialogOpen(true);
}),
[],
);
const handleVisionSwitchSelect = useCallback(
(outcome: VisionSwitchOutcome) => {
setIsVisionSwitchDialogOpen(false);
if (visionSwitchResolver) {
const result = processVisionSwitchOutcome(outcome);
visionSwitchResolver.resolve(result);
setVisionSwitchResolver(null);
}
},
[visionSwitchResolver],
);
const handleModelSelectionOpen = useCallback(() => {
setIsModelSelectionDialogOpen(true);
}, []);
const handleModelSelectionClose = useCallback(() => {
setIsModelSelectionDialogOpen(false);
}, []);
const handleModelSelect = useCallback(
(modelId: string) => {
config.setModel(modelId);
setCurrentModel(modelId);
setIsModelSelectionDialogOpen(false);
addItem(
{
type: MessageType.INFO,
text: `Switched model to \`${modelId}\` for this session.`,
},
Date.now(),
);
},
[config, setCurrentModel, addItem],
);
const getAvailableModelsForCurrentAuth = useCallback((): AvailableModel[] => {
const contentGeneratorConfig = config.getContentGeneratorConfig();
if (!contentGeneratorConfig) return [];
const visionModelPreviewEnabled =
settings.merged.experimental?.visionModelPreview ?? false;
switch (contentGeneratorConfig.authType) {
case AuthType.QWEN_OAUTH:
return getFilteredQwenModels(visionModelPreviewEnabled);
case AuthType.USE_OPENAI: {
const openAIModel = getOpenAIAvailableModelFromEnv();
return openAIModel ? [openAIModel] : [];
}
default:
return [];
}
}, [config, settings.merged.experimental?.visionModelPreview]);
// Core hooks and processors
const {
vimEnabled: vimModeEnabled,
@@ -620,6 +714,7 @@ const App = ({ config, settings, startupWarnings = [], version }: AppProps) => {
setQuittingMessages,
openPrivacyNotice,
openSettingsDialog,
handleModelSelectionOpen,
openSubagentCreateDialog,
openAgentsManagerDialog,
toggleVimEnabled,
@@ -664,6 +759,8 @@ const App = ({ config, settings, startupWarnings = [], version }: AppProps) => {
setModelSwitchedFromQuotaError,
refreshStatic,
() => cancelHandlerRef.current(),
settings.merged.experimental?.visionModelPreview ?? false,
handleVisionSwitchRequired,
);
const pendingHistoryItems = useMemo(
@@ -1034,6 +1131,8 @@ const App = ({ config, settings, startupWarnings = [], version }: AppProps) => {
!isAuthDialogOpen &&
!isThemeDialogOpen &&
!isEditorDialogOpen &&
!isModelSelectionDialogOpen &&
!isVisionSwitchDialogOpen &&
!isSubagentCreateDialogOpen &&
!showPrivacyNotice &&
!showWelcomeBackDialog &&
@@ -1055,6 +1154,8 @@ const App = ({ config, settings, startupWarnings = [], version }: AppProps) => {
showWelcomeBackDialog,
welcomeBackChoice,
geminiClient,
isModelSelectionDialogOpen,
isVisionSwitchDialogOpen,
]);
if (quittingMessages) {
@@ -1322,6 +1423,15 @@ const App = ({ config, settings, startupWarnings = [], version }: AppProps) => {
onExit={exitEditorDialog}
/>
</Box>
) : isModelSelectionDialogOpen ? (
<ModelSelectionDialog
availableModels={getAvailableModelsForCurrentAuth()}
currentModel={currentModel}
onSelect={handleModelSelect}
onCancel={handleModelSelectionClose}
/>
) : isVisionSwitchDialogOpen ? (
<ModelSwitchDialog onSelect={handleVisionSwitchSelect} />
) : showPrivacyNotice ? (
<PrivacyNotice
onExit={() => setShowPrivacyNotice(false)}