refactor: merge coder-model and qwen3.5-plus, remove vision model switching

- Merge coder-model and qwen3.5-plus into a single coder-model with vision capability
- Remove vlmSwitchMode CLI argument and experimental.vlmSwitchMode setting
- Remove useVisionAutoSwitch hook and inline image format checking into useGeminiStream
- Remove ModelSwitchDialog and related vision switch UI components
- Update all related tests to reflect the simplified model structure
- Set DEFAULT_QWEN_MODEL to coder-model

Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>

packages/cli/src/ui/components/DialogManager.tsx

@@ -32,7 +32,6 @@ import process from 'node:process';
 import { type UseHistoryManagerReturn } from '../hooks/useHistoryManager.js';
 import { IdeTrustChangeDialog } from './IdeTrustChangeDialog.js';
 import { WelcomeBackDialog } from './WelcomeBackDialog.js';
-import { ModelSwitchDialog } from './ModelSwitchDialog.js';
 import { AgentCreationWizard } from './subagents/create/AgentCreationWizard.js';
 import { AgentsManagerDialog } from './subagents/manage/AgentsManagerDialog.js';
 import { SessionPicker } from './SessionPicker.js';
@@ -236,10 +235,6 @@ export const DialogManager = ({
   if (uiState.isModelDialogOpen) {
     return <ModelDialog onClose={uiActions.closeModelDialog} />;
   }
-  if (uiState.isVisionSwitchDialogOpen) {
-    return <ModelSwitchDialog onSelect={uiActions.handleVisionSwitchSelect} />;
-  }
-
   if (uiState.isAuthDialogOpen || uiState.authError) {
     return (
       <Box flexDirection="column">