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/config/config.ts

@@ -137,7 +137,6 @@ export interface CliArgs {
   googleSearchEngineId: string | undefined;
   webSearchDefault: string | undefined;
   screenReader: boolean | undefined;
-  vlmSwitchMode: string | undefined;
   inputFormat?: string | undefined;
   outputFormat: string | undefined;
   includePartialMessages?: boolean;
@@ -426,13 +425,6 @@ export async function parseArguments(): Promise<CliArgs> {
           type: 'boolean',
           description: 'Enable screen reader mode for accessibility.',
         })
-        .option('vlm-switch-mode', {
-          type: 'string',
-          choices: ['once', 'session', 'persist'],
-          description:
-            'Default behavior when images are detected in input. Values: once (one-time switch), session (switch for entire session), persist (continue with current model). Overrides settings files.',
-          default: process.env['VLM_SWITCH_MODE'],
-        })
         .option('input-format', {
           type: 'string',
           choices: ['text', 'stream-json'],
@@ -903,9 +895,6 @@ export async function loadCliConfig(
       ? argv.screenReader
       : (settings.ui?.accessibility?.screenReader ?? false);
 
-  const vlmSwitchMode =
-    argv.vlmSwitchMode || settings.experimental?.vlmSwitchMode;
-
   let sessionId: string | undefined;
   let sessionData: ResumedSessionData | undefined;
 
@@ -1016,7 +1005,6 @@ export async function loadCliConfig(
     skipNextSpeakerCheck: settings.model?.skipNextSpeakerCheck,
     skipLoopDetection: settings.model?.skipLoopDetection ?? false,
     skipStartupContext: settings.model?.skipStartupContext ?? false,
-    vlmSwitchMode,
     truncateToolOutputThreshold: settings.tools?.truncateToolOutputThreshold,
     truncateToolOutputLines: settings.tools?.truncateToolOutputLines,
     enableToolOutputTruncation: settings.tools?.enableToolOutputTruncation,