Add z.ai/GLM provider via per-process Claude CLI env injection

Route glm:-prefixed models through the CLI/Anthropic path: ResolveModelId
strips the glm: prefix, and CreateCliStartInfo activates the z.ai
Anthropic-compatible endpoint (ANTHROPIC_BASE_URL/AUTH_TOKEN) only for that
process when IsZaiModel matches, leaving every other request's OAuth login
untouched. GLM model list is loaded through the existing model cache and
exposed via /api/models/glm with a "GLM (z.ai)" optgroup in the agent form.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

wwwroot/js/pages/agent-page.js

@@ -28,6 +28,7 @@ registerPage('agent', {
     const geminiOptgroup       = document.getElementById('geminiOptgroup');
     const openaiOptgroup       = document.getElementById('openaiOptgroup');
     const minimaxOptgroup      = document.getElementById('minimaxOptgroup');
+    const glmOptgroup          = document.getElementById('glmOptgroup');
 
     // Modelle dynamisch laden
     const loadProviderModels = async (url, prefix, optgroup) => {
@@ -55,7 +56,8 @@ registerPage('agent', {
       loadProviderModels('/api/models/nvidia',       'nvidia',       nvidiaOptgroup),
       loadProviderModels('/api/models/pollinations', 'pollinations', pollinationsOptgroup),
       loadProviderModels('/api/models/gemini',       'gemini',       geminiOptgroup),
-      loadProviderModels('/api/models/minimax',      'minimax',      minimaxOptgroup)
+      loadProviderModels('/api/models/minimax',      'minimax',      minimaxOptgroup),
+      loadProviderModels('/api/models/glm',          'glm',          glmOptgroup)
     ]);
     const allowUserChoiceEl = document.getElementById('agentAllowUserChoice');
     const autoCommitEl = document.getElementById('agentAutoCommit');