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/index.html

@@ -249,6 +249,9 @@
           <optgroup label="MiniMax" id="minimaxOptgroup">
             <option value="" disabled>Wird geladen...</option>
           </optgroup>
+          <optgroup label="GLM (z.ai)" id="glmOptgroup">
+            <option value="" disabled>Wird geladen...</option>
+          </optgroup>
         </select>
         <label>Reasoning-Effort <span class="checkbox-hint">(nur Claude: Opus 4.5+, Sonnet 4.6+)</span></label>
         <select id="agentEffort">