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>
This commit is contained in:
MelekiandClaude Opus 4.8 committed 2026-06-20 14:01:43 +02:00
1 parent e6770bb5f8
commit 0f3d658fd3
8 files changed
+83 -9

No files matched your search

+3 -2
View File
@@ -125,8 +125,9 @@ builder.Services.AddHostedService<KeyScannerService>(sp => sp.GetRequiredService
builder.Services.AddSingleton<GitHubEventScannerService>();
builder.Services.AddHostedService<GitHubEventScannerService>(sp => sp.GetRequiredService<GitHubEventScannerService>());
// Claude CLI Service (für OAuth-basierte Chats via CLI)
builder.Services.AddSingleton<ClaudeCliService>();
// Claude CLI Service (für OAuth-basierte Chats via CLI; serverSettings für z.ai/GLM-Env)
builder.Services.AddSingleton<ClaudeCliService>(sp =>
new ClaudeCliService(sp.GetRequiredService<Microsoft.Extensions.Logging.ILogger<ClaudeCliService>>(), serverSettings));
var app = builder.Build();