• Copilot Chat Extension Version:
  • github.copilot: 1.373.1788
  • github.copilot-chat: 0.32.2025091902
• VSCode & System Information:

Version: 1.105.0-insider (Universal)
Commit: 824678f51e533e03ed9edc59e5cf858c47718f42
Date: 2025-09-19T05:02:45.062Z
Electron: 37.3.1
ElectronBuildId: 12404162
Chromium: 138.0.7204.235
Node.js: 22.18.0
V8: 13.8.258.31-electron.0
OS: Darwin arm64 24.6.0

• Feature (e.g. agent/edit/ask mode): Agent Mode
• Selected model (e.g. GPT 4.1, Claude 3.7 Sonnet): Customized OpenAI Compatiable Model (z.ai GLM-4.5 model from their offical API endpoint)
• Logs:

• chat_log.md, and

2025-09-21 02:46:00.011 [info] Request ID for failed request: a2629c8e-0f23-44b0-bf03-ac93a01bb46b
2025-09-21 02:46:00.013 [info] ccreq:8c9434a7.copilotmd | notFound | GLM-4.5 | 139ms | [copilotLanguageModelWrapper]
2025-09-21 02:46:00.541 [info] message 0 returned. finish reason: [stop]

Steps to Reproduce:

1. Download the latest VSCode Insiders version (for me, it's 824678f )
2. Open Copilot Chat panel, and login with your GitHub account for initial setup
3. Manually edit user settings settings.json, and add the following config:

	"github.copilot.chat.customOAIModels": {
		"GLM-4.5": {
			"name": "GLM 4.5",
			"url": "https://api.z.ai/api/coding/paas/v4",
			"maxInputTokens": 131200,
			"maxOutputTokens": 96000,
			"requiresAPIKey": true,
			"thinking": true,
			"toolCalling": true,
			"vision": false,
		}
	}

4. Select GLM-4.5 from Copilot Chat model selector, and then enter the corresponding API key for this model provider
5. Type "what model are you" as prompt, then click "Send" button
6. The following error message will be shown on the screen