Discussion Report: Copilot Agent Mode Causing Error After Update #171582
Replies: 1 comment
-
| 💬 Your Product Feedback Has Been Submitted 🎉 Thank you for taking the time to share your insights with us! Your feedback is invaluable as we build a better GitHub experience for all our users. Here's what you can expect moving forward ⏩ 
 Where to look to see what's shipping 👀 
 What you can do in the meantime 💻 
 As a member of the GitHub community, your participation is essential. While we can't promise that every suggestion will be implemented, we want to emphasize that your feedback is instrumental in guiding our decisions and priorities. Thank you once again for your contribution to making GitHub even better! We're grateful for your ongoing support and collaboration in shaping the future of our platform. ⭐ | 
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Select Topic Area
Bug
Copilot Feature Area
Copilot Agent Mode
Body
After today’s update to the GitHub Copilot VS Code extension, I started encountering errors whenever Agent Mode is enabled. This issue did not exist before, and I’ve been using Copilot for months without problems. Now all GPT models (including GPT-4) return the same error, making Agent Mode completely unusable.
Steps to Reproduce
Open VS Code with the latest Copilot extension update.
Enable Agent Mode in settings.
Ask Copilot to modify or improve existing code.
2025-08-29 19:16:57.591 [info] Request ID for failed request: cb230537-5d85-406a-a465-0fa1ed13dd47
2025-08-29 19:16:57.606 [error] Request Failed: 408 {"error":{"message":"Timed out reading request body. Try again, or use a smaller request size.","code":"user_request_timeout"}}
Copilot throws an error instead of generating suggestions.
Expected Behavior
Copilot should smoothly generate or improve code using Agent Mode, just as it did before today’s update.
Actual Behavior
Copilot errors out immediately.
All GPT models (GPT-4, GPT-3.5, GPT-4o, etc.) fail with the same error.
Normal suggestions (without Agent Mode) work, but agent-driven improvements are broken.
Environment
Editor: VS Code
Extension: GitHub Copilot (latest, updated today)
System: macOS (screenshot attached)
Models tested: GPT-4, GPT-4o, GPT-3.5 – all broken in Agent Mode
Logs
2025-08-29 19:05:11.399 [error] Request Failed: 408 {"error":{"message":"Timed out reading request body. Try again, or use a smaller request size.","code":"user_request_timeout"}}
2025-08-29 19:05:11.403 [info] ccreq:8a360714.copilotmd | failed | claude-sonnet-4 | 60916ms | [panel/editAgent]
2025-08-29 19:15:44.669 [info] Logged in as RaoAhmadRaza
2025-08-29 19:15:46.571 [info] Got Copilot token for RaoAhmadRaza
2025-08-29 19:15:46.599 [info] copilot token chat_enabled: true, sku: free_educational_quota
2025-08-29 19:15:47.223 [info] BYOK: Copilot Chat known models list fetched successfully.
2025-08-29 19:15:47.905 [info] Fetched model metadata in 3452ms 720ce905-23ce-49bf-a471-c7020b3f44b4
2025-08-29 19:15:54.401 [info] message 0 returned. finish reason: [stop]
2025-08-29 19:15:54.402 [info] request done: requestId: [3664e15c-0a53-464d-84d8-f1610acbaaef] model deployment ID: []
2025-08-29 19:15:54.405 [info] ccreq:fcab9837.copilotmd | success | gpt-4o-mini | 5203ms | [intentDetection]
2025-08-29 19:16:57.591 [info] Request ID for failed request: cb230537-5d85-406a-a465-0fa1ed13dd47
2025-08-29 19:16:57.606 [error] Request Failed: 408 {"error":{"message":"Timed out reading request body. Try again, or use a smaller request size.","code":"user_request_timeout"}}
2025-08-29 19:16:57.617 [info] ccreq:893d9a48.copilotmd | failed | claude-sonnet-4 | 62172ms | [panel/unknown]
2025-08-29 19:19:28.749 [info] message 0 returned. finish reason: [stop]
2025-08-29 19:19:28.749 [info] request done: requestId: [25213f3c-bcc0-4317-be3e-48f0baa1893f] model deployment ID: []
2025-08-29 19:19:28.751 [info] ccreq:dbed6bb8.copilotmd | success | gpt-4.1 | 2666ms | [debugCommandIdentifier]
Errors consistently reproduce after update.
Notes
Disabling Agent Mode restores partial functionality (basic completions work), but this defeats the purpose since Agent Mode is crucial for iterative improvements.
This issue started only after the latest extension update.
Beta Was this translation helpful? Give feedback.
All reactions