anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 18:25:32 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

API Rate Limit Not Properly Handled - Model Stops Responding After Few Queries #7920

New Issue
Open
opened 2026-02-16 18:08:40 -05:00 by yindo · 1 comment
yindo commented 2026-02-16 18:08:40 -05:00
Owner
Copy Link
Copy Source

Originally created by @xgc8008-zed on GitHub (Jan 29, 2026).

Originally assigned to: @rekram1-node on GitHub.

I'm experiencing an issue when using NVIDIA model APIs where after asking a few questions, the model suddenly stops responding with no output. However, the animation in the bottom-left
corner continues running, indicating the system is still attempting to process. This can persist for several hours.

 **Environment:**
 - API Provider: https://build.nvidia.com/
 - Rate Limit: 40 rpm
 - Models Affected: GLM-4.7 or other models from NVIDIA API catalog                                                                                                                             

 **Steps to Reproduce:**
 1. Start a conversation with the model (e.g., GLM-4.7 or other models)
 2. Ask 2-3 questions successfully                                                                                                                                                                
 3. On subsequent questions, the model stops responding                                                                                                                                           
 4. Animation continues running indefinitely                                                                                                                                                      
 5. All submitted tasks remain stuck in the task list
                                                                                                                                                                                                  
 **Expected Behavior:**
 - Model should respond to all queries within rate limits
 - If rate limit is exceeded, user should receive clear error message
 - System should handle rate limit gracefully

 **Actual Behavior:**
 - Model silently fails after 2-3 queries                                                                                                                                                         
 - Animation continues but no response is ever returned                                                                                                                                           
 - Issue persists for several hours                                                                                                                                                               
 - No error message displayed to indicate rate limit was reached
                                                                                                                                                                                                  
 **Analysis:**                                                                                                                                                                                    
 It appears the API returns HTTP 429 (Too Many Requests) or similar rate limit error when usage exceeds 40 rpm, but the client (opencode) does not properly detect or display this error,         
 leaving the user in a confused state where the UI shows activity but no actual response is generated.

 **Request:**
 Please implement proper rate limit error handling that:
 1. Detects rate limit responses from the API
 2. Displays a clear error message to the user                                                                                                                                                  
 3. Shows remaining quota or wait time   
 4. Prevents indefinite hanging states   
 5. Provides proper timeout behavior instead of leaving tasks stuck
Originally created by @xgc8008-zed on GitHub (Jan 29, 2026). Originally assigned to: @rekram1-node on GitHub. I'm experiencing an issue when using NVIDIA model APIs where after asking a few questions, the model suddenly stops responding with no output. However, the animation in the bottom-left corner continues running, indicating the system is still attempting to process. This can persist for several hours. **Environment:** - API Provider: https://build.nvidia.com/ - Rate Limit: 40 rpm - Models Affected: GLM-4.7 or other models from NVIDIA API catalog **Steps to Reproduce:** 1. Start a conversation with the model (e.g., GLM-4.7 or other models) 2. Ask 2-3 questions successfully 3. On subsequent questions, the model stops responding 4. Animation continues running indefinitely 5. All submitted tasks remain stuck in the task list **Expected Behavior:** - Model should respond to all queries within rate limits - If rate limit is exceeded, user should receive clear error message - System should handle rate limit gracefully **Actual Behavior:** - Model silently fails after 2-3 queries - Animation continues but no response is ever returned - Issue persists for several hours - No error message displayed to indicate rate limit was reached **Analysis:** It appears the API returns HTTP 429 (Too Many Requests) or similar rate limit error when usage exceeds 40 rpm, but the client (opencode) does not properly detect or display this error, leaving the user in a confused state where the UI shows activity but no actual response is generated. **Request:** Please implement proper rate limit error handling that: 1. Detects rate limit responses from the API 2. Displays a clear error message to the user 3. Shows remaining quota or wait time 4. Prevents indefinite hanging states 5. Provides proper timeout behavior instead of leaving tasks stuck
yindo commented 2026-02-16 18:08:40 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Jan 29, 2026):

This issue might be a duplicate of existing issues. Please check:

  • #10725: [FEATURE]: automatic model switch upon rate limitation - requests intelligent handling of rate limits instead of cooldown
  • #9091: [BUG]: Rate limit popup persists indefinitely and does not clear on model switch - addresses UI/UX issues with rate limit handling
  • #10404: Big Pickle model loops with "too many requests" error in high mode (free trial) - similar rate limit error not properly handled
  • #10724: [FEATURE]: Subagent rate limit hit should surface message like main agent - requests proper error messaging for rate limits

Your issue specifically focuses on silent failures and missing error messages for NVIDIA API rate limits (HTTP 429). While these related issues address rate limiting broadly, they may provide context or overlapping solutions.

Feel free to ignore if none of these address your specific case.

@github-actions[bot] commented on GitHub (Jan 29, 2026): This issue might be a duplicate of existing issues. Please check: - #10725: [FEATURE]: automatic model switch upon rate limitation - requests intelligent handling of rate limits instead of cooldown - #9091: [BUG]: Rate limit popup persists indefinitely and does not clear on model switch - addresses UI/UX issues with rate limit handling - #10404: Big Pickle model loops with "too many requests" error in high mode (free trial) - similar rate limit error not properly handled - #10724: [FEATURE]: Subagent rate limit hit should surface message like main agent - requests proper error messaging for rate limits Your issue specifically focuses on silent failures and missing error messages for NVIDIA API rate limits (HTTP 429). While these related issues address rate limiting broadly, they may provide context or overlapping solutions. Feel free to ignore if none of these address your specific case.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
acp
bad
bug
discussion
docs
documentation
enhancement
extension
good first issue
growth
help-wanted
mcp
model-problem
needs:compliance
nix
opentui
perf
pull-request
Mirrored from GitHub Pull Request
 tui
web
windows
zen
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#7920
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?