anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 02:05:26 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

GLM 4.6 model timing out #2078

New Issue
Closed
opened 2026-02-16 17:34:03 -05:00 by yindo · 8 comments
yindo commented 2026-02-16 17:34:03 -05:00
Owner
Copy Link
Copy Source

Originally created by @felipematos on GitHub (Oct 13, 2025).

Originally assigned to: @rekram1-node on GitHub.

I use Z.ai coding plan, and I have noticed that GLM model runs end quickly with timeout errors.

I was wondering if I could increate timeout limits for the model in settings. Any other tip to solve this will be appreciated.

Originally created by @felipematos on GitHub (Oct 13, 2025). Originally assigned to: @rekram1-node on GitHub. I use Z.ai coding plan, and I have noticed that GLM model runs end quickly with timeout errors. I was wondering if I could increate timeout limits for the model in settings. Any other tip to solve this will be appreciated.
yindo closed this issue 2026-02-16 17:34:03 -05:00
yindo commented 2026-02-16 17:34:03 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Oct 13, 2025):

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

  • #2974: [Bug] Timeout not working for Local LLM with MLX Models - Similar timeout configuration issues with local providers and Z.ai
  • #2944: Getting "AI_APICallError: Invalid API parameter, please check the documentation." in opencode with zAI glm 4.6 - Same Z.ai/GLM 4.6 combination with API errors
  • #2985: Bash tool does not show time out to model or user, model might set time out incorrectly - General timeout handling issues in opencode

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

@github-actions[bot] commented on GitHub (Oct 13, 2025): This issue might be a duplicate of existing issues. Please check: - #2974: [Bug] Timeout not working for Local LLM with MLX Models - Similar timeout configuration issues with local providers and Z.ai - #2944: Getting "AI_APICallError: Invalid API parameter, please check the documentation." in opencode with zAI glm 4.6 - Same Z.ai/GLM 4.6 combination with API errors - #2985: Bash tool does not show time out to model or user, model might set time out incorrectly - General timeout handling issues in opencode Feel free to ignore if none of these address your specific case.
yindo commented 2026-02-16 17:34:03 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 13, 2025):

The timeout is currently 5 min, are you really hitting that timeout frequently?

Just wanted to confirm it wasn't something else: maybe shell commands or tool edits take a long time and have errors?

@rekram1-node commented on GitHub (Oct 13, 2025): The timeout is currently 5 min, are you really hitting that timeout frequently? Just wanted to confirm it wasn't something else: maybe shell commands or tool edits take a long time and have errors?
yindo commented 2026-02-16 17:34:03 -05:00
Author
Owner
Copy Link
Copy Source

@felipematos commented on GitHub (Oct 13, 2025):

Yes, I am hitting that limit very frequently. I’m not sure if this timeout includes waiting for tools usage, but yes, I am using a few tools, like playwright and context7.

I am used to long runs with OpenAI Codex and Claude code. A single prompt may run for dozens of minutes, even hours. So 5 minutes really seems like a very short time.

Is it possible to increase the timeout?

Felipe

Felipe Matos
Em 13 de out. de 2025, 14:35 -0300, Aiden Cline @.***> escreveu:

rekram1-node left a comment (sst/opencode#3139)
The timeout is currently 5 min, are you really hitting that timeout frequently?
Just wanted to confirm it wasn't something else: maybe shell commands or tool edits take a long time and have errors?
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: @.***>

@felipematos commented on GitHub (Oct 13, 2025): Yes, I am hitting that limit very frequently. I’m not sure if this timeout includes waiting for tools usage, but yes, I am using a few tools, like playwright and context7. I am used to long runs with OpenAI Codex and Claude code. A single prompt may run for dozens of minutes, even hours. So 5 minutes really seems like a very short time. Is it possible to increase the timeout? Felipe Felipe Matos Em 13 de out. de 2025, 14:35 -0300, Aiden Cline ***@***.***> escreveu: > rekram1-node left a comment (sst/opencode#3139) > The timeout is currently 5 min, are you really hitting that timeout frequently? > Just wanted to confirm it wasn't something else: maybe shell commands or tool edits take a long time and have errors? > — > Reply to this email directly, view it on GitHub, or unsubscribe. > You are receiving this because you authored the thread.Message ID: ***@***.***>
yindo commented 2026-02-16 17:34:03 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 13, 2025):

The 5 min timeout is only if no data is being sent back and forth (so you can have long lived requests but if nothing is being sent then it errors), but we do have an open issue to allow you to override that

@rekram1-node commented on GitHub (Oct 13, 2025): The 5 min timeout is only if no data is being sent back and forth (so you can have long lived requests but if nothing is being sent then it errors), but we do have an open issue to allow you to override that
yindo commented 2026-02-16 17:34:03 -05:00
Author
Owner
Copy Link
Copy Source

@Chrisja commented on GitHub (Oct 14, 2025):

FWIW I used GLM Coding Plan (Pro tier) with Opencode v0.15.1 and v0.15.2 most of today(14th) and had no issues but did have a couple of timeouts yesterday on v.15.0. Think this may be a Z.ai issue since performance seems sluggish during US work hours and far quicker morning and late evening UK time.

@Chrisja commented on GitHub (Oct 14, 2025): FWIW I used GLM Coding Plan (Pro tier) with Opencode v0.15.1 and v0.15.2 most of today(14th) and had no issues but did have a couple of timeouts yesterday on v.15.0. Think this may be a Z.ai issue since performance seems sluggish during US work hours and far quicker morning and late evening UK time.
yindo commented 2026-02-16 17:34:03 -05:00
Author
Owner
Copy Link
Copy Source

@thaoula commented on GitHub (Oct 15, 2025):

I keep getting timeout trying to split a 125k document . Regardless of of time of day or sessions. I have tried informing the model the file is large but it still times out.

@thaoula commented on GitHub (Oct 15, 2025): I keep getting timeout trying to split a 125k document . Regardless of of time of day or sessions. I have tried informing the model the file is large but it still times out.
yindo commented 2026-02-16 17:34:03 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 15, 2025):

im surprised there are so many 5 min timeouts... I'll try to get you a workaround for this soon

@rekram1-node commented on GitHub (Oct 15, 2025): im surprised there are so many 5 min timeouts... I'll try to get you a workaround for this soon
yindo commented 2026-02-16 17:34:03 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 17, 2025):

This should be fixed on latest, the "timeout" should be respected

@rekram1-node commented on GitHub (Oct 17, 2025): This should be fixed on latest, the "timeout" should be respected
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#2078
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?