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

[Bug] I encountered a terminal rendering crash when using atlas with ProviderModelNotFoundError #7384

New Issue
Closed
opened 2026-02-16 18:07:01 -05:00 by yindo · 7 comments
yindo commented 2026-02-16 18:07:01 -05:00
Owner
Copy Link
Copy Source

Originally created by @RunMintOn on GitHub (Jan 23, 2026).

Originally assigned to: @rekram1-node on GitHub.

Description

I showed that I had configured atlas to use g3pro in omojson, and when I used atlas, I encountered a terminal crash, saying ProviderModelNotFoundError, and the terminal window was restored to normal after I adjusted （drag，resize）it, and it didn't terminate the running. This happens multiple times in a single answer.

Plugins

No response

OpenCode version

1.1.34

Steps to reproduce

1 In opencode, override the configuration : model (I used glm4.7 here); In omo json, the configuration atlas uses g3pro, derived from gemini cli
I used the antigravity auth plugin. omo version beta13
2 Use atlas /start work after using the plan given by Prometheus
3 After that, there is a chance to trigger
The terminal uses wezterm, which also appeared on alaritty

Screenshot and/or share link

Image

Operating System

No response

Terminal

No response

Originally created by @RunMintOn on GitHub (Jan 23, 2026). Originally assigned to: @rekram1-node on GitHub. ### Description I showed that I had configured atlas to use g3pro in omojson, and when I used atlas, I encountered a terminal crash, saying ProviderModelNotFoundError, and the terminal window was restored to normal after I adjusted （drag，resize）it, and it didn't terminate the running. This happens multiple times in a single answer. ### Plugins _No response_ ### OpenCode version 1.1.34 ### Steps to reproduce 1 In opencode, override the configuration : model (I used glm4.7 here); In omo json, the configuration atlas uses g3pro, derived from gemini cli I used the antigravity auth plugin. omo version beta13 2 Use atlas /start work after using the plan given by Prometheus 3 After that, there is a chance to trigger The terminal uses wezterm, which also appeared on alaritty ### Screenshot and/or share link <img width="1208" height="663" alt="Image" src="https://github.com/user-attachments/assets/6ab4245c-969d-4d4f-9472-1246dd1324a0" /> ### Operating System _No response_ ### Terminal _No response_
yindo added the opentuibug labels 2026-02-16 18:07:01 -05:00
yindo closed this issue 2026-02-16 18:07:01 -05:00
yindo commented 2026-02-16 18:07:01 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Jan 23, 2026):

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

  • #7958: Custom provider configuration not loading - ProviderModelNotFoundError for custom providers (zhipuai/glm-4.7) after Jan 7 update
  • #8950: Ollama custom provider error with ProviderModelNotFoundError when selecting agent with custom model
  • #8587: OpenCode Zen GPT-5.2 Codex install fails with ProviderModelNotFoundError
  • #6493: OpenAI provider fails with gpt-5-nano missing from models registry (ProviderModelNotFoundError)
  • #7943: TUI crashes when resizing terminal window (Windows/CMD) - similar terminal rendering crash behavior

These issues all involve ProviderModelNotFoundError or terminal crashes during model operations. Feel free to ignore if your specific case differs from these.

@github-actions[bot] commented on GitHub (Jan 23, 2026): This issue might be a duplicate of existing issues. Please check: - #7958: Custom provider configuration not loading - ProviderModelNotFoundError for custom providers (zhipuai/glm-4.7) after Jan 7 update - #8950: Ollama custom provider error with ProviderModelNotFoundError when selecting agent with custom model - #8587: OpenCode Zen GPT-5.2 Codex install fails with ProviderModelNotFoundError - #6493: OpenAI provider fails with gpt-5-nano missing from models registry (ProviderModelNotFoundError) - #7943: TUI crashes when resizing terminal window (Windows/CMD) - similar terminal rendering crash behavior These issues all involve ProviderModelNotFoundError or terminal crashes during model operations. Feel free to ignore if your specific case differs from these.
yindo commented 2026-02-16 18:07:01 -05:00
Author
Owner
Copy Link
Copy Source

@RunMintOn commented on GitHub (Jan 27, 2026):

I found the problem, I added the category configuration to the configuration file and it worked.

@RunMintOn commented on GitHub (Jan 27, 2026): I found the problem, I added the category configuration to the configuration file and it worked.
yindo commented 2026-02-16 18:07:01 -05:00
Author
Owner
Copy Link
Copy Source

@MusherM commented on GitHub (Jan 30, 2026):

I got the same error, can you make it more clear that how you solved it?

@MusherM commented on GitHub (Jan 30, 2026): I got the same error, can you make it more clear that how you solved it?
yindo commented 2026-02-16 18:07:01 -05:00
Author
Owner
Copy Link
Copy Source

@RunMintOn commented on GitHub (Jan 30, 2026):

I got the same error, can you make it more clear that how you solved it?

Have the AI ​​drag the OMO plugin to your local machine, then have it read the documentation. Then ask it questions about categories.
ai will handle it.

@RunMintOn commented on GitHub (Jan 30, 2026): > I got the same error, can you make it more clear that how you solved it? Have the AI ​​drag the OMO plugin to your local machine, then have it read the documentation. Then ask it questions about categories. ai will handle it.
yindo commented 2026-02-16 18:07:01 -05:00
Author
Owner
Copy Link
Copy Source

@MusherM commented on GitHub (Jan 31, 2026):

I solved it, now my config is just like this:

{
  "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
  "google_auth": false,
  "disabled_hooks": ["anthropic-context-window-limit-recovery"],
  "agents": {
    "sisyphus": {
      "model": "kimi-for-coding/k2p5"
    },
    "prometheus": {
      "model": "kimi-for-coding/k2p5"
    },
    "librarian": {
      "model": "kimi-for-coding/k2p5"
    },
    "atlas": {
      "model": "kimi-for-coding/k2p5"
    },
    "explore": {
      "model": "minimax-cn-coding-plan/MiniMax-M2.1"
    },
    "frontend-ui-ux-engineer": {
      "model": "kimi-for-coding/k2p5"
    },
    "document-writer": {
      "model": "minimax-cn-coding-plan/MiniMax-M2.1"
    },
    "multimodal-looker": {
      "model": "minimax-cn-coding-plan/MiniMax-M2.1"
    }
  },
  "categories": {
    "visual-engineering": {
      "model": "kimi-for-coding/k2p5"
    },
    "ultrabrain": {
      "model": "kimi-for-coding/k2p5"
    },
    "artistry": {
      "model": "kimi-for-coding/k2p5"
    },
    "quick": {
      "model": "minimax-cn-coding-plan/MiniMax-M2.1"
    },
    "unspecified-low": {
      "model": "minimax-cn-coding-plan/MiniMax-M2.1"
    },
    "unspecified-high": {
      "model": "minimax-cn-coding-plan/MiniMax-M2.1"
    },
    "writing": {
      "model": "minimax-cn-coding-plan/MiniMax-M2.1"
    }
  }
}

adding the categories part works.

@MusherM commented on GitHub (Jan 31, 2026): I solved it, now my config is just like this: ```json { "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json", "google_auth": false, "disabled_hooks": ["anthropic-context-window-limit-recovery"], "agents": { "sisyphus": { "model": "kimi-for-coding/k2p5" }, "prometheus": { "model": "kimi-for-coding/k2p5" }, "librarian": { "model": "kimi-for-coding/k2p5" }, "atlas": { "model": "kimi-for-coding/k2p5" }, "explore": { "model": "minimax-cn-coding-plan/MiniMax-M2.1" }, "frontend-ui-ux-engineer": { "model": "kimi-for-coding/k2p5" }, "document-writer": { "model": "minimax-cn-coding-plan/MiniMax-M2.1" }, "multimodal-looker": { "model": "minimax-cn-coding-plan/MiniMax-M2.1" } }, "categories": { "visual-engineering": { "model": "kimi-for-coding/k2p5" }, "ultrabrain": { "model": "kimi-for-coding/k2p5" }, "artistry": { "model": "kimi-for-coding/k2p5" }, "quick": { "model": "minimax-cn-coding-plan/MiniMax-M2.1" }, "unspecified-low": { "model": "minimax-cn-coding-plan/MiniMax-M2.1" }, "unspecified-high": { "model": "minimax-cn-coding-plan/MiniMax-M2.1" }, "writing": { "model": "minimax-cn-coding-plan/MiniMax-M2.1" } } } ``` adding the categories part works.
yindo commented 2026-02-16 18:07:01 -05:00
Author
Owner
Copy Link
Copy Source

@RunMintOn commented on GitHub (Jan 31, 2026):

I solved it, now my config is just like this:

{
"$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
"google_auth": false,
"disabled_hooks": ["anthropic-context-window-limit-recovery"],
"agents": {
"sisyphus": {
"model": "kimi-for-coding/k2p5"
},
"prometheus": {
"model": "kimi-for-coding/k2p5"
},
"librarian": {
"model": "kimi-for-coding/k2p5"
},
"atlas": {
"model": "kimi-for-coding/k2p5"
},
"explore": {
"model": "minimax-cn-coding-plan/MiniMax-M2.1"
},
"frontend-ui-ux-engineer": {
"model": "kimi-for-coding/k2p5"
},
"document-writer": {
"model": "minimax-cn-coding-plan/MiniMax-M2.1"
},
"multimodal-looker": {
"model": "minimax-cn-coding-plan/MiniMax-M2.1"
}
},
"categories": {
"visual-engineering": {
"model": "kimi-for-coding/k2p5"
},
"ultrabrain": {
"model": "kimi-for-coding/k2p5"
},
"artistry": {
"model": "kimi-for-coding/k2p5"
},
"quick": {
"model": "minimax-cn-coding-plan/MiniMax-M2.1"
},
"unspecified-low": {
"model": "minimax-cn-coding-plan/MiniMax-M2.1"
},
"unspecified-high": {
"model": "minimax-cn-coding-plan/MiniMax-M2.1"
},
"writing": {
"model": "minimax-cn-coding-plan/MiniMax-M2.1"
}
}
}
adding the categories part works.

How about the kimi model? Do you think the performance is better than glm4.7?

@RunMintOn commented on GitHub (Jan 31, 2026): > I solved it, now my config is just like this: > > { > "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json", > "google_auth": false, > "disabled_hooks": ["anthropic-context-window-limit-recovery"], > "agents": { > "sisyphus": { > "model": "kimi-for-coding/k2p5" > }, > "prometheus": { > "model": "kimi-for-coding/k2p5" > }, > "librarian": { > "model": "kimi-for-coding/k2p5" > }, > "atlas": { > "model": "kimi-for-coding/k2p5" > }, > "explore": { > "model": "minimax-cn-coding-plan/MiniMax-M2.1" > }, > "frontend-ui-ux-engineer": { > "model": "kimi-for-coding/k2p5" > }, > "document-writer": { > "model": "minimax-cn-coding-plan/MiniMax-M2.1" > }, > "multimodal-looker": { > "model": "minimax-cn-coding-plan/MiniMax-M2.1" > } > }, > "categories": { > "visual-engineering": { > "model": "kimi-for-coding/k2p5" > }, > "ultrabrain": { > "model": "kimi-for-coding/k2p5" > }, > "artistry": { > "model": "kimi-for-coding/k2p5" > }, > "quick": { > "model": "minimax-cn-coding-plan/MiniMax-M2.1" > }, > "unspecified-low": { > "model": "minimax-cn-coding-plan/MiniMax-M2.1" > }, > "unspecified-high": { > "model": "minimax-cn-coding-plan/MiniMax-M2.1" > }, > "writing": { > "model": "minimax-cn-coding-plan/MiniMax-M2.1" > } > } > } > adding the categories part works. How about the kimi model? Do you think the performance is better than glm4.7?
yindo commented 2026-02-16 18:07:01 -05:00
Author
Owner
Copy Link
Copy Source

@MusherM commented on GitHub (Jan 31, 2026):

Capability? Not bad compared to MiniMax M2.1, not been using glm these days due to its alwful speed;
Speed? similar to minimax, maybe a little bit faster
Price & limit? Poooooo, 2 or 3 prompts literally consume 60% of limit in 5 hours, it is absolutely not the ideal model in good price, and yet I don't see any performance gap over minimax, so maybe I will turn back to minimax soon

---Original---
From: @.>
Date: Sat, Jan 31, 2026 14:10 PM
To: @.>;
Cc: @.@.>;
Subject: Re: [anomalyco/opencode] [Bug] I encountered a terminal renderingcrash when using atlas with ProviderModelNotFoundError (Issue #10296)

RunMintOn left a comment (anomalyco/opencode#10296)

I solved it, now my config is just like this:

{
"$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
"google_auth": false,
"disabled_hooks": ["anthropic-context-window-limit-recovery"],
"agents": {
"sisyphus": {
"model": "kimi-for-coding/k2p5"
},
"prometheus": {
"model": "kimi-for-coding/k2p5"
},
"librarian": {
"model": "kimi-for-coding/k2p5"
},
"atlas": {
"model": "kimi-for-coding/k2p5"
},
"explore": {
"model": "minimax-cn-coding-plan/MiniMax-M2.1"
},
"frontend-ui-ux-engineer": {
"model": "kimi-for-coding/k2p5"
},
"document-writer": {
"model": "minimax-cn-coding-plan/MiniMax-M2.1"
},
"multimodal-looker": {
"model": "minimax-cn-coding-plan/MiniMax-M2.1"
}
},
"categories": {
"visual-engineering": {
"model": "kimi-for-coding/k2p5"
},
"ultrabrain": {
"model": "kimi-for-coding/k2p5"
},
"artistry": {
"model": "kimi-for-coding/k2p5"
},
"quick": {
"model": "minimax-cn-coding-plan/MiniMax-M2.1"
},
"unspecified-low": {
"model": "minimax-cn-coding-plan/MiniMax-M2.1"
},
"unspecified-high": {
"model": "minimax-cn-coding-plan/MiniMax-M2.1"
},
"writing": {
"model": "minimax-cn-coding-plan/MiniMax-M2.1"
}
}
}
adding the categories part works.

How about the kimi model? Do you think the performance is better than glm4.7?

—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: @.***>

@MusherM commented on GitHub (Jan 31, 2026): Capability? Not bad compared to MiniMax M2.1, not been using glm these days due to its alwful speed; Speed? similar to minimax, maybe a little bit faster Price &amp; limit? Poooooo, 2 or 3 prompts literally consume 60% of limit in 5 hours, it is absolutely not the ideal model in good price, and yet I don't see any performance gap over minimax, so maybe I will turn back to minimax soon ---Original--- From: ***@***.***&gt; Date: Sat, Jan 31, 2026 14:10 PM To: ***@***.***&gt;; Cc: ***@***.******@***.***&gt;; Subject: Re: [anomalyco/opencode] [Bug] I encountered a terminal renderingcrash when using atlas with ProviderModelNotFoundError (Issue #10296) RunMintOn left a comment (anomalyco/opencode#10296) I solved it, now my config is just like this: { "$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json", "google_auth": false, "disabled_hooks": ["anthropic-context-window-limit-recovery"], "agents": { "sisyphus": { "model": "kimi-for-coding/k2p5" }, "prometheus": { "model": "kimi-for-coding/k2p5" }, "librarian": { "model": "kimi-for-coding/k2p5" }, "atlas": { "model": "kimi-for-coding/k2p5" }, "explore": { "model": "minimax-cn-coding-plan/MiniMax-M2.1" }, "frontend-ui-ux-engineer": { "model": "kimi-for-coding/k2p5" }, "document-writer": { "model": "minimax-cn-coding-plan/MiniMax-M2.1" }, "multimodal-looker": { "model": "minimax-cn-coding-plan/MiniMax-M2.1" } }, "categories": { "visual-engineering": { "model": "kimi-for-coding/k2p5" }, "ultrabrain": { "model": "kimi-for-coding/k2p5" }, "artistry": { "model": "kimi-for-coding/k2p5" }, "quick": { "model": "minimax-cn-coding-plan/MiniMax-M2.1" }, "unspecified-low": { "model": "minimax-cn-coding-plan/MiniMax-M2.1" }, "unspecified-high": { "model": "minimax-cn-coding-plan/MiniMax-M2.1" }, "writing": { "model": "minimax-cn-coding-plan/MiniMax-M2.1" } } } adding the categories part works. How about the kimi model? Do you think the performance is better than glm4.7? — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: ***@***.***&gt;
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 bug opentui
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#7384
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?