[GH-ISSUE #14205] File editing broken with Claude Code/Ollama - sends invalid parameters line_start/line_end #55768

Closed
opened 2026-04-29 09:42:46 -05:00 by GiteaMirror · 4 comments
Owner

Originally created by @colharris113 on GitHub (Feb 11, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14205

What is the issue?

Model: gpt-oss:20b
API: /v1/chat/completions
Error: InputValidationError for unexpected parameters

Request: Add proper error handling for unknown parameters instead of passing them through

Relevant log output

⎿  Read 20 lines                                                                                        
  ⎿  Error: InputValidationError: Edit failed due to the following issues:
     The required parameter `old_string` is missing                                                         
     An unexpected parameter `line_start` was provided                             
     An unexpected parameter `line_end` was provided

OS

macOS

GPU

No response

CPU

Intel

Ollama version

0.15.6

Originally created by @colharris113 on GitHub (Feb 11, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14205 ### What is the issue? Model: gpt-oss:20b API: /v1/chat/completions Error: InputValidationError for unexpected parameters Request: Add proper error handling for unknown parameters instead of passing them through ### Relevant log output ```shell ⎿ Read 20 lines ⎿ Error: InputValidationError: Edit failed due to the following issues: The required parameter `old_string` is missing An unexpected parameter `line_start` was provided An unexpected parameter `line_end` was provided ``` ### OS macOS ### GPU _No response_ ### CPU Intel ### Ollama version 0.15.6
GiteaMirror added the bug label 2026-04-29 09:42:46 -05:00
Author
Owner

@rick-github commented on GitHub (Feb 11, 2026):

What context length have you configured for the model?

<!-- gh-comment-id:3885826011 --> @rick-github commented on GitHub (Feb 11, 2026): What context length have you configured for the model?
Author
Owner

@colharris113 commented on GitHub (Feb 11, 2026):

What context length have you configured for the model?

64K

<!-- gh-comment-id:3885886437 --> @colharris113 commented on GitHub (Feb 11, 2026): > What context length have you configured for the model? 64K
Author
Owner

@rick-github commented on GitHub (Feb 11, 2026):

Full server log may aid in debugging.

<!-- gh-comment-id:3885899016 --> @rick-github commented on GitHub (Feb 11, 2026): Full [server log](https://docs.ollama.com/troubleshooting) may aid in debugging.
Author
Owner

@colharris113 commented on GitHub (Feb 12, 2026):

Ok I'm going to close this off.

I think the main issue is context window, not necessarily that mine is too small (I bumped it up to 128K+), but because Ollama doesn't support cache_control yet so Claude Code is chucking 14K each interaction just on rubbish.

I can see it's on the list, so I will wait patiently.

<!-- gh-comment-id:3891545648 --> @colharris113 commented on GitHub (Feb 12, 2026): Ok I'm going to close this off. I think the main issue is context window, not necessarily that mine is too small (I bumped it up to 128K+), but because Ollama doesn't support cache_control yet so Claude Code is chucking 14K each interaction just on rubbish. I can see it's on the list, so I will wait patiently.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#55768