xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-05 13:20:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge origin/main into es/help_docs

Browse Source
This commit is contained in:
Eyal Sharon
2025-03-23 20:04:58 +02:00
parent 88a17848eb 1aab87516e
commit 1bd65934df
2 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/docs/usage-guide/changing_a_model.md
View File

@ -54,6 +54,10 @@ duplicate_examples=true # will duplicate the examples in the prompt, to help the
api_base = "http://localhost:11434" # or whatever port you're running Ollama on api_base = "http://localhost:11434" # or whatever port you're running Ollama on
``` ```
By default, Ollama uses a context window size of 2048 tokens. In most cases this is not enough to cover pr-agent promt and pull-request diff. Context window size can be overridden with the `OLLAMA_CONTEXT_LENGTH` environment variable. For example, to set the default context length to 8K, use: `OLLAMA_CONTEXT_LENGTH=8192 ollama serve`. More information you can find on the [official ollama faq](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-can-i-specify-the-context-window-size).
Please note that the `custom_model_max_tokens` setting should be configured in accordance with the `OLLAMA_CONTEXT_LENGTH`. Failure to do so may result in unexpected model output.
!!! note "Local models vs commercial models" !!! note "Local models vs commercial models"
Qodo Merge is compatible with almost any AI model, but analyzing complex code repositories and pull requests requires a model specifically optimized for code analysis. Qodo Merge is compatible with almost any AI model, but analyzing complex code repositories and pull requests requires a model specifically optimized for code analysis.

2
pr_agent/git_providers/azuredevops_provider.py
View File

@ -383,7 +383,7 @@ class AzureDevopsProvider(GitProvider):
get_logger().debug(f"Skipping publish_comment for temporary comment: {pr_comment}") get_logger().debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
return None return None
comment = Comment(content=pr_comment) comment = Comment(content=pr_comment)
thread = CommentThread(comments=[comment], thread_context=thread_context, status=5) thread = CommentThread(comments=[comment], thread_context=thread_context, status=1)
thread_response = self.azure_devops_client.create_thread( thread_response = self.azure_devops_client.create_thread(
comment_thread=thread, comment_thread=thread,
project=self.workspace_slug, project=self.workspace_slug,