add support for gpt-4-turbo-preview model

[riya-amemiya]

User description

Use gpt-4-turbo-preview to ensure the latest version is always used.

For those who want to be automatically upgraded to new GPT-4 Turbo preview versions, we are also introducing a new gpt-4-turbo-preview model name alias, which will always point to our latest GPT-4 Turbo preview model.

https://openai.com/blog/new-embedding-models-and-api-updates#updated-gpt-4-turbo-preview

---

Type

enhancement

---

Description

• Added gpt-4-turbo-preview model with a token limit of 128000 to the model token limits configuration.
• Updated the default model settings in configuration.toml to use gpt-4-turbo-preview for both model and model_turbo fields.

---

Changes walkthrough

	Relevant files
Enhancement	__init__.py Add Support for GPT-4 Turbo Preview Model                                pr_agent/algo/init.py Added support for the gpt-4-turbo-preview model with a token limit of 128000. +1/-0
Configuration changes	configuration.toml Update Default Model Settings to GPT-4 Turbo Preview          pr_agent/settings/configuration.toml Updated the default model and model_turbo settings to gpt-4-turbo-preview. +2/-2

---

✨ PR-Agent usage:
Comment /help on the PR to get a list of all available PR-Agent tools and their descriptions

[codiumai-pr-agent-pro]

PR Description updated to latest commit (d064a35)

• Copy walkthrough table to "Files Changed" Tab

[codiumai-pr-agent-pro]

PR Review

⏱️ Estimated effort to review [1-5]	2, because the changes are straightforward and involve updating configuration settings and adding a new model to an existing list. The logic and structure of the code remain unchanged, making it easier to review.
🏅 Score	95
🧪 Relevant tests	No
🔍 Possible issues	Possible Oversight: The comment for the model field in configuration.toml still mentions "gpt-4" as the default model, but the actual default has been changed to "gpt-4-turbo-preview". This might cause confusion and should be updated for clarity.
🔒 Security concerns	No
🔀 Multiple PR themes	No

---

✨ Review tool usage guide:

---

Overview:
The review tool scans the PR code changes, and generates a PR review which includes several types of feedbacks, such as possible PR issues, security threats and relevant test in the PR. More feedbacks can be added by configuring the tool.

The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on any PR.

• When commenting, to edit configurations related to the review tool (pr_reviewer section), use the following template:

/review --pr_reviewer.some_config1=... --pr_reviewer.some_config2=...

• With a configuration file, use the following template:

[pr_reviewer]
some_config1=...
some_config2=...

See the review usage page for a comprehensive guide on using this tool.

[codiumai-pr-agent-pro]

PR Code Suggestions

Category	Suggestions
Maintainability	Extract repeated literal values into a constant variable for maintainability. Consider extracting the token count (128000) into a constant variable since it is repeated multiple times. This will make future updates easier and the code more maintainable. pr_agent/algo/init.py [11-13] -'gpt-4-1106-preview': 128000, # 128K, but may be limited by config.max_model_tokens -'gpt-4-0125-preview': 128000, # 128K, but may be limited by config.max_model_tokens -'gpt-4-turbo-preview': 128000, # 128K, but may be limited by config.max_model_tokens +MAX_TOKENS = 128000 # 128K, but may be limited by config.max_model_tokens +'gpt-4-1106-preview': MAX_TOKENS, +'gpt-4-0125-preview': MAX_TOKENS, +'gpt-4-turbo-preview': MAX_TOKENS,
Best practice	Remove commented-out code to avoid confusion and maintain a clean configuration file. It's recommended to remove the commented-out model setting (# "gpt-4-turbo-preview") to avoid confusion and keep the configuration file clean. If this is meant for documentation purposes, consider adding a separate documentation section or file. pr_agent/settings/configuration.toml [2] -model="gpt-4" # "gpt-4-turbo-preview" +model="gpt-4"

---

✨ Improve tool usage guide:

---

Overview:
The improve tool scans the PR code changes, and automatically generates suggestions for improving the PR code. The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on a PR.

• When commenting, to edit configurations related to the improve tool (pr_code_suggestions section), use the following template:

/improve --pr_code_suggestions.some_config1=... --pr_code_suggestions.some_config2=...

• With a configuration file, use the following template:

[pr_code_suggestions]
some_config1=...
some_config2=...

See the improve usage page for a comprehensive guide on using this tool.

[mrT23]

Definitely not this.

the default model should be fixed.

I don't want the default model to be dangling, and changing without proper checks

[mrT23]

any user can change this on his local deployment, if he wishes

[riya-amemiya]

Thank you for bringing this to my attention. I completely agree with your point.