Add GPT-4o Mini model to OpenAI provider

[vishesh10]

User description

Background

This is in continuation to the #7694 PR.

Along with the addition of GPT-4o Mini support, the chromedriver issue is fixed which was being encountered in the #7694.

Changes 🏗️

• Updated the webdriver-manager version.
• Added the GPT-4o Mini model to the OpenAI provider in the openai.py file.
• Defined new model names GPT4_O_MINI_v1, GPT4_O_MINI_ROLLING, and GPT4_O_MINI.
• Set prompt token cost to 0.15/1,000,000 and completion token cost to 0.6/1,000,000 for GPT-4o Mini.
• Established a maximum token limit of 128,000 for GPT-4o Mini.
• Enabled support for the function call API for the GPT-4o Mini model.

PR Quality Scorecard ✨

• Have you used the PR description template?   +2 pts
• Is your pull request atomic, focusing on a single change?   +5 pts
• Have you linked the GitHub issue(s) that this PR addresses?   +5 pts
• Have you documented your changes clearly and comprehensively?   +5 pts
• Have you changed or added a feature?   -4 pts
  • Have you added/updated corresponding documentation?   +4 pts
  • Have you added/updated corresponding integration tests?   +5 pts
• Have you changed the behavior of AutoGPT?   -5 pts
  • Have you also run agbenchmark to verify that these changes do not regress performance?   +10 pts

---

PR Type

enhancement, dependencies

---

Description

• Added support for the GPT-4o Mini model in the OpenAI provider, including new model names and specifications.
• Defined prompt and completion token costs, and set a maximum token limit for GPT-4o Mini.
• Enabled the function call API for the GPT-4o Mini model.
• Updated the webdriver-manager dependency version to 4.0.2 to fix related issues.

---

Changes walkthrough 📝

	Relevant files
Enhancement	openai.py Add GPT-4o Mini model support to OpenAI provider                  forge/forge/llm/providers/openai.py Added new model names for GPT-4o Mini. Defined cost and token limits for GPT-4o Mini. Enabled function call API for GPT-4o Mini. Updated chat model mapping with GPT-4o Mini. +12/-0
Dependencies	pyproject.toml Update webdriver-manager dependency version                            forge/pyproject.toml Updated webdriver-manager version to 4.0.2. +1/-1

---

💡 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 (61b29e1)

• Copy walkthrough table to "Files Changed" Tab

[netlify]

✅ Deploy Preview for auto-gpt-docs canceled.

Name	Link
🔨 Latest commit	12ea44d
🔍 Latest deploy log	https://app.netlify.com/sites/auto-gpt-docs/deploys/66e88cfc43bb830008ce2821

[codiumai-pr-agent-pro]

PR Reviewer Guide 🔍

⏱️ Estimated effort to review: 2 🔵🔵⚪⚪⚪

🧪 No relevant tests

🔒 No security concerns identified

⚡ Key issues to review Potential Inconsistency The new GPT4_O_MINI model is added with different token costs compared to other models. Verify if these costs are accurate and consistent with OpenAI's pricing.

[codiumai-pr-agent-pro]

PR Code Suggestions ✨

Category	Suggestion	Score
Best practice	Specify a more precise version range for a dependency Consider specifying a more precise version range for the webdriver-manager dependency, similar to other dependencies in the file, to ensure better compatibility and easier maintenance. forge/pyproject.toml [57] -webdriver-manager = "^4.0.2" +webdriver-manager = ">=4.0.2,<5.0.0" Apply this suggestion Suggestion importance[1-10]: 9 Why: Specifying a more precise version range for webdriver-manager aligns with best practices for dependency management, ensuring better compatibility and easier maintenance, making it a significant improvement.	9
Maintainability	Add explanatory comment for model version date Consider adding a comment explaining the significance of the date in the GPT4_O_MINI_v1 model name, as it might not be immediately clear to other developers why this specific date is used. forge/forge/llm/providers/openai.py [79] +# The date represents the initial release of the GPT-4o Mini model GPT4_O_MINI_v1 = "gpt-4o-mini-2024-07-18" Apply this suggestion Suggestion importance[1-10]: 8 Why: Adding a comment to explain the significance of the date in GPT4_O_MINI_v1 enhances maintainability and understanding for future developers, making it a valuable improvement.	8

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 58.18%. Comparing base (0767b17) to head (12ea44d).
Report is 222 commits behind head on master.

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #8007      +/-   ##
==========================================
+ Coverage   49.63%   58.18%   +8.55%     
==========================================
  Files         146      106      -40     
  Lines        8926     5768    -3158     
  Branches     1242      720     -522     
==========================================
- Hits         4430     3356    -1074     
+ Misses       4348     2306    -2042     
+ Partials      148      106      -42     

Flag	Coverage Δ
Linux	57.88% <100.00%> (+8.44%)	⬆️
Windows	54.66% <100.00%> (+4.92%)	⬆️
agbenchmark	?
autogpt-agent	?
forge	58.06% <100.00%> (+0.02%)	⬆️
macOS	57.05% <100.00%> (+8.15%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[kcze]

LGTM, I checked that all numbers are correct (version, pricing, token count)

[kcze]

Was this needed?

[vishesh10]

Thanks for the review @kcze.
This was done to address the chromedriver issue.