feat: add OpenAI GPT-5.1 series models

[PeterDaveHello]

User description

• add support for gpt-5.1, gpt-5.1-2025-11-13, gpt-5.1-chat-latest, gpt-5.1-codex, gpt-5.1-codex-mini
• replace default model gpt-5-2025-08-07 with gpt-5.1-2025-11-13 per OpenAI’s Nov 13 launch

See: https://openai.com/index/gpt-5-1-for-developers/

GitHub Copilot Summary:

This pull request updates the default model configuration to use a newer version and expands support for additional GPT-5.1 model variants. The most important changes are:

Model Support Updates:

• Added support for several new GPT-5.1 model variants in the pr_agent/algo/__init__.py file, including gpt-5.1, gpt-5.1-2025-11-13, gpt-5.1-chat-latest, gpt-5.1-codex, and gpt-5.1-codex-mini, all with a token limit of 200,000.

Configuration Changes:

• Updated the default model in pr_agent/settings/configuration.toml from gpt-5-2025-08-07 to the newer gpt-5.1-2025-11-13.

---

PR Type

Enhancement

---

Description

• Add support for five new GPT-5.1 model variants

• Update default model to gpt-5.1-2025-11-13

• All new models configured with 200K token limit

---

Diagram Walkthrough

flowchart LR
  A["Model Registry"] -->|"Add 5 variants"| B["GPT-5.1 Models"]
  C["Default Config"] -->|"Update to latest"| D["gpt-5.1-2025-11-13"]
  B --> E["200K tokens each"]

Loading

File Walkthrough

	Relevant files
Enhancement	__init__.py Register GPT-5.1 model variants                                                    pr_agent/algo/init.py Added five new GPT-5.1 model variants to the model registry Models include gpt-5.1, gpt-5.1-2025-11-13, gpt-5.1-chat-latest, gpt-5.1-codex, and gpt-5.1-codex-mini All variants configured with 200,000 token limit +5/-0
Configuration changes	configuration.toml Update default model to GPT-5.1                                                    pr_agent/settings/configuration.toml Updated default model from gpt-5-2025-08-07 to gpt-5.1-2025-11-13 Aligns with OpenAI's November 13 GPT-5.1 launch +1/-1

---

[qodo-merge-for-open-source]

PR Compliance Guide 🔍

(Compliance updated until commit d8dcc3c)

Below is a summary of compliance checks for this PR:

Security Compliance
🟢	No security concerns identified No security vulnerabilities detected by AI analysis. Human verification advised for critical code.
Ticket Compliance
⚪	🎫 No ticket provided Create ticket/issue
Codebase Duplication Compliance
⚪	Codebase context is not defined Follow the guide to enable codebase context checks.
Custom Compliance
🟢	Consistent Naming Conventions Objective: All new variables, functions, and classes must follow the project's established naming standards Status: Passed
	No Dead or Commented-Out Code Objective: Keep the codebase clean by ensuring all submitted code is active and necessary Status: Passed
	Robust Error Handling Objective: Ensure potential errors and edge cases are anticipated and handled gracefully throughout the code Status: Passed
	Single Responsibility for Functions Objective: Each function should have a single, well-defined responsibility Status: Passed
	When relevant, utilize early return Objective: In a code snippet containing multiple logic conditions (such as 'if-else'), prefer an early return on edge cases than deep nesting Status: Passed

Compliance status legend

🟢 - Fully Compliant
🟡 - Partial Compliant
🔴 - Not Compliant
⚪ - Requires Further Human Verification
🏷️ - Compliance label

---

Previous compliance checks

Compliance check up to commit 44a0943

Security Compliance
🟢	No security concerns identified No security vulnerabilities detected by AI analysis. Human verification advised for critical code.
Ticket Compliance
⚪	🎫 No ticket provided Create ticket/issue
Codebase Duplication Compliance
⚪	Codebase context is not defined Follow the guide to enable codebase context checks.
Custom Compliance
🟢	Consistent Naming Conventions Objective: All new variables, functions, and classes must follow the project's established naming standards Status: Passed
	No Dead or Commented-Out Code Objective: Keep the codebase clean by ensuring all submitted code is active and necessary Status: Passed
	Robust Error Handling Objective: Ensure potential errors and edge cases are anticipated and handled gracefully throughout the code Status: Passed
	Single Responsibility for Functions Objective: Each function should have a single, well-defined responsibility Status: Passed
	When relevant, utilize early return Objective: In a code snippet containing multiple logic conditions (such as 'if-else'), prefer an early return on edge cases than deep nesting Status: Passed

[qodo-merge-for-open-source]

PR Code Suggestions ✨

Explore these optional code suggestions:

Category	Suggestion	Impact
Possible issue	Verify token limits accuracy Verify the token limits for the newly added gpt-5.1 models are correct, as they appear to be copied from gpt-5 and might be inaccurate. pr_agent/algo/init.py [35-39] -'gpt-5.1': 200000, -'gpt-5.1-2025-11-13': 200000, -'gpt-5.1-chat-latest': 200000, -'gpt-5.1-codex': 200000, -'gpt-5.1-codex-mini': 200000, +# Verify these token limits with OpenAI documentation +'gpt-5.1': 200000, # 200K, but may be limited by config.max_model_tokens +'gpt-5.1-2025-11-13': 200000, # 200K, but may be limited by config.max_model_tokens +'gpt-5.1-chat-latest': 200000, # 200K, but may be limited by config.max_model_tokens +'gpt-5.1-codex': 200000, # 200K, but may be limited by config.max_model_tokens +'gpt-5.1-codex-mini': 200000, # 200K, but may be limited by config.max_model_tokens Apply / Chat Suggestion importance[1-10]: 6 __ Why: The suggestion correctly points out that the token limits for the new gpt-5.1 models might be incorrect assumptions, and verifying them is crucial to prevent potential runtime errors.	Low
Update

• Author self-review: I have reviewed the PR code suggestions, and addressed the relevant ones.

[ofir-frd]

To approve this, please revert the default model config and bump the LiteLLM version.

Thanks!

[ofir-frd]

Approved, thank you for the contribution!