Align OpenAI model defaults and examples with GPT-5.4 variants

docs/docs/installation/github.md

@@ -409,8 +409,8 @@ If you encounter rate limiting:
       env:
         OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        # Add fallback models for better reliability
-        config.fallback_models: '["gpt-4o", "gpt-3.5-turbo"]'
+        # Add a fallback model for better reliability
+        config.fallback_models: '["gpt-5.4-mini"]'
         # Increase timeout for slower models
         config.ai_timeout: "300"
         github_action_config.auto_review: "true"

docs/docs/installation/locally.md

@@ -1,6 +1,6 @@
 To run PR-Agent locally, you first need to acquire two keys:
 
-1. An OpenAI key from [here](https://platform.openai.com/api-keys){:target="_blank"}, with access to GPT-4 and o4-mini (or a key for other [language models](../usage-guide/changing_a_model.md), if you prefer).
+1. An OpenAI key from [here](https://platform.openai.com/api-keys){:target="_blank"}, with access to GPT-5.4 and gpt-5.4-mini (or a key for other [language models](../usage-guide/changing_a_model.md), if you prefer).
 2. A personal access token from your Git platform (GitHub, GitLab, BitBucket, Gitea) with repo scope. GitHub token, for example, can be issued from [here](https://github.com/settings/tokens){:target="_blank"}
 
 ## Using Docker image

docs/docs/usage-guide/automations_and_usage.md

@@ -222,7 +222,7 @@ For detailed step-by-step examples of configuring different models (Gemini, Clau
 
 **Common Model Configuration Patterns:**
 
-- **OpenAI**: Set `config.model: "gpt-4o"` and `OPENAI_KEY`
+- **OpenAI**: Set `config.model: "gpt-5.4"` and `OPENAI_KEY`
 - **Gemini**: Set `config.model: "gemini/gemini-1.5-flash"` and `GOOGLE_AI_STUDIO.GEMINI_API_KEY` (no `OPENAI_KEY` needed)
 - **Claude**: Set `config.model: "anthropic/claude-3-opus-20240229"` and `ANTHROPIC.KEY` (no `OPENAI_KEY` needed)
 - **Azure OpenAI**: Set `OPENAI.API_TYPE: "azure"`, `OPENAI.API_BASE`, and `OPENAI.DEPLOYMENT_ID`

docs/docs/usage-guide/changing_a_model.md

@@ -383,7 +383,7 @@ To bypass chat templates and temperature controls, set `config.custom_reasoning_
 reasoning_effort = "medium" # "low", "medium", "high"
 ```
 
-With the OpenAI models that support reasoning effort (eg: o4-mini), you can specify its reasoning effort via `config` section. The default value is `medium`. You can change it to `high` or `low` based on your usage.
+With the OpenAI models that support reasoning effort (eg: gpt-5.4-mini), you can specify its reasoning effort via `config` section. The default value is `medium`. You can change it to `high` or `low` based on your usage.
 
 ### Anthropic models
 

pr_agent/settings/configuration.toml

@@ -5,9 +5,9 @@
 [config]
 # models
 model="gpt-5.4-2026-03-05"
-fallback_models=["o4-mini"]
-#model_reasoning="o4-mini" # dedicated reasoning model for self-reflection
-#model_weak="gpt-4o" # optional, a weaker model to use for some easier tasks
+fallback_models=["gpt-5.4-mini"]
+#model_reasoning="gpt-5.4-mini" # dedicated reasoning model for self-reflection
+#model_weak="gpt-5.4-nano" # optional, a weaker model to use for some easier tasks
 # CLI
 git_provider="github"
 publish_output=true