feat(docs): Add FAQ for OpenAI o1 best practices

- Provide guidance on context management, model selection, prompting strategy, response time, and quality for using OpenAI o1 models
- Document known technical limitations of o1 models

Author: jdorfman

docs/cody/faq.mdx

@@ -137,3 +137,47 @@ cody chat --model '$name_of_the_model' -m 'Hi Cody!'
 ```
 
 For example, to use Claude 3.5 Sonnet, you'd pass the following command in your terminal, `cody chat --model 'claude-3.5-sonnet' -m 'Hi Cody!'
+
+## OpenAI o1
+
+### What are OpenAI o1 best practices?
+
+#### Context Management
+
+- Provide focused, relevant context
+- Use file references strategically
+- Keep initial requests concise
+
+#### Model Selection
+
+- O1-preview: Best for complex reasoning and planning
+- O1-mini: More reliable for straightforward tasks
+- Sonnet 3.5: Better for tasks requiring longer outputs
+
+#### Prompting Strategy
+
+- Be specific and direct
+- Include complete requirements upfront
+- Request brief responses when possible
+- Use step-by-step approach for complex tasks
+
+#### Response Time
+
+- Start with smaller contexts
+- Use O1-mini for faster responses
+- Consider breaking complex tasks into stages
+
+#### Quality
+
+- Provide clear acceptance criteria
+- Include relevant context but avoid excess
+- Use specific examples when possible
+
+### What are the known limitations?
+
+#### Technical Constraints
+
+- 45k input token limit
+- 4k output token limit
+- No streaming responses for O1 series
+- Limited context window