Set default OPENAI_API_KEY value to prevent startup crashes

[httpdss]

Summary

The STRUCT tool crashes with an OpenAI API key error when the OPENAI_API_KEY environment variable is not set, even when users may not intend to use OpenAI models or may want to use the tool without AI features.

Error Details

openai.OpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

Full Stack Trace:

Traceback (most recent call last):
  File "/opt/hostedtoolcache/Python/3.13.5/x64/bin/struct", line 8, in <module>
    sys.exit(main())
  File "/opt/hostedtoolcache/Python/3.13.5/x64/lib/python3.13/site-packages/struct_module/main.py", line 51, in main
    args.func(args)
  File "/opt/hostedtoolcache/Python/3.13.5/x64/lib/python3.13/site-packages/struct_module/commands/generate.py", line 130, in execute
    self._create_structure(args, mappings)
  File "/opt/hostedtoolcache/Python/3.13.5/x64/lib/python3.13/site-packages/struct_module/commands/generate.py", line 260, in _create_structure
    self._create_structure({
  File "/opt/hostedtoolcache/Python/3.13.5/x64/lib/python3.13/site-packages/struct_module/commands/generate.py", line 163, in _create_structure
    file_item = FileItem(content)
  File "/opt/hostedtoolcache/Python/3.13.5/x64/lib/python3.13/site-packages/struct_module/file_item.py", line 34, in __init__
    self.model_wrapper = ModelWrapper(self.logger)
  File "/opt/hostedtoolcache/Python/3.13.5/x64/lib/python3.13/site-packages/struct_module/model_wrapper.py", line 15, in __init__
    self.agent = Agent(model=self.model_name)
  File "/opt/hostedtoolcache/Python/3.13.5/x64/lib/python3.13/site-packages/pydantic_ai/agent.py", line 338, in __init__
    self.model = models.infer_model(model)
  File "/opt/hostedtoolcache/Python/3.13.5/x64/lib/python3.13/site-packages/pydantic_ai/models/__init__.py", line 637, in infer_model
    return OpenAIModel(model_name, provider=provider)
  File "/opt/hostedtoolcache/Python/3.13.5/x64/lib/python3.13/site-packages/pydantic_ai/models/openai.py", line 226, in __init__
    provider = infer_provider(provider)
  File "/opt/hostedtoolcache/Python/3.13.5/x64/lib/python3.13/site-packages/pydantic_ai/providers/__init__.py", line 137, in infer_provider
    return provider_class()
  File "/opt/hostedtoolcache/Python/3.13.5/x64/lib/python3.13/site-packages/pydantic_ai/providers/openai.py", line 72, in __init__
    self._client = AsyncOpenAI(base_url=base_url, api_key=api_key, http_client=http_client)
  File "/opt/hostedtoolcache/Python/3.13.5/x64/lib/python3.13/site-packages/openai/_client.py", line 449, in __init__
    raise OpenAIError(

Root Cause

The issue occurs in struct_module/model_wrapper.py where:

1. The default model is set to "openai:gpt-4.1" when AI_MODEL environment variable is not set
2. The OpenAI model initialization always requires a valid API key
3. No fallback or default API key is provided when the environment variable is missing

Proposed Solution

Set a programmatic default value for OPENAI_API_KEY at application startup to prevent crashes when the environment variable is not set.

Option 1: Set a placeholder default value

# In main.py or model_wrapper.py
if not os.getenv("OPENAI_API_KEY"):
    os.environ["OPENAI_API_KEY"] = "default_placeholder_key"

Option 2: Enhanced error handling with graceful fallback

# In model_wrapper.py
def __init__(self, logger=None):
    self.logger = logger or logging.getLogger(__name__)
    self.model_name = os.getenv("AI_MODEL") or "openai:gpt-4.1"
    
    # Set default API key if not provided
    if self.model_name.startswith("openai:") and not os.getenv("OPENAI_API_KEY"):
        os.environ["OPENAI_API_KEY"] = "sk-default-placeholder-key"
        self.logger.warning("OPENAI_API_KEY not set. Using placeholder. AI features may not work properly.")
    
    self.agent = Agent(model=self.model_name)

Benefits

• Prevents crashes: Tool won't fail immediately due to missing API keys
• Better UX: Users can explore non-AI features without setting up API keys first
• Graceful degradation: AI features can warn users rather than crash the entire application
• Backward compatibility: Existing configurations continue to work

Alternative Considerations

• Lazy initialization: Only initialize AI models when actually needed
• Optional AI features: Make AI functionality completely optional
• Better error messages: Provide clearer guidance when API keys are missing

Files to be modified

• struct_module/main.py or struct_module/model_wrapper.py
• Potentially update documentation about API key requirements

Acceptance Criteria

• STRUCT tool starts successfully without OPENAI_API_KEY environment variable
• Default/placeholder API key is set programmatically at startup
• Clear warning message when using placeholder API key
• AI features gracefully handle invalid/placeholder API keys
• Existing functionality with valid API keys remains unchanged
• Documentation updated if necessary