- Add optional tool_call_id field to Message model
- Required for tool response messages (role:tool)
- Identifies which tool call the response is for
- Fixes 400 errors for missing tool_call_id in tool messages

- Pass autoselect_config to _get_model_selection in handle_autoselect_streaming_request
- Fixes TypeError: missing 1 required positional argument
- Ensures streaming autoselect requests use the configured selection_model

- Add optional tool_calls field to Message model
- Make content field optional with default None
- Allows assistant messages with tool_calls instead of content
- Fixes 422 validation errors for tool call messages
- Supports OpenAI message format with function calls

- Import RequestValidationError from fastapi.exceptions
- Update exception handler to catch RequestValidationError instead of status code
- Add console logging for immediate visibility of validation errors
- Log validation error details using exc.errors() method

- Add exception handler to catch and log validation errors
- Log request path, method, headers, and raw body
- Log validation error details from FastAPI
- Helps diagnose why requests are failing validation

- Change host from 0.0.0.0 to 127.0.0.1 for improved security
- Change port from 8000 to 17765 to match main.py default
- Ensures consistency between development and production modes

- Log raw request body before validation to diagnose 422 errors
- Log request headers and path for debugging
- Make Message content field more flexible with List type
- Helps identify validation issues in incoming requests

- Set default value for selection_model to 'general' in AutoselectConfig
- Maintains backward compatibility with existing configuration files
- Prevents 422 errors when loading configs without selection_model field

- Add selection_model field to AutoselectConfig model
- Update _get_model_selection to use autoselect_config.selection_model instead of hardcoded 'general'
- Update handle_autoselect_request to log selection_model from config
- Update handle_autoselect_streaming_request to log selection_model from config
- Allows flexible configuration of which rotation to use for model selection

- Add selection_model field to specify which rotation to use for model selection
- Default value is 'general' rotation
- Allows explicit control over which rotation models are available for autoselect
- Provides flexibility in configuring autoselect behavior

- Changed max_retries from 2 to 5 in RotationHandler.handle_rotation_request
- Provides more opportunities to find a working model when errors occur
- Especially helpful for tool call errors and other transient failures
- Improves reliability of rotation and autoselect model selection

- Add tools and tool_choice fields to ChatCompletionRequest model
- Update OpenAIProviderHandler to accept and pass tools/tool_choice parameters
- Update handlers to pass tools/tool_choice from request to provider
- Treat tool call errors during streaming as provider failures
- Record failure and re-raise to trigger retry with next model in rotation
- Allows proper tool/function calling support through the proxy
- Resolves 'Tool choice is none, but model called a tool' error by retrying with another model

- Log chunk type and content before serialization attempt
- Log chunk type and content when serialization fails
- Helps diagnose 'Tool choice is none, but model called a tool' errors
- Apply debug logging to both RequestHandler and AutoselectHandler streaming methods

- Add try-catch around chunk serialization in stream_generator functions
- Skip chunks that fail to serialize (e.g., tool calls without tool_choice)
- Log warnings for chunk serialization errors
- Prevent streaming failures when models attempt tool calls without proper configuration
- Apply fix to both RequestHandler and AutoselectHandler streaming methods

- Add Key Features section to README.md
- Describe Rotation Models with weighted load balancing and automatic failover
- Describe Autoselect Models with AI-powered content analysis
- Update Rotation Endpoints with detailed model descriptions
- Update Autoselect Endpoints with detailed model descriptions
- Add comprehensive Rotation Models section to DOCUMENTATION.md
- Add comprehensive Autoselect Models section to DOCUMENTATION.md
- Include example use cases for both rotation and autoselect models
- Update overview with key features and capabilities
- Document fallback behavior to 'general' when autoselect can't choose a model

- Update version to 0.3.0 in setup.py, pyproject.toml, and aisbf/__init__.py

- Update host from 0.0.0.0 to 127.0.0.1 for localhost-only access
- Update port from 8000 to 17765
- Update log message to reflect new address

- Add prominent ABSOLUTELY CRITICAL section emphasizing ONLY output requirement
- Explicitly state NO additional text, explanations, or commentary
- Add repeated warnings about outputting nothing except the single tag
- Clarify that any extra text will cause system failure
- Add examples of what NOT to include in response

- Properly serialize Stream chunks to JSON format
- Convert ChatCompletionChunk objects using model_dump()
- Apply fix to both RequestHandler and AutoselectHandler streaming methods
- Resolves socket.send() exceptions during streaming

- Fixed AttributeError when stream=True is passed to OpenAI client
- Changed return type to Union[Dict, object] to support streaming
- Added conditional check to return Stream object for streaming requests
- Bumped version to 0.2.7

- Add successful_model variable to track which model actually worked
- Update successful_model when request succeeds in retry loop
- Log which model was successfully used
- Prevents KeyError when trying to access provider_id from selected_model
- Ensures proper model tracking across retry attempts

- Try up to 2 different models when a request fails or times out
- Track which models have been tried to avoid repeating failures
- Log each attempt with attempt number and model details
- Record failures and rate limit providers automatically
- Provide detailed error logging for each failed attempt
- Return comprehensive error message when all retries are exhausted
- Include last error in final error response for debugging

- Validate that all providers referenced in rotations exist in providers.json
- Log visible warnings with !!! CONFIGURATION WARNING !!! markers
- Show available providers when a referenced provider is missing
- Indicate that missing providers will be skipped during requests
- Provide guidance on how to fix the configuration issue
- Log successful validation with checkmarks for available providers

- Check if provider exists in configuration before creating handler
- Log error with available providers when provider is not found
- Skip providers that don't exist instead of crashing
- Prevents AttributeError when rotation references non-existent provider

- Add GET /api/autoselect endpoint to list all available autoselect configurations
- Add POST /api/autoselect/chat/completions endpoint for autoselect chat completions
- Model name in request now selects the specific autoselect configuration
- Add GET /api/autoselect/models endpoint to list all models across all autoselect configurations
- Maintain backward compatibility with existing /api/{provider_id} endpoints
- Follows same pattern as rotation endpoints for consistency

- Add GET /api/rotations endpoint to list all available rotations
- Add POST /api/rotations/chat/completions endpoint for rotation chat completions
- Model name in request now selects the specific rotation (coding, general, etc.)
- Add GET /api/rotations/models endpoint to list all models across all rotations
- Update root endpoint to show available rotations and autoselect options
- Maintain backward compatibility with existing /api/{provider_id} endpoints

Provider State Logging (providers.py):
- Add detailed logging when provider failures are recorded
- Show failure count and remaining failures before disable
- Log provider disable events with cooldown period details
- Log provider re-enable events after successful requests
- Track and display previous failure counts

Autoselect Model Selection Logging (handlers.py):
- Add detailed logging for autoselect model selection process
- Show available models and their descriptions
- Display user prompt information and length
- Log AI model selection request and response
- Show model validation and fallback logic
- Indicate whether selection was AI-selected or fallback
- Add logging for both streaming and non-streaming requests
- Display final model choice with selection method

- Add detailed logging for provider scanning process
- Show which providers are skipped and why (rate limited/deactivated)
- Display model details including weight, rate limit, and provider
- Add priority-based selection visualization
- Show sorted models by weight in descending order
- Indicate whether selection was random or deterministic
- Add clear section headers for different stages of selection
- Provide final selection summary with all relevant details

- Weight now acts as priority instead of frequency
- Higher weight models always take precedence over lower weight models
- Random selection only occurs when multiple models have the same highest weight
- Providers that are rate limited/deactivated are automatically skipped
- Ensures deterministic model selection based on priority

- Add connection health check before making requests
- Test Ollama availability with /api/tags endpoint
- Improve timeout configuration with separate connect/read/write/pool timeouts
- Add logging of available models from Ollama
- Provide clear error message if Ollama is not accessible

- Set timeout to 300 seconds (5 minutes) for total request
- Set connect timeout to 60 seconds
- This fixes httpx.ReadTimeout errors with Ollama cloud models
- Cloud models may take longer to respond than local instances

- Add explicit stream: False to Ollama requests
- Add robust JSON parsing to handle multiple JSON objects in response
- Add detailed logging of raw response content for debugging
- Parse multiple JSON objects line by line and use the last one
- This fixes JSONDecodeError when Ollama returns multiple chunks

- Add rate_limit field to ProviderConfig model with default value 0.0
- This fixes AttributeError when BaseProviderHandler tries to access rate_limit
- The providers.json file already contains rate_limit for all providers

- Add detailed debug logging throughout the codebase to track model and provider selection
- Fix OllamaProviderHandler to accept optional api_key parameter for cloud models
- Add logging in main.py, handlers.py, providers.py, and config.py
- Add catch-all endpoint for invalid routes with helpful error messages
- Create DEBUG_GUIDE.md with comprehensive documentation
- Enhance error messages to show available providers/rotations/autoselect

Debug logging now shows:
- Request path and provider ID
- Available configurations
- Provider config and handler selection
- Model selection process
- Rate limiting application
- Request/response details

This helps diagnose issues with model and provider selection.