GoogleProviderHandler enhancements:
- Process all parts in response content (not just first part)
- Extract and combine all text parts
- Detect and convert Google function_call to OpenAI tool_calls format
- Generate unique call IDs for tool calls
- Handle function responses for debugging
- Set content to None when tool_calls are present (OpenAI convention)
- Add comprehensive logging for tool call detection and conversion
- Support both text and function/tool calls in same response
- Validate response against ChatCompletionResponse Pydantic model
- Add detailed response structure logging

AnthropicProviderHandler enhancements:
- Process all content blocks (not just text)
- Detect and convert Anthropic tool_use blocks to OpenAI tool_calls format
- Generate unique call IDs for tool calls
- Combine all text parts from multiple blocks
- Set content to None when tool_calls are present (OpenAI convention)
- Add comprehensive logging for tool_use detection and conversion
- Validate response against ChatCompletionResponse Pydantic model
- Add detailed response structure logging

Both handlers now properly translate provider-specific function calling
formats to OpenAI-compatible tool_calls structure, ensuring clients receive
valid structured responses with proper schema validation.

- Log response type and all attributes
- Log candidates structure and length
- Log candidate attributes and content structure
- Log parts structure and first part details
- Log raw text extraction and parsing steps
- Log final extracted text and finish reason
- Add error logging with full stack trace for exceptions

This will help identify where the parsing is failing when responses
show as 'parsed=None' and clients receive nothing.

- Properly extract finish_reason from candidate object and map to OpenAI format
- Correctly extract usage metadata from response.usage_metadata structure
- Extract prompt_token_count, candidates_token_count, and total_token_count
- Add logging for usage metadata extraction
- Handle Google finish reasons: STOP, MAX_TOKENS, SAFETY, RECITATION, OTHER

This fixes the issue where Gemini responses were arriving corrupted to
OpenAI-compatible clients due to incorrect parsing of the new Google GenAI
SDK response structure.

- Google: Parse formatted responses with JSON structure (e.g., 'assistant: [{'type': 'text', 'text': '...'}]')
- Anthropic: Extract text from content blocks and map stop_reason to finish_reason
- Both handlers now return properly formatted OpenAI-compatible responses
- Ensures clients receive correctly structured messages without malformed content

- Added AISBF_DEBUG check to control verbose message content logging
- Messages are only dumped when AISBF_DEBUG=true/1/yes
- Otherwise only message count is logged
- Applies to Google, OpenAI, and Anthropic provider handlers
- Reduces log verbosity in production while maintaining debug capability

- Fixed GoogleProviderHandler to properly extract text from response.candidates[0].content.parts[0].text
- Added error handling for text extraction
- Resolves client error 'Cannot read properties of undefined (reading '0')'
- The Google GenAI SDK returns nested response structure, not direct .text property

- Fixed GoogleProviderHandler to return OpenAI-style response format
- Added tools and tool_choice parameters to OllamaProviderHandler (accepted but ignored)
- Fixed OpenAI message building to properly handle tool messages with tool_call_id
- Fixed max_tokens handling to avoid passing null values to APIs
- Converted Ollama response to OpenAI-style format for consistency

This fixes the following errors:
- 'Cannot read properties of undefined (reading '0')' - Google response format issue
- 'OllamaProviderHandler.handle_request() got an unexpected keyword argument 'tools''
- 'for 'role:tool' the following must be satisfied[('messages.23.tool_call_id' : property 'tool_call_id' is missing)]'
- 'Invalid input: expected number, received null' for max_tokens parameter

- 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