CHANGES
- Add -V/--vendor flag to specify model vendor
- Implement vendor-aware model resolution and availability validation
- Warn on ambiguous models; suggest --vendor to disambiguate
- Update bash, zsh, fish completions with vendor suggestions
- Extend --listmodels to print vendor|model when interactive
- Add VendorsModels.PrintWithVendor; sort vendors and models alphabetically
- Pass vendor through API; update server chat handler
- Standardize docs and errors to --yt-dlp-args="..." syntax
- Add test covering ambiguous model warning across multiple vendors
- Promote go-shellquote to direct dependency in go.mod
CHANGES
- Enable Gemini models to use web search tool
- Validate search-location timezone or language code formats
- Normalize language codes from underscores to hyphenated form
- Inject Google Search tool when --search flag enabled
- Append deduplicated web citations under standardized Sources section
- Improve robustness for nil candidates and content parts
- Factor generation config builder for reuse in streaming
- Update CLI help and completions to include Gemini
CHANGES
- Map assistant role to model per Gemini constraints
- Map system, developer, function, tool roles to user
- Default unrecognized roles to user to preserve instruction context
- Add unit test validating convertMessages role mapping logic
- Import chat package in tests for role constants
CHANGES
- Introduce findVTTFilesWithFallback to handle subtitle language absence
- Prefer requested language VTT, gracefully fallback to available alternatives
- Auto-detect downloaded subtitle language and proceed without interruption
- Update yt-dlp processing to use fallback-aware VTT discovery
- Document language fallback behavior and provide usage example
- Return first available VTT when no specific language requested
- Detect language-coded filenames using regex for robust matching
## CHANGES
- Add user argument precedence over built-in flags
- Document argument order and override behavior
- Include new precedence section with detailed explanation
- Add override examples for language and format
- Update tips section with precedence guidance
- Modify Go code to append user args last
- Add testing tip for subtitle language discovery
- Include practical override use case examples
### CHANGES
- Introduce `--yt-dlp-args` flag for advanced control
- Allow passing browser cookies for authentication
- Improve error handling for YouTube rate limits
- Add comprehensive documentation for YouTube processing
- Refactor YouTube methods to accept additional arguments
- Update shell completions to include new flag
CHANGES
- Integrate notification sending into chat processing workflow
- Add --notification and --notification-command CLI flags and help
- Provide cross-platform providers: macOS, Linux, Windows with fallbacks
- Escape shell metacharacters to prevent injection vulnerabilities
- Truncate Unicode output safely for notification message previews
- Update bash, zsh, fish completions with new notification options
- Add docs and YAML examples for configuration and customization
- Add unit tests for providers and notification integration paths
## CHANGES
- Always set temperature parameter for consistent behavior
- Prioritize TopP over temperature when explicitly set
- Override Anthropic's default 1.0 with Fabric's 0.7
- Add comprehensive tests for parameter precedence logic
- Update VSCode dictionary with Keploy entry
- Simplify conditional logic for temperature/TopP selection
## CHANGES
- Upgrade anthropic-sdk-go from v1.4.0 to v1.7.0
- Move changelog generation to separate workflow job
- Add Claude Opus 4.1 model support
- Fix temperature/topP parameter conflict for models
- Separate release artifact upload from changelog update
- Add dedicated update_release_notes job configuration
## CHANGES
- Move changelog generation to separate workflow job
- Add fallback logic for YouTube subtitle language detection
- Remove changelog commands from main release job
- Create dedicated update_release_notes job with Go setup
- Implement retry mechanism without language specification
- Improve yt-dlp command argument construction flexibility
- Add proper checkout and Go configuration steps
## CHANGES
- Add file existence check before creating output file
- Return error if target file already exists
- Change success message to write to stderr
- Update message format with brackets for clarity
- Prevent accidental file overwrites during output creation
## CHANGES
- Update documentation examples to use gemini-2.5-flash-preview-tts
- Replace gemini-2.0-flash-tts references throughout Gemini-TTS.md
- Update voice selection example commands
- Modify CLI help text example command
- Update changelog database binary file
## CHANGES
- Remove redundant byte conversion from audio data extraction
- Extract audio data as string before converting once
- Simplify audio data processing in chat handler
- Fix potential data corruption in audio output
## CHANGES
- Initialize Parts slice with empty slice in Content struct
- Prevent potential nil pointer dereference during message conversion
- Ensure Parts field is ready for append operations
- Improve robustness of convertMessages function in Gemini client
## CHANGES
- Replace deprecated generative-ai-go with google.golang.org/genai library
- Add TTS model detection and audio output validation
- Implement WAV file generation for TTS audio responses
- Add audio format checking utilities in CLI output
- Update Gemini client to support streaming with new SDK
- Add "Kore" and "subchunk" to VSCode spell checker dictionary
- Remove extra blank line from changelog formatting
- Update dependency imports and remove unused packages
## CHANGES
- Add BEDROCK_AWS_REGION requirement for Bedrock initialization
- Implement IsConfigured check for Ollama API URL
- Create comprehensive Docker testing environment with 6 scenarios
- Add interactive test runner with shell access
- Include environment files for different API configurations
- Update spell checker dictionary with new test terms
- Document testing workflow and expected results
## CHANGES
- Add "openaiapi" to VSCode spell check dictionary
- Include API key setup question in Exolab client
- Configure API key as required field for setup
- Maintain existing API base URL configuration order
## CHANGES
- Move timestamp regex initialization to init function
- Add parseSeconds helper function for fractional seconds
- Replace direct strconv.Atoi calls with parseSeconds function
- Support decimal seconds in timestamp format parsing
- Extract seconds parsing logic into reusable function
### CHANGES
- Update `timestampRegex` to support optional seconds/milliseconds
- Change `seenSegments` to use `struct{}` for memory efficiency
- Refactor duplicate check using `struct{}` pattern
- Improve readability by restructuring timestamp logic
- Add deduplication map to track seen segments
- Skip duplicate text segments in plain VTT processing
- Skip duplicate segments in timestamped VTT processing
- Improve timestamp regex to handle more formats
- Use clean text as deduplication key consistently
### CHANGES
- Introduce ensureEnvFile function to create ~/.config/fabric/.env if missing.
- Add directory creation for config path in ensureEnvFile.
- Integrate setup flag in CLI to call ensureEnvFile on demand.
- Handle errors for home directory detection and file operations.
## CHANGES
- Add disable-responses-api flag to CLI completions
- Update zsh completion with new API flag
- Update bash completion options list
- Add fish shell completion for API flag
- Add testpattern to VSCode spell checker dictionary
- Configure disableResponsesAPI in example YAML config
- Enable flag for llama-server compatibility
## CHANGES
- Update `GetDefaultConfigPath` to return error alongside path
- Add proper error handling in flags initialization
- Include debug logging for config path failures
- Move channel close to defer in dryrun SendStream
- Return wrapped errors with context messages
- Handle non-existent config as valid case
### CHANGES
- Rename `_ConstructRequest` to `constructRequest` for consistency
- Update `SendStream` to use `constructRequest`
- Update `Send` method to use `constructRequest`
## CHANGES
- Map both short and long flags to yaml tags
- Add support for short flag parsing with dashes
- Implement default ~/.fabric.yaml config file detection
- Fix think block suppression in dry run mode
- Add think options to dry run output formatting
- Refactor dry run response construction into helper method
- Return actual response content from dry run client
- Create utility function for default config path resolution
## CHANGES
- Add suppress-think flag to hide thinking blocks
- Configure customizable start and end thinking tags
- Strip thinking content from final response output
- Update streaming logic to respect suppress-think setting
- Add YAML configuration support for thinking options
- Implement StripThinkBlocks utility function for content filtering
- Add comprehensive tests for thinking suppression functionality
