### CHANGES
- Remove outdated update notes from README
- Add `--suppress-think` option to suppress 'think' tags
- Introduce `--think-start-tag` and `--think-end-tag` options
- Update bash completion with 'think' tag options
- Update fish completion with 'think' tag options
## 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
## CHANGES
- Add `data/strategies/**` to paths-ignore list
- Add `cmd/generate_changelog/*.db` to paths-ignore list
- Prevent workflow triggers from strategy data changes
- Prevent workflow triggers from changelog database files
### CHANGES
- Enhance changelog to associate PR numbers with version tags
- Improve PR number parsing with proper error handling
- Collect all PR numbers for commits between version tags
- Associate aggregated PR numbers with each version entry
- Update cached versions with newly found PR numbers
- Add check for missing PRs to trigger sync if needed
### CHANGES
- Collect all PR numbers for commits between version tags.
- Associate aggregated PR numbers with each version entry.
- Update cached versions with newly found PR numbers.
- Attribute all changes in a version to relevant PRs.
## CHANGES
- Add storer import for proper git iteration control
- Use storer.ErrStop instead of nil for commit iteration termination
- Handle storer.ErrStop as expected condition in git walker
- Update cache comment to clarify Unreleased version skipping
- Change custom patterns warning to stderr output
- Add storer to VSCode spell checker dictionary
## CHANGES
- Add incremental processing for new Git tags since cache
- Implement `WalkHistorySinceTag` method for efficient history traversal
- Cache new versions and commits after AI processing
- Update AI summarization prompt for better release note formatting
- Remove conventional commit prefix stripping from commit messages
- Add custom patterns directory support to plugin registry
- Generate unique patterns file including custom directory patterns
- Improve session string formatting with switch statement
### CHANGES
- Detail GraphQL API usage for faster PR fetching
- Introduce AI-powered summaries via Fabric integration
- Explain content-based caching for AI summaries
- Document support for loading secrets from .env files
- Add usage examples for new AI summary feature
- Clarify project license is The MIT License
## CHANGES
- Add high-performance Go changelog generator with GraphQL integration
- Implement SQLite-based persistent caching for incremental updates
- Create one-pass git history walking algorithm with concurrent processing
- Add comprehensive CLI with cobra framework and tag-based caching
- Integrate AI summarization using Fabric CLI for enhanced output
- Support batch PR fetching with GitHub Search API optimization
- Add VSCode configuration with spell checking and markdown linting
- Include extensive documentation with PRD and README files
- Implement commit-PR mapping for lightning-fast git operations
- Add content hashing for change detection and cache optimization
## CHANGES
- Remove duplicate comment about reading response body
- Preallocate slice capacity in extractModelIDs function
- Initialize modelIDs slice with known capacity
## CHANGES
- Add proper bounds checking for response body truncation
- Prevent slice out of bounds errors in error messages
- Add ellipsis indicator when response body is truncated
- Improve error message clarity for debugging purposes
## CHANGES
* Read response body once for efficiency
* Use io.ReadAll for response body
* Unmarshal json from bodyBytes
* Return error with raw response bytes
* Improve error handling for json parsing
## CHANGES
- Increase error response limit from 500 to 1024 bytes
- Add documentation comment for ErrorResponseLimit constant
- Remove unnecessary error return from extractModelIDs function
- Fix return statements in DirectlyGetModels parsing logic
- Add TODO comment for proper context handling
- Simplify model ID extraction without error propagation
## CHANGES
- Add provider name to API base URL error message
- Enhance error context for better debugging experience
- Include GetName() method call in error formatting
