- Update `--raw` flag description across all documentation files
- Clarify flag only affects OpenAI-compatible providers behavior
- Document Anthropic models use smart parameter selection
- Remove outdated reference to system/user role changes
- Update help text in CLI flags definition
- Translate updated description to all supported locales
- Update shell completion descriptions for zsh and fish
- chore: incoming 1836 changelog entry
- Add deferred channel close at function start
- Return error immediately instead of breaking loop
- Remove redundant channel close statements from loop
- Ensure channel closes on all exit paths consistently
- chore: incoming 1832 changelog entry
- Add newline to `CreateOutputFile` if missing
- Use `t.Cleanup` for file removal in tests
- Add test for message with trailing newline
- Introduce `printedStream` flag in `Chatter.Send`
- Print newline if stream printed without trailing newline
### CHANGES
- Add v1.4.322 release with concept maps
- Introduce WELLNESS category with psychological analysis
- Upgrade to Claude Sonnet 4.5
- Add Portuguese language variants with BCP 47 support
- Migrate to `openai-go/azure` SDK for Azure
- Add Extensions section to README navigation
### CHANGES
- Remove default space in `BuildSession` message content
- Trim whitespace in `anthropic` message content check
- Trim whitespace in `gemini` message content check
- Change API key setup question to optional
- Add test for optional API key behavior
- Ensure plugin configuration without API key
- chore: incoming 1827 changelog entry
# CHANGES
- Add `apply_ul_tags` pattern for content categorization
- Add `extract_mcp_servers` pattern for MCP server identification
- Add `generate_code_rules` pattern for AI coding guardrails
- Add `t_check_dunning_kruger` pattern for competence assessment
- Renumber all patterns from 37-226 to 37-230
- Insert new patterns at positions 37, 129, 153, 203
- Upgrade `anthropic-sdk-go` to version 1.16.0
- Remove outdated model `ModelClaude3_5SonnetLatest`
- Add new model `ModelClaudeSonnet4_5_20250929`
- Include `ModelClaudeSonnet4_5_20250929` in `modelBetas` map
### CHANGES
- Add `create_conceptmap` for HTML concept maps using Vis.js
- Introduce `fix_typos` for text proofreading and corrections
- Implement `model_as_sherlock_freud` for psychological modeling
- Add `predict_person_actions` for behavior prediction
- Include `recommend_yoga_practice` for personalized yoga guidance
- Credit pattern contribution to @FELIPEGUEDESBR
### CHANGES
- Add `fix_typos` for proofreading and correcting errors
- Introduce `model_as_sherlock_freud` for psychological modeling
- Implement `predict_person_actions` for behavioral response predictions
- Add `recommend_yoga_practice` for personalized yoga guidance
- Include `fix_typos` method for text correction
- Add `model_as_sherlock_freud` for behavior analysis
- Introduce `predict_person_actions` for action prediction
# CHANGES
- Add new WELLNESS category with four patterns
- Add `model_as_sherlock_freud` for psychological detective analysis
- Add `predict_person_actions` for behavioral response predictions
- Add `recommend_yoga_practice` for personalized wellness guidance
- Add `fix_typos` pattern for proofreading corrections
- Update ANALYSIS category to include new patterns
- Update SELF category with wellness-related patterns
- Tag existing patterns with WELLNESS classification
- Add prominent warning at top of Extensions guide with visual indicators
- Update main README with brief Extensions section and link to full guide
- Remove misleading examples showing direct piping to fabric
- Add clear examples: ❌ what DOES NOT WORK vs ✅ what WORKS
- Consolidate all extension documentation in Examples/README.md
- Explain technical reason: extensions only processed via ApplyTemplate()
- Prevents user confusion about extension syntax processing
- Extract InputSentinel constant to shared constants.go file
- Remove duplicate inputSentinel definitions from template.go and patterns.go
- Create withTestExtension helper function to reduce test code duplication
- Refactor 3 test functions to use the helper (reduces ~40 lines per test)
- Fix shell script to use $@ instead of $* for proper argument quoting
Addresses review comments from @ksylvan and @Copilot AI
