- service registration extracted to idempotent _async_register_services,
called from both async_setup and async_setup_entry: unloading the last
entry unregisters services, and a reload (every options change) never
re-ran async_setup, leaving the integration without services
- get_history handler wraps the list in {"history": [...]}: HA rejects
non-dict action responses, so every return_response call failed with a
server error since the service gained SupportsResponse (v2.4.x) - the
path never worked, no consumer could depend on the old shape
- README: get_history example shows response_variable usage and the
actual limit clamp semantics
Both found by live smoke test in HA 2026.7 (Docker), not by static review
- create_pinned_session built directly on aiohttp: the HA helper injects
its own connector and raised TypeError on every setup and config flow
- session lifecycle: closed in APIClient.shutdown, on failed setup, and
in config flow validators; allow_redirects=False everywhere so 3xx
cannot route past the pinned resolver
- defaults: gemini-2.0-flash (shut down 2026-06-01) -> gemini-3.5-flash,
deepseek-chat (retires 2026-07-24) -> deepseek-v4-flash
- DeepSeek V4 disable_thinking via thinking request parameter
- Gemini 3.x disable_thinking via thinking_level (MINIMAL, LOW for Pro)
- get_history limit: no forced default/max in schema, storage layer clamps
- translations: 6 locales caught up with strings.json, 2 orphan keys dropped
- README: manual install path matches zip layout, model sections updated
Replace Creative Commons Attribution-NonCommercial-ShareAlike 4.0
with PolyForm Noncommercial License 1.0.0 across all files:
LICENSE, README badge/footer, and all Python module headers.
- Update recommended models to current versions (Claude 4.6, GPT-5, Gemini 3.1, DeepSeek-V3)
- Add Google Gemini to features list
- Remove YAML configuration section (integration is config_entry_only)
- Remove deleted Api status attribute from documentation
- Update conversation_history display count (1 → 5)
- Fix FAQ with current model names and token limits
- Remove internal spec file
- Update OpenAI models to GPT-5 and GPT-5 mini
- Update Anthropic Claude models to 4.1, 4.0 series
- Update DeepSeek models to V3.1 and R1
- Update Google Gemini models to 2.5 and 2.0 series
- Modernize model descriptions and capabilities
- Simplify HACS installation instructions
- Update recommended models section (remove year from title)
- Update Claude model names to current format (claude-3.5-sonnet, claude-3.5-haiku)
- Add missing parameters to get_history service documentation
- Remove non-configurable history_file_size parameter from table
- Add missing context_messages parameter to configuration table
- Update all model references in examples to use current naming
- Update default model from gpt-4o to gpt-4o-mini
- Update default temperature from 0.7 to 0.1
- Update default max_history_size from 100 to 50
- Add gemini-2.0-flash as latest recommended Gemini model
- Fix logo image link to use main branch instead of specific commit
- Update configuration parameters table with current defaults
🚀 Major Features:
- Add response variables support to ask_question service
- Eliminate 255-character limitation for AI responses
- Enable direct data access in automations without sensors
- Prevent race conditions in parallel automations
🔧 Production Code Audit & Fixes:
- Enhanced resource management with context managers in api_client.py
- Fixed critical race conditions with asyncio.Semaphore implementation
- Improved file operations with atomic writes and corruption handling
- Enhanced error handling and logging security (removed sensitive data)
- Fixed _check_memory_available method placement in coordinator.py
🌐 Translation Updates (8 languages):
- Updated all translation files with response variables information
- Enhanced service descriptions in: en, ru, de, es, it, hi, sr, zh
- Added information about direct response capability
- Maintained consistency across all language files
📚 Documentation Enhancements:
- Added comprehensive Response Variables section to README
- Created advanced automation examples with response_variable usage
- Added migration guide from sensors to response variables
- Enhanced service documentation with response data structure
- Added practical examples for multi-step AI workflows
🔄 Service Improvements:
- Enhanced ask_question service to return structured response data
- Added comprehensive response schema in services.yaml
- Improved error handling with success/failure indicators
- Added metadata support (tokens, model, timestamp)
�� Version & Manifest:
- Bumped version to 2.1.8
- Maintained compatibility with existing integrations
- Updated service documentation
This release addresses GitHub issue #2 and significantly improves the integration's
production readiness while adding powerful new response variable functionality.
SMKRV
SMKRV