Releases: withceleste/celeste-python
Releases · withceleste/celeste-python
Release v0.3.1
Release v0.3.1
Changes
- test: fix Int constraint test to accept booleans
- test: improve test coverage for constraints and parameters
- fix(gradium): fix provider inconsistencies
- feat(speech-generation): add Gradium TTS provider with WebSocket API
- feat(speech-generation): add Gradium TTS provider (#XX)
- chore: prepare v0.3.0 release (#88)
- refactor(client): add APIMixin abstract base for type-safe provider mixins (#87)
- refactor(providers): standardize usage field mapping and add streaming mixins (#86)
- feat(providers): add Cohere, ElevenLabs, and xAI API packages and migrate capabilities to mixins (#85)
- refactor: rename BYTEDANCE to BYTEPLUS and migrate to provider mixins (#84)
- feat(providers): add Mistral Chat API package and migrate capability to mixins (#83)
- feat(providers): add OpenAI API package and migrate capabilities to mixins (#82)
- feat(providers): add BFL Images API package (#81)
- feat(providers): add Google Veo API package (#80)
- feat(providers): add Google GenerateContent and Imagen API packages (#79)
- refactor(core): StructuredOutput types, timeout increase, provider loading (#78)
- refactor(text-generation): use StructuredOutput and improve API (#76)
- refactor(text-generation): migrate Anthropic to mixin pattern (#75)
- feat: add Anthropic Messages API provider with core structured output infrastructure (#74)
- feat: introduce Authentication abstraction for flexible provider auth (#73)
- refactor: reorganize packages into capabilities directory (#72)
- feat: add gpt-image-1-mini model for OpenAI image generation (#70)
- feat: add sora-2-2025-12-08 snapshot for OpenAI video generation (#71)
- feat: add seedream-4.5 model for ByteDance image generation (#69)
- feat: add Devstral 2 and Devstral Small 2 models (#68)
- Add GPT-5.2, GPT-5.2 Pro, and GPT-5.2 Instant models (#67)
- license: change from Apache 2.0 to MIT and enhance README (#65)
- docs: enhance README with social badges, feature highlights, and provider switching examples (#64)
Installation
uv add "celeste-ai==0.3.1"Release v0.3.0
Release v0.3.0
Changes
- fix(test): use correct Google TTS model name gemini-2.5-flash-preview-tts
- fix(ci): rename BYTEDANCE_API_KEY to BYTEPLUS_API_KEY
- fix: update optional dependency constraints to 0.3.0
- chore: prepare v0.3.0 release
- refactor(client): add APIMixin abstract base for type-safe provider mixins (#87)
- refactor(providers): standardize usage field mapping and add streaming mixins (#86)
- feat(providers): add Cohere, ElevenLabs, and xAI API packages and migrate capabilities to mixins (#85)
- refactor: rename BYTEDANCE to BYTEPLUS and migrate to provider mixins (#84)
- feat(providers): add Mistral Chat API package and migrate capability to mixins (#83)
- feat(providers): add OpenAI API package and migrate capabilities to mixins (#82)
- feat(providers): add BFL Images API package (#81)
- feat(providers): add Google Veo API package (#80)
- feat(providers): add Google GenerateContent and Imagen API packages (#79)
- refactor(core): StructuredOutput types, timeout increase, provider loading (#78)
- refactor(text-generation): use StructuredOutput and improve API (#76)
- refactor(text-generation): migrate Anthropic to mixin pattern (#75)
- feat: add Anthropic Messages API provider with core structured output infrastructure (#74)
- feat: introduce Authentication abstraction for flexible provider auth (#73)
- refactor: reorganize packages into capabilities directory (#72)
- feat: add gpt-image-1-mini model for OpenAI image generation (#70)
- feat: add sora-2-2025-12-08 snapshot for OpenAI video generation (#71)
- feat: add seedream-4.5 model for ByteDance image generation (#69)
- feat: add Devstral 2 and Devstral Small 2 models (#68)
- Add GPT-5.2, GPT-5.2 Pro, and GPT-5.2 Instant models (#67)
- license: change from Apache 2.0 to MIT and enhance README (#65)
- docs: enhance README with social badges, feature highlights, and provider switching examples (#64)
Installation
uv add "celeste-ai==0.3.0"Release v0.2.14
Release v0.2.14
Changes
- feat: add missing ElevenLabs models and voices (#59)
Installation
uv add "celeste-ai==0.2.14"Release v0.2.13
Release v0.2.12
Release v0.2.11
Release v0.2.10
Release v0.2.9
Release v0.2.9
Changes
- feat: Add Gemini 3 Pro support with thinking_level parameter (#47)
Installation
uv add "celeste-ai==0.2.9"Release v0.2.8
Release v0.2.7
Release v0.2.7
Changes
- feat: add video-generation package with OpenAI, Google, and ByteDance providers (#43)
- refactor: add Chunk type parameter to Stream class for type-safe streaming (#42)
- refactor: remove redundant StrEnum type annotations from ParameterMapper (#41)
- refactor: migrate Anthropic to native structured outputs API and remove raw_event metadata (#40)
- chore: bump version to 0.2.6 (#38)
- refactor: improve error messages and metadata handling (#39)
- feat: add GPT-5.1 model support (#37)
- refactor: restructure finish_reason handling and add verbosity parameter (#36)
- feat: add ELEVENLABS provider and bump version to 0.2.5 (#35)
- chore: bump version to 0.2.4 and add speech-generation optional dependency (#34)
- chore: bump version to 0.2.2 and add image-intelligence optional dependency (#32)
- refactor: improve code quality and standardize MIME types (#31)
- Add GPT-5 mini and nano model to OpenAI provider (#29)
- fix: add BYTEDANCE_API_KEY to integration test workflow (#28)
- feat: add image-generation package with OpenAI, Google, and ByteDance providers (#27)
- fix: preserve finish_reason in streaming final chunk (#26)
- Replace generic errors with custom exceptions in text-generation (#25)
- implement custom exceptions for Celeste and add unit tests (#23)
- refactor: standardize capability naming to kebab-case (#24)
Installation
uv add "celeste-ai==0.2.7"