Skip to content

Releases: withceleste/celeste-python

Release v0.3.1

19 Dec 16:55

Choose a tag to compare

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

19 Dec 15:13

Choose a tag to compare

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

05 Dec 09:55
dd9596c

Choose a tag to compare

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

05 Dec 09:14
a244208

Choose a tag to compare

Release v0.2.13

Changes

  • fix: detect changes correctly when pushing tags (#58)
  • feat: Add speech-generation package (#56)

Installation

uv add "celeste-ai==0.2.13"

Release v0.2.12

01 Dec 22:42
e6ee2f9

Choose a tag to compare

Release v0.2.12

Changes

  • feat(image-generation): add BFL (Black Forest Labs) provider (#54)
  • refactor: remove explicit None assignments for usage token fields (#53)
  • fix: Cohere usage parsing and remove deprecated models (#52)

Installation

uv add "celeste-ai==0.2.12"

Release v0.2.11

25 Nov 09:08
93bbc2b

Choose a tag to compare

Release v0.2.11

Changes

  • ci: add XAI_API_KEY to integration test workflow (#51)
  • feat: Add XAI provider for text generation (#50)

Installation

uv add "celeste-ai==0.2.11"

Release v0.2.10

20 Nov 16:10
8005d13

Choose a tag to compare

Release v0.2.10

Changes

  • Add Gemini 3 Pro Image Preview model support and bump versions (#49)
  • Integrate Improved Structured Outputs in the Gemini API (#48)

Installation

uv add "celeste-ai==0.2.10"

Release v0.2.9

19 Nov 11:21
cc9b712

Choose a tag to compare

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

18 Nov 08:54
d64b6a3

Choose a tag to compare

Release v0.2.8

Changes

  • Bump versions to 0.2.8 (#46)
  • Standardize provider docstrings with capability suffixes (#44)

Installation

uv add "celeste-ai==0.2.8"

Release v0.2.7

17 Nov 13:47
5546a9a

Choose a tag to compare

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"