Release v0.9.1

Release v0.9.1

Changes

• feat: Add multi-turn conversation support and OpenResponses/Ollama providers (#111)

Installation

uv add "celeste-ai==0.9.1"

Release v0.9.0

Release v0.9.0

Changes

• test: fix integration test failures (#110)
• ci: add missing API key secrets for new providers (#109)
• feat: v1 architecture migration - modality-centric API (#108)

Installation

uv add "celeste-ai==0.9.0"

Release v0.3.9

Release v0.3.9

Changes

• feat(openai): add GPT-5.2 Codex model (#107)

Installation

uv add "celeste-ai==0.3.9"

Release v0.3.8

Release v0.3.8

Changes

• feat: add model serialization with input types and constraint types (#103)

Installation

uv add "celeste-ai==0.3.8"

Release v0.3.7

Release v0.3.7

Changes

• fix(speech-generation): return correct finish reason type in Google provider (#102)
• chore: bump version to 0.3.7 (#101)
• fix(capabilities): add explicit usage and finish_reason types to Output classes (#100)

Installation

uv add "celeste-ai==0.3.7"

Release v0.3.6

Release v0.3.6

Changes

• feat: input class registry and unregistered model fallback (#99)

Installation

uv add "celeste-ai==0.3.6"

Release v0.3.5

Release v0.3.5

Changes

• feat: add flux-2-max and gpt-image-1.5 models (#98)

Installation

uv add "celeste-ai==0.3.5"

Release v0.3.4

Release v0.3.4

Changes

• chore: bump versions to 0.3.4 (#97)
• feat: add gemini-3-flash-preview model (#96)
• feat(core): make capability optional in create_client (#95)
• fix: add missing provider dependencies to capability packages (#94)
• ci: exclude pyproject.toml from integration test triggers (#92)

Installation

uv add "celeste-ai==0.3.4"

Release v0.3.3

Release v0.3.3

Changes

• chore: bump all packages to v0.3.3
• fix: add missing provider dependencies to capability packages
• ci: exclude pyproject.toml from integration test triggers (#92)

Installation

uv add "celeste-ai==0.3.3"

Release v0.3.2

Release v0.3.2

Changes

• chore: bump celeste-ai, celeste-google, and speech-generation to v0.3.2 (#91)
• feat(google): add Cloud TTS API and migrate speech generation (#90)
• feat(speech-generation): add Gradium TTS provider with WebSocket API (#89)
• 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==0.3.2"