tercerapersona 3b4763b3f9 feat: add Anthropic prompt caching via cache_control ...

Inject cache_control: {"type": "ephemeral"} on the system message and
last tool definition for providers that support prompt caching. Adds
supports_prompt_caching flag to ProviderSpec (enabled for Anthropic only)
and skips caching when routing through a gateway.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-02-19 11:05:22 -03:00

..

__init__.py

feat: implement OpenAI Codex OAuth login and provider integration

2026-02-05 17:39:18 +08:00

base.py

fix: preserve reasoning_content in conversation history for thinking models

2026-02-08 18:37:41 +00:00

custom_provider.py

feat: add custom provider with direct openai-compatible support

2026-02-18 02:39:15 +00:00

litellm_provider.py

feat: add Anthropic prompt caching via cache_control

2026-02-19 11:05:22 -03:00

openai_codex_provider.py

fix: resolve Codex provider bugs and simplify implementation

2026-02-16 11:43:36 +00:00

registry.py

feat: add Anthropic prompt caching via cache_control

2026-02-19 11:05:22 -03:00

transcription.py

feat: add voice transcription support with groq (fixes #13)

2026-02-02 04:33:26 -05:00