v0.1.0
What's Changed
- Remove usage callback feature by @Copilot in #2
- Add per-model max_tokens cap with pre-request validation by @Copilot in #4
- Deprecate /v1/chat/completions:stream; use stream=true on standard endpoint by @Copilot in #6
- Deduplicate OpenAI wire types into shared package by @Copilot in #8
- Implement OpenAI-compatible streaming (SSE) for chat completions with usage tracking by @Copilot in #10
- Add Project Positioning section to README by @Copilot in #12
- Add Redis Stream-based usage sink for LLM request auditing by @Copilot in #14
New Contributors
- @Copilot made their first contribution in #2
Full Changelog: https://github.com/poly-workshop/llm-gateway/commits/v0.1.0