Skip to content

Add OpenAI-compatible inference backend adapter#10

Merged
WaffleBits merged 1 commit into
mainfrom
codex/openai-compatible-backend-adapter-20260711
Jul 11, 2026
Merged

Add OpenAI-compatible inference backend adapter#10
WaffleBits merged 1 commit into
mainfrom
codex/openai-compatible-backend-adapter-20260711

Conversation

@WaffleBits

Copy link
Copy Markdown
Owner

Summary

  • add an optional, mock-by-default OpenAI-compatible completion adapter for vLLM/SGLang-style endpoints
  • validate response shape, bound request timeouts, and return generic 502 backend errors without leaking transport details
  • add adapter/app integration tests and deployment documentation

Validation

  • python -m unittest discover -s tests (51 tests)
  • python -m compileall -q gateway tests
  • git diff --check
  • docker compose config

The adapter is an integration boundary, not a claim of production-scale serving. Synthetic capacity and resilience evidence remains labeled as synthetic until a live backend is exercised.

@WaffleBits WaffleBits added the enhancement New feature or request label Jul 11, 2026
@WaffleBits
WaffleBits marked this pull request as ready for review July 11, 2026 13:10
@WaffleBits
WaffleBits merged commit 9c4e30c into main Jul 11, 2026
1 check passed
@WaffleBits
WaffleBits deleted the codex/openai-compatible-backend-adapter-20260711 branch July 16, 2026 12:05
WaffleBits added a commit that referenced this pull request Jul 16, 2026
…ter-20260711

Add OpenAI-compatible inference backend adapter
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant