From bcfc7c7651c1e4ef09dc612e0733e557c6634abc Mon Sep 17 00:00:00 2001 From: Jordan Ritter Date: Wed, 11 Mar 2026 11:45:47 -0700 Subject: [PATCH] docs: clarify live API conformance gap in Future Direction --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 24428fd..d10b1ee 100644 --- a/README.md +++ b/README.md @@ -552,7 +552,7 @@ Areas where llmock could grow, and explicit non-goals for the current scope. ### Testing -- **E2E SDK tests**: The test suite uses raw HTTP and WebSocket frames, not real OpenAI/Anthropic/Gemini client SDKs. +- **Live API conformance**: The `api-conformance` tests validate response format structure but do not run against real LLM APIs. A subset of tests that hit actual OpenAI/Anthropic/Gemini endpoints (gated behind API keys) would catch format drift as providers evolve their APIs. - **Token counts**: Usage fields are always zero across all providers. - **Vision/image content**: Image content parts are not handled by any provider.