Comment by unbrice

I asked Gemini to review the repo. Apparent issues include:

  - Corrupted/dropped Gemini thought_signature (reasoning_details) in tool loops
  - Blinded model.api.id = "contestant" bypasses gemini.txt and serves Claude's prompt (default.txt)
  - Anthropic-only prompt caching

The full report is here, if you're interested: https://docs.google.com/document/d/1-HqujXuDRJSWJIqEvmctcINr...

Prompt was:

> I read on hacker news the following, which does not match my expectations. Check if something in the harness or bench is hurting gemini perf.

followed by your post.