Fix Groq context window display

[mrubens]

Important

Fix GroqHandler to report full input token count without subtracting cached tokens.

• Behavior:
  • GroqHandler in groq.ts now reports full inputTokens without subtracting cached tokens in yieldUsage().
  • Updates test in groq.spec.ts to expect full inputTokens count in createMessage test.
• Tests:
  • Modify createMessage should handle cached tokens in usage data test in groq.spec.ts to expect inputTokens: 100 instead of 70.

^{This description was created by for 417a40f. You can customize this summary. It will automatically update as commits are pushed.}

Thank you for your contribution! I've reviewed the changes and have some questions and suggestions for improvement.

Good to see the test was updated to match this change! However, could you clarify what specific issue this fixes? The PR title mentions "Fix Groq context window display" but it's not clear what was broken.

Also, is this token reporting approach intentional? This makes Groq's behavior different from how it previously worked (subtracting cached tokens from input tokens). The base OpenAI provider reports total tokens, but some other providers handle cached tokens differently. Could you explain the reasoning behind this change?