Update the max-token calculation in model-params to use the shared logic

[mrubens]

Important

Centralizes max-token calculation logic using getModelMaxOutputTokens and updates default maxTokens to 8192 across models and tests.

• Behavior:
  • Updates maxTokens to 8192 for models in groq.ts.
  • Uses getModelMaxOutputTokens in getModelParams in model-params.ts for centralized maxTokens logic.
  • Adjusts default maxTokens to 8192 in calculateTokenDistribution in model-utils.ts.
• Tests:
  • Updates tests in api.spec.ts, ContextWindowProgressLogic.spec.ts, and model-utils.spec.ts to reflect new default maxTokens value of 8192.
  • Ensures tests handle edge cases like negative inputs and zero context window correctly.

^{This description was created by for 918b5ca. You can customize this summary. It will automatically update as commits are pushed.}

[delve-auditor]

✅ No security or compliance issues detected. Reviewed everything up to 918b5ca.

Security Overview

• 🔎 Scanned files: 7 changed file(s)

Detected Code Changes

Change Type	Relevant files
Enhancement	► groq.ts     Update maxTokens values to 8192 for all Groq models ► model-params.ts     Refactor to use centralized maxTokens logic ► api.ts     Update token calculation logic ► model-utils.ts     Update default token distribution calculation ► Various test files updated to reflect new logic

Reply to this PR with @delve-auditor followed by a description of what change you want and we'll auto-submit a change to this PR to implement it.